Robot Policy Learning

Ask about this topic

Overview

Robot policy learning studies how robots can turn camera, depth, tactile, and proprioceptive inputs into actions for tasks such as manipulation, locomotion, and navigation. Common approaches include behavior cloning from demonstrations, reinforcement learning in simulation or on hardware, and diffusion, flow-matching, or vision-language-action policies that generate action sequences; world models and hierarchical planners can add foresight and long-horizon structure. Researchers evaluate these methods in simulation suites such as LIBERO, CALVIN, RoboTwin, and navigation benchmarks, as well as on physical robots, with growing attention to memory, contact, safety, and recovery from failure. A central tension is how to make policies generalize across tasks, robots, and changing conditions while remaining data-efficient, reactive, reliable, and fast enough to deploy.

Latest papers

CardsList

377 papers85 papers in the last four weeks, up 47% on the four weeks before. 0.5% of all new papers.

Jun 6, 2026

Light-WAM: Efficient World Action Models with State-Fusion Action Decoding

World Action Models (WAMs) extend robot policy learning by incorporating future prediction as an additional training objective, encouraging the policy to encode task-relevant temporal structure in its representations. Current WAMs often rely on large-scale generative architectures that incur high training costs and inference latency, making them difficult to deploy as efficient closed-loop policies. We propose Light-WAM, a lightweight World Action Model for efficient robot manipulation. Specifically, it is built with a compact video backbone and performs future-video supervision in a downsampled latent space, reducing the cost of video co-training while retaining its benefits for representation learning. For action prediction, Light-WAM introduces the StateFusionActionExpert, which reads adapted states from multiple backbone layers, fuses them through learned-query pooling, and directly predicts action chunks in a single forward pass. This design provides an efficient interface between video backbone representations and robot actions, avoiding the need for heavy generative action experts. Experiments demonstrate that Light-WAM maintains strong performance on LIBERO and achieves usable multi-task performance on RoboTwin 2.0, while using only 0.44B trainable parameters. It also achieves 72.03ms inference latency with 4.1GiB peak GPU memory and improved training throughput.

Ziang Li, Dongzhou Cheng, Yibin Wang +5

Wuhan University · Shanghai Innovation Institute · Southeast University +2

Robot Policy LearningWorld Models for RoboticsVisuomotor Policy LearningEfficient Inference for World Action ModelsWorld Action Models
AskPDF
Jun 5, 2026

Spline Policy: A Structured Representation for Robot Policies

Modern imitation-learning policies for robot manipulation often represent actions as fixed-resolution action chunks, which are simple and effective but expose limited geometric and temporal structure before execution. This paper studies Spline Policy (SP), a structured representation that replaces action chunks with spline parameters while keeping the policy backbone unchanged. The predicted spline can be decoded as a compact continuous trajectory, queried at different temporal resolutions, constrained or edited in parameter space, and passed to downstream controllers. For quadratic spline outputs, the same representation can also be converted into a state-dependent vector field through an analytical distance-field construction. Under the regularity and projection assumptions of this construction, the induced dynamics do not increase the distance to the generated spline, yielding a principled local corrective mechanism around the predicted motion. The spline output further supports uncertainty propagation from observations to spline parameters, trajectories, and flow fields, and can be combined with classical control mechanisms such as null-space collision avoidance without retraining the policy backbone. We instantiate SP with diffusion, flow-matching, transformer-based, and vision-language-action backbones. Experiments in low-dimensional motion learning, simulated manipulation under matched backbones, dexterous manipulation, and real-robot case studies show that SP remains compatible with modern policy learners while exposing useful motion-structure properties, including compact decoding, temporal resampling, local correction around predicted motions, uncertainty evaluation, and controller compatibility.

Mengze Tian, Yiming Li, Sichao Liu +2

Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland · Idiap Research Institute, Martigny, Switzerland

Robot Policy LearningRobot Skill LearningRobot Motion GenerationRobotic ManipulationRobot Imitation Learning
AskPDF
Jun 5, 2026

ActionMap: Robot Policy Learning via Voxel Action Heatmap

Vision-language-action (VLA) models have advanced rapidly across backbones, training recipes, and data scale, yet the action decoder, which converts the backbone's hidden state into a continuous control signal, has barely changed and remains a single-point predictor across the majority of current VLAs. Whether implemented via autoregressive token bins, L1 regression, or flow-matching denoising, the resulting decoder treats the action space as unstructured, leaving the geometric proximity of neighboring actions unexploited during training. To advance this, we introduce ActionMap, a voxel heatmap action head that drops into an existing VLA in place of its native action decoder. For each new action, the head predicts a voxel heatmap over the action space, where each voxel directly stores the probability of the corresponding action. Across LIBERO simulation and real-world Franka manipulation, our heatmap head surpasses two architecturally distinct backbones at matched training steps (e.g., +8.2% over OpenVLA-OFT's L1 regression head on the LIBERO four-suite average), converges at comparable or faster rates on both backbones, and remains markedly more data-efficient at low training data. The cross-backbone consistency indicates that action representation is a real lever for VLA performance, distinct from further backbone or recipe scaling. Project Page: https://showlab.github.io/ActionMap/.

Pei Yang, Hai Ci, Yanzhe Chen +3

1Show Lab, National University of Singapore · 2NVIDIA

Robot Policy LearningRobot Skill LearningRobotic ManipulationVision-Language-Action ModelsAction Representation Learning
AskPDF
Jun 4, 2026

AEGIS: A Backup Reflex for Physical AI

Long-horizon robot manipulation tends to fail gradually: one bad step degrades the state, and the policy spirals into a basin from which it cannot recover. The failure is often visible before it happens. We introduce AEGIS (Activation-probe Early-warning, Gated Inference Switching), a selective escalation method that uses a lightweight probe on a weak policy's frozen activations to detect high-risk steps while there is still time to act. When the probe flags a step, control switches to a stronger separate policy, but only for the steps that need it. On LIBERO-Spatial, AEGIS recovers 10.1% of the trajectories the weak policy alone loses, versus 4.6% for budget-matched blind escalation and 5.1% for a random-trigger placebo. These gains are significant under one-sided exact paired McNemar tests with Holm-Bonferroni adjustment over three pre-registered contrasts: +5.4pp over blind escalation, p=8.5e-6; +5.0pp over random triggering, p=1.0e-4; paired-trajectory bootstrap CIs exclude zero. AEGIS activates the stronger policy on only 38% of steps, so the lever is timing rather than compute. The probe clears its precondition with an early-window AUROC of 0.764, 95% CI [0.70, 0.84], read from the weak-policy path over the first 30% of trajectory steps before any handoff. We pre-register the full analysis plan, including a conditional recovered-task-rate estimand and explicit kill criteria, and confirm the result on 700 common-random-number episodes per arm, with nA-fail=646.

Josef Chen

KAIKAKU

Robot Policy LearningLong-Horizon Robotic ManipulationRobot Failure DetectionRobot Failure Recovery
AskPDF
Jun 4, 2026

Flow-based Policy Adaptation without Policy Updates

Foundation models and other policies trained on large and diverse datasets can endow robots with semantic and task knowledge that would be difficult to acquire from task-specific demonstrations alone. Despite their broad scene understanding and reasoning capabilities, however, these models often lack the environment- and embodiment-specific knowledge required for precise and reliable execution. We propose GLOVES, a flow-based framework that complements an existing agent with a lightweight, goal-agnostic expert action prior that refines the action chunks proposed by the agent without updating its parameters. The prior captures observation-conditioned expert behavior, while the agent's proposal supplies task- and context-specific intent that the correction aims to preserve. The learned flow also provides a natural in-distribution scoring mechanism through reverse flow evaluation. We use this signal as an intervention gate: actions that appear consistent with the expert distribution are passed through unchanged, while anomalous or out-of-distribution (OOD) actions are corrected. In this way, GLOVES only provides assistance when necessary. By learning local goal-agnostic expert action patterns and using them to adapt agent-proposed actions during execution, GLOVES provides a lightweight shared-control module for robust action adaptation across tasks and environments. Across controlled OOD-recovery studies, simulation benchmarks, and real-robot experiments, GLOVES consistently improves the success of vision-language-action models (VLAs) and Code-as-Policy agents without retraining the underlying policy. Code and demos are available at ripl.github.io/GLOVES_web.

Luzhe Sun, Jingtian Ji, Haoran Chen +2

Toyota Technological Institute at Chicago · Stony Brook University

Robot Policy LearningRobot Policy AdaptationRobot Skill LearningGenerative Flow NetworksImitation LearningShared Autonomy
AskPDF
Jun 4, 2026

Learning of Robot Safety Policies via Adversarial Synthetic Scenarios

In this work, we propose an agentic gamification framework for hazard-informed learning of robot safety policies through synthetic scenarios. We model scenario generation as an adversarial game between two agents: a Red Team that explores the space of potential failures by constructing hazardous situations, and a Blue Team that incrementally refines safety policies to prevent them. This iterative process enables efficient discovery of high-risk edge cases that are unlikely to be captured through random simulation or manual enumeration. By combining classical risk modeling with adversarial scenario generation and modern learning paradigms, this work provides a scalable pathway for embedding safety into Physical AI systems operating in complex real-world environments. The paper describes ongoing work. The contribution is a problem formulation and a proposed solution architecture.

Nikolai Dorofeev, Alexey Odinokov, Rostislav Yavorskiy

SafePI.ai Grenoble, France · SafePI.ai Belgrade, Serbia · SafePI.ai Madrid, Spain

Robot Policy LearningAdversarial Scenario GenerationSynthetic Data Generation for RoboticsRoboticsRobot SafetySafe RL
AskPDF
Jun 4, 2026

TAGA: Terrain-aware Active Gaze Learning for Generalizable Agile Humanoid Locomotion

Agile humanoid locomotion across diverse challenging terrain demands both wide perceptual coverage and precise local geometry understanding. Motivated by the way humans selectively look at relevant terrain during locomotion, we introduce TAGA, a Terrain-aware Active Gaze learning framework for Attention-based humanoid control. By fusing vision, proprioception, and motion commands, our framework guides the model to learn anticipatory cues and actively attend to specific areas of the height scan, selectively using these informative regions for the downstream network. This adaptively increases the information density of observations under tight onboard computational constraints, thus enabling fine-grained perceptive locomotion over larger-scale terrains. We find that such gaze behaviors can naturally emerge through reinforcement learning alone, without requiring additional supervision or explicit guidance, significantly improve training efficiency. As a result, the trained policy demonstrates robust and generalizable locomotion in simulation and on hardware, including reliable terrain-aware foothold selection, elevated-platform traversal, competitive sparse-foothold traversal, and the largest reported real-world gap traversal distance of 1.2m among perceptive humanoid locomotion systems, while maintaining stability under severe perceptual disturbances and environmental interference.

Peizhuo Li, Hongyi Li, Mingfeng Fan +9

MarmotLab, National University of Singapore · Center of X-Mechanics, Zhejiang University · South China University of Technology

Active PerceptionHumanoid Robot LocomotionRobot Policy LearningTerrain-Aware Robot LocomotionRL for Legged LocomotionActive Vision
AskPDF
Jun 3, 2026

WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual Navigation

Visual navigation requires generating smooth and collision-free trajectories under complex geometric and physical constraints. Existing reactive policies that directly map observations to actions lack anticipatory reasoning, limiting their ability to proactively avoid obstacles. While visual imagination offers predictive foresight, conventional modular approaches separate scene prediction from policy learning, often leading to error accumulation and inefficient inference. To address these limitations, we propose WAM-Nav, a Latent World-Action Model for embodied visual navigation that jointly learns action generation and latent visual foresight, enabling more robust and foresighted navigation decisions without compromising inference efficiency. Specifically, WAM-Nav utilizes a shared Diffusion Transformer for asymmetric joint diffusion to concurrently generate long-horizon actions and short-horizon visual foresight, reducing the inference latency and visual error accumulation inherent in multi-step autoregressive rollouts. To further encourage smooth and consistent trajectory generation, we introduce a dual-stream contextual conditioning mechanism that integrates episode-level ego-motion history with sequential visual observations. Combined with a unified goal alignment module that preserves balanced representations across goal types, WAM-Nav naturally supports Image-Goal, Point-Goal, and No-Goal exploration within a single policy. Extensive experiments on the challenging ClutterScenes and InternScenes benchmarks demonstrate strong generalization of WAM-Nav, particularly on Image-Goal and Point-Goal navigation, where it improves success rates by 15.7% and 3.3%, respectively. Real-world deployment further validates effective zero-shot sim-to-real transfer, achieving an average 85% task success rate across diverse indoor and outdoor environments.

Ning Yang, Yan Huang, Kaiwen Peng +9

1Nanjing University · Institute of Automation, Chinese Academy of Sciences · University of Chinese Academy of Sciences +4

Visual NavigationRobot Policy LearningDiffusion-Based PlanningWorld Models
AskPDF
Jun 3, 2026

MAD: Mapping-Aware World Models for Agile Quadrotor Flight

Agile quadrotor flight in cluttered scenes requires more than a reactive mapping from a depth image to a control command: the vehicle must remember which regions have been observed, infer nearby occupied space, and act under partial visibility and tight latency. In this paper, we present Mapping-Aware Dreamer (MAD), a geometry-aware world model for vision-based quadrotor flight. Instead of using raw-image reconstruction as the main self-supervised objective, MAD learns recurrent latent dynamics that reconstruct robocentric occupancy and visibility grid maps together with proprioceptive states. This design forces the latent state to encode local geometry, visibility history, and ego-motion in a form that is directly relevant to collision avoidance. MAD is trained in DiffAero using a GPU-parallel map-construction module that provides high-throughput supervision for occupancy and visibility. The learned representation is used in three policy-learning modes: imagination-based MAD-Dreamer and feature-extractor variants based on PPO and SHAC. Across visual navigation and racing tasks, MAD-based agents achieve higher success rates, faster flight, and better cross-task transfer than corresponding vision-only baselines. The model also produces interpretable map predictions and accurate ego-motion estimates from depth observations. We further deploy the learned policy on a physical quadrotor with an Intel RealSense D435i and demonstrate safe indoor and outdoor flight under limited sensing, reaching 9.66 m/s in simulation and 5.05 m/s in real-world forest experiments. These results show that mapping-aware world models provide a practical middle ground between modular aerial navigation and end-to-end learning.

Xinhong Zhang, Runqing Wang, Yunfan Ren +6

State Key Lab of Autonomous Intelligent Unmanned Systems, Beijing Institute of Technology, Beijing 100081, China · Zhongguancun Academy, Beijing 100094, China · School of Computer Science and Technology, Tongji University +2

Robot Policy LearningWorld Models for RoboticsWorld Models3D Occupancy PredictionQuadrotor ControlVision-Based Robot Control
AskPDF
Jun 2, 2026

Denoising Tells When to Replan: Denoising-Variance Adaptive Chunking for Flow-Based Robot Policies

Action chunking has become a common inference strategy for flow-based robot policies, improving action coherence by modeling multi-step temporal dependencies in demonstrations. However, the execution horizon is still typically set as an empirical fixed value, overlooking that predictable free-space motions and precision-critical interaction phases often require different replanning frequencies. In this work, we first show that the denoising process of flow-based policies contains an intrinsic signal of task phases: clean-action estimates remain stable during predictable motion phases, but fluctuate more strongly around contact-rich or precision-sensitive operations. Motivated by this observation, we propose DVAC (Denoising-Variance Adaptive Chunking), a test-time method that adaptively determines how many actions to execute from each predicted chunk. DVAC measures the variance of clean-action estimates over the final denoising steps, executes the stable low-variance prefix, and replans before high-variance future actions are committed. To transfer across tasks and rollouts, DVAC further calibrates the threshold with a rolling estimate of the local variance scale. Experiments on LIBERO, RoboTwin, CALVIN, and real-world manipulation show that DVAC improves task success while reducing replanning frequency. With a π0.5π_{0.5}-based policy, DVAC improves LIBERO success from 94.75% to 98.00% and reduces replanning by 43.0%, while also yielding aggregate gains on RoboTwin and CALVIN and improving real-world execution efficiency.

Xiangdong Feng, Yuxuan Cheng, Chen Shi +5

Beijing Institute of Technology · Shenzhen Loop Area Institute · The Chinese University of Hong Kong, Shenzhen +4

Robot Policy LearningAction ChunkingDynamic Replanning
AskPDF
Jun 2, 2026

GN0: Toward a Unified Paradigm for Generation, Evaluation, and Policy Learning in Visual-Language Navigation

Embodied navigation connects intelligent agents with the physical world and is fundamental for general robotic intelligence. Limited availability and quality of navigation data have constrained Vision-and-Language Navigation (VLN) systems' generalization and long-horizon capabilities. To address this, we curate diverse 3D scenes and develop an automated pipeline for large-scale navigation data, resulting in the GN-Matrix dataset. Building on a 3D Gaussian Splatting (3DGS) engine, we introduce a high-fidelity simulation platform supporting interactive roaming and collision-aware navigation. We further propose GN-Bench, the first BEV-based benchmark incorporating dynamic 3DGS avatars for human-robot interaction evaluation. To leverage the simulator, we develop an RL-driven navigation foundation model, Break and Establish (BAE). After supervised learning, DAgger exposes the model to rollout-induced states, breaking narrow expert-centric distributions and enabling downstream RL exploration. This unified VLN paradigm integrates map-based and map-free tasks, including instruction following, human following, and goal navigation. GN-BAE formalizes high-fidelity 3DGS-rendered Bird's Eye View representations as compact memory, unlocking latent spatial reasoning in VLMs. Extensive evaluations on GN-Bench and VLN-CE show that GN0 outperforms state-of-the-art VLN methods. Overall, GN-Matrix offers a unified framework spanning data, simulation, and learning, advancing embodied navigation in research and industrial applications.

Xinhai Li, Xiaotao Zhang, Yuehao Huang +10

Institute of Artificial Intelligence, China Telecom · Shanghai Jiao Tong University · Zhejiang University +3

Robot Policy LearningVLN BenchmarksEmbodied NavigationRobotic RLVision-Language Navigation
AskPDF
Jun 1, 2026

World-Task Factorization for Robot Learning

Robot learning must produce policies that generalize to new combinations of constraints, teammates, and environments. To achieve this, we must structurally factor the policy, which is a choice that dictates what generalizes, what requires retraining, and what remains entangled. Existing methods span a wide spectrum, from expecting structure to emerge from data scaling, to hand-designing it via hierarchies, skill libraries or learned specializations. In this paper, we study what we argue is the most fundamental factorization in robotics: separating the world from the task. We investigate the conditions under which this factorization is principled. World factors are properties of the embodied system and the environment; they exist independently of intent. Task factors are defined by the task's logic over what the world admits. We formalize this asymmetry through Bayesian model evidence: it aligns with the data-generating process, maintains high likelihood through an analytical world model, and reduces the Occam razor's penalty on task parameters. We instantiate this factorization by pairing AICON, a differentiable graph of recursive estimators and interconnections that is compositional, operates without task-specific data, and propagates cost gradients to actuators, with a compact, learned policy that modulates gradient paths. Gradients serve as the interface between the two factors: they carry world structure through the graph and task structure through costs, enabling low-dimensional learning while preserving structural generalization. We test the world/task factorization across three problems that encompass heterogeneous robots, environments, task logic and sensorimotor modalities. Our framework outperforms end-to-end baselines and analytical heuristics in all settings, generalizes zero-shot to out-of-distribution configurations, and transfers to real hardware without retraining.

Eduardo Sebastián, Adrian Pfisterer, Vito Mengers +2

Department of Computer Science and Technology, University of Cambridge, United Kingdom · Robotics and Biology Laboratory, Technische Universität Berlin, Germany · Robotics and Biology Laboratory, Technische Universität Berlin +1

Robotic ControlRobot Policy LearningWorld Models for RoboticsRobot Policy GeneralizationPolicy Learning
AskPDF
May 31, 2026

Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry

Generative action policies based on diffusion or flow matching excel in behavior cloning, yet their iterative sampling is prohibitive for high-frequency robot control. While recent one-step formulations alleviate this latency, they inevitably discard the intermediate trajectory evolution that provides crucial action correction. Directly recovering this mechanism by explicitly estimating a training-time drifting field is mathematically ill-posed due to extreme conditional demonstration sparsity. We introduce Implicit Drifting Policy (IDP), a one-step imitation learning framework that brings the training-time correction of Drifting into policy learning without explicit vector field estimation. IDP extracts a conditional expert geometry from the local variation of observation-similar expert actions, and compares it against a global reference geometry to isolate condition-specific constraints. This local geometric structure adaptively weights a scalar potential objective. Combined with an expert-proximal terminal evaluation, IDP directly enforces manifold constraints on the one-step generator during training. Extensive evaluations across 2D, 3D, and real-world manipulation tasks show IDP effectively maintains adherence to valid action manifolds, improving upon explicit drifting methods and achieving competitive performance with strong one-step baselines.

Zemin Yang, Yaoyu He, Yiming Zhong +5

ShanghaiTech University · Shanghai Jiao Tong University · The Chinese University of Hong Kong +1

Robot Policy LearningImitation LearningRobotic ManipulationRobot Imitation Learning
AskPDF
May 31, 2026

Learning Multi-Modal Trajectory Policies for Data-Efficient Robotic Manipulation

Robotic manipulation requires the effective integration of heterogeneous inputs, including visual observations, language instructions, and trajectory representations, to generate accurate actions. Existing transformer-based policies typically process these heterogeneous modalities within a shared parameter space, which often leads to modality interference and inefficient representation learning, especially in data-scarce scenarios. While Mixture-of-Experts (MoE) offers a scalable solution through expert specialization, conventional routing mechanisms are often sensitive to such cross-modal representation discrepancies, resulting in unstable expert assignment and expert collapse. In this work, we propose MATE (Multi-ModAl TrajEctory Policies), a novel trajectory prediction framework built upon MoE. Specifically, we introduce a Multi-Modal MoE architecture to achieve fine-grained sub-token feature decoupling, and design a cross-modal cosine router for stable and scale-invariant expert assignment across heterogeneous modalities. We further employ temperature-controlled routing and stochastic noise injection to improve expert balance and prevent premature routing collapse under scarce demonstrations. Experiments on the LIBERO benchmark show that our MATE consistently outperforms prior work under data scarcity. It achieves a 4.75% improvement in average success rate over the trajectory-guided counterpart. Real-world experiments on robotic ping-pong also suggest that the predicted trajectories can provide useful guidance for downstream robotic execution, further indicating the practical feasibility of our algorithm.

Zijia Chen, Yuenan Hou, Xinhua Jiang +3

College of Electronic Science and Technology, National University of Defense Technology Changsha, 410073, China · Shanghai AI Laboratory Shanghai, 200000, China

Robot Policy LearningMixture of ExpertsRobotic ManipulationData-Efficient Robot LearningMultimodal Trajectory PredictionMultimodal Learning+1
AskPDF
May 30, 2026

Too Much of a Good Thing: When sim2real Efforts Impede Policy Learning (And What to Do About It)

While sim2real efforts are necessary for effective policy transfer to hardware, there is such a thing as too much of a good thing. We argue that sim2real efforts have led to misaligned incentives with policy learning, resulting in simulator lock in and poor policy exploration due to the unreasonable constraints imposed by the real world. We offer a diagnosis and explanation of the current status of the problem, and propose a potential solution via a sim2sim2real paradigm that leverages the robot's kinematics as the sole design constraint.

Kyle Morgenstein, Bharath Masetty, Stephen Welch +1

Apptronik · University of Texas at Austin

Robot Policy LearningRobotics SimulationSim-to-Real TransferTransfer Learning
AskPDF
May 29, 2026

From Noise to Control: Parameterized Diffusion Policies

We propose Parameterized Diffusion Policy (PDP), a framework for learning diffusion policies conditioned on low-dimensional, continuous parameters embedded in a learned behavior manifold. By constructing this manifold so that distances between latent representations reflect the semantic similarity between physical trajectories, we transform diffusion from a mechanism for stochastic diversity into a precise and optimizable tool for behavior steering. Our approach enables smooth interpolation between known strategies and efficient adaptation to novel constraints without updating policy weights. We demonstrate that PDP significantly improves adaptation performance on complex multimodal benchmarks in both simulated and real-robot experiments compared to standard diffusion policies, particularly in scenarios requiring the synthesis of novel behaviors.

Renhao Zhang, Haotian Fu, Mingxi Jia +3

University of Massachusetts · 2Brown University · 3Harvard

Robot Policy LearningRobot Policy AdaptationDiffusion PolicyRobot Policy GeneralizationPolicy Learning
AskPDF
May 28, 2026

UniLab: A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigms

Simulation-based RL for contemporary robot control is increasingly organized around GPU-resident simulation: physics, rollout collection, and learning are placed on a single GPU-centric execution path. This paradigm has greatly improved training speed, but it has also encouraged a default assumption that efficient training requires physics to reside on the GPU. We revisit this assumption. Our view is that, in simulation-dominated robot control, the essential question is not which processor runs physics, but whether simulation throughput, policy learning, and runtime synchronization form an efficient end-to-end loop. We present UniLab, a heterogeneous CPU-simulation / GPU-learning architecture that decouples CPU-parallel simulation from GPU policy updates through a unified runtime for data movement, buffering, and synchronization. UniLab is implemented as a complete and extensible training system using MuJoCoUni and MotrixSim CPU-batched physics backends, supporting PPO, FastSAC, FlashSAC, and APPO. On representative simulation-based robot control tasks, UniLab improves end-to-end training efficiency by 3--10×\times under the same hardware configuration, while reducing dependence on the NVIDIA CUDA-based software stack and supporting cross-platform execution on the Apple macOS platform and the AMD ROCm and Intel XPU accelerator backends. These results show that GPU simulation is an effective path to efficient training, but not a necessary one, broadening the practical system choices available for robot RL training. Project page: https://unilabsim.github.io.

Yufei Jia, Zhanxiang Cao, Mingrui Yu +48

Robot Policy LearningRobotics SimulationRobotic RLHeterogeneous Computing
AskPDF
May 28, 2026

MARS Policy: Multimodality Only When It Matters

Imitation learning has become a cornerstone for solving complex robotic manipulation tasks. In particular, multimodality, which enables robots to capture diverse yet valid behavioral patterns, has driven the rapid emergence of generative policies as a dominant paradigm in robot learning. However, achieving such multimodality typically relies on stochastic noise initialization and iterative denoising procedures, resulting in substantial training complexity and low inference efficiency. Meanwhile, not all phases of a robotic task inherently require behavioral diversity. Motivated by this insight, we propose the Modality-Adaptive Robot Sampling (MARS) policy, which adaptively invokes tailored stochasticity only when it is truly beneficial, while reverting to an efficient deterministic learning during single-modal phases. In other words, the proper amount of noise is injected only at the proper time. By selectively activating multimodal generation, MARS policy bridges the gap between the multimodal capability of generative policies and the superior training and inference efficiency of deterministic models. Empirical studies across 8 simulated and 4 real-world tasks demonstrate that MARS exhibits robust multimodal expressivity and high efficiency, with a 16.67% success rate improvement and an 83.20% inference latency reduction in real-world tests. Counterintuitively, MARS also outpaces deterministic policies in training efficiency on near-deterministic tasks by more effectively modeling nuanced action diversity.

Jindou Jia, Tuo An, Yuxuan Hu +7

1MARS Lab, Nanyang Technological University

Efficient Multimodal InferenceRobot Policy LearningRobot Imitation Learning
AskPDF
May 27, 2026

Turning Video Models into Generalist Robot Policies

Video generative models have emerged as a promising robotics backbone, capable of generating videos that depict the completion of complex tasks across embodiments and environments. Recent work proposes robot foundation models that jointly predict future observations and actions by finetuning video models with action-labeled data. In this paper, we test the limits of an alternative approach: leave the video planner as-is while training an embodiment-specific inverse dynamics model (IDM). This decoupling offers several natural benefits: the video planner remains embodiment-agnostic, different video models can be interchanged easily without re-training the IDM, and the IDM can be independently trained with readily available self-play data. We present a closed-loop, video-to-action policy that combines an action-free video world model with a carefully-designed IDM based on the robot embodiment Jacobian. We demonstrate that our IDM design is both data-efficient and scalable to high-dimensional action spaces. Our policy, which we coin the Video-to-Embodied Robot Action Model (VERA), achieves strong performance across simulated and real-world benchmarks, including zero-shot Panda arm manipulation and 16-DoF Allegro-hand dexterous cube re-orientation. The same video planner can be used across multiple embodiments by pairing it with different embodiment-specific IDMs. Our results show that decoupled video planning plus faithful video-to-action translation is a viable alternative route towards zero-shot, cross-embodiment, and generalizable robot control. More results are available on our project website: https://vera.csail.mit.edu.

Sizhe Lester Li, Evan Kim, Xingjian Bai +4

1MIT · 2Independent Researcher · 3CMU +1

Robot Policy LearningCross-Embodiment Robot LearningRobot Policy GeneralizationInverse Dynamics
AskPDF
May 26, 2026

Adversarial Dual On-Policy Distillation from Expressive Teacher

Learning from demonstrations in embodied control is often cast as behavioral cloning, and recent diffusion or flow-matching policies improve this paradigm by modeling multi-modal expert actions. Yet these methods remain offline supervised learners: the policy is trained only on expert states and receives no corrective signal on the states it actually visits. On-policy distillation (OPD) offers a natural remedy, but standard OPD assumes a strong fixed teacher, which is unavailable in demonstration-only control. We propose FA-OPD, an adversarial dual on-policy distillation method in which a Flow Matching (FM) teacher is learned from demonstrations and co-trained with a lightweight MLP student. The teacher provides two complementary signals on student rollouts. The reward channel learns an expert-likeness objective over state-action pairs and drives online exploration through long-horizon policy optimization. The action channel supplies dense local targets at student-visited states, stabilizing exploitation. FA-OPD couples them so that reward distillation enables generalization beyond point-wise demonstrations, while action distillation keeps exploration anchored near expert-like behavior. Across six robot navigation, manipulation, and locomotion benchmarks, FA-OPD beats strong baselines and shows much stronger robustness under noisy or limited demonstrations. Source code: https://github.com/vanzll/FA-OPD.

Zhenglin Wan, Jingxuan Wu, Xingrui Yu +5

School of Computing, National University of Singapore · Department of Statistics and Operations Research, UNC-Chapel Hill, America · CFAR, Agency for Science, Technology and Research, Singapore +4

Robot Policy LearningAdversarial Imitation LearningImitation LearningLearning from DemonstrationOn-Policy Distillation
AskPDF
May 25, 2026

A Factory-Floor Deployment Case Study of VLA Pipelines for Industrial Packaging Task: Workflow, Failures, and Lessons

Vision-Language-Action (VLA) policies have shown promising manipulation capabilities, yet their practical impact is often limited by the reliability demands of real-world deployment. We present a deployment study of an industrial packaging task at Siemens Factory (GWE, Erlangen, Germany), where a robot must pick a transparent accessory bag from a cluttered pile, insert it into the remaining cavity of a cardboard package, and ensure that the bag and its contents remain below the closing plane. Our goal is to understand the practical effort required to adapt a pretrained Pi0.5 policy to a single factory-floor task through iterative fine-tuning and deployment-driven refinement. The pipeline consists of repeated loops of data collection, curation, fine-tuning, evaluation, and targeted recovery data collection. We have accumulated 2535 episodes (10 hours) from the on-site factory settings. In this paper, we contribute an empirical account of a factory-floor VLA deployment, highlighting recurring failure modes and lessons that inform how to improve the deployment workflow.

Brian Zhu, Philipp Schmitt, Philine Meister +12

Siemens Corporation

Robot Policy LearningRoboticsRobotic ManipulationVision-Language-Action ModelsDynamic Robotic ManipulationIndustrial Robotics
AskPDF
May 25, 2026

ParkourFormer: Integrating Predictive Supervision and Sequence Modeling into Parkour Locomotion

Humanoid parkour requires locomotion policies to coordinate whole-body dynamics across rapidly changing terrains such as stairs, gaps, slopes, and obstacles. Existing learning-based humanoid locomotion policies typically infer actions from current and historical observations, while the future evolution of the robot state is represented only implicitly. Explicitly anticipating short-horizon state evolution is particularly beneficial for multiple terrains locomotion, where current actions must account for upcoming contact transitions and whole-body dynamics. We present ParkourForme, a Transformer-based sequence modeling framework that reformulates humanoid locomotion as a future-conditioned decision-making problem. The current robot state queries historical sensorimotor trajectories through cross-attention, while a lightweight prediction head forecasts short-horizon future proprioceptive states. The future states are predicted solely from historical observations and actions, with ground-truth future states used only as supervision targets, and are fused with temporal features to generate the current action without future-information leakage. We evaluate ParkourFormer on a diverse multi-terrain humanoid parkour benchmark including stairs, gaps, slopes, rough terrain, and obstacle traversal. ParkourFormer achieves a 93.96% mean traversal success rate, compared with 90.49% for a vanilla Transformer and 87.16% for a MoE-MLP policy, while maintaining a single policy across all terrain types. These results demonstrate that explicit future-state modeling significantly improves robustness and generalization for agile whole-body locomotion.

Yanheng Mai, Wenhao Xu, Zirui Huang +6

The Hong Kong University of Science and Technology (Guangzhou) · CLAI-LAB, CL-TECH · South China Agricultural University

Humanoid Robot LocomotionRobot Policy Learning
AskPDF
May 25, 2026

Action-Prior Denoising for Smooth Real-Time Chunking

Real-time chunking (RTC) lets chunked action policies operate under inference delay by conditioning a newly generated action chunk on actions already committed by the previous chunk. Training-time RTC simulates this delay during learning and avoids expensive guidance at deployment, but its binary prefix mask treats all non-prefix tokens as fully unconstrained. This under-models asynchronous execution: early overlap actions are fixed, while later overlap actions remain editable but should still stay close to the previous plan. We propose Soft RTC, a training-time RTC generalization based on action-prior denoising. Soft RTC constructs corrupted overlap tokens from partially denoised states instead of pure noise and injects the aligned previous chunk as the same prior during inference through a lightweight token-wise blending rule. On the 12 released large Kinetix levels, a short soft window nearly matches hard training-time RTC in overall solve rate (0.809 vs. 0.815), while a medium window reduces high-delay action delta and jerk by 9.1% and 9.6% relative to hard RTC. Both variants keep near-naive runtime, unlike inference-time RTC baselines. A small preliminary real-robot sorting study provides additional evidence that training-time RTC can improve completion and that Soft RTC gives the lowest commanded-action finite-difference metrics among the tested policies.

Dongyang Liu, Zhaowen Zheng, Yu Sun +3

ROKAE (Shandong) Robot Group Co., Ltd. · School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing, China · The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China

Robot Policy LearningAction Chunking
AskPDF
May 25, 2026

Parallel Differentiable Reachability for Learning and Planning with Certified Neural Dynamics and Controllers

Neural network (NN) dynamics models and control policies achieve strong performance in robotics, but providing sound guarantees under uncertainty remains difficult, especially for closed-loop NN systems. Existing reachability tools provide formal over-approximations, yet are often non-differentiable, overly conservative, or too slow for modern learning and online planning pipelines. To address this, we present a parallelizable, differentiable reachability framework in JAX for continuous- and discrete-time systems with analytical and NN-based dynamics and controllers. Our framework combines Taylor-model flowpipe construction with CROWN-style linear bound propagation through a unified representation that preserves affine dependencies while supporting GPU-batched computation and automatic differentiation. Building on this reachability primitive, we develop (i) a certified training method that encourages reachability-friendly dynamics models and controllers, and (ii) a reachability-aware sampling-based MPC scheme with gradient-based refinement. Experiments on non-prehensile manipulation and quadrotor tasks, including hardware and higher-dimensional evaluations (up to 72D), demonstrate practical online planning while maintaining certified reachable-set over-approximations under bounded uncertainty.

Keyi Shen, Glen Chou

Georgia Institute of Technology, Atlanta, GA 30308

Robotic ControlNeural Network VerificationReachability AnalysisRobot Policy LearningModel Predictive ControlNeural Network Control
AskPDF
May 24, 2026

Learning High-Frequency Continuous Action Chunks in Latent Space

Modern robotic policies increasingly rely on action chunking to execute complex tasks in the physical world. While action chunking improves temporal consistency at moderate action frequencies, it becomes insufficient when the action frequency is further increased (e.g., to 60~Hz). At such high frequencies, policies often fail to generate actions that are both temporally smooth and spatially consistent. We address this challenge by shifting high-frequency action learning from the action space to a latent space with variational autoencoder (VAE). This formulation significantly improves both temporal and spatial consistency of high-frequency control. To enable smooth real-time execution, we further introduce Reuse-then-Refine, a chunk-level refine strategy that improves continuity between adjacent action chunks under asynchronous inference. As a result, robots controlled by our policy can execute complex contact-rich tasks continuously, with less pauses and jerky motions. Experiments on three real-world contact-rich robotic tasks show that our approach consistently completes tasks with smooth motions. Our code and data are available at https://github.com/tars-robotics/RTR.

Kunyun Wang, Yuhang Zheng, Yupeng Zheng +2

School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · TARS Robotics · National University of Singapore, Singapore +2

Robotic ControlLatent Action LearningRobot Policy LearningAction Chunking
AskPDF
May 23, 2026

Smoother Action Chunking Flow Policy via Prior-Corrected Orthogonal Trust-Region Guidance

Flow-matching robot policies commonly use action-chunking inference for efficient closed-loop control, but chunk boundaries can introduce discontinuous action transitions. Existing RTC guidance improves continuity by injecting correction signals during denoising, yet its weight schedule is weak at intermediate timesteps and its unconstrained correction direction may introduce transverse perturbations. We propose POTR, a prior-corrected orthogonal trust-region guidance method. First, we incorporate a data-prior scale σdσ_d into the RTC guidance weight, yielding stronger intermediate-time correction. Second, we decompose the guidance vector into components parallel and perpendicular to the denoising velocity, and constrain the perpendicular component within a trust region. On LIBERO with π0.5π_{0.5}, POTR improves success rate and consistently reduces chunk-boundary discontinuity, acceleration, and jerk compared with RTC. Ablations show that the prior-corrected weight provides the main correction gain, while the orthogonal trust region further improves stability.

Kai Fang, Hailong Pei, Xuemin Chi

South China University of Technology · Guangzhou, China · Zhejiang University +1

Robot Policy LearningAction ChunkingInference-Time Guidance
AskPDF
May 22, 2026

Neuro-Inspired Inverse Learning for Planning and Control

We present a neuro-inspired framework for embodied planning and control. Building on three principles that enable fast and highly effective goal-directed behavior in the mammalian brain - paired forward/inverse internal models, open-loop multi-step motor commands, and sequential, hierarchical organization of action - our Inverter framework uses learned components, trained end-to-end through Inverse Learning (IL) and supplemented where natural by analytic or algorithmic modules; we formalize IL and delineate it from supervised, reinforcement, and imitation learning. IL bridges Reinforcement Learning (RL)-style amortization, which runs in a single forward pass but emits only one action at a time, and Optimal Control (OC)-style sequence planning over whole trajectories, but with iterative test-time computation. Single Inverters or hierarchical n=2 Inverter stacks match or improve on offline-RL and diffusion-planner baselines on all 3 maze2d and 6 antmaze D4RL variants by an average of +24.2% (range -1.9% to +78.2%), at one-to-two orders of magnitude less inference compute time. Distinctively, optimizing through the Forward Model (FoM) over the entire T-step action sequence - rather than per step - lets Inverters produce smooth, goal-coherent, trajectory-wide structure and reach control policies closer to the analytic optimum than the policy underlying the training data itself. We also identify a failure mode of IL: FoM hacking under narrow training-data coverage, which we mitigate by using random training data with broader coverage. As an application example, a Pulse Inverter synthesizes arbitrary single-qubit quantum gates with fidelity matching the standard iterative numerical baseline (GRAPE), at more than 1000x lower per-gate compute time. In summary, we conclude that IL enables a versatile class of world-interfaces, especially for latency- and resource-critical embodied AI.

Maryna Kapitonova, Tonio Ball

NeuroMentum AI · IMBIT, University of Freiburg, Germany

Robot Policy LearningModel-Based PlanningModel-Based RL
AskPDF
May 22, 2026

Point Tracking Improves World Action Models

Robot policy learning benefits from world-action models that capture environment dynamics, but pixel-level prediction entangles dynamics with nuisance factors such as lighting and texture, making learned representations vulnerable to task-irrelevant visual variation. We propose JOPAT, a JOint Pixel-And-Track World-Action Model that predicts latent visual observations, 2D point tracks with visibility, and actions in a single denoising diffusion transformer. The key insight is that tracks provide an explicit representation of motion that captures long-horizon dynamics and remains robust under occlusion or partial out-of-frame motion, offering greater utility than modeling pixel appearance alone. On LIBERO and real-world LeRobot tasks, JOPAT improves over pixel-based baselines, with the largest gains on long-horizon tasks involving occlusion, object interaction, and off-screen motion.

Jiarui Guan, Wenshuai Zhao, Yue Pei +3

Aalto University · ELLIS Institute Finland · Beihang University +3

Point TrackingRobot Policy LearningWorld Models for RoboticsAction-Conditioned World ModelsWorld Action ModelsDiffusion Models
AskPDF
May 22, 2026

Semantically Structured Mixture-of-Experts for Compositional Robotic Manipulation

Diffusion-based policies have established a new standard for precise robotic manipulation but face a critical scalability bottleneck: high-performance models are computationally expensive, while lightweight alternatives often fail to generalize across diverse multi-task environments. Mixture-of-Experts (MoE) architectures offer a promising path to efficiency by activating only a subset of parameters. However, existing MoE routing mechanisms typically rely on low-level noise or latent statistics, ignoring the compositional nature of manipulation tasks. This can fragment reusable behaviors across experts, limiting interpretability and transferability. We introduce Semantically Structured Mixture-of-Experts Diffusion Policy (SMoDP) for compositional robotic manipulation, a framework that grounds expert specialization in semantic task structure. SMoDP leverages a lightweight, inference-time skill predictor, supervised by offline annotations from Vision-Language Models (VLMs), to route action chunks to experts specialized for specific behavioral phases. To ensure robust assignment, we propose a dual contrastive alignment strategy that grounds multi-modal observations in language-defined skill semantics (Inter-modal) while enforcing routing consistency across visually distinct but functionally related behaviors (Intra-modal). Our approach outperforms representative diffusion and MoE-based baselines on multi-task benchmarks with significantly improved parameter efficiency and demonstrates effective compositional transfer to novel tasks through parameter-efficient fine-tuning. Project website: https://deng-cy20.github.io/SMoDP/

Chengyu Deng, Guanqi Chen, Yizhou Chen +4

The University of Hong Kong · Southern University of Science and Technology

Robot Policy LearningRobot Skill LearningGeneralization in Robotic ManipulationMulti-Task Robotic ManipulationDiffusion PolicyRobotic Manipulation+1
AskPDF
May 20, 2026

PGDG: Physically Grounded Data Generation for Robust Bimanual Policy Learning from a Single Demonstration

Behavior cloning for contact-rich bimanual manipulation remains challenging because diverse demonstrations are expensive to collect, and even small disturbances can push the system into off-manifold states where no recovery supervision is available. We propose PGDG, a data generation framework with zero-shot curation that expands a single demonstration into a compact dataset of physically plausible, successful, and diverse recovery behaviors without additional human labeling. PGDG iterates between a physics-grounded sampler and a dataset curator, where the curator selects informative, non-redundant, and recoverable behaviors to update the sampling distribution toward under-covered recovery modes, and the sampler draws physically plausible rollout candidates from this updated distribution and retains successful trajectories. To further improve data quality, PGDG applies short-horizon sampling-based control to relabel selected risky states with corrective actions. Across four bimanual manipulation tasks, PGDG consistently outperforms spatial-only augmentation in both simulation and zero-shot real-world transfer. On RotateBox-Pitch, success improves from 38% to 93% in simulation and from 35% to 82% in the real world. PGDG also enables effective foundation models fine-tuning such as GR00T, increasing success from 46% to 77%. Additional results are available in our website: https://cunxid.github.io/PGDG/.

Cunxi Dai, Haoran Chang, Aditya Nisal +5

Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA · Dexmate, USA

Robot Policy LearningBimanual Robotic ManipulationContact-Rich Robotic ManipulationGeneralization in Robotic ManipulationSynthetic Data Generation for RoboticsRobot Imitation Learning
AskPDF