Robot Policy Adaptation

Ask about this topic

Overview

Robot policy adaptation studies how a trained controller can adjust when tasks, surroundings, sensors, or robot dynamics differ from training. Common approaches range from fine-tuning with demonstrations or online reinforcement learning to lightweight residual modules, latent or noise-space steering, and world-model-guided correction of a frozen policy. Work spans manipulation, locomotion, and navigation, with evaluation in simulation and on real robots using benchmarks such as LIBERO and RoboTwin. A central challenge is improving performance with little feedback while preserving skills, safety, and reliable behavior under distribution shifts.

Latest papers

CardsList

175 papers57 papers in the last four weeks, up 148% on the four weeks before. 0.3% of all new papers.

  1. Interpreting Context-Aware Human Preferences for Multi-Objective Robot Navigation

    Mar 18, 2026Tharun Sethuraman, Subham Agrawal, Nils Dengler +3Robot NavigationRobot Policy Adaptation

    Hochschule Bonn-Rhein-Sieg, Germany · University of Bonn, Germany · Lamarr Institute for Machine Learning and Artificial Intelligence, Germany

  2. WINFlowNets: Warm-up Integrated Networks Training of Generative Flow Networks for Robotics and Machine Fault Adaptation

    Mar 18, 2026Zahin Sufiyan, Shadan Golestan, Yoshihiro Mitsuka +2Generative Flow NetworksRL for Robotics

    University of Alberta · Alberta Machine Intelligence Institute (Amii) · Mitsubishi Electric Corporation

  3. Conservative Offline Robot Policy Learning via Posterior-Transition Reweighting

    Mar 17, 2026Wanpeng Zhang, Hao Luo, Sipeng Zheng +6Instance ReweightingRobot Policy Adaptation

    Peking University · BeingBeyond · Tsinghua University

  4. Encoding Predictability and Legibility for Style-Conditioned Diffusion Policy

    Mar 17, 2026Adrien Jacquet Crétides, Mouad Abrini, Hamed Rahimi +1Human-Robot CollaborationDiffusion Policy

    Institut des Systèmes Intelligents et de Robotique (ISIR), CNRS UMR7222, Inserm ERL U1150, Sorbonne Université, Paris, France

  5. Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation

    Mar 16, 2026Jacob Levy, Tyler Westenbroek, Kevin Huang +6World Models for RoboticsRobot Policy Adaptation

    University of Texas at Austin · University of Washington · FieldAI

  6. You've Got a Golden Ticket: Improving Generative Robot Policies With A Single Noise Vector

    Mar 16, 2026Omkar Patil, Ondrej Biza, Thomas Weng +9Robot Policy AdaptationRobotic Manipulation

    Robotics and AI Institute (RAI) · Arizona State University (ASU) · Northeastern University

  7. Beyond Imitation: Reinforcement Learning Fine-Tuning for Adaptive Diffusion Navigation Policies

    Mar 13, 2026Junhe Sheng, Ruofei Bai, Kuan Xu +5Robot NavigationRobot Policy Adaptation

    Nanyang Technological University, Singapore. · A*STAR, Singapore. · National University of Singapore, Singapore.

  8. MAVEN: A Meta-Reinforcement Learning Framework for Varying-Dynamics Expertise in Agile Quadrotor Maneuvers

    Mar 11, 2026Jin Zhou, Dongcheng Cao, Xian Wang +1Robot Policy AdaptationQuadrotor Control

    Authors are with the College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China

  9. Few-Shot Adaptation to Non-Stationary Environments via Latent Trend Embedding for Robotics

    Mar 11, 2026Yasuyuki Fujii, Emika Kameda, Hiroki Fukada +3Robot Policy AdaptationFew-Shot Domain Adaptation

    College of Information Science and Engineering, Ritsumeikan University, Osaka, Japan · College of Information Science and Engineering, Ritsumeikan University, Osaka, Japan. · Production and Technology Department, NIPPN CORPORATION, Tokyo, Japan +5

  10. Update-Free On-Policy Steering via Verifiers

    Mar 10, 2026Maria Attarian, Ian Vyse, Jasper Gerigk +7Robot Policy AdaptationRobot Imitation Learning

    University of Toronto · Google DeepMind · University of Alberta +2

  11. Robotic Scene Cloning:Advancing Zero-Shot Robotic Scene Adaptation in Manipulation via Visual Prompt Editing

    Mar 10, 2026Binyuan Huang, Yuqing Wen, Yucheng Zhao +5Robot Policy AdaptationZero-Shot Robotic Manipulation

    Binyuan Huang and Zhenzhong Chen are with Wuhan University. · Yuqing Wen is with University of Science and Technology of China. · Yucheng Zhao, Tiancai Wang and Haoqiang Fan are with Dexmal. +1

  12. Stability-Aligned Residual Adaptation for Rapid Recovery from Dynamics Shifts

    Mar 8, 2026Nethmi Jayasinghe, Diana Gontero, Francesco Migliarba +4Robot Policy AdaptationResidual Policy Learning

    Department of Electrical and Computer Engineering, University of Illinois Chicago, Chicago, IL, USA. · Department of Neurobiology, Northwestern University, Evanston, IL, USA. · Department of Materials Science and Engineering, Northwestern University, Evanston, IL, USA. +2

  13. RoboPocket: Improve Robot Policies Instantly with Your Phone

    Mar 5, 2026Junjie Fang, Wendi Chen, Han Xue +7Data-Efficient Robot LearningRobot Learning

    Shanghai Jiao Tong University · Noematrix Ltd. · Shanghai Innovation Institute

  14. Online Self-Training for Co-Adaptation in Hierarchical Diffusion Policies

    Mar 5, 2026Clemence Grislain, Mathilde Kappel, Olivier Sigaud +1Robot Policy LearningRobot Policy Adaptation

    ISIR, Sorbonne Université, CNRS, Paris, France

  15. Adaptive Policy Switching of Two-Wheeled Differential Robots for Traversing over Diverse Terrains

    Mar 5, 2026Haruki Izawa, Takeshi Takai, Shingo Kitano +2Terrain-Aware Robot LocomotionRobot Policy Adaptation

    Graduate School of Information Science, University of Hyogo, Hyogo, Japan · Takenaka Research & Development Institute, Takenaka Corporation, Chiba, Japan

  16. Self-adapting Robotic Agents through Online Continual Reinforcement Learning with World Model Feedback

    Mar 4, 2026Fabian Domberg, Georg SchildbachRobot Policy AdaptationContinual Robot Learning

    Autonomous Systems Lab (ASL), Institute for Electrical Engineering in Medicine, University of Lübeck, 23562 Lübeck, Germany

  17. IROSA: Interactive Robot Skill Adaptation using Natural Language

    Mar 4, 2026Markus Knauer, Samuel Bustamante, Thomas Eiband +3Robot Policy AdaptationRobot Skill Learning

    All authors are with the German Aerospace Center (DLR), Institute of Robotics and Mechatronics (RMC), Münchener Str. 20, 82234 Weßling, Germany. · Markus Knauer, Alin Albu-Schäffer and Samuel Bustamante are also with the School of Computation, Information and Technology (CIT), Technical University of Munich (TUM), Arcisstr. 21, 80333 Munich, Germany.

  18. Closed-Loop Action Chunks with Dynamic Corrections for Training-Free Diffusion Policy

    Mar 2, 2026Pengyuan Wu, Pingrui Zhang, Zhigang Wang +3Diffusion PolicyRobot Policy Adaptation

    Zhejiang University. · Shanghai Artificial Intelligence Laboratory. · Fudan University. +2

  19. When to Act, Ask, or Learn: Uncertainty-Aware Policy Steering

    Feb 25, 2026Jessie Yuan, Yilin Wu, Andrea BajcsyRobot Policy AdaptationVLMs for Robotics

    Carnegie Mellon University

  20. FlowCorrect: Efficient Interactive Correction of Generative Flow Policies for Robotic Manipulation

    Feb 25, 2026Edgar Welte, Yitian Shi, Rosa Wolf +2Robot Policy AdaptationRobotic Manipulation

    Institute for Material Handling and Logistics (IFL), Karlsruhe Institute of Technology, 76131, Germany.

  21. GeCo-SRT: Geometry-aware Continual Adaptation for Robotic Cross-Task Sim-to-Real Transfer

    Feb 24, 2026Wenbo Yu, Wenke Xia, Weitao Zhang +1Sim-to-Real TransferRobot Policy Adaptation

    Beijing Forestry University, Beijing, China · Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China · Beijing Key Laboratory of Research on Large Models and Intelligent Governance +1

  22. AdaWorldPolicy: World-Model-Driven Diffusion Policy with Online Adaptive Learning for Robotic Manipulation

    Feb 23, 2026Ge Yuan, Qiyuan Qiao, Jing Zhang +1Robot Policy AdaptationRobotic Manipulation

    The University of Hong Kong · Beihang University

  23. TTT-Parkour: Rapid Test-Time Training for Perceptive Robot Parkour

    Feb 2, 2026Shaoting Zhu, Baijun Ye, Jiaxuan Wang +5Robot LocomotionHumanoid Robot Locomotion

    Tsinghua University · Shanghai Qi Zhi Institute · Princeton University

  24. ARMADA: Autonomous Online Failure Detection and Human Shared Control Empower Scalable Real-world Deployment and Adaptation

    Oct 2, 2025Wenye Yu, Jun Lv, Zixi Ying +3Robot Policy AdaptationRobot Imitation Learning

    Shanghai Jiao Tong University · Shanghai Innovation Institute · Noematrix Ltd.

  25. Prior Reinforce: Goal-Conditioned Dynamic Manipulation with Limited Trials

    May 28, 2025Yihang Hu, Pingyue Sheng, Yuyang Liu +2Robot Policy AdaptationRobot Skill Learning

    IIIS, Tsinghua University. · Shanghai Qi Zhi Institute. · Spirit AI.