Vision-language-action (VLA) models provide a promising paradigm for scalable robotic manipulation, yet their reliance on success-only behavioral cloning leaves them brittle; lacking corrective training signals, minor execution errors rapidly compound into unrecoverable, out-of-distribution failures. To address this limitation, we propose Adaptive Failure-Informed Learning (AFIL), an end-to-end framework that leverages failure trajectories as adaptive negative guidance for diffusion- and flow-based VLA policies. AFIL uses a pretrained VLA to generate failure rollouts online, avoiding the need for handcrafted failure-mode design or human-in-the-loop recovery. It then jointly trains Dual Action Generators (DAGs) for successful and failed behaviors while sharing a common vision-language backbone, enabling efficient failure-aware policy learning with limited parameter overhead. During sampling, the failure generator adaptively steers action generation away from failure-prone regions and toward more reliable success modes, with guidance strength determined by the per-diffusion-step distance between success and failure distributions. Experiments across in-domain and out-of-domain robotic manipulation tasks, covering both short- and long-horizon settings, show that AFIL consistently improves task success rates and robustness over existing VLA baselines, demonstrating its effectiveness, efficiency, and generality.
https://arxiv.org/abs/2610.37330
This work investigates the use of event-based spiking controllers, implemented as spiking neural networks, for trajectory tracking in underactuated robots. Specifically, we address the problem of stabilizing a prescribed periodic orbit. It is well known that, by applying the method of transverse linearization to the robot dynamics in a neighborhood of a periodic trajectory, the dynamics can be approximately described by a linear time-varying system with periodic coefficients (a periodic LTV system). The problem of orbital stabilization can therefore be reduced to stabilizing the trivial solution of this LTV system. We show that a previously proposed Lyapunov-based greedy design, originally developed for LTI systems, can also be extended to the corresponding linearized transverse dynamics, which take the form of a periodic LTV system. This enables the construction of a feedback controller for orbital stabilization of the robot. The effectiveness of the proposed method is demonstrated on the trajectory stabilization problem for the butterfly robot.
https://arxiv.org/abs/2610.37310
Human-robot collaboration requires partners to coordinate interdependent contributions toward a shared goal. Joint Action theory provides concepts for understanding this coordination, but how these concepts are instantiated and combined across empirical research remains fragmented. We conducted a systematic review following PRISMA 2020, identifying 83 empirical papers published between 2021 and 2026. Through theory-driven framework analysis, we organized the literature into nine constructs across three capacities: Representation, Prediction, and Integration. We analyze how these constructs are distributed and co-occur across studies, revealing where empirical evidence concentrates and where it is absent. By mapping empirical HRC research onto a unified Joint Action framework, this review offers a coherent overview of HRC studies, identifies gaps in current evidence, and provides guidelines for future research.
https://arxiv.org/abs/2610.37298
Autonomous vehicles in enclosed spaces such as tunnels and mines rely on range maps that smoke, dust and fog make inaccurate. Conformal prediction calibrates a keepout around the mapped walls that covers the true unsafe set at a chosen probability. Typically an unmodified planner treats the keepout as an inflated obstacle, and nothing ensures that the vehicle can stop before the keepout as it moves when sensing degrades. In narrow passages this margin and the planner's buffer close the route, and existing remedies recover reach by relaxing the coverage level. This paper conditions the conformal margin on a label-free severity estimate to hold coverage near its target as degradation varies. A planning and control layer enforces one braking-distance condition on the keepout at plan time and at every command, takes the measured tracking residual as its only margin and never alters the keepout. The keepout is validated on ground-robot smoke recordings and the closed loop in simulated quadrotor flights in a foggy tunnel against the standard deployment. In closed-loop simulation the proposed system substantially reduces entries into the calibrated keepout and reaches numerically more goals than the deployment pattern in both calibration regimes, an observed gain of 3.2 percentage points pooled whose per-regime confidence intervals include zero. The per-class keepout holds its coverage near the target on held-out recordings.
https://arxiv.org/abs/2610.37217
Vision-Language-Action (VLA) policies demonstrate remarkable semantic generalization, yet remain highly vulnerable to out-of-distribution (OOD) visual shifts during execution. While existing test-time methods attempt to suppress spurious visual cues, they fundamentally overlook the rich, uncorrupted kinematic priors embedded in the policy's own training experience. We introduce Retrieve to Act (R2A), a test-time scaling framework that formulates OOD robustness purely as a geometric motion primitive retrieval problem. R2A bypasses fragile visual features by structuring successful training demonstrations into an offline spatiotemporal motion primitive graph. During inference, a query-dependent Graph Neural Network dynamically localizes the robot's ongoing execution within this graph, retrieving structurally compatible future motion primitives. These retrieved geometric priors are then seamlessly harmonized with the frozen VLA's predicted actions via a learned, dimension-wise gating mechanism, adaptively rectifying erroneous spatial trajectories while preserving the policy's local reactivity. Extensive experiments across three state-of-the-art VLA architectures, GR00T N1.7, $\pi_{0.5}$, and StableVLA, demonstrate that R2A consistently and significantly enhances robustness against diverse contextual perturbations. R2A achieves absolute success rate improvements of up to +12% in simulation benchmarks (LIBERO-Plus, RoboTwin2.0-Plus) and +40% in real-world deployments, without requiring any finetuning of the base policies. Project page: this https URL
https://arxiv.org/abs/2610.37215
Humanoids and other legged robots operating in complex environments must remember information that leaves their field of view and only becomes relevant much later. Reinforcement learning policies address this using memory networks such as LSTMs that are trained end-to-end with the policy to memorize such task-relevant aspects. Yet, such architectures often fail to preserve sufficient information over long horizons. In this work, we propose a network architecture based on Hadamard memory that specifically targets robot navigation. Our Local Spatial Matrix Memory (LSMM) enables RL agents to store generic task-relevant information at specific, position-based memory cells, enabling flexible and spatially grounded memorization. We evaluate LSMM on the task of autonomous maze exploration, where it matches the maze coverage of strong recurrent and finite-history baselines while being the only architecture that remembers the maze layout, reducing the reconstruction error threefold.
https://arxiv.org/abs/2610.37203
Legged robots for lunar exploration must be designed for low gravity, where reduced contact forces and long flight phases make leg morphology and controller choice interdependent. We study this for a planar monoped in lunar gravity ($1.625$ m/s$^2$) using a bi-level co-design framework: a differential evolution outer loop searches over link lengths, and each candidate is evaluated on a vertical jump by either a quadratic program based task-space controller (QP-TSC) or a direct-collocation based trajectory optimization. The two controllers yield different optimal link lengths, and trajectory optimization outperforms the QP-TSC across most of the design space, with 17% lower Cost of Transport (COT) at their respective optima. We then extend to a 2D jump, where trajectory optimization with centroidal angular momentum regulation produces stable in-place and forward jumps, and an LQR controller absorbs impact and stabilizes the robot after touchdown. This is demonstrated on a baseline morphology with both links 0.3 m long.
https://arxiv.org/abs/2610.37199
Flapping-wing micro air vehicles are prized for quiet flight, yet the few existing measurements show engineered wings to be 15-30 dB louder than the animals they imitate. This paper investigates two passive geometric approaches to reduce the acoustic signature of a flapping membrane wing, and applies these to an exemplary wing. A significant sound source in flapping wings is the impulsive click radiated at stroke reversal, when a slack membrane snaps between two curvatures. Our first noise-reduction approach optimises the wing's venation layout, based on an analytical model of the reversal click as a dynamic snap-through of the membrane. The optimised venation pattern was manufactured and resulted in a reduction of up to 8 dB during the reversal snap in experiments. During testing, the venation was found to be sensitive to orientation rather than thickness. Secondly, an additive trailing-edge fringe inspired by hummingbird feathers was shown to further reduce the broadband swoosh by 3-4 dB at no lift cost, matching a cut serration wing without removing lifting area.
https://arxiv.org/abs/2610.37190
We trained four widely used imitation-learning policies, ACT, Diffusion Policy, SmolVLA and $\pi_{0.5}$, on nested subsets of 12, 25, 50, 100 and 200 teleoperated demonstrations of one pick-and-place task with distractor objects, using one fixed training recipe per policy. Every trained model was then run on a physical SO-101 arm on a fixed set of object placements: 1,340 scored episodes in 126 blocks. ACT, trained from scratch, rose from 1 success in 40 episodes at 12 demonstrations to 37 in 40 at 100. $\pi_{0.5}$ with its action expert fine-tuned was the best policy when data was scarce (16 of 40 at 12 demonstrations, 28 of 40 at 25) and then stayed near 70%; from 100 demonstrations ACT was ahead, by a margin this study does not fully resolve. SmolVLA and Diffusion Policy peaked near 50%, and both were affected by a failure to start: SmolVLA's arm never started moving in 47% of episodes, and Diffusion Policy hardly ever started until an idle lead-in was trimmed from the demonstrations. For $\pi_{0.5}$ the fine-tuning recipe mattered more than the amount of data: low-rank adaptation succeeded in 4 of 110 episodes, against 130 of 200 for action-expert fine-tuning. From the joint and camera recordings we place every episode on a four-stage ladder (started, reached the ball, carried it, delivered it) and show that for ACT more data moves failures from reaching, to grasping, to none, while the failures $\pi_{0.5}$ retains are in grasping. We also measure how weak a ten-episode block is as a measurement (the same checkpoint tested twice differs by 2 successes in 10 on average), separate seed-to-seed variation from that noise, and audit the human scoring against the recordings. Training length was fixed within each recipe, so the amount of data and the number of times it was seen change together; we state which conclusions survive that confound and which do not.
https://arxiv.org/abs/2610.37170
Multi-robot informative path planning (IPP) for persistent target monitoring requires robots to reason about spatial uncertainty, temporal evolution, and practical sensing and communication constraints. Recent learning-based multi-robot IPP methods use Gaussian Processes (GPs) for target uncertainty, but often rely on simplified sensing models and centralized belief updates. We propose a grid-based spatio-temporal GP-Kalman filtering framework for learning-based multi-robot IPP. Instead of maintaining one GP per target, we represent anonymous target presence as a single latent field over a discrete workspace grid. The proposed recursive update assimilates footprint-level camera measurements and supports arbitrary fields of view and range-dependent noise. A GP-derived temporal process update inflates uncertainty over time to account for moving targets. For decentralized deployment, each robot maintains its own mapper and exchanges fixed-size belief summaries rather than raw measurements. Received beliefs are fused using diagonal covariance intersection to remain conservative under unknown inter-robot correlations. We integrate the mapper with a reinforcement-learning policy for graph-based neighbor selection. In simulation, the centralized deployment improves target visitation and attains about 20% lower posterior target uncertainty than learning-based and classical auction/coverage baselines, a large share of which stems from the belief representation itself. A real-world two-UAV experiment demonstrates transfer to outdoor multi-robot search over a large field (>7000 m^2). Code is available at this https URL.
https://arxiv.org/abs/2609.05515
Active simultaneous localization and mapping (SLAM) addresses the problem of planning robot motion to build complete and accurate maps of unknown environments through efficient exploration while maintaining high localization accuracy. This raises a dilemma between exploring unknown spaces to expand coverage and exploiting visited regions to perform active loop closures. Despite numerous prior works on ground robots, aerial robots with high agility and constrained sensor suites face more significant localization drift and thereby demand dedicated active SLAM planning. Moreover, a unified strategy that adapts performance based on task-specific priorities remains an open question. In this article, we introduce RAVEN, a unified active SLAM framework for Rapid Autonomous Visual ExploratioN using quadrotors, which systematically accounts for localization uncertainty. The framework starts with identifying frontiers and active loop closure candidates, from which global tour candidates are generated. These candidates are evaluated using a utility vector that separately quantifies exploration efficiency and localization accuracy, and the final tour is selected according to a prioritization parameter ranging from $[0,1]$. Finally, a perception-aware navigation planner generates smooth execution trajectories that minimize visual state estimation error based on the online Fisher information field that provides visual localization information in real-time. Benchmark evaluations demonstrate that RAVEN outperforms state-of-the-art active SLAM methods, highlighting its advantages in producing a spectrum of performance across prioritizations. Fully onboard field experiments with a customized stereo-inertial quadrotor further validate its practical applicability in challenging environments. The source code will be released to benefit the community.
https://arxiv.org/abs/2610.37111
World-action models (WAMs) incorporate the prediction of future observations into robot policy learning. However, most WAMs build on billion-parameter vision-language or video-generation backbones, which incur high training cost and inference latency. In this letter, we present GAWM (Geometry-Aware World Model), a compact multi-task WAM that predicts future observations in the latent space of a frozen DINOv3 encoder. GAWM compresses the features of each camera view into a small set of tokens. A lightweight predictor, conditioned on the task rather than on actions, forecasts these tokens at two future horizons. The forecast is supervised with the dense patch features of future frames, which requires it to encode the spatial layout of the future scene. An action decoder directly regresses a chunk of future actions from the current and predicted tokens. With fewer than 100M parameters and no robot or video pretraining, GAWM outperforms billion-parameter WAMs on RoboTwin 2.0 and performs comparably to billion-parameter VLAs on LIBERO. On a dual-arm robot, it achieves lower action-prediction error on held-out demonstrations than a fine-tuned billion-parameter VLA, with substantially lower inference latency. Ablation studies show that the latent world model substantially improves performance when training data or training time is limited. Code is available at this https URL.
https://arxiv.org/abs/2610.37091
Spacecraft-mounted robotic manipulators can support long-term operability of orbiting assets by conducting tasks such as on-orbit assembly, repair, upgrade, and refueling. In this context, the integration of continuum/soft robotic mechanisms into space manipulator designs promises to reduce stowage volume and mass, as well as to improve operational safety through the inherent mechanical compliance of soft structures. This work presents a novel state reconstruction pipeline for a hybrid soft-rigid space manipulator, in which the distal link is a tendon-driven continuum robot. The estimation problem is formulated as a maximum a posteriori (MAP) inference problem over the hybrid manipulator's configuration, conditioned on discrete, noisy measurements from joint encoders and a vision-based sensing pipeline. The resulting soft-constrained optimization problem is transcribed as a factor graph, providing a compact representation for fusing heterogeneous measurements with the rigid-soft kinematic model. Furthermore, the adoption of the Geometric Variable Strain (GVS) approach yields a minimum-order parameterization of the configuration, a property expected to facilitate model-based feedback control design in future work. The proposed implementation is validated in simulation on a closed-loop trajectory where, for better realism, position measurements for the continuum link are obtained by means of a simulated visual pipeline leveraging synthetic photorealistic images. The state reconstruction accuracy and computational performance confirm the potential of the proposed framework for hybrid soft-rigid robotic applications in orbit.
https://arxiv.org/abs/2610.37043
This paper presents a mixed discrete-continuous multiobjective bilevel framework for the structure-actuation co-design of all-electric heavy-duty robotic manipulators. The upper level optimizes manipulator geometry and actuation topology, while joint-specific lower-level searches construct feasible archives of discrete motor, gearbox, and screw configurations. A system-level coordinator selects actuator packages according to hardware mass, co-design cost, and loss-aware supply energy, and the resulting actuator masses are fed back to the robot model until a mass-consistent fixed point is obtained. Evaluation on a full-pose SE(3) benchmark with a 100-kg tool payload yields eight feasible nondominated designs, all satisfying the 12 prescribed poses. Actuator-mass coupling converges in three iterations for every reported design. A fixed-design ablation shows that one-pass sequential sizing changes hardware mass by up to 2.13%, co-design cost by 10.20%, and supply energy by 9.40% in magnitude. Payload screening further reveals increasing mass-cost-energy demand and changes in competitive mechanism topology with carried load.
https://arxiv.org/abs/2610.36996
Image-goal navigation (ImageNav) requires an agent to reach a location specified by a goal image in an unknown environment. For drones, this task demands exploration, goal- directed navigation, and collision avoidance under limited onboard computing resources. Existing aerial ImageNav methods are built on single-view observations, requiring additional rotation and exploration to search for goal-relevant cues outside the field of view. In this paper, we present Omni-IGN, a fully onboard ImageNav system that integrates quad-fisheye perception, an attention-based reinforcement learning (RL) policy, and a collision-aware safety layer. The policy adaptively fuses goal-relevant features across multiple views to provide directional guidance for continuous navigation. The quad-fisheye RGB images support both ImageNav and obstacle avoidance without a dedicated depth sensor. On Habitat benchmarks, Omni-IGN achieves the best performance among continuous-action baselines. Moreover, flight tests in IsaacSim validate the effectiveness of integrating learning-based depth estimation with the action safety layer for collision avoidance. Finally, real-world experiments demonstrate zero-shot sim-to-real transfer without any fine-tuning or external localization. The code and model checkpoints will be released upon acceptance.
https://arxiv.org/abs/2610.36968
Maintaining contact in non-prehensile manipulation requires more than nominal friction cone feasibility: a force barely inside the cone and one well inside it are both feasible, but they provide different margins against slip and contact loss. This paper uses signed friction distance to measure friction margin in force space and derives a task-adaptive margin from the force correction needed to balance pivot moment deviations in bimanual tilting. The resulting contact margins are embedded in a sequence of second-order cone programs (SOCPs), each giving a globally optimal contact force solution at a tilt angle. The optimizer balances the object about an environmental pivot while keeping robot and pivot contact forces away from the nominal friction boundary. Optimizer-level results show interpretable force redistribution and adaptation to object property changes. Real-world experiments demonstrate successful execution under object property variations and model mismatch, while fixed margin and no-margin comparisons illustrate the importance of adapting the margin to task demand. These results support signed friction distance margins as a force planning mechanism for maintaining contact in bimanual non-prehensile manipulation. Project page: this https URL
https://arxiv.org/abs/2610.36961
Robot foundation models may generalize across tasks and embodiments, but their actions still depend on sensors that can fail. When the policy is frozen or inaccessible, can an external monitor diagnose and repair corrupted inputs without access to its internals? We test a structured surrogate that separates periodic gait from sensor-dependent corrections to guide input repair around a frozen locomotion policy. On simulated Go2, offline diagnosis raises walking success from 259/640 to 429/640 episodes; online repair reaches 382/640, with no triggers in 64 held-out fault-free episodes. A matched boosted-tree surrogate predicts clean actions similarly well but yields no detected repair improvement over no repair. Separate fits improve walking on Go1 and ANYmal C, although phase-aware gradients perform better. Evidence remains limited to one policy and a partly screened simulated fault suite; robot foundation model and hardware validation remain open.
https://arxiv.org/abs/2610.36852
World Action Models (WAMs) learn representations for robot control by coupling future visual prediction with action generation. Successful manipulation depends primarily on how the robot and task-relevant objects evolve, whereas future-video prediction must also reconstruct the appearance and background of the entire scene. We therefore propose Trace-WAM, which augments video-action learning with future 3D motion prediction as an auxiliary objective. This objective supervises temporal point correspondence together with image-plane displacement and depth change, directly describing the interaction dynamics and spatial changes involved in manipulation. To this end, we adopt a three-branch Mixture-of-Transformer (Tri-MoT) architecture to jointly learn video prediction, motion prediction, and action generation. The motion expert predicts future trajectories from current visual features, allowing motion supervision to shape the representations used for action generation. Because the action expert does not consume predicted trajectories, inference retains the current-observation policy path: a single visual forward pass followed by action denoising. Experiments on RoboCasa-GR1, LIBERO, and LIBERO-Plus demonstrate strong in-distribution performance and out-of-distribution generalization, with particularly clear gains over Fast-WAM under limited demonstrations and distribution shifts.
https://arxiv.org/abs/2610.36840
Generative planners are often evaluated by the trajectories they can generate, although closed-loop driving ultimately depends on the single candidate committed to control. We identify this mismatch as the sample-to-execution gap and show that improving proposal quality alone can worsen the executed decision. Here, we introduce ExecDiffuser, a recurrent proposal-to-execution framework that couples candidate generation, trajectory selection, and subsequent replanning through shared execution semantics. Intent-Guided Diffusion Proposal (IGD) assigns hypothesis responsibility and shapes trajectories with execution-conditioned supervision. Execution-Grounded Selection (EGS) learns a candidate-conditioned publication utility, commits one trajectory to control, and returns it as context for the next planning cycle. Across nuPlan, InterPlan, and NAVSIM, ExecDiffuser achieves leading closed-loop performance against strong state-of-the-art baselines. Under a unified five-seed protocol, it obtains an average score of 85.62, improving over Diffusion Planner and FlowDrive by 4.02 and 1.31 points, respectively. On NAVSIM, it achieves 92.6 PDMS under the official evaluation pipeline. Matched counterfactual analysis further shows that ExecDiffuser more reliably converts strong candidates into committed decisions, while prefix interventions confirm that this advantage persists after physical execution and subsequent replanning.
https://arxiv.org/abs/2610.36837
Humanoid parkour requires robots to reason about future footholds and whole-body motions over highly discontinuous terrain. We revisit the information asymmetry in asymmetric actor-critic learning for perceptive humanoid locomotion: the critic exploits privileged simulator signals during training, whereas the deployable actor operates solely from onboard perception. We argue that the key is not exposing privileged information to the actor, but learning a deployable approximation of it to narrow the information gap between training and deployment. We present HC2Robot, a deployable perceptive humanoid parkour framework consisting of a Predicted Foresight Module (PFM) and a Hyper-Connection (HC) Transformer. PFM predicts from deployable observations the policy-conditioned timing, location, and support quality of each foot's next touchdown event, converting privileged supervision into a deployable latent representation that provides the actor with predicted touchdown information without privileged runtime sensing. The HC Transformer further enhances temporal reasoning through learnable multi-stream routing, while a future motion prediction head provides short-horizon motion priors for regularization. Across stairs, gaps, high platforms, and slopes, HC2Robot achieves a mean simulated traversal success rate of 97.60% and consistently higher safe foothold rates than strong perceptive locomotion baselines, supporting improved traversal performance and geometric foothold support under deployable sensing.
https://arxiv.org/abs/2610.36825