Robot Policy Generalization

Ask about this topic

Overview

Robot policy generalization asks whether a controller can act reliably when objects, scenes, instructions, camera views, robot bodies, or dynamics differ from training. Approaches include collecting diverse demonstrations and using simulation randomization, structured object- or geometry-centered representations, modular skills, and vision-language-action or world-model policies. Researchers also use reinforcement-learning fine-tuning, test-time adaptation, and cross-embodiment action representations to help policies recover from unfamiliar conditions. A central challenge is that strong performance on familiar tasks or isolated shifts does not guarantee compositional generalization, so benchmarks increasingly test multiple interacting changes and real-world transfer.

Latest papers

CardsList

179 papers20 papers in the last four weeks, up 150% on the four weeks before. 0.1% of all new papers.

  1. Probabilistic Energy Modeling Unifies Versatile Swarm Control

    Oct 22, 2026Xiang Zhou, Xiangyu Zhu, Xintong Wang +5Swarm RoboticsRobotic Control

    School of Aeronautics and Astronautics, Sun Yat-sen University, Shenzhen 518107, China.

  2. Self-Distilling Future Video Representations for World Action Models

    Oct 21, 2026Huiwon Jang, Suhyeok Jang, Hyeonmo Kang +3World Action ModelsRobot Learning from Video

    KAIST · RLWRLD

  3. Robot Generalization Beyond Volume: The Diversity Path via Zero-Shot Capabilities

    Oct 21, 2026Rafael Felix, Flavia YanaseRobot Policy GeneralizationRobot Learning

    runibiLABS

  4. FCTS: Failure-Guided Curriculum Tree Search Over Generated Terrain for Legged Parkour

    Oct 15, 2026Narayanan Palghat Parameswaran, Dong-Ki Kim, Jay Patrikar +4Legged RoboticsCurriculum Learning

    Carnegie Mellon University · FieldAI

  5. CoDA: Co-Evolution of Data Engines and Action Policies

    Oct 15, 2026Tianjiao Yu, Zhilin Ou, Yifan Shen +5Robot Policy LearningSynthetic Data Generation for Robotics

    University of Illinois Urbana-Champaign · The Chinese University of Hong Kong, Shenzhen · Amazon

  6. What Happens to the Goal? Distinct Failures of Policy Alignment in Goal Misgeneralization

    Oct 14, 2026Julia Barth, Armin Sommer, Kunvar Thaman +1AI AlignmentGeneralization in RL

    Pantheon Industries · ETH Zurich

  7. PolyMorph: Learning Locomotion Policy for Cross-Embodiment Adaptation

    Oct 14, 2026Hyunsik Oh, Seunghun Jeon, Donghoon Youm +5Robot Policy LearningCross-Embodiment Robot Learning

  8. Imagining Goals with Geometric Horizon Models for Policy Generalization

    Oct 13, 2026Daniel Lawson, Dhruv Sreenivas, Adriana Hugessen +2Robot Policy GeneralizationGeneralization in RL

    Mila · Université de Montréal · Google DeepMind

  9. Value-Preserving Action Quantization

    Oct 12, 2026Max Muchen Sun, Jueun Kwon, Benjamin Riviere +1Data-Efficient Robot LearningRobot Imitation Learning

    Department of Mechanical Engineering, Northwestern University, Evanston, IL 60208, USA · Department of Mechanical and Aerospace Engineering and the Department of Computer Science, New York University, New York City, NY 10012, USA

  10. Higher-Order Morphology Priors for Quadruped Reinforcement Learning Under Actuator Degradation

    Oct 7, 2026Derek You, Zafir Shamsi, Keqin Wang +1Higher-Order GNNsRL for Legged Locomotion

    Edison Academy Magnet School. · South Brunswick High School. Work done during the Princeton Laboratory Learning Program. · Princeton University.

  11. Many Ways to Succeed: Diversity-Driven RL Fine-Tuning for VLA Generalization

    Oct 7, 2026Haoru Li, Jinmei Liu, Zhiyong Wang +5Robot Policy GeneralizationRL Fine-Tuning

    Nanjing University · Harbin Institute of Technology (Shenzhen) · Australian National University +1

  12. Arm-wise Compositional Generalization in Dual-Arm Vision-Language-Action Models

    Oct 5, 2026Zaibin Zhang, Binghao Ran, Yuhan Wu +10Bimanual Robotic ManipulationVision-Language-Action Models

    Dalian University of Technology · Shanghai Jiao Tong University · The Chinese University of Hong Kong, Shenzhen +1

  13. RoboIRS: Inference-Time Internal Representation Steering for Generalist Robot Policies

    Oct 3, 2026Jiuzhou Lei, Chang Liu, Dayou Li +5Robot Policy GeneralizationTest-Time Adaptation of VLA Models

    J. Mike Walker ’66 Department of Mechanical Engineering, Texas A&M University, College Station, TX 77843, USA · Edwardson School of Industrial Engineering, Purdue University, West Lafayette, IN, USA · Zachry Department of Civil and Environmental Engineering, Texas A&M University, College Station, TX 77843, USA +1

  14. Ego4WAM: What Matters When Scaling Egocentric Human Data for Robot Learning?

    Sep 30, 2026Zhihao Sun, Liu Liu, Xinjiang Wang +6Data-Efficient Robot LearningRobot Imitation Learning

    Institute of Trustworthy Embodied AI, Fudan University · Horizon Robotics · Huazhong University of Science & Technology +1

  15. Scale and Selection: What Makes Automatic Harness Evolution Work for Visual-Interface Robot Agents

    Sep 30, 2026Zhijie Wei, Ferris Tan, Jinghui Wang +1Agent Harness OptimizationRobot Policy Generalization

    Novaxbot · QuantGroup

  16. Memorize, Adapt, Ignore: Diagnosing Robot Learning Mechanisms under Training Data Variation

    Sep 29, 2026Ke Zhang, Danica J. Sutherland, Chao LiuDomain RandomizationRobot Policy Adaptation

    PRIME Robotics Lab, Department of Mechanical Engineering, The University of British Columbia · Department of Computer Science, University of British Columbia · Alberta Machine Intelligence Institute

  17. Skill-Space Shooting for Autonomous Robot Policy Improvement

    Sep 29, 2026Zihang Rui, Renhao Wang, Haoxu Huang +1Robot Policy LearningRobot Policy Adaptation

    Tsinghua University · UC Berkeley · Shanghai Qi Zhi Institute

  18. ComManip: Overfitting Manipulation Policies to Comfortable Regions

    Sep 29, 2026Yidan Lai, Xinyi Chen, Shuquan Man +1Visuomotor Policy LearningRobotic Manipulation

    South China University of Technology, Guangzhou, China · Nanyang Technological University, Singapore

  19. SkillWeaver: Agentic Exploration over Neural Interaction Skills for Scalable Robot Data Generation

    Sep 28, 2026He Zhu, Lusen Zhao, Kwan Man Cheng +2Robot Skill LearningRobotics Simulation

    Carnegie Mellon University · University of Illinois Urbana-Champaign

  20. Agent Priors-guided Policy Learning

    Sep 28, 2026Puming Jiang, Tianrun Hu, Haozhe Du +4Robot Skill LearningRobot Imitation Learning

    National University of Singapore

  21. Recursive Harness Distillation across Agents for Robot Manipulation

    Sep 27, 2026Seungyeon Kim, Junhoo Lee, Minkyu Kim +2Robotic ManipulationRobot Policy Generalization

    Seoul National University · Korea Advanced Institute of Science and Technology

  22. RACaP: Agentic Reasoning, Acting, and Coding as Policies for Evolvable Robot Learning

    Sep 24, 2026Zexi Li, Yehang Zhang, Haojian Huang +10Robot Policy LearningRobot Policy Generalization

    The Chinese University of Hong Kong · Knowin AI · The Hong Kong University of Science and Technology (Guangzhou)

  23. Latent Policy Steering: An Efficient and Flexible Framework for Cross-Embodiment Transfer

    Sep 18, 2026Yiqi Wang, Mrinal Verghese, Jeff SchneiderCross-Embodiment TransferVisuomotor Policy Learning

    Robotics Institute, School of Computer Science, Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, United States

  24. ReShoot: Generative Visual Domain Randomization of Recorded Robot Demonstrations for Visuomotor Policy Learning

    Sep 17, 2026Chiyoung Kim, Min Sung Choi, Jinho Ju +5Domain RandomizationVisuomotor Policy Learning

    Chung-Ang University, Seoul, Republic of Korea

  25. RecMorph: Topology-Guided Spatial Recurrence for Generalized Morphology Control

    Sep 16, 2026Quanrui Rao, Yong Liu, Xueming Xiao +4Recurrent Neural NetworksCross-Embodiment Robot Learning

    Jilin University, China · State Key Laboratory of Special Vehicle Design and Manufacturing Integration Technology, China · Changchun University of Science and Technology, China

  26. XPACE: Joint World and Action Modeling from Heterogeneous Experience

    Sep 15, 2026Jiacheng Wei, Jerry Bai, Xiaoyu Yue +13Cross-Embodiment Robot LearningSynthetic Data Generation for Robotics

    World Model Team, XPENG Robotics

  27. MemCorr-DP: Counterfactual Correspondence Conditioning for a Diffusion Policy Guided by a Reference

    Sep 6, 2026Tan Su, Haoxiang Yang, Ruxin Wang +1Goal-Conditioned Robotic ManipulationDiffusion Policy

    Southern University of Science and Technology · Sun Yat-sen University · Knowin

  28. MINERVA: How Small Can a Manipulation Policy Be and Still Solve LIBERO?

    Sep 3, 2026Kohei Sendai, Tatsuya Matsushima, Yusuke IwasawaRobot Skill LearningVisuomotor Policy Learning

    Matsuo-Iwasawa Lab, Graduate School of Engineering, The University of Tokyo, Japan

  29. Advantage-Driven Explicit Memory for Social Navigation

    Aug 26, 2026Yeonsoo Park, Mattia Racca, Guillaume Bono +4Memory-Augmented AgentsRobot Policy Generalization

    Interdisciplinary Program in Artificial Intelligence, Seoul National University, Korea · Naver Labs Europe, France

  30. CARO: Contact-Agnostic Residual Observation for Zero-Shot Robust Quadruped Locomotion

    Aug 25, 2026Zihan Yang, Shixuan Han, Kexin Guo +1Robot Policy AdaptationQuadruped Locomotion

    School of Aeronautic Science and Engineering, Beihang University, Beijing 100035, China · School of Automation Science and Electrical Engineering, Beihang University, Beijing 100035, China