Visuomotor Policy Learning

Overview

Visuomotor policies map what a robot sees to actions, helping it manipulate objects, navigate, and interact when the scene or task changes. Common approaches learn from demonstrations through action-chunking transformers, diffusion or flow-matching policies, and vision-language-action models; reinforcement learning and policy distillation are also used. Researchers improve these policies with geometric and object-centered visual features, memory, contact sensing, and predictions of how actions will change the scene, evaluating them on benchmarks such as LIBERO and RoboTwin as well as physical robots. A central tension is achieving reliable generalization and safe, precise control in real settings while keeping data needs, model size, and inference latency low.

Latest papers

CardsList

309 papers24 papers in the last four weeks, down 62% on the four weeks before. 0.2% of all new papers.

  1. PhysVAM: Physics-oriented Future Value Action Model for Dynamic Object Manipulation

    Nov 19, 2026Yuxiang Yang, Jingbo Zhang, Jiaru Zhong +7Visuomotor Policy Learning

  2. Hindsight Self-Distillation: Teaching Robots to Act from the Present

    Nov 19, 2026Haisen He, Yechi Liu, Tianle Shi +7Visuomotor Policy LearningRobot Imitation Learning

  3. RefreshGrad: An Online Adaptive Data-sampling Method for Diffusion-based Visuomotor Learning

    Nov 19, 2026Dijia Zhan, Jinyi Li, Xuemiao Xu +4Visuomotor Policy LearningImitation Learning

  4. Body Schema Policy: Body as the Vision-Action Interface for Efficient Robot Loco-Manipulation

    Nov 17, 2026Lechen Zhang, Chenyuan Chen, Muxin Zhou +2Robot LearningRobotic Loco-Manipulation

  5. ACiT: Proprioceptive-Prior Action Chunking with Inverted Transformers

    Nov 16, 2026Haixiang Wu, Zhihao Guan, Yang YangRobot Policy LearningVisuomotor Policy Learning

  6. AsymEEF: Bimanual Manipulation with Asymmetric End Effectors

    Nov 16, 2026Xiaokang Sun, Ningyue Wang, Kunqi Xu +4Bimanual Robotic ManipulationCross-Embodiment Robot Learning

  7. Kimodo-Policy: Learning Kinematic Action Models for Humanoid Loco-Manipulation

    Nov 8, 2026Yunheng Wang, Jiaxi Zhang, Wei Lu +12Humanoid Loco-ManipulationWhole-Body Humanoid Control

  8. DexForesight: Grounding Dexterous Policies with Implicit Spatial Foresight

    Nov 8, 2026Zhongxi Chen, Yi Yang, Xinyi Chen +6Robotic ManipulationVisuomotor Policy Learning

  9. SUGARv2: Learning Diverse Visual Humanoid Loco-Manipulation Skills from Synthesized Interaction References

    Nov 6, 2026Tianshu Wu, Tianxiang Gui, Yue Chen +7Robotic Loco-ManipulationVisuomotor Policy Learning

  10. Latent RL Priors for Data-Efficient Dexterous Manipulation

    Nov 5, 2026Yixiao Wang, Peiyi Chen, Mustafa Mukadam +3Robotic ManipulationData-Efficient Robot Learning

  11. Aligning Policy Encoders with a Shape Teacher

    Nov 5, 2026Madelon Bernardy, Mohammad Mahdi Derakhshani, David M Knigge +2Visuomotor Policy LearningRobotic Manipulation

  12. All-For-One: Distilling Visual Foundation Models to a Fast, Memory-Efficient Visuomotor Policy

    Nov 3, 2026Byungkun Lee, Minho Park, Hojoon Lee +6Visuomotor Policy LearningRobot Learning

  13. GoalDex: Learning Image-Goal-Conditioned Policies for Dexterous In-Hand Manipulation

    Nov 1, 2026Arjun Bhardwaj, Mayank Mittal, Maximum Wilder-Smith +2Dexterous ManipulationGoal-Conditioned Robotic Manipulation

  14. ODE Policy: Robot Learning via Action Dynamics, Not Actions

    Nov 1, 2026Jindou Jia, Jingliang Li, Kuangji Zuo +9Robot Policy LearningRobotic RL

  15. Language-Conditioned Behavioral Cloning for Autonomous Endoscope Guidance

    Oct 30, 2026Ariel Rodriguez, Lorenzo Mazza, Ortrun Hellig +3Robotic EndoscopySurgical Robotics

  16. Direct Action-Manifold Modeling for Efficient and Robust Bimanual Manipulation

    Oct 30, 2026Hongren Wang, Mingyu You, Zihan Li +3Bimanual Robotic ManipulationVisuomotor Policy Learning

  17. RTPolicy: Real-Time (32.9 Hz) Multi-View Visuomotor Policy for Robotic Manipulation on Edge Devices

    Oct 30, 2026Xianbao Hou, Zehao Ni, Yonghao He +5Visuomotor Policy LearningRobotic Manipulation

  18. From Teleoperation to Long-Horizon Dexterity: Evaluating Visuomotor Skills and Offline Proxies for Dexterous Manipulation

    Oct 29, 2026Ammar N. Abbas, Aayush Jain, Prashanth Viswanath +3Visuomotor Policy LearningRobotic Manipulation

  19. Learning Visuomotor Quadrotor Flight Through Dynamic Narrow Gaps via Differentiable Simulation

    Oct 27, 2026Riccardo Bianco, Yunfan Ren, Jiaxu Xing +1Quadrotor ControlVisuomotor Policy Learning

  20. PS-DLO: Property- and Spatially Aware Deformable Linear Object Manipulation Policy

    Oct 25, 2026Mengdi Li, Boxian Yao, Xiyu Zhu +6Deformable Object ManipulationVisuomotor Policy Learning

  21. TAD: Distilling Vision-Language-Action Policies from Teacher Trajectories Alone

    Oct 24, 2026Yun Zhu, Da WangVisuomotor Policy LearningKnowledge Distillation

  22. Tiny Recursive Policy: Recursive Latent Refinement for Visuomotor Control

    Oct 23, 2026Hakan Aktas, Cengiz OztireliRobot Policy LearningVisuomotor Policy Learning

  23. What Novice Operators See Changes What the Policy Learns: A User Study of Keypoint Hand Visual Representation for Teleoperated Demonstration

    Oct 20, 2026Amane Yamaguchi, Shohei Kamiguchi, Masashi Hamaya +3Robot Imitation LearningLearning from Demonstration