https://hu-zlatan.github.io/embodied-ai-radar/topics/learning.xml 2026-10-29T00:00:00ZEmbodied AI Radar https://arxiv.org/abs/2610.37666 2026-10-28T00:00:00Z

Vision-Language-Action (VLA) models have made substantial progress in robotic manipulation, but their generalization remains constrained by the diversity and coverage of action-labeled robot demonstrations. Human videos provide much broader behavioral and environmental experience, while learning from them faces a fundamental trade-off between scalable data and explicit action grounding. We introduce ThinkWorld, a VLA learning framework that grounds action reasoning in world dynamics and strengthens it through reinforcement learning with world imagination. ThinkWorld represents each action …

https://arxiv.org/abs/2610.37547 2026-10-28T00:00:00Z

Imitation policies that reliably execute most of a manipulation trajectory can still fail in localized regions requiring last-mile precision. Updating the full policy or exploring residual actions everywhere treats this local failure as a global learning problem. We introduce Adaptive Residual Correction (ARC), a lightweight post-training module that uses reinforcement learning (RL) to learn a residual correction on top of a frozen policy while using sparse human corrections to structure autonomous exploration. Rather than treating human corrections as imitation targets, ARC uses …

https://arxiv.org/abs/2610.37543 2026-10-28T00:00:00Z

Event cameras offer low latency, high dynamic range, and milliwatt-level power consumption, making them ideal for agile robots such as tiny drones navigating through cluttered environments. However, existing simulators generally render photorealistic images before converting them into events, making large-scale reinforcement learning prohibitively slow. We propose an analytic event simulator that exploits what event cameras fundamentally measure - moving contrast edges - to synthesize event streams directly from scene geometry and ego-motion without visual rendering. Our simulator generates a …

https://arxiv.org/abs/2610.37535 2026-10-28T00:00:00Z

A joint of pipe run into the hole swings from the elevator over the well and strikes a fixed stabbing guide at whatever speed the swing has. StabBot, a robotic stabbing system, predicts the swing and meets the pipe at its own speed. A pendulum Kalman filter tuned from the pipe tally tracks the joint in stereo images. A six-axis arm with an open V-shaped roller head closes in at matched velocity, confirms the last millimetres by touch, aims the pin over the box when the elevator hangs off centre, and follows the block down with lateral compliance. A ResNet-18 keypoint network locates the pipe, …

https://arxiv.org/abs/2610.37470 2026-10-28T00:00:00Z

Medium altitude, long endurance unmanned aerial systems such as Shahed-type strike drones are an unanswered threat in modern conflicts. Conventional air defense systems are too expensive to provide a feasible large-scale solution. Quadcopter interceptors are a cheap, battle-proven alternative, but their extremely limited flight time restricts them to low altitude targets at short range, whereas fixed-wing platforms have the endurance to reach higher altitude targets from longer distances. However, such interceptors are still operated manually. Recent developments in learning-based controllers …

https://arxiv.org/abs/2610.37441 2026-10-28T00:00:00Z

Objective: This study aims to determine whether a hip-exoskeleton policy trained in simulation, by co-adapting with a musculoskeletal human model under a metabolic-energy reward, reduces the metabolic cost of walking in new users without per-user tuning, and how mechanical-power shaping affects the learned assistance. Methods: We developed MARL-Exo, a multi-agent reinforcement learning framework in which a full-body human model (304 muscle actuators; randomized anatomy, gait, and speed) and a bilateral hip-exoskeleton policy are trained concurrently in two stages. The exoskeleton observes …

https://arxiv.org/abs/2610.37393 2026-10-28T00:00:00Z

Robot policy evaluation often relies on a binary success signal for task completion. In real-world deployment, however, desired execution behaviors are also defined by quality attributes such as execution speed and motion smoothness, which need to be dynamically controlled according to task requirements. To address this, we introduce Quality-Controllable Policy (QCP), a robot policy that enables inference-time control over both individual quality attributes and their combinations. To extend the controllable quality range beyond initial demonstrations, we further propose an iterative hindsight …

https://arxiv.org/abs/2610.37378 2026-10-28T00:00:00Z

Vision-Language-Action (VLA) models integrate high-level reasoning with low-level action execution for end-to-end robotic control. However, most VLA models target static manipulation in unconstrained environments, overlooking spatial constraints and dynamic obstacles. Fine-tuning VLAs on obstacle-avoidance data is a straightforward solution, but collecting such data is costly, especially for dynamic scenarios, and may degrade their original task capabilities. To address these limitations, we propose VLA-Stem, a lightweight, reinforcement-learning-based safety mechanism for VLA systems. …

https://arxiv.org/abs/2610.37203 2026-10-28T00:00:00Z

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 …

https://arxiv.org/abs/2610.37170 2026-10-28T00:00:00Z

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 …

https://arxiv.org/abs/2610.37091 2026-10-28T00:00:00Z

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 …

https://arxiv.org/abs/2610.36968 2026-10-28T00:00:00Z

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) …

https://arxiv.org/abs/2610.36852 2026-10-28T00:00:00Z

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 …

https://arxiv.org/abs/2610.36452 2026-10-28T00:00:00Z

While velocity-commanded RL policies are effective for controlling quadrupeds, they are a limited interface for humanoids that need to perform complex whole-body motions. Furthermore, RL tracking policies for whole-body motions typically have limited information about the desired future motion, preventing them from performing controlled deviations to achieve long-term task success; such information is particularly relevant when a controller must prepare for transitions between behaviors. We address these challenges using concise motion representations that can be generated by a high-level …

https://arxiv.org/abs/2610.36374 2026-10-28T00:00:00Z

Robotic agents operating in real-world environments must adapt continuously from a stream of multimodal demonstrations, often under constraints that preclude storing or revisiting past data. In this replay-free, single-pass lifelong imitation learning setting, sequential updates can progressively distort the representation space, making expert-based approaches particularly sensitive to routing interference, causing expert selection to degrade over time. We propose HIDRA, a structured routing framework that mitigates this issue through a hierarchical dual-attention mechanism, which decouples …

https://arxiv.org/abs/2610.36309 2026-10-28T00:00:00Z

Deep reinforcement learning (RL) algorithms have been observed to lose the ability to adaptively learn from new data, a phenomenon termed Loss of Plasticity (LoP). While many metrics have been shown to correlate with it, the causal mechanisms and the geometric conditions from which it can arise have not been clearly identified. We analyze LoP in Proximal Policy Optimization with isotropic Gaussian policies, the state-of-the-art formulation for many continuous action spaces in RL. We report multiple metrics which characterize the effect that the policy standard deviation $\sigma$ has on LoP, …

https://arxiv.org/abs/2610.36068 2026-10-28T00:00:00Z

Action-conditioned world models offer a scalable alternative to costly real-world interaction for improving robot policies. However, existing world-model-based methods largely treat world models as forward-only surrogates of the physical environment, leaving untapped a capability no physical environment affords: rewinding to past decision points to explore counterfactual futures. We introduce Rollback, a policy improvement paradigm that turns world models from passive simulators into counterfactual engines: it rolls back to critical decision points, branches into alternative actions, and …

https://arxiv.org/abs/2610.35852 2026-10-27T00:00:00Z

This paper proposes a smooth analytic gradient for frictional contact and applies it to policy learning and contact-implicit trajectory optimization for legged locomotion. The exact contact sensitivity is available in closed form but describes changes within the current contact mode, providing no first-order information toward neighboring contact modes. The proposed gradient replaces this sensitivity only in the backward pass, leaving the hard-contact forward solve unchanged and the realized rollout feasible. A central-path relaxation of the de Saxc\'e-corrected second-order-cone …

https://arxiv.org/abs/2610.35733 2026-10-27T00:00:00Z

Multi-objective reinforcement learning is a fundamental problem for modern AI, with applications spanning post-training, reasoning models, and robotic control. A central challenge is to learn policies that balance competing objectives, such as helpfulness versus honesty in safety and alignment, or speed versus energy in robotics. The optimal policy can vary sharply with objective-weighting combinations, and the extent of this variation depends crucially on the degree of conflict among objectives, making per-preference policy learning sample-inefficient. In this paper, we introduce …

https://arxiv.org/abs/2610.35604 2026-10-27T00:00:00Z

Generalist robot policies and language-model agents provide complementary capabilities, but completing a task also requires adapting their use to the consequences of physical interaction. We study execution as a locus of adaptation: feedback guides the current action and supplies evidence for revising subsequent decisions under fixed model weights. We introduce RoboDoctor, a training-free framework that connects diagnosis, grounded action, and persistent experience across three revision targets. The harness allocates control between policy and agent; intervention determines when to assist …

https://arxiv.org/abs/2610.35494 2026-10-27T00:00:00Z

Training robotic manipulation policies in simulation is widely adopted due to safety and cost efficiency; however, tasks involving obstacles remain under-performing and often converge slowly under Deep Reinforcement Learning (DRL). To address this challenge, we propose a task decomposition framework for DRL that integrates Transfer Learning (TL) with Reward Redesign (RR) to improve learning efficiency and robustness in obstacle environments. The TL strategy selectively transfers only the first-layer critic parameters across structurally related tasks, since that layer captures general …

https://arxiv.org/abs/2610.34839 2026-10-27T00:00:00Z

Human behaviour models are increasingly used to provide simulated human interactions for training robots via reinforcement learning (RL). Existing approaches primarily evaluate these models according to how closely their generated behaviours resemble real human data, while their usefulness as training partners is less commonly assessed. This creates a potential objective mismatch: a model that performs well according to behavioural evaluation metrics may not necessarily provide useful training experiences for downstream robot policy learning. Across two human-robot interaction (HRI) domains, …

https://arxiv.org/abs/2610.34466 2026-10-27T00:00:00Z

Achieving safety in autonomous driving through Multi-Agent Reinforcement Learning (MARL) is a critical yet challenging task due to non-stationarity, partial observability, and the need for effective coordination among agents. Although earlier cooperative MARL methods have aimed to improve coordination by sharing encoded state observations, we find these strategies are insufficient in safety-critical scenarios. To address this gap, we present IntNet, a novel MARL framework that enhances safety by incorporating the transmission of vehicle intent and adaptive communication scheduling into a …

https://arxiv.org/abs/2610.34280 2026-10-27T00:00:00Z

Endowing robot policies with anticipatory capabilities has proven effective in improving control performance. However, existing methods predominantly rely on explicit supervision derived from future observations, in either pixel or latent space, at the cost of additional architectural and computational complexity. Departing from explicit future supervision, we ask whether such foresight can be elicited directly from the action signal. To this end, we propose \textbf{AdaPolicy}, an \textbf{A}ction-\textbf{d}riven \textbf{a}nticipatory policy framework that shapes future-aware representations …

https://arxiv.org/abs/2610.33584 2026-10-27T00:00:00Z

Cooperative transport with heterogeneous legged robots requires coordinating different motion capabilities while supporting an unfixed shared payload. We present HA-DiPO (Heterogeneous-Agent Diffusion Policy Optimization), a hierarchical multi-agent reinforcement learning framework under centralized training with decentralized execution (CTDE). The framework decouples team-level coordination from embodiment-specific motion control: at the high level, a centralized critic uses team-value estimates to jointly train independent coordination policies, aligning robot-specific action responses with …

https://arxiv.org/abs/2610.33565 2026-10-27T00:00:00Z

Robot policy evaluation informs deployment decisions and policy improvement, but physical testing and simulator preparation require substantial effort. World models offer a complementary route through closed-loop interaction in generated environments. Recent benchmarks have demonstrated their potential as policy evaluators through outcome-based evaluation (i.e., assessing task success or failure). However, such evaluation does not establish whether world models faithfully simulate how policies fail. Misrepresenting failures can lead to incorrect diagnoses of policy weaknesses and make …

https://arxiv.org/abs/2610.33494 2026-10-27T00:00:00Z

Dexterous manipulation requires robots to leverage existing datasets for rapid skill acquisition while maintaining safety during real-world deployment to prevent damage to the robot or its surroundings. Offline-to-online safe reinforcement learning (O2O safe RL) provides a promising solution for this problem by leveraging prior experience for online improvement under safety constraints, thereby mitigating the sample inefficiency and exploration risk of learning safe policies from scratch. However, existing O2O safe RL approaches do not explicitly account for the safety budget already consumed …

https://arxiv.org/abs/2610.33480 2026-10-27T00:00:00Z

Dexterous manipulation requires high-dimensional control policies to accomplish complex contact-rich tasks while simultaneously satisfying multiple safety requirements, such as joint limits, unsafe finger configurations, arm collisions, and unstable object interactions. Constrained reinforcement learning (RL) provides a principled framework for incorporating these requirements into dexterous manipulation policy learning. However, existing constrained RL methods for dexterous manipulation primarily focus on cumulative cost constraints and struggle to simultaneously handle multiple …

https://arxiv.org/abs/2610.32971 2026-10-26T00:00:00Z

Robust reinforcement learning (RL) is critical for reliable real-world deployment, where policies may fail under diverse shifts and disruptions. Existing robust RL algorithms offer a rich set of mechanisms and principles, yet two major barriers limit their broader potential: limited algorithm reusability and an unclear empirical capability boundary. We introduce RobustRLlib, an algorithm-centric library and benchmark that addresses both challenges. It integrates 17 representative robust online, offline, and safe RL algorithms under a unified interface for substantially improved reusability, …

https://arxiv.org/abs/2610.32855 2026-10-26T00:00:00Z

Regularised reinforcement learning (RL) has provable robustness guarantees that should ease the transfer of policies from simulation to robots, known as sim-to-real. Yet, weakly regularised algorithms like Proximal Policy Optimisation (PPO) remain the de facto choice in sim-to-real pipelines, while the practical benefits of regularisation for transfer remain poorly characterised. In this work, we study the sim-to-real performance of commonly used RL algorithms, with the aim of characterising the effects of regularisation on robotic performance. To that end, we derive Soft MellowMax …

https://arxiv.org/abs/2610.32538 2026-10-26T00:00:00Z

These lecture notes provide an introduction to optimization, optimal control, and reinforcement learning for robotics, emphasizing their mathematical connections and practical relevance. They present established material compiled and edited by Yonghyeon Lee, rather than new research results. The notes were developed through a human and AI collaborative writing process, with AI assistance in drafting, organizing, and refining the exposition. This first version is a preliminary collection of notes, not yet a fully developed textbook, and currently contains no figures or graphs. The notes may be …

https://arxiv.org/abs/2610.32439 2026-10-26T00:00:00Z

Designing effective reward functions is a critical challenge in Reinforcement Learning (RL), which traditionally requires costly manual trial-and-error. While Large Language Model (LLM)-based methods have shown promise in reward design, undifferentiated sampling and limited use of historical feedback often lead to insufficient exploration of the reward space and optimization instability. To address these challenges, we propose $R^2E$, a Role-driven Reward Evolutionary framework for automated reward function design that structures the process through explicit role specialization. $R^2E$ …

https://arxiv.org/abs/2610.32431 2026-10-26T00:00:00Z

A failed vision-language-action (VLA) rollout does not imply that every action contributed to failure. Yet in group-relative policy optimization (GRPO), a single trajectory-level advantage is assigned to all actions in a rollout. Potentially useful recovery attempts can thus be penalized alongside the errors they aim to correct. Ideal stopping conditions for failure feedback are characterized using success-probability and policy-score martingales. At these stops, the removed gradient contribution has zero conditional expectation given the retained information. Truncation therefore preserves …

https://arxiv.org/abs/2610.32225 2026-10-26T00:00:00Z

Recent robot manipulation policies commonly predict continuous action chunks directly from observations, without explicitly modeling reusable structure in the action space. However, manipulation demonstrations often contain recurring short-horizon motion patterns that are shared across tasks. We introduce \textsc{RoboCode}, which learns these patterns through a shared soft-gated primitive action interface. Rather than assigning each action chunk to a single discrete code, \textsc{RoboCode} represents it as a soft composition of multiple learned primitives, providing a flexible intermediate …

https://arxiv.org/abs/2610.32143 2026-10-26T00:00:00Z

Robot-assisted dressing is particularly challenging due to narrow openings and articulated body parts. Even small errors in the relative pose between the body part and garment opening can cause snagging, missed insertion, or incomplete dressing. To address these challenges, we formulate dressing as a geometry-aware insertion problem that represents task-relevant spatial relationships between the body part and object opening, rather than relying on the full deformable-object state. Based on this formulation, we propose a Reinforcement Learning (RL) framework combining a staged curriculum, …

https://arxiv.org/abs/2610.32093 2026-10-26T00:00:00Z

Behavior cloning for robotic manipulation is highly sensitive to the coverage of its training data, yet collecting diverse successful demonstrations remains costly. We study reinforcement learning (RL) not as a deployable controller, but as a data generator for downstream visuomotor imitation learning. Our key premise is that multiple successful solution modes cover a broader range of successful trajectories than repeatedly collecting a single narrow solution. We introduce DiscoDemo, which trains a privileged latent-conditioned RL generator with a parallel reverse curriculum and a …

https://arxiv.org/abs/2610.31845 2026-10-26T00:00:00Z

Scaling policy learning requires broad experience and reliable supervision. Robot demonstrations provide high-quality trajectory supervision but are costly to collect. Egocentric videos broaden task and environment coverage, yet motion reconstruction and retargeting introduce noisy action labels. To address this challenge, we introduce EgoForesight, a vision-language-action framework that learns jointly from both sources by reducing the influence of unreliable action labels and exploiting demonstrated outcomes as complementary supervision. A joint vision-action flow couples future visual …

https://arxiv.org/abs/2610.31829 2026-10-26T00:00:00Z

Real-world reinforcement learning has enabled contact-rich manipulation tasks to be trained directly on physical robots, but unsafe interactions during online learning remain a key barrier to practical deployment. We propose Safe Evidential Real-World Reinforcement Learning (SEVI), a framework for reliability-aware safety intervention during real-world policy learning. SEVI introduces an Evidential Safety Critic that estimates both future constraint-violation risk and epistemic uncertainty in a single forward pass. During online learning, SEVI evaluates each task-policy action before …

https://arxiv.org/abs/2610.31812 2026-10-26T00:00:00Z

Preference-based reinforcement learning (PbRL) has emerged as a promising paradigm for learning robot behaviors aligned with human intent. However, its scalability is fundamentally limited by the need to collect expensive human preference labels for every new task. In this work, we present PrefO2O, an offline-to-online latent preference transfer framework that enables zero-shot PbRL on unseen target tasks without requiring any human feedback. The core idea is to learn a task-invariant latent preference space from a small amount of offline preference data on source tasks, where transferable …

https://arxiv.org/abs/2610.31617 2026-10-23T00:00:00Z

Tasks such as quadrotor dynamic-gate racing require agents to anticipate external motion while maintaining precise high-frequency control. World-model-based reinforcement learning provides a natural solution by learning latent dynamics for future imagination, yet it often entangles environmental evolution and the robot's own dynamics in a single learned rollout, where model bias can affect policy optimization efficiency. We propose DiffDreamer, a differentiable reinforcement learning framework that tightly couples a learned world model with differentiable simulation for actor optimization. In …

https://arxiv.org/abs/2610.31608 2026-10-23T00:00:00Z

Humanoid mobility over complex terrain requires accurate foot placement and coordinated whole-body motion capable of robust adaptation. Reinforcement learning (RL) policies trained without motion references generalize well across terrains, yet eliciting effective whole-body coordination through reward design and exploration alone remains challenging. In contrast, reference-based methods yield natural motions but struggle to adapt beyond the predefined trajectories in their training data. We introduce a learning framework that bridges these two approaches by using motion data strictly as a …

https://arxiv.org/abs/2610.31427 2026-10-23T00:00:00Z

Agentic robot systems combine language-model reasoning with robot policies to monitor execution and recover from failures. However, reviewing every action chunk incurs substantial overhead, even in familiar situations. We introduce FastHarness, an experience-driven execution harness that adaptively schedules GPT-6 Astra supervision of a {\pi}0.5 policy. A fast path uses stage memory and reviewed outcomes to reduce review frequency as experience accumulates, while a complementary recovery path focuses supervision on correcting errors. Once recovery is verified, routine execution resumes, with …

https://arxiv.org/abs/2610.31010 2026-10-23T00:00:00Z

End-to-end control policies trained via Reinforcement Learning (RL) have emerged as an alternative to conventional surgical robotic control approaches, with recent studies exploring state-based policies trained on privileged state observations. However, such approaches rely on precise physical states that are difficult to obtain reliably in surgical environments. Vision-based RL provides an alternative by learning manipulation policies directly from RGB observations, avoiding explicit state estimation and manually engineered perception pipelines while enabling policies to acquire …

https://arxiv.org/abs/2610.30810 2026-10-23T00:00:00Z

Loco-manipulation extends the workspace of conventional manipulation by combining mobility with physical interaction, while aerial loco-manipulation further expands this capability into three-dimensional space, enabling robots to reach environments inaccessible to ground-based systems. Moving to an aerial platform, however, gives rise to a demanding control problem, since the vehicle must track trajectories accurately in three dimensions while the motion of the arm and its interaction with the environment continuously shift the center of mass, alter the inertia, and impose force and moment …

https://arxiv.org/abs/2610.30334 2026-10-23T00:00:00Z

Designing and tuning reward functions remains one of the main challenges in building effective reinforcement learning (RL) pipelines for humanoid locomotion. While shaping rewards can accelerate learning, naively formulated terms often conflict with the desired behavior, overfit to a specific robot, or become unstable under small weight changes. Potential-Based Reward Shaping (PBRS) offers an alternative solution: shaping the reward via differences of a potential function to guide exploration without changing the optimal policy. In this paper, we study Multi-PBRS for humanoid locomotion and …

https://arxiv.org/abs/2610.30319 2026-10-23T00:00:00Z

End-to-end autonomous driving has achieved state-of-the-art performance on benchmarks and real-world deployments. Its standard training recipe, however, is expensive across all existing paradigms: imitation learning requires fleet-scale driving logs whose behavior distribution only thinly covers the safety-critical tail; closed-loop reinforcement learning in a photorealistic simulator, while offering diverse behaviors, is bottlenecked by sample-efficiency, per-step cost of rendering, and a forward pass through a large vision backbone. Self-play in vectorized simulators changes the economics: …

https://arxiv.org/abs/2610.30097 2026-10-22T00:00:00Z

Vision-language-action (VLA) models have shown promise in robotic manipulation, but imitation learning (IL) alone often struggles to master complex long-horizon skills. Reinforcement learning (RL) offers an effective avenue for further improving VLA policies. However, existing VLA-RL methods typically suffer from delayed and biased credit assignment due to trajectory-level sparse rewards, while imbalanced subtask mastery creates bottlenecks that limit overall performance. To address these challenges, we propose AtomicRL, an RL post-training framework that leverages atomic task structures for …

https://arxiv.org/abs/2610.29845 2026-10-22T00:00:00Z

Autonomous mobile robots operating in dense crowds and cluttered sites require $360^\circ$ perception to react to surrounding hazards. While panoramic LiDAR offers full-surround coverage, learning representations within reinforcement learning (RL) is sample-inefficient under sparse rewards, and existing 3D pretrained point-cloud encoders are too memory-heavy for massively parallel RL simulation. We present RangeNav, a compact (183k parameters) LiDAR range-image encoder pretrained entirely on synthetic data. RangeNav uses anisotropic convolutions and circular padding to handle the extreme …

https://arxiv.org/abs/2610.29716 2026-10-22T00:00:00Z

We present SpatialDex, a framework that learns 3D-grounded bimanual dexterity from RGB-only human videos through reconstruction-augmented visuomotor pre-training. The central idea is to learn human behavior together with its spatial context. From each video, we reconstruct the scene geometry and estimate the hand motion, align them at a shared video-level scale using the hand-size prior of 3D hand estimates. We retain the reconstructed geometry as both a policy input and a prediction target. The policy grounds the token grid of a pre-trained vision-language model in this geometry through …

https://arxiv.org/abs/2610.29676 2026-10-22T00:00:00Z

Learning motion planning policies that remain reliable under closed-loop execution is a central challenge in Autonomous Driving (AD). Imitation Learning (IL) scales well to large AD datasets but suffers from distribution shift, causal confusion, and compounding errors under closed-loop execution. In contrast, Reinforcement Learning (RL) typically requires handcrafted rule-based rewards and massive simulation. We study a simple closed-loop IL framework that uses RL purely as an optimization tool, guided by a trajectory-distance reward derived from logged expert data. We refer to this training …

https://arxiv.org/abs/2610.29586 2026-10-22T00:00:00Z

Legged robots can extend planetary exploration to rugged and discontinuous terrain that is inaccessible to conventional rovers. In lunar gravity, jumping further expands this mobility by enabling robots to cross obstacles and gaps that cannot be traversed by walking alone. We present a multistage reinforcement-learning approach that produces a single end-to-end control policy for commanded point-to-point jumping under lunar gravity. The resulting policy has a simple architecture and relies exclusively on mission-compatible onboard sensing, making its deployment on a real lunar mission …

https://arxiv.org/abs/2610.29452 2026-10-22T00:00:00Z

Robust and reactive collision avoidance remains a central challenge for deploying Reinforcement Learning (RL) policies on real robotic manipulators, particularly when transferring behaviours learned in simulation to the physical world. This paper presents an RL framework that integrates the Euclidean Distance Field (EDF) directly into the observation space, providing the agent with continuous geometric cues that support stable and responsive avoidance behaviours. By leveraging the rich spatial information encoded in the EDF, the method enables a streamlined reward formulation that achieves …

https://arxiv.org/abs/2610.29264 2026-10-22T00:00:00Z

Large pretrained robot foundation models provide strong priors for manipulation, yet adapting them to target tasks with offline teleoperated demonstrations often fails to cover the contact-rich, recovery, and precision-critical states encountered during deployment. Existing methods mitigate this issue by augmenting offline demonstrations with human-in-the-loop data or online reinforcement learning. Despite this, offline post-training adapts slowly because it cannot immediately absorb deployment experience, while online RL typically relies on value functions or auxiliary actor-critic models, …

https://arxiv.org/abs/2610.28953 2026-10-22T00:00:00Z

Autonomous mobile robots require spatial representations that capture geometry and semantics while staying sparse enough for planning in large, unknown environments. Graphs provide a natural representation for this purpose and underpin both classical planning methods and a growing class of reinforcement-learning (RL) policies. However, RL training needs hundreds to thousands of parallel environments, each constructing and updating its own graph. Existing graph libraries are typically designed for either single-robot deployment or fixed graphs, and CPU-based graph construction limits scalable …

https://arxiv.org/abs/2610.28699 2026-10-22T00:00:00Z

Reinforcement learning (RL) enables adaptive and autonomous decision-making in embedded, edge, and heterogeneous computing systems. Field-programmable gate arrays (FPGAs) and integrated circuits (ICs) offer low latency, energy efficiency, and architectural flexibility for RL deployment, while introducing challenges in resource constraints, implementation complexity, and hardware-algorithm co-design. This review surveys more than 100 studies on RL implementations across FPGA and IC platforms, emphasizing architectures, implementation strategies, performance evaluation, and applications. The …

https://arxiv.org/abs/2610.28628 2026-10-21T00:00:00Z

Dexterous multi-finger hands hold promise to unlock diverse skills like functional grasps, in-hand reorientation, and dynamic handover that the human-designed world assumes, yet existing learning recipes force a trade-off. Goal-reaching reinforcement learning generalizes to arbitrary object poses but, lacking any human prior, converges to unnatural and unreliable finger strategies; motion tracking reproduces human-like behavior from a single clip but cannot deviate from it. We present AdaDex, a goal-conditioned RL framework that turns a single hand-object trajectory of a few seconds---from …

https://arxiv.org/abs/2610.28613 2026-10-21T00:00:00Z

Evaluating and post-training robot policies through physical interaction is costly and difficult to scale, motivating action-conditioned world models as interactive simulators. However, visually plausible predictions can misrepresent contact dynamics, providing unreliable feedback for policy evaluation and learning. We introduce PhysCanvas, a state-consistent visuo-tactile world model for contact-rich robot manipulation. PhysCanvas unifies multi-view RGB, tactile images, marker displacement, task state, and actions within a unified vision space. All modalities share a video VAE and pretrained …

https://arxiv.org/abs/2610.28589 2026-10-21T00:00:00Z

Agentic robotics systems combine planners with robot harnesses to perform complex manipulation tasks. Recent work improves these systems through better harnesses and external memory, but relies on powerful closed-source models as planners and does not improve the planners' own capabilities. In contrast, coding agents have improved substantially by post-training the model itself. We therefore investigate whether post-training can also improve robot planners. However, applying it across robot harnesses requires accommodating different execution mechanisms, including VLA skill invocation and …

https://arxiv.org/abs/2610.28329 2026-10-21T00:00:00Z

Trajectory tracking for compliant robots is challenging due to nonlinear dynamics and modeling uncertainties, often requiring learning-based methods to avoid explicit parameter identification. Iterative Learning Control (ILC) ensures theoretically high precision and preserves the passive compliance of the robot. However, traditional ILC requires a separate learning phase for each new trajectory. Conversely, Reinforcement Learning (RL) generalizes to new trajectories, but practically suffers from high sample complexity and limited tracking precision. This work proposes Reinforced Iterative …

https://arxiv.org/abs/2610.28121 2026-10-21T00:00:00Z

Safe autonomous navigation of UASs requires tactical deconfliction to address conflicts that strategic coordination cannot prevent. This task is challenging under partial observability, when sensor or traffic data are missing, delayed, or degraded. Geometry-based methods can offer separation assurances but face limitations in dense encounters. Recurrent reinforcement learning has therefore been proposed to learn navigation policies that integrate observation-action histories to optimise long-term safety-efficiency trade-offs. However, operational safeguards may require a remote pilot, onboard …

https://arxiv.org/abs/2610.27998 2026-10-21T00:00:00Z

Learning loco-manipulation policies requires demonstrations that capture coordinated base and arm motion on the target embodiment. Robot-free interfaces allow demonstrations to be collected independently of the target robot, increasing flexibility but without directly capturing platform-specific commands, proprioception, and body-mounted observations. On-robot teleoperation allows to capture these signals directly, but requires an interface capable of commanding the complete system concurrently. This paper presents LocoPilot, a single-operator bilateral teleoperation and data-collection …

https://arxiv.org/abs/2610.27736 2026-10-21T00:00:00Z

Human-collected real-world robotic manipulation demonstrations often contain mixed-quality trajectories, including hesitant, indirect, or inefficient action segments. While diffusion- and flow-based policies can model such multimodal data, standard behavior cloning (BC) assigns equal likelihood to all demonstrated actions and may therefore reproduce suboptimal modes. Offline RL value estimates offer a natural signal for biasing policies toward higher-value behavioral modes, but directly fine-tuning the generative policy or using critic gradients for policy steering can amplify critic errors …

https://arxiv.org/abs/2610.27732 2026-10-21T00:00:00Z

Connected and Autonomous Vehicles (CAVs) face significant challenges in roundabout navigation due to dense traffic interactions and unpredictable agent behaviors, necessitating high levels of adaptability and safety. While the combination of Reinforcement Learning (RL) and Model Predictive Control (MPC) offers a promising approach, existing frameworks suffer from a structural mismatch where pointwise RL decisions fail to align with MPC's trajectory level optimization, and often lack rigorous safety guarantees. This work proposes RLTrajGen-PPMPC-CBF, a hierarchical framework for safe, smooth …

https://arxiv.org/abs/2610.27194 2026-10-21T00:00:00Z

Diffusion policies with linearly composed scores have emerged as a promising approach to multitask robotic learning by combining separate factors to enable modular, task-wise adaptation, compositional generalization, and interpretable functional decomposition. However, current training objectives do not encourage factor specialization, often resulting in uninterpretable denoisers whose composed prediction is an average over identical copies, undermining their architectural premise. To address this, we propose a drop-in score-decorrelation auxiliary loss, motivated by projective composition …

https://arxiv.org/abs/2610.26757 2026-10-20T00:00:00Z

Reinforcement learning enables learning high-performance control policies, but its reliance on extensive interaction limits deployment on physical systems where data collection is costly, and failures are unsafe. We introduce Prior-Informed Adaptation (PIA), an offline-to-online model-based RL framework that uses structured simulation priors for rapid adaptation. PIA pretrains a world model on heterogeneous low- and high-fidelity simulated trajectories, then adapts it with limited target-domain interaction using uncertainty-regularized planning. Rather than requiring an accurate simulator for …

https://arxiv.org/abs/2610.26507 2026-10-20T00:00:00Z

A bimanual demonstration specifies both what the robot should do and one particular schedule for when each arm should act. Standard imitation learning does not distinguish task-required cross-arm constraints from incidental scheduling choices, and may therefore exploit opposite-arm progress as a shortcut cue, creating spurious cross-arm coupling even where relative timing is irrelevant for the current task phase. We introduce Constraint-preserving Temporal Recombination (CTR), a training-time data intervention that preserves recorded arm-local sensorimotor content while retiming the …

https://arxiv.org/abs/2610.26487 2026-10-20T00:00:00Z

The limited onboard computing resources of robots make the inference demands of vision-language-action (VLA) models costly to accommodate. Reducing these demands through aggressive compression, however, can degrade manipulation performance beyond what supervised fine-tuning alone recovers. We present SPAR (Structural Pruning and Action Recovery), which simultaneously prunes the hidden and feed-forward intermediate dimensions of the large language model (LLM) backbone through pruning-aware tuning, then applies reinforcement learning (RL) to recover policy performance. Applied to $\pi_{0.5}$, …

https://arxiv.org/abs/2610.26455 2026-10-20T00:00:00Z

Human-collected robot manipulation data often mix successful behavior with retries, pauses, recoveries, and failures. Advantage-Conditioned Behavior Cloning (AC-BC) can exploit such mixed-quality data, but only if the conditioning signal is both accurately constructed from offline trajectories and effectively incorporated into the policy's action-vector-field prediction. Existing pipelines can weaken this signal by thresholding estimator-derived advantage scores into noisy conditions, and by routing conditions through prompts that weakly affect the action vector field. We introduce ALIGN, a …

https://arxiv.org/abs/2610.26170 2026-10-20T00:00:00Z

Learning from Demonstration (LfD) allows robots to learn new skills from human examples; however, many vision-based methods require large datasets and resource-intensive end-to-end training. This paper introduces a data-efficient LfD framework for humanoid robots that learns manipulation skills from compact, task-specific features instead of raw images. The proposed approach integrates layered visual preprocessing, Kinect-based human joint estimation, prompt-based object detection, and depth information to extract human motion features and three-dimensional object locations from demonstration …

https://arxiv.org/abs/2610.25946 2026-10-20T00:00:00Z

Developing coordination policies for complex multi-agent systems relies on either labor-intensive algorithm design or opaque task-specific reinforcement learning. With recent advances in autonomous coding agents, we show that policy search directly in code space offers a compelling third path that combines automated optimization with explicit interpretability. We investigate a human-directed workflow in which coding agents iteratively propose, implement, evaluate, diagnose, and eventually refine algorithms guided by simulation feedback and explicit correctness verification. We conducted two …

https://arxiv.org/abs/2610.25691 2026-10-20T00:00:00Z

Data-driven learning for general-purpose robotic manipulation presents a fundamental trade-off between data-collection cost and adaptability to real-world environments. Imitation learning (IL) requires costly human demonstrations, whereas simulation-based learning is vulnerable to sim-to-real gaps in dynamics and sensor observations. We propose ReDOA (Real-World Distillation via Observation Alignment), a framework that decouples control learning from perception learning to learn image-based policies in the real world. A state-based teacher policy trained in simulation is executed on a real …

https://arxiv.org/abs/2610.24847 2026-10-20T00:00:00Z

Humanoid loco-manipulation is particularly challenging because it requires coordinating locomotion, balance, and object interaction, making it difficult to learn from limited demonstrations or from scratch through Reinforcement Learning (RL). We introduce DiPLO (self-distilled Diffusion Planning for Loco-manipulation), a framework that combines a self-distilled diffusion planner with a low-level whole-body tracking policy. Our planner is pretrained via supervised learning on motions derived from human-to-humanoid retargeting, while the tracker is trained via RL to execute them. DiPLO centers …

https://arxiv.org/abs/2610.24804 2026-10-20T00:00:00Z

Lifelong robot learning requires acquiring new tasks sequentially without forgetting earlier ones. With large pre-trained vision-language-action (VLA) backbones, adapter-based methods effectively mitigate this challenge. However, their task-specific adapters and selection modules accumulate with the task stream, creating a scalability challenge in on-disk storage and deployment cost under fixed onboard resource budgets. We propose SARAM, a lifelong learning framework that limits storage growth while keeping GPU memory and per-step inference cost independent of the task stream length. For each …

https://arxiv.org/abs/2610.24241 2026-10-20T00:00:00Z

This work demonstrates the use of a fast simulation-based training framework to learn control policies using reinforcement learning. The hardware requirements are minimal and the simulation-learned policies transfer reliably to the real world. With this setup, we show that a quadruped robot can learn to traverse diverse real-world terrains reliably---including in a lunar-analog facility---after less than 20 minutes of training on a single consumer-grade GPU. These results provide a glimpse of a future where reinforcement learning is a crucial tool in developing more capable and robust space …

https://arxiv.org/abs/2610.23550 2026-10-19T00:00:00Z

Reinforcement learning (RL) policies optimized for task rewards may produce behaviors that are efficient but misaligned with human expectations, safety preferences, or intent. This paper presents a reason-guided preference-based reinforcement learning (PbRL) framework that learns a human reward model from trajectory-level feedback. In addition to preference labels, the framework incorporates reason tags explaining why a behavior is preferred, enabling the learned reward to capture both human choices and their underlying rationale. Compared with preference-only reward learning, the …

https://arxiv.org/abs/2610.23548 2026-10-19T00:00:00Z

Legged robots equipped with manipulators offer promising capabilities for loco-manipulation tasks in unstructured environments. However, achieving task-consistent end-effector behavior during locomotion remains challenging due to terrain-induced disturbances and the strong coupling between locomotion and manipulation, particularly for small-scale quadruped platforms. A reinforcement-learning based whole-body control framework is proposed for quadruped loco-manipulation on complex terrain. The proposed framework combines a hybrid task representation with task-prioritized whole-body learning to …

https://arxiv.org/abs/2610.23438 2026-10-19T00:00:00Z

Humans manipulate objects within their hands through touch alone with remarkable ease, but for robots, achieving sustained real-world manipulation without vision remains an open challenge. Although reinforcement learning (RL) can generate sophisticated blind manipulation policies in simulation, transferring them to a real dexterous hand remains hindered by continuously changing contacts, motion-induced tactile information drift, and the gap between simulated and physical dynamics. We study this problem through Baoding ball rotation on the Shadow Dexterous Hand Lite, using only proprioception …

https://arxiv.org/abs/2610.23127 2026-10-19T00:00:00Z

Humanoid control requires coordinating whole-body posture with position and heading in the world frame. Mainstream controllers imitate trajectories in the root frame, but struggle to regain the target world pose after displacement. We introduce BeJEPA, a goal-conditioned Behavior World Model learned through unsupervised reinforcement learning from human motion priors and robot interaction. BeJEPA learns a shared representation of body configuration and world placement through a joint-embedding predictive architecture (JEPA). A Dynamic Predictor predicts the next state embedding under an …

https://arxiv.org/abs/2610.22977 2026-10-19T00:00:00Z

Low-cost passive leader arms enable scalable data collection for imitation learning, but their lack of restoring forces leaves redundant joints unconstrained, yielding highly inconsistent joint-space trajectories. We address this with a low-cost passive joint module (an adjustable mechanical clutch and a 3D-printed spiral spring) that pulls each joint toward a user-defined neutral posture. This passive restoring force acts as a physical prior equivalent to joint-space $L_2$ regularization (``Hardware-as-Regularization''), improving kinematic consistency with shorter completion time than an …

https://arxiv.org/abs/2610.22932 2026-10-19T00:00:00Z

Contact locations and interaction forces are critical for contact-rich robot manipulation but are often ambiguous from vision alone. Measuring them on robots requires specialized tactile hardware and platform-specific data collection, which keeps robot tactile data scarce. Human egocentric video is far easier to scale but lacks touch. Recent predictors trained on egocentric recordings paired with tactile-glove measurements can predict this missing signal from video alone. These predictors, however, remain confined to human hands, which differ from robot hands in appearance and tactile layout. …

https://arxiv.org/abs/2610.22852 2026-10-19T00:00:00Z

Generalist robot policies offer strong behavioral priors, but achieving deployment-level reliability and throughput remains difficult. Reinforcement learning (RL) can improve these policies, yet its effectiveness is constrained by the cost of online interaction. Existing methods adapt frozen flow-matching policies by treating noise space as a continuous action space. We show that this behaviorally unstructured space makes exploration inefficient, often preventing these methods from extracting meaningful learning signals on challenging tasks. We introduce AnchorQ, which enables coarse-to-fine …

https://arxiv.org/abs/2610.22765 2026-10-19T00:00:00Z

Precise pedicel-targeted grasping in strawberry harvesting remains a critical bottleneck due to the pedicel's small diameter (1.3-3 mm), color similarity with surrounding foliage, and precise force control required for clean abscission zone detachment. As a market-grade crop, strawberry aesthetic value makes bruise-free pedicel detachment essential over direct fruit grasping. Classical approaches struggle to unify vision models, motion planning, and contact manipulation into a robust framework, particularly in occluded canopy environments. Therefore, this work presents a visuomotor imitation …

https://arxiv.org/abs/2610.22368 2026-10-15T00:00:00Z

Real-world post-training of generalist robot policies faces two challenges: partial observability makes action selection ambiguous, while offline post-training methods delay feedback from deployment experience. We present Value as Memory (VaM), a framework that addresses these challenges through value caching and online real-world reinforcement learning (RL). Value caching conditions actions on recent value predictions as task-progress memory, while online updates enable timely policy improvement by combining offline demonstrations, off-policy interventions, and on-policy rollouts for …

https://arxiv.org/abs/2610.22337 2026-10-15T00:00:00Z

Robotic harvesting requires precise manipulation to ensure accurate positioning of the end-effector, especially in a constraint workspace. This study introduces the Path-Safe Approach Proximal Policy Optimization (PSA-PPO), a target-conditioned local reaching framework designed for robotic harvesting of nutrient film technique (NFT)-hydroponic lettuce in greenhouses. The proposed PSA-PPO preserves the standard clipped PPO objective while introducing a harvesting-oriented policy formulation that integrates target-conditioned observations, corridor-aware spatial constraints, …

https://arxiv.org/abs/2610.22193 2026-10-15T00:00:00Z

In robotic manipulation, the same observation often admits multiple feasible actions. Generative policies such as diffusion and flow matching naturally capture such multimodal behaviors, yet which mode is executed is left to random sampling and cannot be actively controlled. We propose Mode-Oriented Source Shaping (MOSS), which turns mode selection into an explicit choice of where generation starts. We first reveal, both empirically and theoretically, that deterministic flow transport induces mode-dependent structure in the source space. Under ideal deterministic ODE transport, distinct …

https://arxiv.org/abs/2610.22020 2026-10-15T00:00:00Z

Learning from demonstration is an effective strategy for endowing robots with manipulation capabilities but requires training on datasets comprised of massive amounts of demonstrations. Existing demonstration collection approaches either require constant human involvement, for example, via teleoperation or are specialized for a single task. Task and Motion Planning (TAMP) systems are able to autonomously solve and therefore generate demonstrations for general-purpose tasks; however, learning from their demonstrations has proven difficult due to multi-modality in their solutions. In this work, …

https://arxiv.org/abs/2610.21984 2026-10-15T00:00:00Z

Autonomous driving planning requires selecting trajectories that remain safe, rule-compliant, and comfortable under complex multi-agent interactions, yet robust closed-loop decision making in planning-critical scenes remains challenging. Existing diffusion- and RL-based planners often rely on generic rewards and use relational structure mainly for representation, limiting how planning-critical rollouts shape policy improvement. We present GRID-Planner, a graph--reward integrated diffusion planning framework that aligns generative planning with structured relational signals. Specifically, …

https://arxiv.org/abs/2610.21915 2026-10-15T00:00:00Z

Vision-language-action (VLA) policies are typically trained with action prediction as the primary supervision signal, since robots ultimately execute actions. Auxiliary objectives such as latent-action (LA) and future-vision (FV) prediction are often added to improve policy learning, yet they compete with action prediction for the same training budget. We ask whether, under a fixed budget, allocating a substantial share of training samples to such objectives, rather than to further action prediction, can improve policy learning. We build a unified VLA framework that couples a two-stream …

https://arxiv.org/abs/2610.21798 2026-10-15T00:00:00Z

Scaling robot manipulation models requires large amounts of interaction data, yet collecting diverse real-robot experience remains costly. Human manipulation videos, in contrast, provide abundant and diverse task experience that could potentially benefit robot learning. However, differences in morphology, action spaces, and control mechanisms make human motions unsuitable as direct supervision for robot actions, raising a scientific question: what knowledge in human videos should be transferred across embodiments to robot manipulation? To address this question, we analyze subtask transfer …

https://arxiv.org/abs/2610.21792 2026-10-15T00:00:00Z

Imitation learning enables robots to perform complex tasks by leveraging human-collected demonstrations. However, most existing approaches require labor-intensive data collection with additional teleoperation systems, which hinders scalability. Human videos represent a natural source of data that implicitly contain knowledge of manipulation behaviors. However, transferring them to robots remains challenging due to the visual domain gap and the absence of explicit action labels. In this work, we introduce TDV, a trajectory-based framework that leverages data generation to enable generalizable …

https://arxiv.org/abs/2610.21735 2026-10-15T00:00:00Z

Object manipulation often requires combining non-prehensile actions with grasping. However, existing approaches typically develop these capabilities separately and integrate them by sequencing distinct primitives through prescribed intermediate objectives, limiting the coordination of contact motions and grasping. Their integration also remains sensitive to object and gripper geometry and depends on particular environmental supports, complicating real-world deployment. We present Uni-PNP, a unified policy that jointly learns prehensile and non-prehensile manipulation for object pose reaching …

https://arxiv.org/abs/2610.21666 2026-10-15T00:00:00Z

Small observation or action errors can compound during closed-loop execution and disrupt a trained imitation learning policy. We study whether the original expert demonstrations can improve robustness through test-time hidden-state steering without additional demonstrations or policy retraining. Our analysis of a trained policy finds that expert hidden-state variation is concentrated in relatively few dimensions, while the directions capturing this variation differ across regions. Motivated by this geometry, we propose Diffeomorphic Hidden-State Steering (DHS), which learns an invertible …

https://arxiv.org/abs/2610.21450 2026-10-15T00:00:00Z

Aerial vision-language navigation (VLN) agents built on large vision-language models are expensive to query. Executing a complete predicted action chunk before replanning amortizes this cost, reducing model inference from 195 to 42 ms per executed waypoint for our policy. It also moves the states at which the policy is queried away from expert demonstrations, which supervise neither recovery from these states nor termination at the learner's own arrival. On OpenFly test-seen, no-stop failures account for 47.78% of full-chunk behavior cloning (BC) outcomes. We present X-Fly, a staged training …

https://arxiv.org/abs/2610.21140 2026-10-15T00:00:00Z

Contact-rich robotic tasks require coordinated motion and impedance under uncertain interaction dynamics and physical constraints. While recent methods on learned policies provide useful interaction strategies, they may fail when contact conditions differ from those encountered during training. Model-based generative methods show promising receding-horizon trajectories optimization results, but often lack structured behavioral guidance and refinement that jointly accounts for constraint geometry and actual contact responses. To this end, we propose Manifold Generative Annealing (MGA), a joint …

https://arxiv.org/abs/2610.20998 2026-10-14T00:00:00Z

Passive human videos of everyday activity offer robots access to a massive amount of human experience without requiring a demonstration for each task. However, using this experience requires recovering knowledge from unstructured video recordings and adapting it to a different body (i.e., the robot). To overcome these challenges, we present mobile code-as-policy (MoCaP), an agentic framework that turns passive human video recordings into guidance for an end-to-end mobile manipulation policy. MoCaP extracts spatial memory and cues of how people prepare to interact with objects, which inform …

https://arxiv.org/abs/2610.20607 2026-10-14T00:00:00Z

Mobile Manipulation (MoMa) is a cornerstone of autonomous robotic systems, yet real-world fine-tuning remains a formidable challenge because of high-dimensional action spaces and intricate coupling between heterogeneous modules. In this paper, we propose HiRe-MoMa (Hierarchical Residual Mobile Manipulation), a systematic framework for stable and sample-efficient real-world fine-tuning of complex MoMa systems. At its core, HiRe-MoMa adopts a Hierarchical Residual Architecture that fine-tunes a frozen base policy. A Policy-Agnostic Residual learns additive corrections atop the base policy, …

https://arxiv.org/abs/2610.20524 2026-10-14T00:00:00Z

Existing robot policy memories typically evolve with observation sequences, implicitly treating each update as the same amount of physical time. Yet identical observation histories can span different durations and require different actions, exposing physical time as a missing dimension of policy memory. We introduce Temporal Flow Policy (TFP), which learns memory dynamics to retain past events and evolve the memory state over measured time intervals. Observations and prior memory determine the content and time scales of each transition; elapsed time determines how far the state advances. TFP …

https://arxiv.org/abs/2610.20504 2026-10-14T00:00:00Z

Long-horizon precise manipulation produces mixed-quality data for post-training vision-language-action (VLA) models: even successful demonstrations and intervention-assisted rollouts may contain detours, hesitations, failed attempts, and imperfect recoveries. The key challenge is to identify which action chunks actually advance the task, rather than uniformly cloning or discarding imperfect trajectories. We propose Graph-Reweighted Behavior Cloning (GR-BC), an offline iterative post-training framework that builds a task-conditioned goal-reachability graph over demonstrations and iteratively …

https://arxiv.org/abs/2610.20318 2026-10-14T00:00:00Z

Reinforcement-learning policies for robot locomotion can fail at deployment when operating conditions shift (e.g., rough or slippery terrain, payload changes, sensing degradation), and retraining or manual recalibration is often infeasible under on-device latency and memory constraints. We study test-time adaptation (TTA) for robotic control: adapting a pretrained policy online and in a self-supervised manner during execution, without access to rewards. Our starting point is a lightweight baseline that updates only the actor using a frozen pretrained critic as a deployment-time performance …

https://arxiv.org/abs/2610.20255 2026-10-14T00:00:00Z

Despite the Markov assumption, safety failures in robot reinforcement learning rarely occur instantaneously; they typically emerge over several steps as the policy enters unfamiliar states under disturbances and domain shift. We address this limitation by learning a receding-horizon safety critic that predicts whether a state will remain non-terminating over the next receding horizon, enabling anticipatory detection of impending locomotion failures. The critic is trained from rollout-derived horizon labels with a composite objective that combines horizon classification, …