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

405 papers42 papers in the last four weeks, down 58% on the four weeks before. 0.3% of all new papers.

Feb 27, 2026

ABPolicy: Asynchronous B-Spline Flow Policy for Real-Time and Smooth Robotic Manipulation

Robotic manipulation requires policies that are smooth and responsive to evolving observations. However, synchronous inference in the raw action space introduces several challenges, including intra-chunk jitter, inter-chunk discontinuities, and stop-and-go execution. These issues undermine a policy's smoothness and its responsiveness to environmental changes. We propose ABPolicy, an asynchronous flow-matching policy that operates in a B-spline control-point action space. First, the B-spline representation ensures intra-chunk smoothness. Second, we introduce bidirectional action prediction coupled with refitting optimization to enforce inter-chunk continuity. Finally, by leveraging asynchronous inference, ABPolicy delivers real-time, continuous updates. We evaluate ABPolicy across seven tasks encompassing both static settings and dynamic settings with moving objects. Empirical results indicate that ABPolicy reduces trajectory jerk, leading to smoother motion and improved performance. Project website: https://teee000.github.io/ABPolicy/.
Feb 27, 2026

MicroPush: A Lightweight Simulator for Sim-to-Real Microrobotic Pushing and Assembly

Developing learning-based autonomy for microrobotic manipulation is difficult because physical trials are slow, variable, and poorly suited to large-scale training. We present MicroPush, a lightweight simulation and benchmarking environment for pushing and assembly with magnetic rolling microrobots. The simulator combines overdamped planar dynamics with calibrated rolling actuation, reduced-order contact handling, short-range interaction corrections, and optional background flow, while providing common interfaces for planning, model-based control, reinforcement learning (RL), interactive visualization, and headless evaluation. In no-render tests, MicroPush remains substantially faster than real time, reaching 37.0x real time with 100 passive particles. We further evaluate the simulator through zero-shot sim-to-real policy transfer. A Residual RL-MPC policy is trained entirely in MicroPush, frozen after simulation training, and deployed on the physical system without real-world policy fine-tuning. A 20 μm magnetic microrobot pushes a similarly sized silica particle along a figure-eight trajectory with 1.91 μm median and 4.65 μm 95th-percentile path error, and the same autonomy stack performs sequential line, triangle, and six-particle hexagonal assembly. These results show that a deliberately reduced-order simulator can provide an efficient training and development substrate for sim-to-real microrobotic autonomy.
Feb 26, 2026

Embedding Morphology into Transformers for Cross-Robot Policy Learning

Cross-robot policy learning -- training a single policy to perform well across multiple embodiments -- remains a central challenge in robot learning. Transformer-based policies, such as vision-language-action (VLA) models, are typically embodiment-agnostic and must infer kinematic structure purely from observations, which can reduce robustness across embodiments and even limit performance within a single embodiment. We propose an embodiment-aware transformer policy that injects morphology via three mechanisms: (1) kinematic tokens that factorize actions across joints and compress time through per-joint temporal chunking; (2) a topology-aware attention bias that encodes kinematic topology as an inductive bias in self-attention, encouraging message passing along kinematic edges; and (3) joint-attribute conditioning that augments topology with per-joint descriptors to capture semantics beyond connectivity. Across a range of embodiments, this structured integration consistently improves performance over a vanilla pi0.5 VLA baseline, indicating improved robustness both within an embodiment and across embodiments.
Feb 26, 2026

Demystifying Action Space Design for Robotic Manipulation Policies

The specification of the action space plays a pivotal role in imitation-based robotic manipulation policy learning, fundamentally shaping the optimization landscape of policy learning. While recent advances have focused heavily on scaling training data and model capacity, the choice of action space remains guided by ad-hoc heuristics or legacy designs, leading to an ambiguous understanding of robotic policy design philosophies. To address this ambiguity, we conducted a large-scale and systematic empirical study, confirming that the action space does have significant and complex impacts on robotic policy learning. We dissect the action design space along temporal and spatial axes, facilitating a structured analysis of how these choices govern both policy learnability and control stability. Based on 13,000+ real-world rollouts on a bimanual robot and evaluation on 500+ trained models over four scenarios, we examine the trade-offs between absolute vs. delta representations, and joint-space vs. task-space parameterizations. Our large-scale results suggest that properly designing the policy to predict delta actions consistently improves performance, while joint-space and task-space representations offer complementary strengths, favoring control stability and generalization, respectively.
Feb 23, 2026

Universal Pose Pretraining for Generalizable Vision-Language-Action Policies

Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency because they entangle high-level perception with sparse, embodiment-specific action supervision. Since these models typically rely on VLM backbones optimized for Visual Question Answering (VQA), they excel at semantic identification but often overlook subtle 3D state variations that dictate distinct action patterns. To resolve these misalignments, we propose Pose-VLA, a decoupled paradigm that separates VLA training into a pre-training phase for extracting universal 3D spatial priors in a unified camera-centric space, and a post-training phase for efficient embodiment alignment within robot-specific action space. By introducing discrete pose tokens as a universal representation, Pose-VLA seamlessly integrates spatial grounding from diverse 3D datasets with geometry-level trajectories from robotic demonstrations. Our framework follows a two-stage pre-training pipeline, establishing fundamental spatial grounding via poses followed by motion alignment through trajectory supervision. Extensive evaluations demonstrate that Pose-VLA achieves state-of-the-art results on RoboTwin 2.0 with a 79.5% average success rate and competitive performance on LIBERO at 96.0%. Real-world experiments further showcase robust generalization across diverse objects using only 100 demonstrations per task, validating the efficiency of our pre-training paradigm.
Feb 21, 2026

Temporal Action Representation Learning for Tactical Resource Control and Subsequent Maneuver Generation

Autonomous robotic systems should reason about resource control and its impact on subsequent maneuvers, especially when operating with limited energy budgets or restricted sensing. Learning-based control is effective in handling complex dynamics and represents the problem as a hybrid action space unifying discrete resource usage and continuous maneuvers. However, prior works on hybrid action space have not sufficiently captured the causal dependencies between resource usage and maneuvers. They have also overlooked the multi-modal nature of tactical decisions, both of which are critical in fast-evolving scenarios. In this paper, we propose TART, a Temporal Action Representation learning framework for Tactical resource control and subsequent maneuver generation. TART leverages contrastive learning based on a mutual information objective, designed to capture inherent temporal dependencies in resource-maneuver interactions. These learned representations are quantized into discrete codebook entries that condition the policy, capturing recurring tactical patterns and enabling multi-modal and temporally coherent behaviors. We evaluate TART in two domains where resource deployment is critical: (i) a maze navigation task where a limited budget of discrete actions provides enhanced mobility, and (ii) a high-fidelity air combat simulator in which an F-16 agent operates weapons and defensive systems in coordination with flight maneuvers. Across both domains, TART consistently outperforms hybrid-action baselines, demonstrating its effectiveness in leveraging limited resources and producing context-aware subsequent maneuvers.
Feb 10, 2026

Learning Force-Regulated Robotic Manipulation with a Low-Cost Tactile-Force-Controlled Gripper

Successfully manipulating many everyday objects, such as potato chips, requires precise force regulation. Failure to modulate force can lead to task failure or irreversible damage to the objects. Humans can precisely achieve this by adapting force from tactile feedback, even within a short period of physical contact. We aim to give robots this capability. However, commercial grippers exhibit high cost or high minimum force, making them unsuitable for studying force-controlled policy learning with everyday force-sensitive objects. We introduce TF-Gripper, a low-cost (~$150) force-controlled parallel-jaw gripper that integrates tactile sensing as feedback. It has an effective force range of 0.45-45 N and is compatible with different robot arms. Additionally, we designed a teleoperation device paired with TF-Gripper to record human-applied grasping forces. While we can train standard low-frequency policies with the collected force data, achieving reliable performance remains challenging due to the reactive and contact-dependent nature of force-regulated manipulation. To overcome this, we propose RETAF (REactive Tactile Adaptation of Force), a framework that decouples grasping force control from arm pose prediction. RETAF regulates force at high frequency using wrist images and tactile feedback, while a base policy predicts end-effector pose and gripper open/close action. Our experiments show that, compared to position control, direct force control with TF-Gripper improves grasp stability and overall task performance across six real-world tasks. We further show that tactile feedback is essential for force regulation, and that RETAF consistently outperforms baselines and can be integrated with various base policies. We hope this work opens a path for scaling the learning of force-controlled policies in robotic manipulation. Project page: https://force-gripper.github.io .
Feb 8, 2026

USER: A Unified and Extensible System for Real-World Online Policy Learning in Embodied AI

Online policy learning directly in the physical world is a promising yet challenging direction for embodied intelligence. Unlike simulation, real-world systems cannot be arbitrarily accelerated, cheaply reset, or massively replicated, suggesting that real-world policy learning is not merely an algorithmic problem, but inherently a systems problem. We present USER, a Unified and extensible SystEm for real-world online policy leaRning. On the systems side, USER introduces a hardware abstraction layer for unified robot management and an adaptive communication plane that enables efficient cloud-edge training. On the learning side, USER adopts a fully asynchronous training framework, designs a persistent and cache-aware replay buffer, and provides extensible abstractions for rewards, algorithms, and policies. Experiments in both simulation and the real world demonstrate that USER supports multi-robot coordination, heterogeneous manipulators, cloud-edge training with large models, and long-running asynchronous training. Together, these capabilities establish USER as a unified and extensible systems foundation for real-world online policy learning.
Jan 28, 2026

OGPO: One-Step Generative Policy Optimization for Real-Time Robot Control

Real-time robot control demands fast action generation. Diffusion and flow matching policies for robot control require multi-step sampling, limiting their deployment in real-time scenarios. Natively reducing the sampling steps to one sacrifices representation quality and task performance, creating a trilemma among speed, fidelity, and performance. We present One-Step Generative Policy Optimization (OGPO), a systematic framework to resolve this trilemma. OGPO first pairs a lightweight architecture with the interval velocity principle for distillation-free one-step inference, while representation spreading prevents representation quality degradation. It then performs on-policy reinforcement learning (RL) fine-tuning on this fast, stable policy to break the imitation learning ceiling. Experiments on RoboMimic and OpenAI Gym benchmarks show that OGPO matches or exceeds multi-step baselines while achieving a 5-20 times inference speedup and over 120Hz control frequency. Physical deployment on a Franka-Emika-Panda robot validates real-world applicability. Project page: https://ogpo-project.github.io/
Nov 10, 2025

Rapidly Learning Soft Robot Control via Implicit Time-Stepping

With the explosive growth of rigid-body simulators, policy learning in simulation has become the de facto standard for most rigid morphologies. In contrast, soft robotic simulation frameworks remain scarce and are seldom adopted by the soft robotics community. This gap stems partly from the lack of easy-to-use, general-purpose frameworks and partly from the high computational cost of accurately simulating continuum mechanics, which often renders policy learning infeasible. In this work, we demonstrate that rapid soft robot policy learning is indeed achievable via implicit time-stepping. Our simulator of choice, DisMech, is a general-purpose, fully implicit soft-body simulator capable of handling both soft dynamics and frictional contact. We further introduce delta natural curvature control, a method analogous to delta joint position control in rigid manipulators, providing an intuitive and effective means of enacting control for soft robot learning. To highlight the benefits of implicit time-stepping and delta curvature control, we conduct extensive comparisons across four diverse soft manipulator tasks against one of the most widely used soft-body frameworks, Elastica. With implicit time-stepping, parallel stepping of 500 environments achieves up to 6x faster speeds for non-contact cases and up to 40x faster for contact-rich scenarios. Finally, a comprehensive sim-to-sim gap evaluation--training policies in one simulator and evaluating them in another--demonstrates that implicit time-stepping provides a rare free lunch: dramatic speedups achieved without sacrificing accuracy.
Sep 23, 2025

N2M: Bridging Navigation and Manipulation by Learning Pose Preference from Rollout

Determining where to execute the manipulation policy is a fundamental challenge in mobile manipulation. Most approaches have formulated this as a geometric search problem, prioritizing physical reachability. However, given the high sensitivity of modern learning-based manipulation policies, geometric criteria alone are insufficient. Optimal performance requires base positioning that is aware of the policy's preference. While recent works have attempted to address this, they remain limited in practicality due to reliance on pre-built scene reconstruction and slow inference. In this work, we introduce N2M that systematically reformulates the approach to base positioning problem, naturally overcoming limitations of previous methods. Our key insight is that policy preferences are inherent to the local scene structure and can be effectively learned from the policy rollouts. Technically, we propose a novel viewpoint augmentation strategy that enables the model to learn robust, viewpoint-invariant pose preferences with remarkable data efficiency. Extensive experiments demonstrate that N2M achieves state-of-the-art performance, outperforming both non-policy-aware baselines and recent policy-aware alternatives. Furthermore, we provide a comprehensive analysis highlighting N2M's broad applicability, generalization capabilities, and data efficiency. Project website: https://clvrai.github.io/N2M/
Sep 22, 2025

GeCCo -- a Generalist Contact-Conditioned Policy for Loco-Manipulation Skills on Legged Robots

Most modern approaches to quadruped locomotion focus on using Deep Reinforcement Learning (DRL) to learn policies from scratch, in an end-to-end manner. Such methods often fail to scale, as every new problem or application requires time-consuming and iterative reward definition and tuning. We present Generalist Contact-Conditioned Policy (GeCCo) --- a low-level policy trained with Deep Reinforcement Learning that is capable of tracking arbitrary contact points with a quadruped robot. We shift from task-specific end-to-end learning to a modular hierarchy in which a single planner-agnostic, contact-conditioned tracking policy serves as a robust interface between planning and control. By maintaining stable contact execution under dynamic uncertainty and planner mismatch, the policy enables high-level planners (e.g., handcrafted, learned, or optimization-based) to be composed and swapped without retraining. We demonstrate the scalability and robustness of our method by evaluating on a wide range of locomotion and manipulation tasks in a common framework and under a single generalist policy. These include a variety of gaits, traversing complex terrains (e.g., stairs and slopes) as well as previously unseen stepping-stones and narrow beams, and interacting with objects (e.g., pressing a button, pushing a barrel). Our framework acquires new behaviors more efficiently, simply by combining a task-specific high-level contact planner and the pre-trained generalist policy. Project website: https://vassil-atn.github.io/gecco.github.io
Jun 3, 2025

Learned Controllers for Agile Quadrotors in Pursuit-Evasion Games

We study one-versus-one (1v1) quadrotor pursuit-evasion, where a pursuer and an evader are trained with reinforcement learning (RL). Direct adversarial RL tends to be unstable because opponent policies change during training, causing non-stationarity, forgetting, and strategy cycling. We propose Asynchronous Multi-Stage Population-Based training, inspired by Policy-Space Response Oracles (PSRO). Proximal Policy Optimization (PPO) trains responses against previously learned opponents held fixed during each stage. The uniform variant, AMSPB-U, samples opponents equally, while AMSPB-P combines hard prioritized fictitious self-play (PFSP) with uniform exploration to emphasize currently difficult opponents. In cross-evaluations against learned opponents, both variants improve pursuit-evasion balance over latest-opponent training. AMSPB-P scores highest while retaining competence against earlier strategies. Across varied starting positions and after larger-arena retraining, both population variants retain higher average success across the two roles than latest-opponent training. Hardware experiments with two 10 cm, approximately 40 g Crazyflie brushless quadrotors demonstrate zero-shot sim-to-real transfer against baseline controllers and learned adversaries across 42 flights. Recorded flights include captures of evaders reaching robust peak speeds of 3.31 m/s and accelerations of 17.95 m/s^2, with pursuer flight speeds up to 4.87 m/s.
May 8, 2025

CubeDAgger: Interactive Imitation Learning for Dynamic Systems with Efficient yet Low-risk Interaction

Interactive imitation learning makes an agent's control policy robust by stepwise supervisions from an expert. The recent algorithms mostly employ expert-agent switching systems to reduce the expert's burden by limitedly selecting the supervision timing. However, this approach is useful only for static tasks; in dynamic tasks, timing discrepancies cause abrupt changes in actions, losing the robot's dynamic stability. This paper therefore proposes a novel method, named CubeDAgger, which improves robustness with less dynamic stability violations even for dynamic tasks. The proposed method is designed on a baseline, EnsembleDAgger, with three improvements. The first adds a regularization to explicitly activate the threshold for deciding the supervision timing. The second transforms the expert-agent switching system to an optimal consensus system of multiple action candidates. Third, autoregressive colored noise is injected to the agent's actions for time-consistent exploration. These improvements are verified by simulations, showing that the trained policies are sufficiently robust while maintaining dynamic stability during interaction. Finally, real-robot scooping experiments with a human expert demonstrate that the proposed method can learn robust policies from scratch based on just 30 minutes of interaction. https://youtu.be/kBl3SCTnVEM
Oct 4, 2024

Synergistic Action and Style Priors for Learning Legged Locomotion

Deep Reinforcement Learning (DRL) enables robots to learn complex behaviors through interaction with the environment. However, due to the unrestricted nature of the learning algorithms, the resulting solutions are often brittle and appear unnatural. This is especially true for learning direct joint-level torque control, as inductive biases are difficult to integrate into the learning process. We propose an inductive bias for learning locomotion that is especially useful for torque control: latent actions learned from a small dataset of expert demonstrations. This prior allows the policy to directly leverage knowledge contained in the expert's actions and facilitates more efficient exploration. We observe that the agent is not restricted to the reward levels of the demonstration, and performance in transfer tasks is improved significantly. Latent action priors combined with style rewards for imitation lead to a closer replication of the expert's behavior. Videos are available at https://sites.google.com/view/latent-action-priors.