本期机器人顶刊精选

State estimation is one of the fundamental problems in robotics. For soft continuum robots, this task is particularly challenging because their states (poses, strains, internal wrenches, and velocities) are inherently infinite - dimensional due to continuous deformability, while sensing provides only discrete measurements. Recently, a dynamic state estimation method known as a boundary observer was introduced, which uses Cosserat rod theory to recover all states from tip velocity measurements. In this work, we present a dual design that instead relies on measuring the internal wrench at the robot’s base. Despite the duality, this approach offers a key practical advantage: it requires only a force/torque (FT) sensor at the base and eliminates the need for external motion capture systems. Both observer types are inspired by energy dissipation principles and can be combined to enhance performance. We conduct a Lyapunov-based analysis to study convergence and reveal a useful property: as observer gains increase, the convergence rate first improves and then degrades. This convex trend enables efficient gain tuning. We also identify cases where linear and angular states are fully determined by each other, further relaxing sensing requirements. In summary, this work achieves dynamic infinite-dimensional state estimation with minimal sensing requirements and systematic parameter tuning, which has not been demonstrated in existing approaches. Simulation and experimental studies using a tendon-driven continuum robot validate convergence under fast dynamic motions, the existence of optimal gains, robustness to external forces, measurement noise, and model uncertainty, and real-time computational performance.

Aerial manipulation extends robotic operations to previously inaccessible aerial environments. Unlike arm-equipped aerial systems, tiltable-multirotors can directly generate six-degree-of-freedom wrenches through their flight bases, enabling both efficient movement and omnidirectional operation by tilting the thrust direction. This work presents a design analysis and a wrench-based control framework for tiltable-multirotors in aerial manipulation. We show that a four-rotor tiltable configuration provides a balance between interference-free propeller sizing and hovering efficiency across different attitudes, and its null-space redundancy is crucial for traversing singular configurations under physical constraints. We further show that an upward end-effector placement yields a favorable trade-off between geometric clearance and available wrench. To address disturbances, we propose a dual strategy consisting of a modified integral term for model error and an acceleration-based estimator for external wrenches. Building on these insights, we develop an effector-centric nonlinear model predictive control (NMPC) framework that integrates design choices, singularity handling, and disturbance compensation into a unified formulation. The proposed framework runs fully onboard at 100 Hz on a custom-built tiltable-quadrotor. Real-world experiments, including a 90-deg step cartwheel rotation, whiteboard pushing, and continuous 360-deg valve turning, demonstrate the feasibility of wrench-based omnidirectional manipulation with singularity traversal on a one-DoF-per-arm tiltable-quadrotor.

By maintaining global consistency across robot teams, multi-robot light detection and ranging (LiDAR) map merging enables faster exploration and efficient area coverage. However, map merging requires exchanging massive sensor data between the server and robots, making communication the bottleneck, especially in communication-constrained environments. Therefore, we present Commerge , a communication-efficient map merging framework that achieves bandwidth reduction through graph-theoretic selective data exchange. By doing so, our Commerge reduces inter-robot communication by up to 5000× while maintaining alignment accuracy. Our key insight is that only a small subset of carefully selected scans is sufficient for robust map merging. We formulate this as a three-stage cascaded optimization problem on an exchange graph, where vertices represent robot keyframes and edges denote candidate inter-robot loops. Through three cascade stages, we select a sequentially overlapped, balanced-transmission-cost, and geometrically-perceptually optimal scan subset that preserves alignment quality while reducing communication. Unlike existing approaches that either transmit whole scans, which require GB-scale data exchange, or employ naïve downsampling, our approach exchanges only MB-scale data while achieving comparable alignment accuracy. Extensive evaluation on five public datasets and four in-house datasets covering cave, planetary-analog, indoor, and outdoor campus environments shows up to 99.98% reduction in data exchange (e.g., from 7000 MB to 1.3 MB on the HeLiPR dataset), while maintaining alignment performance across embedded to desktop platforms. Furthermore, we demonstrate that our proposed framework operates on resource-constrained hardware where existing methods fail, enabling real-world multi-robot deployment in bandwidth-limited field operations. Finally, we validate system robustness under a real-world non-line-of-sight (NLOS) communication environment with up to 73.3% dropout rate, as well as under emulated network degradation scenarios including delay, bandwidth limitation, and packet loss, confirming reliable map merging even under severely degraded connectivity.

Hybrid dynamical systems provide a powerful modeling framework for robotic systems, particularly in contact-rich environments. However, ensuring safety and performance in such systems remains challenging due to the intricate coupling between continuous dynamics and discrete mode transitions. In this work, we extend classical Hamilton-Jacobi (HJ) reachability analysis, a formal verification method for continuous-time nonlinear systems, to hybrid dynamical systems. Our framework characterizes safe sets for hybrid systems through a generalized value function defined over both discrete and continuous states while accounting for control constraints and model uncertainty. We additionally provide a numerical algorithm to compute this value function. Building on these safe sets, we propose two different mechanisms to integrate performance objectives. First, we introduce a hybrid least-restrictive safety filter that intervenes on both the discrete and continuous components of a nominal controller only when necessary to avoid unsafe states, thereby preserving nominal behavior whenever possible. Second, we formulate and compute hybrid backward reach-avoid tubes, enabling the simultaneous enforcement of safety and goal-reaching behavior, an extension not previously addressed within hybrid HJ reachability. This enables the synthesis of continuous and discrete control policies that guarantee both safety and task completion. We validate our framework through simulation studies and real-world experiments on a quadrupedal robot, demonstrating its effectiveness in hybrid mode planning and safety-critical applications.

3D Scene Graphs (3DSGs) have emerged as a powerful representation for robotic perception and reasoning, capturing not only the geometric layout of the environment but also its semantic and relational structure. By organizing objects, places, and agents within structured graphs, 3DSGs provide a rich abstraction layer that enables a wide range of robotic tasks, from navigation and manipulation to interaction and planning. In this survey, we present a comprehensive overview of current approaches for constructing, maintaining and querying 3DSGs, along with a historical perspective and an in-depth review of the literature. We propose a unified formulation of the 3DSG construction problem and analyze the dominant architectural and algorithmic choices, including modular pipelines, end-toend learning strategies, and open-vocabulary methods. The paper concludes with a discussion of emerging trends, open challenges, and opportunities for future work in 3DSG representations and multi-agent collaboration, and beyond.

LiDAR point cloud registration is fundamental to robotic perception and navigation. However, in geometrically degenerate or narrow environments (e.g., corridors), registration problems become ill-conditioned: certain motion directions are weakly constrained, leading to unstable solutions and degraded accuracy. Existing methods adopt a detect-then-mitigate paradigm but fail to reliably detect, physically interpret, and stabilize such ill-conditioning without corrupting the optimization problem. In this study, we introduce DCReg ( Decoupled Characterization for Ill-conditioned Registration ), which establishes a principled detect–characterize–mitigate paradigm that systematically addresses ill-conditioned registration through three integrated innovations. First, DCReg achieves reliable ill-conditioning detection by employing a Schur complement decomposition to the hessian matrix. This structure-aware technique decouples the 6-DoF registration problem into 3-DoF clean rotational and translational subspaces, eliminating coupling effects that mask degeneracy patterns in conventional full-Hessian analyses. Second, within these decoupled subspaces, we develop physically interpretable characterization techniques that resolve eigenbasis ambiguities through principled basis alignment. This establishes stable and quantitative mappings between mathematical eigenspaces and physical motion directions, providing actionable insights about which specific motions lack constraints and to what extent. Third, leveraging this directional spectral information, we design a targeted mitigation strategy via a structured preconditioner. While guided by MAP regularization principles for spectral shaping, our approach implements eigenvalue clamping exclusively within the preconditioner rather than modifying the origin problem. This preserves the original least-squares objective and its minimizer while enabling efficient and stable optimization via Preconditioned Conjugate Gradient with a single physically interpretable parameter. Extensive experiments demonstrate DCReg achieves at least 20%–50% improvement in long-duration localization accuracy and typical speedups of 5 − 30× (up to 116× in certain scenarios) over comparable degeneracy-aware baseline methods across diverse environments. Our implementation will be available at https://github.com/JokerJohn/DCReg .

The humanlike form of humanoid robots uniquely positions them to achieve the agility and versatility in motor skills that humans have. Learning from human demonstrations offers a scalable approach to acquiring these capabilities. However, prior works either produced unnatural motions or relied on motion-specific tuning to achieve satisfactory naturalness. Furthermore, these methods are often motion or goal specific, lacking the versatility to compose diverse skills, especially when solving unseen tasks. We present BeyondMimic, a framework that scales to diverse motions and carries the versatility to compose them seamlessly in tackling unseen downstream tasks. A compact motion tracking formulation enables mastery of a wide range of highly agile behaviors, including aerial cartwheels, spin kicks, flip kicks, and sprinting, with a single setup and shared hyperparameters, all while achieving humanlike performance. Moving beyond the mere imitation of existing motions, we propose a unified latent diffusion model that empowers versatile goal specification, seamless task switching, and dynamic composition of these agile behaviors. Leveraging classifier guidance, a diffusion-specific technique for test-time optimization toward unseen objectives, our model extended its capability to solve downstream tasks never encountered during training, including motion inpainting, joystick teleoperation, and obstacle avoidance, and transferred these skills zero-shot to real hardware. Together, these components enable scalable acquisition of humanlike motor skills from human motion and motion synthesis that generalizes and adapts beyond the training setup.

This paper addresses the problem of trajectory planning for information gathering with a dynamic and resolution-varying sensor footprint. Ergodic planning offers a principled framework that balances exploration (visiting all areas) and exploitation (focusing on high-information regions) by planning trajectories such that the time spent in a region is proportional to the amount of information in that region. Existing ergodic planning often oversimplifies the sensing model by assuming a point sensor or a footprint with constant shape and resolution. In practice, the sensor footprint can drastically change over time as the robot moves, such as aerial robots equipped with downward-facing cameras, whose field of view depends on the orientation and altitude. To overcome this limitation, we propose a new metric that accounts for dynamic sensor footprints, analyze the theoretic local optimality conditions, and propose numerical trajectory optimization algorithms. Experimental results show that the proposed approach can simultaneously optimize both the trajectories and sensor footprints, with up to an order of magnitude better ergodicity than conventional methods. We also deploy our approach in a multi-drone system to ergodically cover an object in 3D space.

The Boreas Road Trip (Boreas-RT) dataset extends the multi-season Boreas dataset to new and diverse locations that pose challenges for modern autonomous driving algorithms. Boreas-RT comprises 60 sequences collected over 9 real-world routes, totalling 643 km of driving. Each route is traversed multiple times, enabling evaluation in identical environments under varying traffic and, in some cases, weather conditions. The data collection platform includes a 5MP FLIR Blackfly S camera, a 360° Navtech RAS6 Doppler-enabled spinning radar, a 128-channel 360° Velodyne Alpha Prime lidar, an Aeva Aeries II FMCW Doppler-enabled lidar, a Silicon Sensing DMU41 inertial measurement unit, and a Dynapar wheel encoder. Centimetre-level ground truth is provided via post-processed Applanix POS LV GNSS-INS data. The dataset includes precise extrinsic and intrinsic calibrations, a publicly available development kit, and a live leaderboard for odometry and metric localization. Benchmark results show that many state-of-the-art odometry and localization algorithms overfit to simple driving environments and degrade significantly on the more challenging Boreas-RT routes. Boreas-RT provides a unified dataset for evaluating multi-modal algorithms across diverse road conditions. The dataset, leaderboard, and development kit are available at boreas.utias.utoronto.ca.

There is great interest in alternative pollination strategies for crop production in the face of climate change and perennial threats to the traditional pollination mechanisms. This review explores the potential of robotic pollination as a promising solution to these challenges affecting crop fertilization, agricultural sustainability, and global food production. We comprehensively examine recent advances in robotic pollination systems that integrate artificial intelligence, machine vision, robotics, and precision sensing to supplement or complement conventional insect‐mediated pollination. The review first examines aerial robotic pollination, beginning with insect‐scale aerial robots, their technological evolution from biomimetic flapping‐wing platforms toward autonomous operation, and the key challenges that continue to limit their practical deployment. It then reviews unmanned aerial vehicles (UAVs) for robotic pollination, highlighting their progression from broad aerial pollen dispersal to precision‐oriented pollination, followed by a synthesis of current limitations and future research priorities for UAV‐based robotic pollination. The review subsequently discusses ground‐based robotic pollination systems, emphasizing their perception, navigation, and pollen delivery strategies together with the technical challenges associated with field deployment. Beyond individual robotic platforms, we examine the cost, scalability, and commercial development of robotic pollination technologies and discuss emerging industrial efforts that are accelerating adoption in modern agriculture. Finally, we present a future roadmap for robotic crop pollination, outlining critical research directions in autonomy, perception, precision pollen delivery, multirobot coordination, ecological compatibility, and system‐level intelligence required to transition robotic pollination from experimental prototypes to commercially viable agricultural solutions. Overall, this review highlights robotic pollination as a practical, intelligent, and environmentally sustainable technology for modern agriculture, capable of enhancing crop pollination resilience, mitigating pollinator decline and labor shortages, and supporting long‐term agricultural productivity and global food security.

End-to-end autonomous driving is increasingly data-driven, yet data reuse across vehicles remains limited. Each new vehicle often requires additional data collection and retraining because camera translation, orientation, and field of view differ across sensor layouts. Cross-sensor view synthesis offers a promising route for cross-platform data reuse by synthesizing images under novel sensor configurations from existing sensor data. To realize this goal, we propose GS-Net, a lightweight plug-and-play module that aggregates local geometric context from sparse Structure-from-Motion (SfM) point clouds and expands each point into multiple dense Gaussian primitives in a single forward pass, learning a cross-scene generalizable initialization for standard 3DGS that improves rendering quality for both interpolated views along the original sensor trajectories and extrapolated views at new sensor positions. In such settings, target camera viewpoints often lie beyond the convex hull of training cameras, whereas existing methods and benchmarks predominantly evaluate in-hull interpolation, leaving the extrapolation regime underexplored. To enable quantitative evaluation under this setting, we introduce CARLA-NVS, the first benchmark explicitly designed for cross-sensor view synthesis. Unlike existing autonomous driving datasets that typically employ no more than eight cameras in fixed configurations, CARLA-NVS features 12 cameras uniformly distributed at 30-degree azimuth intervals, enabling controlled evaluation of both interpolated and extrapolated viewpoints. Experiments on CARLA-NVS show that GS-Net improves rendering quality by 2.08 dB PSNR on interpolated views and 1.86 dB on extrapolated views over standard 3DGS, while achieving a 50x faster initialization compared to MVS-based densification. These results offer a practical step toward scalable cross-vehicle data reuse in autonomous driving.

Hydraulic quadruped robots exhibit exceptional terrain adaptability, offering significant potential for environmental exploration and military transportation. However, conventional hydraulic architectures are often plagued by excessive weight, complex pipeline network and mechanical interference, which restrict the improvement of its compactness and flexibility. To address these issues, this paper proposes a tubeless limb leg unit (LLU) featuring an electro‐hydraulic hybrid drive and topologically optimized structural components. By exploring the relationship between motion capability and joint performance parameters, a hybrid drive configuration integrating rotary and linear (RL) actuators is proposed, achieving full integration of actuators and hydraulic flow channels within the LLU. Furthermore, a lightweight reconstruction of critical thigh components is executed using the variable density penalty method combined with a lattice‐filling strategy to mitigate local stress concentrations, which reduces redundant mass by 37% without compromising structural integrity. Subsequently, a compact hydraulic power system is constructed, and an integrated control and simulation platform based on the robot operating system (ROS) framework is designed. Experimental validation demonstrates that the robot exhibits better dynamic stability during standing, trot gait, heavy payload, uneven terrain, and disturbance recovery tests.

Robotic manipulation policies are commonly initialized through imitation learning, but their performance is limited by the scarcity and narrow coverage of expert data. Reinforcement learning can refine polices to alleviate this limitation, yet real-robot training is costly and unsafe, while training in simulators suffers from the sim-to-real gap. Recent advances in generative models have demonstrated remarkable capabilities in real-world simulation, with diffusion models in particular excelling at generation. This raises the question of how diffusion model-based world models can be combined to enhance pre-trained policies in robotic manipulation. In this work, we propose World4RL, a framework that employs diffusion-based world models as high-fidelity simulators to refine pre-trained policies entirely in imagined environments for robotic manipulation. Unlike prior works that primarily employ world models for planning, our framework enables direct end-to-end policy optimization. World4RL is designed around two principles: pre-training a diffusion world model that captures diverse dynamics on multi-task datasets and refining policies entirely within a frozen world model to avoid online real-world interactions. We further design a two-hot action encoding scheme tailored for robotic manipulation and adopt diffusion backbones to improve modeling fidelity. Extensive simulation and real-world experiments demonstrate that World4RL provides high-fidelity environment modeling and enables consistent policy refinement, yielding significantly higher success rates compared to imitation learning and other baselines.

Wildfires and deforestation pose significant threats to forest ecosystems, motivating scalable methods for reforestation beyond labor‐intensive cultivation of native forest seedlings in nurseries. To enable large‐scale direct seeding of native species, this paper presents the design, analysis, and field evaluation of a UAV‐based seed‐dropping system. The approach integrates a lightweight carriage mechanism for gravity‐based seeding systems with an open‐source multirotor UAV to enable precision seeding operations. Precise seed placement enables adherence to ecologically motivated spacing, for example, 1.8 m for framework‐species plots, which broadcast seeding cannot readily achieve. Additionally, the system uses 30 mm biochar‐coated seed balls, which facilitate the handling of multiple seed varieties and enhance overall germination success in framework‐species approaches. The autonomy stack combines LiDAR‐based terrain following with deterministic actuation and on‐board seed‐drop confirmation via an outlet limit switch, providing a geotagged record of each seed drop for post hoc analysis of the reforestation efforts. Field evaluations at an active reforestation site in Northern Thailand have demonstrated the feasibility of the proposed solution. An altitude sensitivity study at 5, 10, and 15 m height revealed wind‐aligned drift and terrain interactions; operations at 3–5 m height were found to provide practical operating windows for precision deployments, with 95% of drops landing within 0.66 m of the target for a controlled test at 5 m height. A representative 27‐waypoint autonomous mission demonstrated a 90% success rate, with 24 drops confirmed by the on‐board system and matched ground observations. Unlike conventional aerial seeding systems, the proposed precision seed‐dropping approach significantly reduces seed wastage, making the solution scalable for large‐scale ecological restoration and biodiversity recovery initiatives.

Soft robotic grippers have been developed for high‐speed handling of soft, fragile foods. For example, our previously designed soft‐containing gripper has been implemented on food production lines. However, existing soft robotic grippers remain inadequate for food pick‐and‐place tasks at extreme handling speeds (e.g., > 70 pcs/min). The handling of highly deformable products with smooth, fragile surfaces (e.g., raw oysters) also remains underexplored. Such products may slip within the gripper, be tossed through gripper gaps, or become misaligned on plastic trays. To address these challenges, this study proposes an enhanced soft‐containing gripper for pick‐and‐place of oyster products at extreme handling speed and validates its feasibility under industrial conditions. The geometries of the soft fingers and cushion were carefully designed to passively and securely contain foods. Finite element simulations were conducted to evaluate the effects of gripper configurations and actuation‐induced stiffness on object responses under extreme conditions. The cushion and fingers were printed by silicone 3D printing, thereby reducing fabrication time and improving manufacturing consistency. Experiments conducted with a parallel robot at four handling speeds and three initial food orientations demonstrate that the proposed gripper achieves stable pick‐and‐place of soft and fragile oyster products at extreme handling speeds. It outperforms manual handling by skilled workers, our previous soft‐containing gripper, and a commercial gripper. The results indicate that fully containing soft and fragile foods through compliant contact while avoiding over‐compression is critical for stable handling under extreme conditions.

Multi-segment suction-based soft robots are promising for inspection and maintenance in confined or fragile environments, but existing approaches still depend heavily on manually designed gaits and environment-specific motion scripts. This work presents a planning framework for serial multi-segment soft robots with deformable body segments and boundary suction pads. The formulation targets full 3D navigation on complex surfaces and explicitly handles discrete adhesion switching and continuous body deformation under geometric, collision, and quasi-static feasibility constraints, while remaining agnostic to the specific actuation realization used to produce segment deformation. Its core, block-wise IK hybrid search (IKHS), performs best-first search over feasible adhesion transitions while solving inverse kinematics only on induced free blocks. On top of IKHS, primitive-augmented hybrid search (PaHS) uses a learned observation--primitive embedding to retrieve short validated motion segments for fast local proposal, with fallback to standard IKHS branching when retrieval fails. In simulation, the framework consistently outperforms controlled baselines in planning success, transition quality, and efficiency across diverse terrains. PaHS matches IKHS in success rate while substantially reducing planning time. Repeated hardware experiments on a pneumatic multi-segment soft robot further demonstrate executability and online recovery under actuation and adhesion uncertainty.

Collaborative transport requires robots to infer partner intent through physical interaction while maintaining stable loco-manipulation. This becomes particularly challenging in complex environments, where interaction signals are difficult to capture and model. We present PAINT, a hierarchical learning framework for partner-agnostic intent-aware collaborative legged transport that represents partner intent as an explicit interaction wrench and recovers it from payload-coupled proprioceptive histories. PAINT decouples intent understanding from terrain-robust locomotion: A high-level policy uses the inferred interaction wrench for transport and reconstructs it through teacher-student training, while a low-level locomotion backbone ensures robust execution. This enables lightweight deployment without external force-torque sensing or payload tracking. Extensive simulation and real-world experiments demonstrate compliant cooperative transport across diverse terrains, payloads, and partners. Furthermore, we show that PAINT can reuse the same single-agent policy for decentralized multi-robot transport by mechanically combining team interactions into a common wrench space, and supports heterogeneous-team transport. Our results suggest that payload-coupled proprioceptive interaction provides a physically grounded interface for partner-agnostic intent-aware collaborative transport.

Parallel trajectory optimization via the Alternating Direction Method of Multipliers (ADMM) has emerged as a scalable approach to long-horizon motion planning. However, existing frameworks typically decompose the problem into parallel subproblems based on a predefined fixed structure. Such structural rigidity often causes optimization stagnation in highly constrained regions, where a few lagging subproblems delay global convergence. A natural remedy is to adaptively re-split these stagnating segments online. Yet, deciding when, where, and how to split exceeds the capability of rule-based heuristics. To this end, we propose ATRS, a novel framework that embeds a shared Deep Reinforcement Learning policy into the parallel ADMM loop. We formulate this adaptive adjustment as a Multi-Agent Shared-Policy Markov Decision Process, where all trajectory segments act as homogeneous agents and share a unified neural policy network. This parameter-sharing architecture endows the system with size invariance, enabling it to handle dynamically changing segment counts during re-splitting and generalize to arbitrary trajectory lengths. Furthermore, our formulation inherently supports zero-shot generalization to unseen environments, as our network relies solely on the internal states of the numerical solver rather than on the geometric features of the environment. To ensure solver stability, a Confidence-Based Election mechanism selects only the most stagnating segment for re-splitting at each step. Extensive simulations demonstrate that ATRS accelerates convergence, reducing the number of iterations by up to 26.0% and the computation time by up to 19.1%. Real-world experiments further confirm its applicability to both large-scale offline global planning and real-time onboard replanning within 35 ms per cycle, with no sim-to-real degradation.

Multi-agent systems in the real-world (e.g., drone swarms, autonomous cars, warehouse robots) must satisfy rich, temporal tasks while avoiding collisions. Signal Temporal Logic (STL) elegantly encodes such objectives, but current STL planning methods face critical limitations. State-of-the-art optimization-based approaches can handle arbitrary STL specifications but struggle with scalability, becoming computationally impractical as the number of agents grows. Learning-based methods efficiently handle a large number of agents with rapid planning times but fare poorly when deployment-time objectives differ from those used during training, and do not support planning tasks that require different specifications to be ascribed to different agents (i.e., heterogeneity) or team-level specifications requiring coordination of multiple agents. This fundamental trade-off between generalizability and scalability presents a challenge for realizing multi-agent STL planning algorithms in practice. To overcome this challenge, we introduce a new diffusion method for multi-agent planning with STL specifications. Using a differentiable approximation of STL, we integrate the STL gradient in the denoising process, making our approach generalizable to novel formulas whose predicates are placed anywhere within the goal region covered during training, while achieving the same scalability as existing learning-based methods. Our method supports heterogeneous specifications, and by using diffusion models, naturally enhances plan diversity, thereby significantly reducing safety-related violations (e.g., collisions) among agents. A detailed evaluation study justifies the utility of STL-guided diffusion-based multi-agent planners for constructing generalizable, scalable, and diverse plans. Videos and code are available at https://www.jeappen.com/diff-ma-stl/ and https://github.com/jeappen/diff-ma-stl .

This paper presents a novel model predictive control (MPC) approach for autonomous pick-and-place between moving platforms with a hook-equipped aerial manipulator. First, for accurate and rapid modeling of the complex dynamics, a digital twin model of the quadcopter equipped with a hook-based gripper, implemented in MuJoCo, is constructed and used as the predictive model for the MPC. To handle uncertainties of the predictive model (e.g. due to aerodynamics and uncertain payloads), a robust adaptive MPC approach is proposed. By systematic integration of zero-order robust optimization (zoRO) based uncertainty propagation and an extended Kalman filter (EKF) for parameter estimation, the MPC algorithm ensures robust constraint satisfaction, high performance, and computational efficiency. The effectiveness of the proposed method is evaluated in complex simulated scenarios and in real-world flight experiments.

Visual reinforcement learning is appealing for robotics but expensive. Off-policy methods are sample-efficient yet slow while on-policy methods parallelize well but waste samples. Recent work has shown that off-policy methods can train faster than on-policy methods in wall-clock time for state-based control. Extending this to vision remains challenging, where high-dimensional input images complicate training dynamics and introduce substantial storage and encoding overhead. To address these challenges, we introduce Squint, a visual Soft Actor Critic method that achieves faster wall-clock training than prior visual off-policy and on-policy methods. Squint achieves this via parallel simulation, a distributional critic, resolution squinting, layer normalization, a tuned update-to-data ratio, and an optimized implementation. We evaluate on the SO-101 Task Set, a new suite of eight manipulation tasks in ManiSkill3 with heavy domain randomization, and demonstrate sim-to-real transfer to a real SO-101 robot. We train policies for 15 minutes on a single RTX 3090 GPU, with most tasks converging in under 6 minutes.

This paper presents Parallel ARC (P-ARC), a parallel formulation of the Adaptive Robot Coordination (ARC) approach to multi-robot motion planning (MRMP) which exploits subproblem independence. ARC's adaptive (de)composition of the multi-robot planning space exposes parallelism: single-robot paths are solved independently and iterative conflict detection and resolution create locally coupled subproblems. While distributing single-robot queries is trivial, not all conflicts are independent, so P-ARC proposes robot-disjoint conflict batches which enable efficient distributed detection and concurrent repair. Additionally, OR-multi-start strategies are employed at the global and subproblem resolution levels, creating a hybrid parallel strategy OR-P-ARC. We evaluate the methods against sequential ARC, multi-start OR-ARC, and coupled and prioritized parallel baselines on controlled 2D mobile robot and planar-manipulator problems with up to 256 robots and 3D Panda manipulator problems with up to 16 robots. On 16-robot Panda tasks, with 16 workers, P-ARC and OR-P-ARC achieve 3.48X and 6.67X speedups, respectively.

In this paper, we introduce DynaRetarget, a complete pipeline for retargeting human motions to humanoid control policies. The core component of DynaRetarget is a novel Sampling-Based Trajectory Optimization (SBTO) framework that refines imperfect kinematic trajectories into dynamically feasible motions. SBTO incrementally advances the optimization horizon, enabling optimization over the entire trajectory for long-horizon tasks. We validate DynaRetarget by successfully retargeting hundreds of humanoid-object demonstrations and achieving higher success rates than the state of the art. The framework also generalizes across varying object properties, such as mass, size, and geometry, using the same tracking objective. This ability to robustly retarget diverse demonstrations opens the door to generating large-scale synthetic datasets of humanoid loco-manipulation trajectories, addressing a major bottleneck in real-world data collection.

Data-driven approaches struggle with precise manipulation; imitation learning requires many hard-to-obtain demonstrations, while reinforcement learning yields brittle, non-generalizable policies. We introduce VisuoTactile Local (ViTaL) policy learning, a framework that solves fine-grained manipulation tasks by decomposing them into two phases: a reaching phase, where a vision-language model (VLM) enables scene-level reasoning to localize the object of interest, and a local interaction phase, where a reusable, scene-agnostic ViTaL policy performs contact-rich manipulation using egocentric vision and tactile sensing. This approach is motivated by the observation that while scene context varies, the low-level interaction remains consistent across task instances. By training local policies once in a canonical setting, they can generalize via a localize-then-execute strategy. ViTaL achieves around 90% success on contact-rich tasks in unseen environments and is robust to distractors. ViTaL's effectiveness stems from three key insights: (1) foundation models for segmentation enable training robust visual encoders via behavior cloning; (2) these encoders improve the generalizability of policies learned using residual RL; and (3) tactile sensing significantly boosts performance in contact-rich tasks. Ablation studies validate each of these insights, and we demonstrate that ViTaL integrates well with high-level VLMs, enabling robust, reusable low-level skills. Results and videos are available at https://vitalprecise.github.io.

Recent advances in large Vision-Language Models (VLMs) have provided rich semantic understanding that empowers drones to search for open-set objects via natural language instructions. However, prior systems struggle to integrate VLMs into practical aerial systems due to orders-of-magnitude frequency mismatch between VLM inference and real-time planning, as well as VLMs' limited 3D scene understanding. They also lack a unified mechanism to balance semantic guidance with motion efficiency in large-scale environments. To address these challenges, we present AirHunt, an aerial object navigation system that efficiently locates open-set objects with zero-shot generalization in outdoor environments by seamlessly fusing VLM semantic reasoning with continuous path planning. AirHunt features a dual-pathway asynchronous architecture that establishes a synergistic interface between VLM reasoning and path planning, enabling continuous flight with adaptive semantic guidance that evolves through motion. Moreover, we propose an active dual-task reasoning module that exploits geometric and semantic redundancy to enable selective VLM querying, and a semantic-geometric coherent planning module that dynamically reconciles semantic priorities and motion efficiency in a unified framework, enabling seamless adaptation to environmental heterogeneity. We evaluate AirHunt across diverse object navigation tasks and environments, demonstrating a higher success rate with lower navigation error and reduced flight time compared to state-of-the-art methods. Real-world experiments further validate AirHunt's practical capability in complex and challenging environments. Code and dataset will be made publicly available before publication.

Existing visual navigation models often aim to develop foundation models that can generalize robot navigation across diverse platforms. However, many of these models are prone to collisions when deployed in complex indoor environments, particularly in structured layouts and narrow passages. To address this problem, we propose a depth image- and point-goal-conditioned navigation system, DevGRU. The proposed system employs an action predictor (AP) that generates collision-aware future trajectories, enabling effective avoidance of immediate obstacles. In conjunction with a collision predictor, the AP further compensates for errors accumulated in the goal pose estimation and proactively mitigates future deviations. To evaluate our method, we conducted experiments across nine different scenes and three state-of-the-art approaches - ViNT, NoMaD, and NavDP - as well as four additional variants of ViNT and NoMaD. In terms of navigation performance, DevGRU significantly outperforms ViNT and NoMaD by a large margin. In addition, the proposed model has a relatively small number of trainable parameters, resulting in the fastest inference time among the baselines, particularly outperforming NavDP by 7x in model size and 17x in inference time.

The design of robotic binocular camera systems has been inspired by human vision, as has their use in humanoid robots. One aspect of this inspiration has yet to play a major role, namely, that humans determine depth using a convergent binocular imaging geometry with both eyes pointing at the same location. Although some robot heads have the functionality to use vergence and version movements and thus alter binocular imaging geometry, a method to exploit it for depth computation has not been explored. Even though to an observer, their motions and appearance might resemble that of humans, in detail, the resemblance to the motions required for actual convergent depth computation is not seen. To bridge this gap, we present convergent binocular stereo (CBS), a stereo algorithm designed to provide a foundation for purposeful binocular computations under the humanoid constraint, intended for active binocular robots. CBS computes horizontal and vertical disparities using a coarse-to-fine refinement strategy with Gabor-filtered responses. We also introduce the Convergent Binocular Stereo–BenchMark (CBS-BM), a convergent, natural image dataset containing 49 scenes with ground-truth horizontal disparity collected on a four-degrees-of-freedom robotic system. Our evaluation, a quantitative comparison between parallel and convergent stereo systems, shows that CBS is broadly competitive with state-of-the-art parallel methods, even outperforming them in scenes with repeated patterns and in mean horizontal disparity and depth error over all scenes. Although not intended to replace parallel stereo where humanlike behavior is unnecessary, CBS enables functionally realistic depth computation for humanoid robotic heads.

Learning sensorimotor contingencies—that is, the link between one’s actions and their sensory effects—is fundamental to developing body knowledge, understanding causality, and developing a sense of agency. In developmental psychology, this process is classically studied using the mobile paradigm, where infants learn that movement of a limb causes motion of a connected mobile. To expand our understanding of how infants learn this, we tested an embodied computational model that learns through two biologically inspired mechanisms: prediction and curiosity. Implemented on the child-sized iCub humanoid robot interacting with a mobile, the model detected sensorimotor contingencies across several experimental conditions using a variety of movement strategies. Our findings suggest that contingency learning cannot be captured by a single behavioral metric, such as the amount of movement, but instead emerges through a spectrum of exploratory behaviors. Analysis of the robot’s internal activity reveals that these behaviors emerge from the dynamic trade-off between prediction and curiosity—between exploitation and exploration. Our work provides a biologically motivated, physically embodied model of sensorimotor interaction that connects theories of infant learning with robotic implementations. The results allow us to generate testable hypotheses for developmental research and to inform the design of autonomous learning systems.

This paper presents the development of an adaptive negative pressure adsorption wall‐climbing robot (WCR) designed for building exterior cleaning and maintenance. The study begins by analyzing the robot's adsorption principle and mechanical structure, proposing a force model for both static and dynamic states, and deriving the negative pressure conditions required for safe adhesion. Computational fluid dynamics (CFD) simulations are conducted to examine the distribution and flow characteristics of air in the adsorption chamber at various motor speeds. To enhance the robot's adaptability to diverse building surfaces, an adaptive negative pressure control system based on fuzzy PID control is designed and tested. The feasibility and effectiveness of the control system are validated through simulation and experimental results. Finally, real‐world tests are performed to assess the robot's performance across different building facades, including evaluations of its load capacity and anti‐air leakage capabilities. The results demonstrate that the proposed robot offers stable adsorption and improved adaptability, making it a promising solution for automated building maintenance in various environments. These findings provide valuable insights for the application of the WCR.

With the expansion of marine resource development, the ecological health of Uninhabited Islands and Reefs urgently requires prolonged and precise monitoring. Nevertheless, the extensive spatial scale, complex topography, and dynamic temporal variations caused by tidal processes in reef regions make it challenging for traditional methods based on predefined trajectories to balance observation efficiency and accuracy. Therefore, an Information‐Driven Multilevel Path Planning Framework is proposed to achieve dual mission requirements of topographic mapping and ecological data sampling. At the global level, the Boundary Adaptive Coverage based on Grid Completeness algorithm is proposed to enhance coarse mapping coverage in irregular island and reef areas. At the local level, an Information‐Driven Coverage Neural Network algorithm is designed to address tide‐induced variations in local terrain, enabling online fine mapping of regions of interest. At the sampling level, an Information‐Driven Travel Neural Network algorithm is proposed to address the path planning challenge involving both ocean current disturbances and energy constraints, enabling energy‐efficient planning of ecological data sampling routes. Experiments demonstrate that the proposed framework significantly outperforms existing methods in metrics such as path length, repeat coverage rate, local observation accuracy, and energy consumption control, effectively enhancing the observation efficiency and reliability of environmental monitoring tasks on Uninhabited Islands and Reefs.

The cover image is based on the article PROMO-Orchard: A Robust Semantic-Enhanced Framework for Dual-Robot Simultaneous Localization and Mapping Merging in Orchard by Liang Gong et al., https://doi.org/10.1002/rob.70323

This paper studies tactile-only 6-DoF pose refinement and belief maintenance for grasped objects in static and short quasi-static in-hand configurations where vision is unavailable or heavily occluded. The key difficulty is tactile partial observability: whole-hand taxel contacts are sparse, intermittent, and ambiguous under limited excitation and object symmetries. We propose a physics-informed particle filter on $\mathrm{SE}(3)$ that updates pose beliefs from dense whole-hand tactile measurements. The likelihood combines active-contact signed-distance consistency, force-normal alignment, friction-cone feasibility, zero-force negative evidence, and optional feasibility guards. A sliding-window log-likelihood fuses recent tactile frames to reduce single-frame ambiguity, while a potential-field-guided proposal steers particles away from hand--object penetration. Symmetry-aware resampling preserves multiple plausible modes. Experiments on an Allegro Hand V5 with five objects show lower normalized ADD-S than tactile-only geometric, particle-filter, and learning baselines, and ablations confirm the benefits of temporal fusion, potential guidance, and mode preservation.

This special issue examines what it takes to move humanoids beyond task-specific demonstrations toward dependable generality.

Existing machine‐learning applications in agricultural spraying have mainly focused on droplet‐size descriptors, canopy coverage, deposition, or image‐based spray detection, while the simultaneous prediction of hydraulic and geometric spray responses from controllable operating variables remains limited. This study developed an experimental–computational framework for predicting mean nozzle discharge, effective spray width, derived spray angle, and mean inter‐nozzle overlap from nozzle model, operating pressure, and spray height. Four hollow‐cone ceramic nozzle models were evaluated at five pressures (6.0–9.5 bar) and three heights (30–50 cm), producing 60 operating conditions tested in triplicate. The resulting 180 experimental runs were averaged into 60 condition‐level records for machine‐learning analysis. Mean nozzle discharge ranged from 0.98 to 2.03 L , effective spray width ranged from 34.75 to 71.50 cm, the maximum derived spray angle reached 96.77°, and mean inter‐nozzle overlap ranged from 34.00 to 71.67 cm across the investigated operating conditions. Extra Trees Regressor provided the best predictions for mean nozzle discharge (, RMSE = 49.25 mL , MAE = 37.99 mL ), effective spray width (, RMSE = 2.37 cm), and mean overlap (, RMSE = 3.13 cm). Support vector regression with a radial basis function kernel performed best for derived spray angle (, RMSE = 3.53°). Pressure increased discharge and lateral footprint, whereas increasing height widened the footprint but generally reduced the geometrically derived angle. The models provide rapid condition‐level estimates within the investigated experimental domain and may complement physical calibration. Their transfer to other nozzle families, moving platforms, field environments, or real‐time control requires additional validation.

Multimodal large language models (MLLMs) have advanced zero-shot end-to-end Vision-Language Navigation (VLN), yet robust navigation requires not only semantic understanding but also predictive modeling of environment dynamics and spatial structure. We propose PROSPECT, a unified streaming navigation agent that couples a streaming Vision-Language-Action (VLA) policy with latent predictive representation learning. PROSPECT uses CUT3R as a streaming 3D foundation spatial encoder to produce long-context, absolute-scale spatial features, and fuses them with SigLIP semantic features via cross-attention. During training, we introduce learnable stream query tokens that query the streaming context and predict next-step 2D and 3D latent features (rather than pixels or explicit modalities), supervised in the latent spaces of frozen SigLIP and CUT3R teachers. The predictive branch shapes internal representations without inference overhead. Experiments on VLN-CE benchmarks and real-robot deployment demonstrate state-of-the-art performance and improved long-horizon robustness under diverse lighting. We will release code for the community soon.

Object-goal navigation requires an agent to reason over object relationships and prioritize target-relevant objects for efficient decision making in unseen environments. While existing graph-based methods incorporate target-awareness at the feature or attention level, they remain permutation-invariant and lack an explicit mechanism to control information propagation order, limiting their ability to model target-dependent importance and long-range dependencies. In contrast, Graph-Mamba highlights that node prioritization through sequence ordering is critical for effective global reasoning. In this work, we investigate the node prioritization mechanism in Graph-Mamba and study its role in object navigation. We propose Graph-MambaNav, a target-aware spatial-temporal graph encoding framework that introduces a heuristic ordering over objects based on their relevance to the target, allowing more informative objects to be processed later to aggregate richer context. Both node ordering and edge weights are initialized from LLM-derived commonsense object relationships, providing a unified prior for structured reasoning. A spatial module integrates local message passing with global GraphMamba-based selective scanning, while a temporal module applies Mamba-based sequence modeling over object-wise temporal orders, allowing selective aggregation of historical context for long-range temporal reasoning. Experiments on AI2-THOR and RoboTHOR demonstrate improved navigation performance with generalization, and additional real-world robot deployment further validates the effectiveness of our proposed approach.

We propose a sensor-guided adaptive contrastive learning framework for visual representation learning in PointGoal navigation. During training, privileged LiDAR sensing guides the contrastive objective through a geometry-aware similarity metric and adaptive temperature scaling, encouraging visual embeddings to capture navigation-relevant structure rather than scene-specific appearance. The resulting encoder is pretrained independently, frozen, and used as the perceptual backbone for reinforcement learning, decoupling representation learning from policy optimization. We further introduce a cross-stage domain mismatch between representation pretraining and policy learning to suppress environment-specific shortcuts and promote reliance on task-relevant features. Extensive experiments in high-fidelity simulation demonstrate that our approach significantly improves policy-level scene transfer across diverse indoor and outdoor environments. At deployment, the agent relies only on monocular RGB observations together with standard task-related inputs such as goal position and proprioceptive signals, without access to LiDAR or other privileged sensors. Our method outperforms large pretrained vision models and standard contrastive baselines under severe appearance and semantic shifts. We also release a multimodal dataset to support future research on privileged-guided visual representation learning for navigation. The code is available at:

Monolithic vision-action models represent an emerging paradigm in autonomous driving. However, this architecture produces token sequences that quickly exceed real-time computational budgets when encoding extended temporal context for complex interactions. While approaches like linear transformers and external memory try to make the context lightweight, token compression is most compatible with the architecture as it requires no backbone modifications. Yet existing compression adopts rule-based heuristics like temporal decay, decoupled from planning, risking loss of decision-critical information. We propose COMPACT-VA, a planning-aligned working memory framework built on conditional VQ-VAE, compressing extended context into bounded representations. Compression is conditioned on both historical trajectory and a learned planning intent that the posterior encoder distills from future trajectories during training, while the prior encoder learns to predict it from compressed observations. The compressed memory, concatenated with the predicted latent, feeds the policy for end-to-end optimization, planning with retained decision-critical information. We evaluate on high-signal dynamic scenarios where historical context is most critical for behavior correctness (e.g., stop, yield, or proceed), and accordingly design behavioral metrics. Under comparable token budgets, we achieve $>$6% improvement (68.3%) on success rates with consistent gains across metrics. Ablations validate planning-aligned coupling effectiveness. Closed-loop evaluation confirms that COMPACT-VA maintained general driving performance with 3.3* speedup and 2.7* memory reduction over uncompressed processing.

Image-goal navigation using lightweight topological maps is a practical paradigm for indoor robot deployment: the map requires only geotagged images, and localization relies on visual matching rather than precise pose estimation. However, learned waypoint predictors can produce targets that violate geometric constraints or deviate from the global path. Executing these waypoints safely further requires a local planner capable of collision avoidance, yet existing systems either lack one or rely on fixed parameters that cannot adapt to confined spaces. To address these limitations while retaining the navigational intuition of the learned predictor, we present EgoNav, a hierarchical system that implements this idea by generating candidates from semantically segmented traversable regions and scoring them alongside the learned waypoint for geometric safety, directional coherence, and fidelity to the learned prior. An adaptive local path planner then executes the refined waypoint with parameters modulated based on the refinement outcome. Experiments in Habitat-sim and on a physical humanoid robot show that EgoNav consistently outperforms contemporary baselines in both success rate and path efficiency.

Many aerial tasks involving quadrotors demand both instant reactivity and long-horizon planning for obstacle avoidance, energy efficiency, or trajectory tracking. High-fidelity models enable accurate control but are too slow for long horizons. Low-fidelity planners scale but cannot directly control the system, necessitating cascaded architectures. Prevailing hierarchical approaches plan with a simplified model and use a high-fidelity controller for tracking, yet this decomposition is inherently suboptimal. The controller is limited by the coarse plan, and conventional MPC alternatives shorten the horizon to stay real-time feasible. We present UNIQUE, an MPC architecture that replaces this hierarchical stacking with temporal cascading. The planning problem is formulated as the second-tail horizon of a single multi-phase MPC, rather than being solved separately. We align costs across horizons, derive feasibility constraints for the point-mass planning model, and introduce transition constraints that convert high-fidelity states into meaningful low-fidelity states. Parallel point-mass and mixed-integer solvers address nonconvexities while incorporating progressive 3D obstacle smoothing over the planning horizon. In simulations and real flights, under equal computational budgets, UNIQUE improves closed-loop tracking by up to 75% compared with standard MPC and hierarchical baselines. Ablations and Pareto analyses confirm performance gains across variations in horizon, constraint approximations, and smoothing schedules.

Unmanned aerial vehicle (UAV) swarm agents operating in radio-frequency (RF)-degraded environments require coordination mechanisms that connect directly observable signals to executable responses. This work presents an embodied visual-communication approach in which bio-inspired motion–LED glyphs are represented by a reduced six-parameter semantic chart embedded within a full 24-dimensional hybrid execution manifold. A learned translator large language model (LLM) maps a perceived glyph to a response that is instantiated as an executable trajectory and propagated through closed-loop quadrotor dynamics. The system is evaluated in 200 three-UAV search-and-rescue trials with receiver-specific degradation from sensing range, field of view, occlusion, and relative motion. Under clean observations, the quantized small model and rule-based translator both achieve $$100\%$$ 100 % semantic correctness, but under single- and two-parameter corruption, the quantized small model achieves $$64.7\%$$ 64.7 % and $$64.1\%$$ 64.1 % , compared with $$44.8\%$$ 44.8 % and $$35.2\%$$ 35.2 % for rule-based, while reducing mean multi-agent trajectory error from $$2.902~\textrm{m}$$ 2.902 m to $$0.993~\textrm{m}$$ 0.993 m . All methods maintain $$100\%$$ 100 % rotor-allocation and finite-horizon feasibility. The quantized small model also has comparable overall semantic correctness with the large model ( $$83.3\%$$ 83.3 % vs. $$86.3\%$$ 86.3 % ) while dropping latency from $$5.115~\textrm{s}$$ 5.115 s to $$2.789~\textrm{s}$$ 2.789 s and is validated onboard a Jetson–Pixhawk UAV platform, where airborne inference and bounded command execution produce measurable physical motion. These results establish a unified pathway from degraded visual observation to semantically meaningful, dynamically grounded UAV coordination.

This paper introduces Embodied Scene Rearrangement Planning (ESRP), a novel task requiring embodied agents to rearrange furniture in 3D scenes to match a target configuration using only egocentric observations and a top-down target layout. Unlike prior rearrangement tasks, ESRP precludes global state access and introduces mutual object occlusions, reflecting the practical constraints of real-world robotic deployment. These factors make aligning partial egocentric observations with the global target layout particularly challenging for long-horizon planning. To facilitate research, we present ESRP-Bench, a comprehensive benchmark built on OmniGibson featuring over 5,400 scene pairs and 8,200 objects. We define three multi-level metrics to evaluate rearrangement quality and provide four baselines: a hierarchical task-and-motion planning method, a vision-language-model-based method, and two learning-based approaches (IL and RL). Experimental results demonstrate that current methods struggle to complete the task efficiently, highlighting ESRP as a challenging frontier for embodied agents in scene understanding and long-horizon task planning. This work serves as a stepping stone toward deploying intelligent agents in real-world scenarios. Project page: https://pie-lab.cn/ESRP/.

Navigation in the natural world is a feat of adaptive inference, where biological organisms maintain goal-directed behaviour despite noisy and incomplete sensory streams. Central to this ability is the Free Energy Principle (FEP), which posits that perception is a generative process where the brain minimises Variational Free Energy (VFE) to maintain accurate internal models of the world. While Deep Neural Networks (DNNs) have served as powerful analogues for biological brains, they typically lack the real-time plasticity required to handle abrupt sensory shifts. We introduce FEP-Nav, a biologically inspired framework for real-time perceptual adaptation in robust visual navigation. Motivated by the decomposition of VFE into prediction error and Bayesian surprise, FEP-Nav combines a Top-down Decoder, which provides an internal expectation of uncorrupted sensory input, with Adaptive Normalisation, which adjusts shifted feature distributions toward prior statistics. We interpret reconstruction and normalisation as approximate mechanisms for reducing the corresponding VFE-related terms during inference without gradient-based updates. Experiments across simulated and real-world visual corruptions show that FEP-Nav restores performance lost under visual corruption, outperforming non-adaptive baselines and strong adaptive methods. These results suggest that variational principles can provide a useful design perspective for robust autonomous behaviour under degraded sensory conditions.

Flapping-wing micro aerial vehicles offer quieter and safer operation than rotary-wing drones, yet achieving precise autonomous control of bird-scale ornithopters remains challenging: lift, airspeed, and turning authority are tightly coupled and governed by only a few control inputs. Conventional cascaded controllers treat altitude, speed, and heading independently, producing persistent tracking errors during complex maneuvers, while time-parameterized trajectory tracking requires predefined speed profiles that existing methods cannot robustly produce for these coupled dynamics. We address both limitations simultaneously with a Model Predictive Contouring Control (MPCC) approach that tracks arc-length-parameterized trajectories while optimizing progress online, eliminating the need for predefined timing. However, MPCC requires a dynamical model that captures the coupled aerodynamics without exceeding the computational budget of real-time nonlinear optimization. Here, we propose a compact, continuously differentiable model that captures the dominant couplings of bird-scale ornithopters, enabling real-time predictive control. We validated the method with the XFly ornithopter flying along circular and three-dimensional racing trajectories and achieved a mean deviation from the reference trajectory between 6.5 and 9 cm at speeds up to 3 m/s, which represents an 8.5x improvement over prior ornithopter control methods.

Robust stereo visual-inertial odometry (VIO) remains challenging in low-texture scenes and under abrupt illumination changes, where point features become sparse and unstable, leading to ambiguous association and under-constrained estimation. Line structures offer complementary geometric cues, yet many efficient point-line systems still rely on point-guided line association, which can break down when point support is weak and may lead to biased constraints. We present a stereo point-line VIO system in which line segments are equipped with dedicated deep descriptors and matched using an entropy-regularized optimal transport formulation, which performs global mass-transport assignment and supports unmatched observations under ambiguity, outliers, and partial observations. The proposed descriptor is training-free and is computed by sampling and pooling network feature maps. To improve estimation stability, we analyze the impact of line measurement noise and introduce reliability-adaptive weighting to regulate the influence of line constraints during optimization. Experiments on EuRoC and UMA-VI, together with real-world deployments in low-texture and illumination-challenging environments, demonstrate improved accuracy and robustness over representative baselines while maintaining real-time performance.

We present Riemannian Informed Trees (RIT*), a planning framework that replaces Euclidean primitives in batch-informed search with their Riemannian counterparts. RIT* constructs a tighter, cost-consistent informed set, performs a nearest-neighbour search under an anisotropic distance metric, and evaluates edge costs efficiently via a cascading scheme. We further introduce a Collision-Adaptive Metric Refinement (CARM), which learns an obstacle-proximity cost field online from collision feedback, reducing the reliance on prior metric design in practical settings. Experiments across environments from 2-D to 14-D show that RIT* is competitive in low-dimensional and spatially constant-metric settings and produces substantially lower-cost solutions when the metric varies spatially in high-dimensional configuration spaces. Performance gains scale with anisotropy and dimension, reaching up to 13.0% improvement in median initial cost over BIT* in the 3-D anisotropic benchmark, up to 9.0% in median final cost over BIT* in 6-DOF manipulation, and 24.8-63.5% in a 14-DOF bimanual planning problem, where Euclidean-informed baselines degrade. Videos and code can be found here: https://muhayyuddin.github.io/ritstar/

Skill abstraction---the process of learning reusable and temporally extended behaviors---has emerged as a key paradigm for improving sample efficiency and generalization in robot learning. For efficient skill transfer to real robots, learned skills must generalize across tasks and domains, remain robust to visual and dynamic perturbations, and be efficient enough for practical deployment. However, existing methods typically satisfy only a subset of these properties, as they capture either high-level semantic intent (what) or low-level motion dynamics (how). This incomplete skill transfer yields weak priors for policy learning, thereby demanding substantial in-domain data for downstream adaptation. To address these challenges, we introduce BooST, a two-stage framework that explicitly bridges semantics and motions to satisfy all three desiderata. BooST first leverages a cross-modal VQ-VAE to capture both semantic intent and motion dynamics, yielding a unified skill representation. It then distills this representation into a lightweight policy for efficient downstream adaptation to new tasks. Extensive experiments across simulation and real-robot settings demonstrate that BooST achieves superior few-shot adaptation, cross-domain skill transfer, and robustness to dynamic visual distractors, while maintaining a lightweight yet expressive design suitable for real-world deployment.

From early Movement Primitive (MP) techniques to modern Vision-Language Models (VLMs), autonomous manipulation has remained a pivotal topic in robotics. As two extremes, VLM-based methods emphasize zero-shot and adaptive manipulation but struggle with fine-grained planning. In contrast, MP-based approaches excel in precise trajectory generalization but lack decision-making ability. To leverage the strengths of the two frameworks, we propose VL-MP, which integrates VLM with Kernelized Movement Primitives (KMP) via a low-distortion decision information transfer bridge, enabling fine-grained robotic manipulation under ambiguous situations. One key of VL-MP is the accurate representation of task decision parameters through semantic keypoints constraints, leading to more precise task parameter generation. Additionally, we introduce a local trajectory feature-enhanced KMP to support VL-MP, thereby achieving shape preservation for complex trajectories. Extensive experiments conducted in complex real-world environments validate the effectiveness of VL-MP for adaptive and fine-grained manipulation.

In the automated sorting and processing of agricultural products, the nonlinear mechanical degradation induced by lipid oxidation severely restricts the grasping reliability of high‐fat fragile targets. To address the resulting damage and slip issues, this study proposes a damage‐less grasping strategy driven by an oxidation prior, integrating variable impedance control and quadratic programming‐based control barrier functions (QP‐CBF). By fusing multimodal optical and tactile information, the proposed strategy utilizes hyperspectral imaging to predict the degree of oxidative deterioration, mapping this prior into a dynamic safety threshold for the normal gripping force. Furthermore, fractional‐order calculus is introduced to reconstruct the viscoelastic mechanical response of the targets, effectively suppressing the normal force overshoot during the initial contact phase. To mitigate the spatial slippage risks exacerbated by strict underlying force constraints, the framework employs a QP‐CBF module to dynamically constrain hazardous spatial accelerations, thereby achieving active anti‐slip intervention. Experiments conducted on multi‐gradient oxidized samples demonstrate that under severe oxidation‐induced embrittlement, the proposed intervention mechanism effectively compensates for the friction deficit. Compared to conventional feedforward perception strategies that frequently fail due to insufficient normal gripping force, our approach improves the intact handling success rate by 37%, achieving an overall success rate exceeding 93%. These results indicate that the integrated control framework successfully resolves the physical contradiction between preventing breakage and avoiding slippage, providing a highly robust algorithmic reference for the compliant robotic manipulation of fragile objects.

Multi-modal trajectory generation is essential for safe autonomous driving, yet existing diffusion-based planners suffer from high inference latency due to iterative neural function evaluations. This paper presents MISTY (Mixer-based Inference for Single-step Trajectory-drifting Yield), a high-throughput generative motion planner that achieves state-of-the-art closed-loop performance with pure single-step inference. MISTY integrates a vectorized Sub-Graph encoder to capture environment context, a Variational Autoencoder to structure expert trajectories into a compact 32-dimensional latent manifold, and an ultra-lightweight MLP-Mixer decoder to eliminate quadratic attention complexity. Importantly, we introduce a latent-space drifting loss that shifts the complex distribution evolution entirely to the training phase. By formulating explicit attractive and repulsive forces, this mechanism empowers the model to synthesize novel, proactive maneuvers, such as active overtaking, that are virtually absent from the raw expert demonstrations. Extensive evaluations on the nuPlan benchmark demonstrate that MISTY achieves state-of-the-art results on the challenging Test14-hard split, with comprehensive scores of 80.32 and 82.21 in non-reactive and reactive settings, respectively. Operating at over 99 FPS with an end-to-end latency of 10.1 ms, MISTY offers an order-of-magnitude speedup over iterative diffusion planners while while achieving significantly robust generation.

Musculoskeletal robots require an internal body schema that remains consistent under a wide range of physical state changes, including abnormalities such as muscle rupture and actuator jamming. Conventional approaches based on autoencoders or variational autoencoders learn average behaviors by projecting sensor and actuator signals into a low-dimensional latent space; however, exploration within the latent space alone has limited capability to handle out-of-distribution or abnormal states that are not included in the training data. To address this limitation, this study proposes a diffusion-based framework for body schema learning in musculoskeletal robots. Unlike generative models that operate through low-dimensional latent spaces, diffusion models can directly and iteratively estimate physically consistent sensor and actuator values in the high-dimensional space through a denoising process, even under partial observations and constraints, without requiring retraining. By formulating body schema adaptation as a gradient-guided denoising process, the proposed method enables adaptive estimation of appropriate muscle lengths and muscle tensions even under abnormal conditions such as muscle rupture and actuator jamming. The validity of the proposed framework is verified through simulation experiments using a musculoskeletal robot model.

Kinodynamic planning for car-like vehicles on uneven terrain requires simultaneously optimizing competing objectives such as path efficiency and pose stability. This work presents an adaptive epsilon-constraint method integrated into a Model Predictive Control (MPC) framework, where the epsilon bounds are dynamically adjusted based on terrain descriptors to explore the Pareto front in real time. To capture vehicle-terrain dynamics, we develop a semi-parametric model combining analytical vehicle dynamics with a Sparse Gaussian Process (SGP) trained on the same terrain descriptors. The proposed epsilon-MPC is evaluated against MPPI and GAKD baselines, achieving a 94% navigation success rate while reducing maximum orientation deviation by 24% and improving multi-objective trade-off quality by 23%.

In structured multi-agent transportation systems, agents often must follow predefined routes, making spatial rerouting undesirable or impossible. This paper addresses route-constrained multi-agent coordination by optimizing waypoint passage times while preserving each agent's assigned waypoint order and nominal route assignment. A differentiable surrogate trajectory model maps waypoint timings to smooth position profiles and captures first-order tracking lag, enabling pairwise safety to be encoded through distance-based penalties evaluated on a dense temporal grid spanning the mission horizon. The resulting nonlinear and nonconvex velocity-scheduling problem is solved using an inexact-projection Alternating Direction Method of Multipliers (ADMM) algorithm that combines structured timing updates with gradient-based collision-correction steps and avoids explicit integer sequencing variables. Numerical experiments on random-crossing, bottleneck, and graph-based network scenarios show that the proposed method computes feasible and time-efficient schedules across a range of congestion levels and yields shorter mission completion times than a representative hierarchical baseline in the tested bottleneck cases.

Many fish species are capable of leaping out of water, and several robotic fish have been developed to mimic this behavior. However, enhancing jumping performance and achieving low‐altitude gliding—as seen in flying fish—remain challenging. This study presents a bionic flying‐fish robot capable of efficient high‐speed swimming and water‐exiting motion. Its morphology is reconstructed from a 3D scan of a flying fish, a representative cross‐medium organism. Unlike conventional jumping robotic fish, the proposed design features an optimized body shape and an improved tail‐drive mechanism, which reduce kinetic energy loss during high‐frequency oscillation. Experimental tests and analyses of the Strouhal number (St) and Reynolds number (Re) confirm efficient propulsion and swimming characteristics comparable to real fish, with a maximum speed of 2.54 m/s. The simplified pectoral‐fin structure further enables agile steering and pitching control. During high‐speed swimming, the Froude number (Fr) exceeds 1, demonstrating the robot's ability to fully exit the water. In the test, the robotic fish was able to leap out of the water to a height of 0.5–0.55 m at a sprint angle of to . These results highlight the robot's exceptional locomotion performance and provide insights for the design of cross‐medium robotic systems.

Electroaerodynamic propulsion is compelling for use in micro air vehicles due to its silent and solid-state nature, but its limited efficiency has thus far precluded a path towards power-autonomous flight. Recent work has shown that thrust density and efficiency for small-scale atmospheric ion thrusters can be vastly increased when operating close to a ground plane. Here, we explore the design space of centimeter-scale hovercraft, which can leverage this ground effect for low-altitude flight. We first perform an empirical investigation, characterizing the performance benefits and trade-offs for different geometries and configurations of passive hovercraft skirts, then use the results to fabricate a viable point design. We demonstrate a palm-sized hovercraft that, while tethered to an external power source, can fly for extended periods, withstand dozens of takeoff and landing cycles, passively stabilize to reject significant mechanical disturbances, and generate practically zero audible noise signature. The measured thrust efficiency of 16 mN/W and additional payload capacity of almost 1.5 grams above the vehicle's self mass of about 1.6 grams exceeds any similarly sized electroaerodynamically propelled robot by an order of magnitude. This is the first time an ion-propelled micro hovercraft has been shown in the open literature, and our work points the way towards an entirely new class of robot.

Autonomous 3D reconstruction with depth sensors is strongly affected by reflective surfaces, which cause missing or unreliable measurements and reduce the effectiveness of conventional Next-Best-View (NBV) strategies. This limitation is particularly critical in industrial applications involving reflective components and low-cost, low-resolution depth sensing, where robustness to sensing failures is essential. This paper proposes a Fast Reflectivity-Aware Next-Best-View (FRA-NBV) strategy that explicitly addresses reflection-induced depth loss without relying on prior object models or assumptions on material reflectance, making it suitable for a wide range of industrial configurations. Reflective regions are identified from the spatial distribution of missing depth measurements and localized in three-dimensional space using an online ellipsoid-based representation of the object estimate. A recovery strategy then selects additional poses that modify the sensor's angle of incidence to improve the likelihood of reconstructing the affected regions. Experiments on objects with different geometric and reflective complexity demonstrate that the approach significantly improves reconstruction coverage under realistic industrial conditions.

Various drawbacks exist in traditional visual SLAM methods for wind turbine blade polishing scenarios. Insufficient feature extraction, unstable matching, and reduced positioning accuracy are easily produced. These issues are triggered by weak textures, strong reflections, and illumination fluctuations. A point‐line fused visual‐inertial positioning method named EPL‐VINS is therefore proposed. FAST feature points and EDLines feature lines are adopted in the visual front end of this method. An adaptive threshold feature detection strategy and a texture complexity‐based feature distribution optimization mechanism are put forward, so that the capability of effective feature extraction is strengthened and the spatial distribution of features is optimized. At the back end, a tightly coupled optimization framework based on sliding window is constructed. Marginal prior information, IMU pre‐integration residuals, visual point‐line feature residuals, and loop closure constraints are all integrated into the optimized objective function to realize the joint estimation of visual and inertial information. Meanwhile, the LM optimization algorithm is improved by the dynamic update strategy of damping factors, and the convergence speed and numerical stability of back‐end nonlinear optimization are enhanced. On the public EuRoC data set, an average positioning accuracy improvement of 22.3% is achieved by EPL‐VINS compared with VINS‐Mono. Higher positioning accuracy and environmental adaptability are also exhibited by EPL‐VINS in actual factory scenarios for wind turbine blade polishing. High‐precision robot positioning is realized by the proposed method in complex industrial environments.

Path planning for orchard robots is one of the most fundamental technologies of smart agriculture. Introducing reinforcement learning (RL) into path planning has become a promising approach at the frontier of robotics research, addressing the problem that existing methods primarily focus on the optimal path at the immediate moment, lack a holistic perspective, and fail to achieve optimal overall performance. However, the sim‐to‐real issue presents a critical challenge for implementing RL in orchard robots. To solve this issue, an RL‐enhanced path‐planning method is proposed for orchard robots. The proposed method avoids directly using RL to generate a path, thereby eliminating the primary source of the sim‐to‐real problem in RL. In the proposed method, multiple candidate paths are computed using a Bézier curve and are physically navigable for robots, leveraging LiDAR to dynamically update the environmental map. Meanwhile, a comprehensive reward function is designed for RL to achieve optimal path planning. Subsequently, RL is employed to select the optimal path among multiple candidate paths, thereby avoiding the sim‐to‐real problem in complex orchard environments. Finally, validation tests are carried out in both simulation and field environments. The experimental results show that the proposed method effectively addresses the sim‐to‐real challenges of RL and achieves optimal path planning.

Embodied artificial intelligence (Embodied AI) aims to develop agents that can perceive, reason, and act through continuous interaction with physical world. To achieve this goal, agents must not only understand visual scenes and language instructions, but also transform multimodal information into executable actions. This requirement calls for models that can integrate perception, semantic reasoning, and action generation within a unified decision‐making framework. Recent advances in large language models (LLMs) have provided important technical foundations for this integration, leading to emergence of vision‐language‐action (VLA) models as a central paradigm for embodied systems. Although existing surveys have reviewed Embodied AI from perspectives such as robotic systems, simulation environments and task settings, few have systematically analyzed action‐generation mechanisms of VLA models. This limitation makes it difficult to distinguish VLA architectures. To address this gap, we provide a comprehensive review of VLA models for Embodied AI from an action‐generation perspective. We first formulate VLA models as embodied decision‐making systems that map visual observations and language instructions to action sequences through interaction with dynamic environments. Building on this formulation, we review historical evolution of VLA models. Furthermore, we propose an action‐generation‐centered taxonomy that categorizes VLA models into three paradigms: direct policy learning, generative action modeling, and reasoning‐guided modeling. For each paradigm, we analyze representative methods, action‐generation mechanisms, advantages and limitations, thereby providing a coherent framework for comparing diverse VLA architectures. Beyond model architectures, we summarize key resources and benchmarking settings and discuss recent applications. Finally, we identify major challenges and future directions. By organizing VLA models around the central problem of action generation, we aim to provide a structured technical map for future research toward more general, reliable, and physically grounded Embodied AI.

With the goal of effective chlorophyll mapping in space and time using autonomous underwater vehicles, we study algorithms for hotspot sampling. We develop, implement and test a sampling algorithm using the expected improvement in chlorophyll to evaluate potential sampling designs. Working in a depth and lateral mode, the vehicle intelligently chooses the survey path for each sampling stage. The onboard system for design evaluation and data assimilation builds on a Gaussian random field representation of the log chlorophyll variations in north, east, depth, and time coordinates. Using a grid-free approach with spatio-temporal thinning of data, the random field model is quickly updated with in situ measurements made by the autonomous vehicle. This approach further enables real-time calculations for the expected improvement criterion used for sampling decisions. Via simulation studies, we compare the suggested sampling approach with others. Results of trials in the Mausund area, Norway, are used to demonstrate field deployments of our implementation for adaptive sampling. Here, we also discuss and compare the chlorophyll samples with that of zooplankton data gathered at the same locations.

Path planning for construction robots in complex construction environments suffers from insufficient adaptability, poor path quality, and high computational cost. This paper proposes a hierarchical path planning method based on improved‐bidirectional‐rapidly‐exploring random tree‐artificial potential field. The proposed method integrates the following key techniques: (1) a semantically enhanced unified bounding volume hierarchy collision detection mechanism for identifying multiple categories of construction obstacle; (2) goal‐biased sampling and dynamic step size to enhance global search efficiency, combined with a modified potential field to improve obstacle avoidance; turning‐angle constraints and B‐spline smoothing are applied to optimize trajectory feasibility; (3) a weakly coupled mechanism model of the mobile vehicle and the robotic arm to reduce computational complexity. Digital twin and large language model are introduced to further enhance the engineering practicality. Ablation experiments are conducted in multiple simulation scenarios based on a scaled cable‐truss structure, demonstrating the superiority of the method in effectiveness and efficiency.

This study develops a binocular stereo vision system to enhance the operational safety of agricultural unmanned aerial vehicles (UAVs) by detecting and localizing thin cables—one of the most prevalent and hazardous obstacles in farmland environments. The system integrates cost‐effective hardware (dual OV4689 CMOS sensors, 36°/8 mm lenses, 120 mm baseline) with a process‐enhanced SemiGlobal Block Matching algorithm, specifically tailored to address the core challenge of low‐contrast cable detection in complex agricultural settings. The algorithmic innovation combines Hue, Saturation, and Lightness color space segmentation with adaptive dynamic threshold processing, effectively resolving cable feature extraction under variable illumination conditions and intense background interference from crops or terrain. Experimental results demonstrate maximum detection distances of 14.547 and 16.846 m for 20 and 40 mm diameter cables, respectively, with an average ranging error of 0.055 m (0.58% error rate). UAV Flight tests confirm reliable obstacle avoidance within a 2–5 m/s velocity range, achieving an average braking distance of 11.828 m—sufficient to ensure safe maneuvering given agricultural UAVs' inherent dynamic constraints of high moment of inertia and low thrust‐to‐weight ratio. Compared with conventional approaches, the proposed system exhibits superior chromatic separation between cables and backgrounds and enhanced dynamic noise suppression, while maintaining low hardware cost. This renders it a highly cost‐efficient and deployable safety solution for agricultural scenarios with dense cable distributions. The research outcomes provide robust technical support for autonomous obstacle avoidance of agricultural UAVs and offer significant practical value for improving operational safety in precision agriculture.

In robot operation, ensuring the robot can safely contact the target requires accurate contact force information. At present, in most scenarios, robots can accurately measure contact force using force sensors. However, in special environments such as healthcare and nuclear industries, due to the limited installation space for sensors and the harsh working conditions, the use of force sensors faces numerous challenges and is difficult to deploy widely or operate stably. Therefore, this paper proposes a robot end force estimation method without force sensors. This method utilizes the state information of each joint of the robot and establishes the correlation between the contact force and the state information through the Neighbor‐Aware RNN Network we proposed to accurately estimate the contact force at the robot end. This neural network can handle the dynamic temporal characteristics of the information of each joint of the robot, as well as the spatial correlation information of each joint. It learns the relationship between the state information of each joint of the robot and the contact force through an end‐to‐end approach, and ultimately outputs the three‐axis force estimation results. The experimental results show that this method performs exceptionally well in the task of robot contact force estimation, and its various evaluation indicators are significantly superior to those of other force estimation methods.

Maintaining traffic restrictions has become more difficult because growing number of vehicles on the road, particularly in locations with high populations. Efficient traffic monitoring and road safety management have become critical challenges due to the rapid increase in vehicular density in urban environments. This paper proposes a novel IoT‐aided robotic framework, termed MAGCNN‐RTMS‐IoT‐AR, for real‐time traffic sign detection and recognition using the German Traffic Sign Recognition Benchmark (GTSRB) dataset. Initially, the input images are pre‐processed using an Innovation Saturated Koopman Kalman Filter (ISKKF) to enhance data quality and robustness against noise. Subsequently, a Multi‐component Attention Graph Convolutional Neural Network (MAGCNN) is employed to effectively capture spatial and contextual dependencies for accurate classification of traffic signs. To further improve model performance, a Gradient Jellyfish Search Algorithm (GJSA) is integrated for optimal parameter tuning. The proposed approach is evaluated using multiple performance metrics, including accuracy, precision, recall, F 1‐score, error rate, loss, and mean square error (MSE). Experimental results demonstrate that the proposed method; significantly outperforms existing models such as RTMS‐IoT‐LeNet‐5, EATS‐CR‐CNN, and ETSR‐DS‐VGG‐16, achieving notable improvements in 19.36%, 24.82%, and 31.36%, higher accuracy; 21.62%, 24.54%, and 30.54% higher precision. The integration of IoT, robotics, and optimized deep learning makes the proposed system highly suitable for real‐time intelligent transportation applications.

Rice cultivation is a cornerstone of global food security, yet effective weed management remains a critical challenge. Autonomous weeding robots offer a sustainable alternative, but their efficacy hinges on precise navigation, particularly in the complex visual environments of paddy fields. This study introduces a novel instance segmentation‐based navigation line extraction method tailored for paddy‐field robots. Unlike conventional machine vision techniques, which struggle with noise, water reflections, and irregular crop rows, our approach leverages a lightweight instance segmentation model to accurately identify and differentiate rice seedling rows. The model, optimized for deployment on resource‐constrained edge devices like the Jetson Nano, achieves high precision with minimal angular and pixel deviations (0.54° and 6.40 pixels, respectively). It also demonstrates real‐time inference speeds of 16.13 FPS, making it suitable for practical applications. Furthermore, our method eliminates the need for high‐precision data annotation, reducing labeling complexity and enhancing generalizability. Comparative experiments with existing methods, such as YOLOv8‐seg, ESNet, VGG‐UNet, Mobile‐UNet, and Mobile‐DeeplabV3+, demonstrate that our method achieves superior performance in both accuracy and computational efficiency. The proposed navigation line extraction method not only meets the demands of agricultural robots in paddy fields but also lays a foundation for future advancements in automated field navigation, potentially integrating GNSS/INS systems for fully autonomous operations. This research represents a significant step toward sustainable and efficient agricultural practices, addressing both environmental and economic challenges in rice cultivation.

In this study, a bionic fin drive system suitable for deep‐sea environments is proposed. The system heats the phase change material (PCM) through the heat‐conducting medium and converts the expansion generated during the phase change process into hydraulic energy. Finally, the tail fin swing and pectoral fin expansion are realized through a novel motion conversion device, which offers the advantages of simple structure and low cost. In addition, the effects of the heat transfer medium and the thickness of the fish body outside the phase change actuator (PCA) on the output performance of the fin PCA were analyzed. The flexible adjustment of the tail fin's swinging characteristics can be realized by adjusting the voltage and duty cycle applied to the PCA heating sheet. A bionic fish prototype equipped with a phase‐change drive system has been successfully fabricated. The experimental results indicate that the robot can swim straight at a speed of 36 mm/s and complete a quick turn with a radius of 3.2 BL. Through the simulation of deep‐sea environment experiments, the robot can still achieve flexible underwater movement under water pressure of up to 110 MPa without bulky pressure‐resistant devices. These excellent performances demonstrate the reliable movement ability of the bionic robotic fish in the extreme deep‐sea environment.

Acoustic fields are emerging as a promising wireless and tissue‐penetrant power source for micro‐ and nanorobots, with propulsion efficiency, steering precision, and biocompatibility all critically linked to fabrication strategy. To clarify these interdependencies, we conducted a Preferred Reporting Items for Systematic Reviews and Meta‐Analyses (PRISMA)‐guided systematic review of literature from Scopus, Web of Science, PubMed, and IEEE Xplore (January 1, 2010–May 31 2025). Of 144 records, 63 primary studies and 22 secondary/background sources met predefined criteria and were synthesized. The evidence reveals five dominant actuation modes: boundary‐driven streaming (~40%), bubble oscillation (~25%), acoustic radiation forces (~12%), whole‐body resonance (~13%), and hybrid magneto‐/chemo‐acoustic mechanisms (~9%), each shaped by distinct fabrication approaches. Photolithography produces sharp fins for high‐Re streaming; soft lithography forms gas‐tight cavities for cavitation; two‐photon and micro‐DLP printing achieve nanometer‐scale smoothness for radiation‐pressure traps; and emerging multimaterial printers combine rigid acoustic chambers with magnetic or catalytic components. Three themes recur: (i) geometry–material–control co‐design consistently outperforms sequential prototyping; (ii) scalability and biocompatibility remain major barriers, with ad hoc quality metrics; and (iii) inverse‐design algorithms and closed‐loop acoustic imaging are accelerating optimization. This review maps fabrication techniques to actuation demands and application contexts, offering a consolidated roadmap toward clinically and industrially viable acoustic microrobots.

This paper presents an active disturbance rejection dynamic positioning (DP) control scheme of overactuated autonomous underwater vehicles (AUVs) for inspection missions. The proposed control scheme consists of dynamic control and control allocation. First, the DP process of the slender‐shaped AUV is decomposed into three sequential stages: yaw regulation, path following and position keeping. The tracking error calculation and control allocation are distinctively designed based on the motion performance of the AUV in each stage. Second, the adaptive line‐of‐sight (ALOS) guidance and extended state observer (ESO) are constructed to estimate and compensate for external disturbances to meet the high‐accuracy positioning requirements. A stability analysis is provided to establish the local UUB property of the closed‐loop system. Third, the thruster dead‐zone effect is compensated by shifting the control commands, and smooth control allocation between rudder and thrusters is achieved using a smooth transition function. Finally, the effectiveness and robustness of the proposed DP control scheme are verified through comparative lake trials. Compared to the conventional PID controller, the proposed method achieves statistically significant tracking error reductions () and substantially reduces equivalent control effort during steady‐state station‐keeping by suppressing actuator chattering.