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

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

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

    Feb 27, 2026Fan Yang, Peiguang Jing, Kaihua Qu +2B-Spline Trajectory RepresentationRobot Policy Learning

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

    Feb 27, 2026Yanda Yang, Zion Lee, Sambeeta DasRobot Policy LearningRobotics Simulation

  3. Embedding Morphology into Transformers for Cross-Robot Policy Learning

    Feb 26, 2026Kei Suzuki, Jing Liu, Ye Wang +4Robot Policy LearningCross-Embodiment Robot Learning

  4. Demystifying Action Space Design for Robotic Manipulation Policies

    Feb 26, 2026Yuchun Feng, Jinliang Zheng, Zhihao Wang +5Robot Policy LearningRobotic Manipulation

  5. Universal Pose Pretraining for Generalizable Vision-Language-Action Policies

    Feb 23, 2026Haitao Lin, Hanyang Yu, Jingshun Huang +5Robot Policy LearningVision-Language-Action Models

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

    Feb 21, 2026Hoseong Jung, Sungil Son, Daesol Cho +3Robot Policy LearningLatent Action Learning

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

    Feb 10, 2026Xuhui Kang, Tongxuan Tian, Sung-Wook Lee +3Robot Policy LearningRobotic Grasping

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

    Feb 8, 2026Hongzhi Zang, Shu'ang Yu, Hao Lin +14Robot Policy LearningReinforcement Learning

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

    Jan 28, 2026Guowei Zou, Haitao Wang, Hejun Wu +3Robotic ControlReal-Time Robot Control

  10. Rapidly Learning Soft Robot Control via Implicit Time-Stepping

    Nov 10, 2025Andrew Choi, Dezhong Tong, Xiaonan HuangRobot Policy LearningRobotics Simulation

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

    Sep 23, 2025Kaixin Chai, Hyunjun Lee, Joseph J. LimRobot Policy LearningMobile Manipulation

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

    Sep 22, 2025Vassil Atanassov, Wanming Yu, Siddhant Gangapurwala +2Robotic ControlLegged Robotics

  13. Learned Controllers for Agile Quadrotors in Pursuit-Evasion Games

    Jun 3, 2025Alejandro Sanchez Roncero, Yixi Cai, Olov Andersson +1Robot Policy LearningAdversarial MARL

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

    May 8, 2025Taisuke KobayashiSafe Imitation LearningImitation Learning

  15. Synergistic Action and Style Priors for Learning Legged Locomotion

    Oct 4, 2024Oliver Hausdörfer, Alexander von Rohr, Éric Lefort +1RL for Legged LocomotionRobot Policy Learning