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.

Jul 29, 2026

Route by Kinematics, Act by Observation: Kinematics-Supervised Expert Routing in MoE-Augmented VLA

While MoE augments VLA via expert specialization, router suffers from ineffective expert routing owing to the kinematic heterogeneity of actions across manipulation tasks and, even worse, the unavailability of the kinematic signals at inference time. In this work, we first observe that most semantically distinct manipulation tasks reduce to multiple kinematic archetypes. Motivated by this finding, we propose Kinematics-supervised explicit routing (KinRT), a new paradigm that shifts from implicit, observation-driven expert routing to explicit, kinematics-guided expert dispatching. Specifically, we perform kinematic clustering on action trajectories into multiple kinematically coherent groups, whose IDs serve as ground truth to supervise the training of the router; at inference time, the router dispatches experts only using visual-language observations, without any reliance on action kinematics. KinRT actually introduces an asymmetric bridging mechanism that distills the task kinematics from the action space in training into the observation space at inference. In addition, to assess KinRT's cross-platform generalization, we build an economical, Do-It-Yourself robot (DIYRobot) platform from scratch using 3D-print technology (<< 2,000USD). Extensive experiments demonstrate KinRT's superiority over both dense and MoE-featured VLAs by more than 23.26% on RoboTwin benchmark and 20.27% on our introduced DIYRobot platform. Our code and DIYRobot platform will be open-sourced.

Tianhang Yang, Yanze Zheng, Junjie Wang +3

Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Pengcheng Lab, Shenzhen, China

Robot Policy LearningExpert RoutingVLMs for Robotics
AskPDF
Jul 28, 2026

HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone

Learning deployable manipulation policies is bottlenecked by the scarcity of data that is both high-fidelity and scalable. Real-robot teleoperation is accurate but costly to scale; robot-free UMI capture scales readily, and current practice uses the resulting data mainly for pre-training, adding a small real-robot "anchor" at post-training. We ask whether raising the fidelity of robot-free UMI data, rather than shrinking the real-robot fraction, can remove that anchor. We present HiFi-UMI, a portable UMI data-production system co-designed for trajectory accuracy, inter-gripper relative pose, synchronization, and field of view: head-mounted offline stereo-inertial SLAM, native rather than reconstructed relative pose, a shared microsecond GPIO trigger, and two wide-angle cameras per hand covering ~200 degrees. It reaches 3 mm workspace-local end-effector accuracy without external tracking infrastructure. Using this corpus, we demonstrate zero-robot post-training: a policy post-trained solely on HiFi-UMI demonstrations deploys directly on a real robot and matches in-domain teleoperation across three backbones spanning the vision-language-action and world-action-model families, with success-rate differences of -2.5, +3.1, and -0.6 percentage points on StarVLA-QwenPI, OpenPI-pi_0.5, and LingBot-VA; the strongest policy reaches 85% on a precision insertion task, even though the teleoperation baseline is collected in the evaluation scene and no HiFi-UMI trajectory is. Pre-training on 4,000 hours from the same corpus lowers action error on ten unseen tasks by 41% and, on StarVLA-QwenPI, raises real-robot success by a further 18.1 percentage points. We open-source HiFi-UMI-2K, 2,000 hours of microsecond-synchronized, ultra-wide-FoV demonstrations, each automatically reconstructed and validated through simulation replay, as a large-scale, high-fidelity resource for the robot-learning community.

Simple AI, :, Yuteng Wei +16

Simple AI

Robot Policy LearningRobot Manipulation DatasetsRobotic Data CollectionRobot Imitation Learning
AskPDF
Jul 28, 2026

P3: Probabilistic Policy Propagation for Stable VAE-Based Robot Learning

Variational Autoencoders are widely used to encode high-dimensional and noisy observations in robotics. However, their stochastic latent creates a mismatch with Proximal Policy Optimization (PPO): an effective policy marginalizes over the latent distribution, whereas former implementations estimate its probability ratio and KL divergence using only one latent sample. We identify a fundamental but overlooked theoretical cause: naive single-sample approximations in stochastic latent space induce significant variance and bias in the surrogate loss. To address this, we introduce P^3 (Probabilistic Policy Propagation), a distribution-aware optimization framework for VAE-based policies. P3P^3 couples moment-based probabilistic method for stable and efficient learning with sampling-based calibration for robust policy behavior under latent uncertainty. In our experiments, P^3 boosts data efficiency from 64.6% to >96%, reduces convergence steps by >20%. Furthermore, P^3 is evaluated on challenging humanoid parkour tasks and shows an effective foundation for VAE-based PPO. Code is available at https://github.com/ylyem9x/P3_Open.

Liyun Yan, Jianming Ma, Yang Zhang +5

Shanghai Jiao Tong University, Shanghai, China · Shanghai Innovation Institute, Shanghai, China · Tongji University, Shanghai, China +1

Variational AutoencodersRobot Policy LearningPolicy OptimizationProximal Policy Optimization
AskPDF
Jul 27, 2026

PAC-DP: PAC-Bayesian Diffusion Policy Learning

Diffusion Policies (DPs) are able to perform complex manipulation tasks. However, DPs are typically trained by minimizing a denoising objective, which provides limited control over generalization in the finite-data regimes common in robotics. In this letter, we propose PAC-DP, an approach that increases the performance of DPs in robotic manipulation tasks. By modeling the DP as a Bayesian neural network, and defining a PAC-Bayes generalization bound, we derive a novel training objective that augments the standard denoising loss with a Kullback-Leibler divergence regularizer between the posterior and prior parameter distributions. From the theoretical perspective, our approach provides a principled approach to regularize the training of DPs without significantly increasing the training time. From the practical point of view, experimental results demonstrate improved denoising performance, lower variational negative log-likelihood, and higher success rates across multiple robotic manipulation benchmarks. Crucially, the largest improvements are observed in low-data training regimes and complex tasks, establishing PAC-DP as a theoretically grounded framework for robot policy learning.

Mohammad Hasan Yeganegi, Dian Yu, Andrea Del Prete +2

Department of Industrial Engineering, University of Trento, Italy. · Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich (TUM), Germany.

PAC-Bayesian Generalization BoundsRobot Policy LearningDiffusion PolicyRobotic ManipulationPolicy Learning
AskPDF
Jul 27, 2026

LeapBot-WA: World-Anchor Action Models via Predictive Latent Alignments

World Action Models (WAMs) have emerged as a powerful paradigm for embodied intelligence, yet the prevailing reliance on pixel-level video generation creates a fundamental bottleneck. Forcing models to reconstruct task-irrelevant visual details dissipates representational capacity and renders policies vulnerable to visual distractors. In this paper, we propose LeapBot-WA, which establishes a novel Predictive-Latent paradigm for WAMs by operationalizing the Joint-Embedding Predictive Architecture (JEPA) as a World-Anchor. Departing from the traditional reliance on visual synthesis, LeapBot-WA shifts the core of world modeling to Predictive Semantic Alignment, extracting abstract physical dynamics directly within a latent foundation space. To bridge the modality gap between non-Gaussian predictive features and diffusion priors, we introduce the Isotropic Semantic Autoencoder (ISAE), which reshapes the anchor's latent space into a diffusion-friendly manifold to prevent off-manifold drift. Furthermore, we design an Asymmetric Mixture-of-Transformers (MoT) architecture. During training, an Anchor Diffusion Transformer acts as a privileged dynamics expert to guide the Action Diffusion Transformer; at inference, this heavy dynamics branch is pruned, enabling zero-overhead execution. LeapBot-WA achieves state-of-the-art performance among predictive models on LIBERO and matches top-tier generative WAMs on RoboTwin 2.0 without requiring large-scale trajectory pre-training. It further demonstrates superior zero-shot robustness to unseen environments and successful real-world transfer, establishing a highly efficient and robust latent-centric paradigm for scalable robotic control. Code: https://github.com/LeapWM/leapbot-wa.

Pei Liu, Nan Zheng, Lang Zhang +8

1The Hong Kong University of Science and Technology (Guangzhou) · 2The Hong Kong University of Science and Technology · 3Leapmotor +1

Robot Policy LearningWorld Models for RoboticsJoint-Embedding Predictive ArchitectureDiffusion PolicyWorld Action ModelsLatent World Models
AskPDF
Jul 26, 2026

PRISM: Polynomial Representations for Interaction-Structured Motor Control

Robot policies map observations to actions, typically using multilayer perceptrons (MLPs). Yet robot dynamics and control objectives involve multiplicative interactions among observable physical variables. MLPs can approximate these interactions but must learn them implicitly, at a representational cost. We introduce PRISM (Polynomial Representations for Interaction Structured Motor Control), a physics-motivated yet data-driven representation that learns multiplicative interactions by recursively adding scaled bilinear features, without enumerating all polynomial terms. Replacing only the MLP's first affine layer, PRISM is plug-and-play for reinforcement and imitation learning, requiring no changes to training objectives, sensing, or controllers. Across humanoid locomotion and contact-rich manipulation, PRISM improves survival from 51.0% to 92.5%, outperforming even larger MLPs. More strikingly, its performance advantage persists under out-of-distribution changes in friction, robot mass, and payload, without retraining. PRISM also exhibits sensorless compliance-like behavior, increases failure-recovery success from 40.9% to 52.3% without explicit admittance control, improves real-robot manipulation, and learns features that better predict physical quantities. These results make PRISM a compelling alternative to standard MLPs for robot policy learning. The project page is available at https://lsh3163.github.io/prism/.

Seung Hyun Lee, Stella X. Yu

University of Michigan

Robotic ControlRL for RoboticsRobot Policy LearningPolynomial Neural NetworksRobot Imitation Learning
AskPDF
Jul 22, 2026

Robostral Navigate

Deploying navigation systems at scale requires a recipe that minimizes sensor assumptions, generalizes across robot embodiments, and trains efficiently. Yet, today's best systems depend on depth sensors, multi-camera rigs, or pre-built maps, limiting the hardware they support and increasing deployment cost. We introduce Robostral Navigate, an 8B vision-language model built around this scalability objective. The model consumes only a stream of monocular RGB images - the most ubiquitous sensor across robotic platforms and predicts waypoints by pointing to the next target location in the current camera view. Operating purely in image space, rather than robot-specific coordinates, makes the policy naturally robust to changes in camera intrinsics and scene scale, enabling deployment across wheeled, legged, and aerial robots without recalibration. We generate 2.4 million trajectories across 350k simulated scenes to reduce the reliance on real-world data collection and scale easily. We further introduce a prefix-caching training recipe that packs entire episodes into single training sequences, reducing training tokens by 22x and cutting training time from months to days. A tree-based attention mask prevents conditioning on previous ground-truth actions, encouraging visually grounded action prediction, and reinforcement learning is used to further improve exploration and recovery capabilities. On the Room-to-Room and Room-Across-Room in Continuous Environments (R2R-CE and RxR-CE) benchmarks, Robostral Navigate sets a new state of the art. On R2R-CE, it achieves a 77.4% success rate, surpassing the best monocular method by 10.5 points and the strongest depth- or multi-camera system by 5.3 points despite using only a single RGB camera. On RxR-CE, it reaches 75.1% success rate, outperforming all monocular baselines.

Abdelaziz Bounhar, Abhijeet Somani, Aditi Kabra +273

Vision-Language NavigationRobot NavigationRobot Policy LearningVLMs for RoboticsVisual Robot NavigationIndoor Robot Navigation+1
AskPDF
Jul 22, 2026

Emergent Compositional Skills in Mixture-of-Experts VLAs

We consider the problem of learning compositional robot policies end-to-end from expert demonstrations, without any pre-specified notion of task decomposition or hierarchy. We ask whether a VLA trained with a simplified Mixture-of-Experts (MoE) action head can emergently learn to decompose tasks into reusable, interpretable primitives. We find that learned experts are heavily reused across tasks and consistently correspond to qualitatively distinct low-level behaviors, suggesting that the router implicitly learns to perform high-level sequencing while experts serve as compositional primitives. Our MoE matches the task performance of a monolithic baseline while demonstrating meaningful expert specialization, a step toward modular, interpretable robot policies that emerge from data alone.

Shlok Shah, Rhiaan Jhaveri, Tharun Kumar Tiruppali Kalidoss +3

Department of Computer Science, Princeton University, Princeton, NJ, USA · Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA

Robot Policy LearningRobot Skill LearningRobot Imitation LearningAgent Skill LearningInterpretability in RLMixture-of-Experts Models+1
AskPDF
Jul 17, 2026

When to Plan: Learning to Select Between Reactive Control and Deliberative Planning

It has long been recognized that humans have the ability to switch between fast, reactive decision-making and slower, deliberative planning. In this paper, we study the question of how to learn this ability, known as meta-reasoning, in artificial agents. We model reactive decision-making as a policy that directly maps state observations to actions. Such policies can be trained with reinforcement learning (RL) or imitation learning, but may generalize poorly outside of their training distribution. Alternatively, model-based decision-time planning is more likely to produce good actions across a broader set of states but requires additional computation time, which delays acting. In this work, we introduce an RL method for training a meta-reasoning policy that allocates computation by conditioning on a reactive-policy uncertainty score. This score enables it to predict when the reactive policy is likely to perform poorly and when planning is needed. We conduct an empirical study on motion planning and navigation environments, showing that this design enables the meta-reasoning policy to learn when the reactive policy provides a good-enough action versus when decision-time planning is needed. Additionally, we show that our design enables the meta-agent to shift toward fully reactive control as the reactive policy improves.

Adam Labiosa, Josiah P. Hanna

Department of Computer Sciences, University of Wisconsin–Madison, USA

Robot Policy LearningRobotic RLRoboticsPolicy Learning
AskPDF
Jul 16, 2026

Learning Agile Navigation in Crowded Environments for Quadruped Robots

Navigating dynamic and crowded environments presents significant challenges for quadruped robots due to severe sensor occlusion and unpredictable human motion. Existing approaches face a trade-off: model-based methods, such as Velocity Obstacles (VO), theoretically guarantee safety but rely on accurate obstacle motion estimates that often fail in dense crowds, while end-to-end learning methods offer robustness but lack motion prediction capability of obstacles, leading to collisions or conservative behaviors. To solve this, we propose VOP-Nav, a novel navigation system that combines the geometric safety of VO with the agile adaptability of end-to-end learning. Using only local onboard observations, our system avoids explicit obstacle detection and tracking pipelines. The VOP-Net processes multi-frame LiDAR data to implicitly encode dynamic constraints and predict a safe velocity region derived from Velocity Obstacle theory. Importantly, the VO predictions serve a dual role: they are used as input to the navigation policy during inference and as a reward signal during training to encourage safe motion. Evaluations in Isaac Gym demonstrate that VOP-Nav achieves higher success rates than all baselines while balancing locomotion speed and collision avoidance. Real-world deployment on a Unitree Go2 quadruped robot further validates the system's robustness and efficiency in complex indoor and outdoor dynamic environments.

Shuyu Wu, Zeyu Liu, Tianbao Zhang +6

Shanghai Jiao Tong University, Shanghai 200240, China · State Key Laboratory of High-end Heavy-load Robots, Midea Group, Foshan 528300, China

Robot Policy LearningRobot NavigationDynamic Obstacle AvoidanceQuadruped Robot Navigation
AskPDF
Jul 15, 2026

Zero2Skill: Bootstrapping Robot Skills through Autonomous Data Collection, Training, and Deployment

Autonomous data collection governs the volume and quality of real-world trajectories for manipulation policy learning. Existing pipelines reduce human effort via self-resetting, VLM verification, or language-guided correction, yet episode-scoped fixes must be reissued whenever the same failure recurs, so oversight cost grows with session length rather than with the number of distinct problems. We present Zero2Skill, a human-robot symbiotic agentic system in which corrections are retained and reused across rounds. The collection loop collects, verifies, and resets autonomously, pausing for a remote operator only when a phase exhausts an explicit retry budget. An LLM parser maps each natural-language utterance to a structured adjustment stored in Corrective Memory, so addressed failure modes typically need not be corrected again under the same conditions. On a real-robot desktop-clearing testbed, Zero2Skill matches teleoperation episode success while reducing human working time to 16%. Language corrections improve verifier-human agreement in all four evaluated settings and raise average single-attempt success from 12.5% to 47.5% (arm-selection: 20.0% to 50.0%). Policies fine-tuned on Zero2Skill data match teleoperation-trained policy success at a fraction of collection human cost.

Boyuan Wang, Zhenyuan Zhang, Zhiqin Yang +16

GigaAI · University of Chinese Academy of Sciences · Hong Kong University of Science and Technology +6

Robot Policy LearningRobotic Data CollectionRoboticsHuman-in-the-Loop AIHuman-Robot Collaboration
AskPDF
Jul 15, 2026

GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch

World Action Models (WAMs) improve robot policy learning by jointly modeling actions and future visual observations, using future scene evolution as dense supervision for physically grounded action generation. However, a common design in existing WAMs is to explicitly generate future videos at inference time, incurring substantial computational overhead and hindering real-time closed-loop deployment. GigaWorld-Policy addresses this issue with an action-centered formulation, where future visual dynamics are used during training while action-only decoding is used at inference time. Building upon this framework, we present GigaWorld-Policy-0.5, an enhanced action-centered WAM designed for more efficient robot control. During pretraining, GigaWorld-Policy-0.5 adopts a mixed Action-Conditioned World Modeling (AC-WM) and WAM training strategy. This strengthens the coupling between visual dynamics and robot actions and improves the transferability of action representations for downstream policy learning. For efficient inference, GigaWorld-Policy-0.5 introduces a Mixture-of-Transformers architecture that separates visual dynamics modeling and action generation into specialized experts, reducing active computation during action-only inference and achieving 85 ms inference latency on a local RTX 4090 setup. In addition, we employ an agent-based AutoResearch pipeline to systematically search training configurations, enabling more efficient identification of optimal experimental setups while reducing the time and manual intervention required for hyperparameter tuning. Experiments and ablations show that GigaWorld-Policy-0.5 preserves the training benefits of future visual dynamics while improving inference efficiency for robot control.

GigaWorld Team, Angen Ye, Angyuan Ma +26

GigaAI Tsinghua University

Robot Policy LearningWorld Model LearningEfficient InferenceWorld Models for RoboticsAction-Conditioned World ModelsMixture-of-Transformers+2
AskPDF
Jul 15, 2026

An Empirical Study on Stage-Information Interfaces for VLA Fine-Tuning

One high-level instruction in long-horizon manipulation can cover several action stages. We use segmented action annotations as an intermediate representation between the full-task instruction and VLA action chunks. A progress module tracks the active stage, while the action policy receives stage information either as current-stage text or as a normalized ordinal stage index in robot state. We compare these interfaces with GR00T N1.6 on LIBERO-10 under direct fine-tuning and continuation fine-tuning from a full-task instruction baseline. Under direct fine-tuning, full-task instruction, current-stage text, and Ordinal Stage-State achieve mean success rates of 57.45%, 50.24%, and 54.36%, respectively, showing that explicit stage information does not automatically improve the policy. Under continuation, the corresponding means are 49.07%, 50.00%, and 53.75%, with Ordinal Stage-State exceeding both alternatives in all three paired runs. The observed benefit differs across interface representations and training arrangements.

Yingwei Ji

Robot Policy LearningLong-Horizon Robotic ManipulationVLA Model TrainingVision-Language-Action Models
AskPDF
Jul 13, 2026

EDAR: Learning Environment-Dependent Action Representations for Robotic Manipulation

Learning effective action representations is critical for robotic manipulation, where raw control trajectories are often noisy, redundant, and difficult to model directly. Existing methods mainly encode the structure of the action stream itself, treating the role of actions in the environment as implicit. Yet manipulation is about changing the world: the same action segment can induce different outcomes under different scene contexts, making action semantics inherently environment-dependent. We propose EDAR, an Environment-Dependent Action Representation that grounds action tokens in both executable control structure and expected visual consequences. By coupling motor commands with their environment-conditioned effects, EDAR encourages the learned action space to capture interaction semantics rather than merely command-level patterns. Experiments on simulated and real-robot manipulation benchmarks demonstrate that EDAR improves downstream policy learning, especially in long-horizon manipulation. These results highlight the importance of grounding action representations in executable control structure and environment-conditioned visual change.

Yuecheng Xu, Tong Yang, Jingkai Jia +3

College of Intelligent Robotics and Advanced Manufacturing, Fudan University · Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University · TeleAI, China Telecom

Latent Action LearningRobot Policy LearningLong-Horizon Robotic ManipulationRobotic ManipulationRobot LearningAction Representation Learning
AskPDF
Jul 13, 2026

WALA Learning Executable Latent Actions from Action-Labeled Demonstrations and Action-Free Videos

Human videos provide rich information about object manipulation at a scale difficult to reproduce with robots, but often lack action annotations that can directly supervise robot policies. Realizing this potential requires distinguishing interaction-relevant changes from static appearance and connecting the learned interaction knowledge to executable robot actions. We present WALA, a framework named for World- and Action-supervised Latent Actions. Its semantic-geometric latent action model (LAM) learns latent actions by encoding and predicting semantic and geometric changes, emphasizing interactions over static appearance while retaining spatial detail. During robot policy training, the LAM encoder and decoder provide guidance through distillation and visual prediction, respectively. Together with robot action supervision, these signals shape policy-generated latent actions to support world prediction and capture the information needed to directly generate executable robot actions. Because LAM supervision requires no action labels, WALA enables co-training on action-labeled robot demonstrations and task-relevant action-free videos. In simulation experiments, our method achieves 92.33% average success on RoboTwin and 75.2% on RoboCasa-GR1-Tabletop, exceeding the previous state of the art on RoboCasa by 5.0 percentage points. WALA also shows strong real-robot performance, further enhanced by task-relevant action-free human videos that improve data efficiency and support target-task zero-shot and few-shot transfer.

Jiahao Liu, Yupeng Zheng, Zhongpu Xia +10

CASIA · Anyverse Dynamics · UCAS +2

Latent Action LearningRobot Policy LearningRobot Imitation Learning
AskPDF
Jul 13, 2026

Learning to Navigate with Minimal Parameters: Decomposing Visual Navigation Through Closed-Form Geometric Interfaces

Visual navigation policies have grown to hundreds of millions of parameters trained on billions of frames, with geometry, mapping, and control learned implicitly. We propose a decomposed point-goal navigation system in which operations with known closed-form structure, such as projective geometry, occupancy, and coordinate transforms, are computed analytically and serve as interfaces between three small learned modules: an egress predictor that grounds the episode goal as a local subgoal in the current view, a navigation predictor that estimates a goal-conditioned posterior over where trajectories travel, and an endpoint-pinned residual diffusion generator that samples trajectory shapes from this posterior. Only 0.58M out of 23M parameters are trained, on 44k frames, in under one GPU-hour. Across 6060 point-goal episodes in 60 environments, the system attains competitive success rates with the lowest collision rate among evaluated methods. We further show that under this decomposition, the frozen image encoder can be replaced by a 0.54M MobileNetV2 at a -2.0 SR cost, bringing the full system under 1.2M parameters. It also transfers to no-goal exploration by retraining only the 123k-parameter egress head, and its failure modes under sensor corruption are transparent and analytically correctable. We deploy and evaluate the system zero-shot on a low-cost UGV, running navigation and localization on a Jetson Orin Nano in real-time.

Edward Beng Wai Tan, Siew-Kei Lam

College of Computing and Data Science, Nanyang Technological University, Singapore.

Visual NavigationRobot Policy LearningTrajectory GenerationDiffusion-Based PlanningRobot NavigationData-Efficient Robot Learning+1
AskPDF
Jul 11, 2026

PIER-Flow: Physics-Informed Efficient Rectified Flow for Real-Time Mobile Robot Navigation

Autonomous navigation in dense and highly dynamic environments requires both physically feasible control and low-latency replanning. Optimization-based methods such as Model Predictive Control (MPC) explicitly handle robot kinematics and safety constraints, but repeated nonlinear optimization can limit real-time responsiveness. Deterministic behavior-cloning policies enable efficient inference but may fail to represent multimodal avoidance behaviors, whereas diffusion policies capture multimodality at the cost of time-consuming iterative denoising. We propose PIER-Flow (Physics-Informed Efficient Rectified Flow), a lightweight navigation policy for mobile robots. By distilling an MPC expert into a continuous-time Ordinary Differential Equation (ODE), PIER-Flow achieves single-step action generation through parallel latent sampling and lightweight feasibility selection. We introduce a physics-informed training objective to enforce kinematic consistency, paired with an asynchronous action chunking architecture for robust sim-to-real deployment. Extensive simulations demonstrate that PIER-Flow achieves a 98.85% success rate and zero collisions, with an average inference of ∼\sim1.29 ms, which accelerates planning by 37.2×\times compared to MPC and over 800×\times against standard diffusion models. Crucially, real-world deployment on a resource-constrained edge computer further achieves an approximately stable inference latency of ∼\sim5.3 ms, avoiding the latency spikes and freezing events observed with planning baselines.

Shibo Li, Zhongcheng Wang, Jiahe Cao +2

School of Automation, Northwestern Polytechnical University, Xi’an, China · Department of Robotics, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi SE45 05, United Arab Emirates

Constrained Motion PlanningRobot Policy LearningRectified FlowRobot NavigationPhysics-Informed ML
AskPDF
Jul 10, 2026

B-spline Policy: Accelerating Manipulation Policies via B-spline Action Representations

In this work, we present B-spline Policy (BSP), an action representation designed for accelerating robot manipulation policies. Rather than predicting discrete-time action chunks, BSP parameterizes actions as continuous B-spline curves defined by a set of knots and control points. This representation yields smooth, time-continuous trajectories that can be temporally scaled and executed by low-level controllers at higher frequencies and speeds. We show that B-spline-parameterized actions can be seamlessly integrated into standard policy learning pipelines by directly predicting B-spline parameters. Experiments on simulated and real-world tasks demonstrate that BSP significantly reduces task completion time, achieving substantial improvements over baseline methods while maintaining strong success rates. More results: https://b-spline-policy.github.io

Xiaoshen Han, Haoyu Xiong, Haonan Chen +4

1Harvard · 2MIT · 3UT Austin

Robot Policy LearningRobotic ManipulationB-Spline Trajectory Representation
AskPDF
Jul 10, 2026

Implicit Behavior Coordination from Sub-Task Demonstrations by Exploiting Overlap-Induced Multimodality

Long-horizon robotic rearrangement is commonly formulated as a skill-sequencing problem, where distinct behaviors are explicitly represented and coordinated by a planner or high-level policy. We investigate whether such explicit behavior identities and sequencing interfaces are necessary at all. We introduce implicit behavior coordination from sub-task demonstrations, where separately collected behaviors are coordinated without behavior identity labels, complete-task demonstrations, or task-ordering supervision. Our key observation is that overlap between sub-task demonstrations induces multimodal action distributions that need not be resolved through explicit behavior partitioning. Instead, this overlap-induced multimodality can be exploited as a coordination resource. We instantiate this idea with a shared Flow Matching policy that preserves multiple action modes and critic-guided in-sample planning that propagates task value across demonstrations and selects task-relevant modes. Experiments in Habitat and on a real robot show that implicit behavior coordination remains effective under reduced cross-behavior overlap, larger behavior mixtures, longer horizons, and execution failures, supporting the idea that long-horizon coordination can emerge directly from sub-task demonstrations without explicitly recovering or sequencing behavior identities.

Ahmed Shokry, Usama Ahmed Siddiquie, Sicong Pan +1

Humanoid Robots Lab and Center for Robotics, University of Bonn, Germany · Lamarr Institute for Machine Learning and Artificial Intelligence, Bonn, Germany

Robot Policy LearningLong-Horizon Robotic ManipulationRobot Imitation Learning
AskPDF
Jul 9, 2026

FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space

Pretrained generative robot policies based on flow matching and diffusion have achieved impressive results across a wide range of manipulation tasks. Yet real-world deployments routinely expose failure modes outside the pretraining distribution. Closing these gaps typically requires large-scale data collection or online reinforcement learning on physical hardware, which is impractical for rapid and safe adaptation. We present FlowDAgger, a sample- and compute-efficient method for adapting frozen generative robot policies from human interventions in latent space. Our key idea is action inversion: each human expert action is mapped to the noise that would have produced it under the frozen base policy, using reverse-time integration followed by local refinement. The resulting inverted noise provides supervision for a lightweight latent policy that steers the base model at deployment time, enabling rapid skill acquisition while preserving its behavioral priors. We evaluate FlowDAgger in simulation and on real-world bimanual and single-arm manipulation, adapting both action-head VLAs and world-action models from a handful of interventions. FlowDAgger outperforms supervised fine-tuning and latent-space RL baselines and preserves pretrained skills on held-out tasks, offering a practical path for adapting robot foundation models in the real world. Website: https://microsoft.github.io/FlowDAgger

Michael Murray, Daphne Chen, Simran Bagaria +7

1Microsoft Research · University of Washington · 2Microsoft +1

Latent Action LearningRobot Policy LearningRobot Policy AdaptationRobot Skill LearningRobot Foundation ModelsData-Efficient Robot Learning+2
AskPDF
Jul 8, 2026

PriGo: Test-Time Primitive Guidance to Diffusion and Flow Policies for Adaptive Robotic Manipulation

Imitation learning has enabled remarkable progress in robotic manipulation, especially with diffusion and flow-based policies that generate complex visuomotor behaviors directly from demonstrations. Yet, despite their strong performance, these policies often fail to generalize across tasks and environments. A key reason is that existing policies tend to imitate superficial action correlations rather than the underlying intent. Inspired by the compositional structure of human behaviors, we propose PriGo, a primitive-guided test-time adaptive framework for robust robotic manipulation. PriGo introduces PANet, a lightweight primitive prediction module that infers primitive distributions directly from observations. We further propose a differentiable primitive guidance mechanism that refines generated actions during inference, steering trajectories toward semantically consistent behaviors. Unlike prior primitive-conditioned approaches, PriGo operates entirely at test time and can be seamlessly integrated into pretrained diffusion and flow policies without retraining. Extensive experiments on LIBERO, CALVIN, SIMPLER, and real-world robotic tasks demonstrate that PriGo consistently improves robustness, long-horizon execution, and generalization ability across both diffusion and flow-based policies.

Zezeng Li, Enda Xiang, Thuy Tran +3

Ecole Centrale de Lyon, France · Beihang University, China

Robot Policy LearningTest-Time AdaptationGeneralization in Robotic ManipulationDiffusion PolicyRobotic ManipulationRobot Policy Generalization
AskPDF
Jul 7, 2026

RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures

Pretrained video generative models are promising backbones for visuomotor control, but their imagined futures often drift from task intent and are not reliably action-conditional. As a result, these models can be difficult to use for planning or policy extraction. To address these limitations, we propose RoboTALES, a single-stage framework that learns task-aligned simulated futures and uses them to train robot policies. Our approach introduces two key innovations: (1) a hierarchical LLM-based planner that breaks complex tasks into a sequence of subgoals to guide the model's imagination; and (2) a VLM-based critic that evaluates these ``imagined'' futures and uses reward-based feedback to keep the model's internal representations focused on the goal. By anchoring the video generator in abstract reasoning, we produce temporally consistent rollouts and more coherent actions. We evaluate RoboTALES on diverse manipulation tasks from RoboCasa and LIBERO10, and show that our method consistently outperforms existing methods, especially in long-horizon tasks. Our code and models are publicly available at https://github.com/hananshafi/RoboTALES.

Hanan Gani, Tejal Kulkarni, Madhoolika Chodavarapu +2

University of California, San Diego, CA 92093, USA

Robot Policy LearningRobot Skill LearningWorld Models for RoboticsLarge Language Model-Based Robot PlanningSynthetic Data Generation for RoboticsVLMs for Robotics
AskPDF
Jul 6, 2026

GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks

For robots to work reliably in commercial and industrial applications, recent advances in agentic coding systems have potential to combine interpretable robot programming with the open-world adaptability of model-free policies. We focus on "Variational Automation" (VA), a class of tasks that have larger variations in object geometry and pose than fixed automation. Model-free policies often struggle to close the reliability gap for VA tasks, which must be executed persistently and reliably in commercial and industrial applications. Motivated by prior work on Task and Motion Planning (TAMP) and the Robot Operating System (ROS), we introduce Graph-as-Policy (GaP), a multi-agent coding harness that generates directed computation graphs with perception, planning, and control nodes from a Modular Open Robot Skill Library (MORSL). GaP generates an internal simulation environment to rehearse task instances with different graphs in parallel to iteratively refine the graph structure and parameters to improve success rates and throughput. Evaluation with 8 new open VA task benchmarks, 4 in simulation and 4 in real-world, suggests that GaP can achieve success rates that significantly outperform baselines. Details, code, and data: https://graph-robots.github.io/gap

Kaiyuan Chen, Shuangyu Xie, Letian Fu +21

University of California, Berkeley · Carnegie Mellon University · Bosch +1

Robot Policy LearningGraph-Based PlanningMotion PlanningMulti-Agent Planning
AskPDF
Jul 6, 2026

Spatial Attention: Adapting Execution Horizons for Diffusion Policies via Observation Sensitivity

Sampling action chunks via generative models has become a widely adopted methodology for robotic learning from demonstration. However, existing methods often struggle to balance responsiveness and computational cost because they execute each action chunk for a fixed execution horizon. In this paper, we adaptively adjust the execution horizon of sampled action chunks, balancing responsiveness and computational efficiency. We introduce Spatial Attention -- defined as the expected squared norm of the gradient of the action log-likelihood with respect to the observation -- which indicates the sensitivity of the policy's action distribution to variations in the observation. We show that, under a fixed budget of chunk samplings, the execution horizon that minimizes the cumulative likelihood drop induced by disturbances decreases as Spatial Attention increases. By forecasting future Spatial Attention values alongside the action chunk, our framework dynamically assigns shorter execution horizons to phases with high Spatial Attention, and longer horizons to phases with low Spatial Attention. Experiments on standard and perturbed tasks, in both simulation and on a real robot, show that our method significantly improves success rates over fixed-horizon baselines while maintaining the average execution horizon.

Che-Sang Park, Junsu Ha, Jianlong Fu +1

Robotics Laboratory, Seoul National University, Seoul, South Korea · Microsoft Research Asia, Beijing, China

Robot Policy LearningDiffusion-Based PlanningRobot Imitation LearningAction Chunking
AskPDF
Jul 5, 2026

XS-VLA: Teaching Tiny Vision-Language-Action Models with Spatial Supervision and Demonstration Conditioning

How can richer training supervision improve robot control while keeping the deployed policy compact? We present XS-VLA, a staged training framework using teacher-derived spatial labels and demonstration-conditioned action learning. Coarse-Grained Spatial Distillation (CSD) initializes the backbone through an auxiliary region-label task. Latent Flow Matching (LFM) then conditions an action-space velocity field on a demonstration latent, using KL regularization while jointly optimizing the backbone and action modules. The deployed policy contains 243.99M parameters and operates without the teacher or posterior encoder. XS-VLA achieves 90.25% average LIBERO success in each of two training seeds, compared with 86.00% for a SmolVLA-256M base trained under our settings. Ablations examine both training stages through matched image pretraining and Huber/MSE controls. On three Mobile ALOHA tasks, average strict success increases from 21.7% to 65.0%. These results demonstrate the control utility of auxiliary representation initialization and regularized demonstration-conditioned flow learning for compact VLA~policies.

Iok Tong Lei, Ying Jie Yap, Wei Huang +5

Department of Computer Science and Technology, Tsinghua University, Beijing, China. · National College for Excellent Engineers, Beihang University, Beijing, China. · Independent Researcher +1

Robot Policy LearningLanguage-Conditioned Robot ManipulationEfficient VLA ModelsVision-Language-Action ModelsVision-Based Robot ControlKnowledge Distillation
AskPDF
Jul 2, 2026

Learning Agile Intruder Interception using Differentiable Quadrotor Dynamics

This paper presents a methodology for learning a control policy to intercept an intruder using the 3D direction unit vector to the intruder and the interceptor state. Prior deep reinforcement learning approaches assume either relative position or distance to the intruder is available, but this information is not readily accessible in real-world applications that employ passive, monocular camera sensors. Instead, we propose a solution that leverages an analytical policy gradient method using differentiable quadrotor dynamics to learn agile interception at speeds up to 10 m/s. The proposed approach outperforms baseline methods that utilize simplified point mass dynamics by an average of 30%.

Michael Anoruo, Xiaoyu Tian, Abhishek Rathod +5

Carnegie Mellon University · Artificial Intelligence Integration Center

RL ControlRobot Policy LearningQuadrotor ControlPolicy Learning
AskPDF
Jul 2, 2026

Lightweight Safe Reinforcement Learning for End-to-End UAV Navigation

With the rapid development of autonomous aerial systems, Unmanned Aerial Vehicles (UAVs) are increasingly deployed in applications such as inspection, environmental monitoring, and rescue, creating growing demand for reliable autonomous navigation. However, autonomous UAV navigation in dense environments remains challenging under sparse perception and dynamic constraints. Most reinforcement learning (RL) methods lack explicit safety mechanisms, leading to unsafe exploration, unstable training, and risky behaviors, especially during high-speed flight. Even in safe RL approaches, safety is often enforced by projecting policy outputs onto a safe action set, which may introduce instability. Meanwhile, many learning-based methods rely on dense inputs or large networks, increasing computational burden and limiting lightweight onboard deployment. Facing the above challenges, we propose a safety-constrained perception-control integrated framework for UAV navigation. A lightweight network encodes sparse observations into collision-risk-aware features using asymmetric and depthwise separable convolutions. We formulate the task as a constrained Markov decision process within a hierarchical control architecture and solve it using a Lagrangian-based safe PPO algorithm. Curriculum learning further improves training stability. Experiments with varying obstacle densities and flight speeds demonstrate higher success rates, improved safety, and better efficiency than existing reinforcement learning baselines.

Shenghui Zhang, YuXuan Gao, Songwei Zhao +3

Robot Policy LearningUAV NavigationConstrained RLSafe RL
AskPDF
Jul 1, 2026

BIFROST: Bridging Invariant Feature Representation for Observation-space Sim2Real Transfer

Sim2real transfer for robot policy learning suffers due to mismatch between simulation and reality. Existing methods typically address each gap in isolation through separate adaptation modules, which are composed or layered when both gaps coexist. Yet the basis for attempting sim2real in the first place is that there is shared structure between a task in simulation and reality, where equivalent actions from equivalent configurations produce equivalent long term outcomes regardless of domain specific differences in rendering or physics. In this paper, we study whether we can identify and exploit this shared structure from raw observations to train a policy that enables zero shot transfer. We introduce BIFROST, which learns a shared history encoder on paired cross-domain data via cross-domain bisimulation objective: observation-action sequences leading to equivalent long-term behavior are mapped to nearby latent states, regardless of domain. Policies trained on these latent states in simulation transfer zero-shot to reality. We provide empirical evidence on sim2sim visual navigation and sim2real contact rich manipulation task and visual servoing task that BIFROST achieves effective transfer where domain adaptation and co-training baselines fail under both visual and dynamics domain gaps.

Yunfu Deng, Josiah P. Hanna

Department of Computer Sciences, University of Wisconsin–Madison, Madison, WI 53706 USA

Zero-Shot LearningRobot Policy LearningRepresentation LearningSim-to-Real TransferInvariant Representation Learning
AskPDF
Jul 1, 2026

FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement

Robot policies inevitably encounter failures when deployed in real environments. Naive retries often repeat the same mistakes, while many existing recovery methods rely on human intervention. In this paper, we propose Failure-Aware Retry (FAR), a framework that enables robots to learn from previous failures at test time, adapt their behavior accordingly, and eventually complete the task autonomously. FAR combines Failure-Contrastive Preference Adaptation, which constructs preference learning data from failures to steer the policy away from previously unsuccessful behaviors, with lightweight action perturbations during retries to encourage local exploration. We further incorporate successful recovery trajectories into a training loop for continual policy improvement. Experiments in both simulation and real-world manipulation tasks show that FAR substantially improves success rates and robustness, with average gains of 17.6% over the standard diffusion policy in simulation and 11.7% in the real world. In addition, FAR improves data efficiency under both reset and timestep budgets during continual policy improvement by exploiting informative failure cases. Videos and code are available at https://hoar012.github.io/FAR-Project.

Haoran Hao, Shahram Najam Syed, Jeffrey Ichnowski +1

Carnegie Mellon University

Robot Policy LearningRobot Policy AdaptationRobot Skill LearningRobot Failure RecoveryRobotic ManipulationContinual RL+1
AskPDF
Jun 30, 2026

ASPIRE: Agentic /Skills Discovery for Robotics

Traditional robot programming is notoriously challenging: it requires orchestrating multimodal perception, managing physical contact dynamics, and handling diverse environment configurations and execution failures. We introduce ASPIRE (Agentic Skill Programming through Iterative Robot Exploration), a continual learning system that autonomously writes and refines robot control programs in a code-as-policy paradigm while compounding experience into a reusable skill library. ASPIRE operates in an open-ended learning loop, consisting of three components: (1) a closed-loop robot execution engine that exposes fine-grained multimodal traces, enabling the agent to autonomously diagnose failures, synthesize repairs, and validate outcomes; (2) a continually expanding skill library that distills validated fixes into reusable, transferable robotic knowledge; and (3) an evolutionary search procedure that generates diverse programs, systematically debugging them to explore beyond single-trajectory refinement. ASPIRE surpasses prior methods by up to 77% on manipulation tasks under perturbation, 72% on Robosuite's bimanual handover task, and up to 32% on long-horizon household tasks. The accumulated skill library further enables zero-shot generalization: on representative unseen long-horizon tasks, ASPIRE achieves 31% success, outperforming the 4% success rate of prior methods. Performance scales with the capabilities of frontier models. With Claude Opus 5.5, ASPIRE nearly saturates these benchmarks, achieving 99% average success across all 80 LIBERO-Pro tasks and 100% success on representative Robosuite and BEHAVIOR-1K tasks. Beyond simulation, skills discovered in simulation reduce real-world robot programming effort across embodiments and robot APIs, while skills acquired through online interaction with physical robots enable ASPIRE to solve a Rubik's Cube with progressively improving efficiency.

Runyu Lu, Yubo Wu, Ethan Kou +13

NVIDIA · UMich · UIUC +2

Robot Policy LearningLong-Horizon Robotic ManipulationContinual Robot LearningRobot Skill LearningMulti-Task Robotic ManipulationAI Control+7
AskPDF