Robot Imitation Learning

Ask about this topic

Overview

Robot imitation learning studies how robots can acquire manipulation, navigation, locomotion, and whole-body skills from demonstrations rather than hand-coded rules or task rewards. Common approaches include behavior cloning with transformers or diffusion policies, interactive methods such as DAgger, inverse reinforcement learning, and hierarchical skill learning; demonstrations may come from teleoperation, human video, simulation, or robot-free interfaces. Research also uses visual, tactile, force, and proprioceptive feedback, with motion retargeting and data augmentation helping transfer skills across robots and settings. A central challenge is making policies reliable beyond their demonstrations: distribution shift, imperfect data, compounding errors, and sim-to-real gaps remain, alongside the need for efficient data collection and safe recovery.

Latest papers

CardsList

703 papers116 papers in the last four weeks, down 19% on the four weeks before. 0.8% of all new papers.

  1. Pixel-UMI: Learning Environment-Aware Whole-Body Manipulation from Sensorized Human Demonstrations

    Nov 2, 2026Jason Jingzhou Liu, Tony Tao, Deepak Pathak +1Whole-Body Robotic ManipulationRobot Imitation Learning

    Carnegie Mellon University

  2. When Robots Outweigh Objects: How Inertia Mismatch Shapes Robot Policy Learning

    Nov 2, 2026Younghyo Park, Antonia Bronars, Pulkit AgrawalRobotic ManipulationRobotic RL

    MIT

  3. KlaskTron-IL: A Contact-Rich Adversarial Imitation Learning Benchmark with a Validated Sim-to-Real Bridge

    Nov 2, 2026Nicklas Sohm, Aswin Ramachandran, Raffaello D'AndreaRobot Imitation LearningImitation Learning

    ETH Zürich, IDSC

  4. Beyond Policy Patches: Distilling RL Specialists into Vision-Language-Action Policies

    Nov 2, 2026Zhennan Jiang, Tingying Xie, Shilong Ji +11Robotic ManipulationKnowledge Distillation

    University of Chinese Academy of Sciences · Institute of Automation, Chinese Academy of Sciences · Zhongguancun Academy +3

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

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

    MARS Lab, Nanyang Technological University

  6. Evaluating Tactile Foundation Models for End-to-End Imitation Learning in Contact-Rich Manipulation

    Oct 31, 2026Masaki Murooka, Ryoichi Nakajo, Tomohiro Motoda +4Robot Imitation LearningContact-Rich Robotic Manipulation

    Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology (AIST), 2-3-26 Aomi, Koto-ku, Tokyo 135-0064, Japan. · CNRS-AIST JRL (Joint Robotics Laboratory), IRL, 1-1-1 Umezono, Tsukuba, Ibaraki 305-8560, Japan.

  7. Learning from an Imitable Teacher: Competition Solution for the MetaFine Challenge

    Oct 31, 2026Yanze Zhang, Hao Liu, Haochang Hao +3Robotic ManipulationLearning from Demonstration

  8. Faster Imitation by Re-timing Demonstrations Within the Controller Limit

    Oct 31, 2026Zongtan Li, Tianming Liu, Ye ZhaoRobot Imitation LearningImitation Learning

    University of Georgia, Athens, GA, USA · Georgia Institute of Technology, Atlanta, GA, USA

  9. Does Validation Loss Predict Real-Robot Success? Evidence from Four Imitation-Learning Policies on a Low-Cost Arm

    Oct 30, 2026Simon CowlingRobotic Policy EvaluationRobot Imitation Learning

    fysical.ai, Denmark

  10. FOCUS: First-Order Control Using Optimal Transport Supervision for Imitation from Observations

    Oct 30, 2026João A. Cândido Ramos, Lionel Blondé, Hugues Vinzant +2Imitation LearningRobot Imitation Learning

    University of Geneva, Switzerland (UNIGE) · University of Applied Sciences and Arts Western Switzerland (HES-SO)

  11. Contact Imitation Interface: Transferring Dexterous Skills by Showing How Contact Unfolds

    Oct 29, 2026Zhixuan Xu, Yichen Li, Bingchen Wu +5Robotic ManipulationRobot Imitation Learning

    National University of Singapore · RoboScience · South China University of Technology

  12. 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

    Analog Devices, Inc., EdgeAI Robotics, Limerick, Ireland

  13. Improving Fine-Grained Manipulation through Demonstration Expansion and Execution Design

    Oct 29, 2026Jingxu Gu, Dongze LianRobotic ManipulationVLA Model Adaptation

    Nanjing University

  14. Smooth Action Chunking Via Movement-Primitive Representations for Imitation Learning

    Oct 29, 2026Shota Nomura, Takayuki Osa, Yasuhiro Kato +3Robot Imitation LearningAction Chunking

    The University of Tokyo, Tokyo, Japan. · RIKEN Center for Advanced Intelligence Project, Tokyo, Japan.

  15. ScheduleGen: Demonstration Generation via Skill Scheduling for Multi-Arm Imitation Learning

    Oct 29, 2026Neel Jawale, Stephan Pleines, Soha Pouya +3Robot Demonstration GenerationRobot Imitation Learning

    NVIDIA · The University of Texas at Austin

  16. UMI-Live for In-The-Wild Bimanual Robotics Data Collection

    Oct 29, 2026Govind Velamoor, Adrian Lin, Sam Jung +3Robotic Data CollectionRobot Manipulation Datasets

    Yale University · Carnegie Mellon University · AfterQuery +2

  17. SimRetract: Zero-Shot Sim-to-Real Robotic Assistance for Retractor Take-Over in Open Surgery

    Oct 28, 2026Xucheng Wang, Zhizhou Yang, Sung Eun Kim +7Surgical RoboticsSim-to-Real Transfer

    Department of Biomedical Informatics, Harvard Medical School · Department of Surgery, Massachusetts General Hospital · Weill Cornell Medical College +1

  18. CuraEval: Evaluating Demonstration Curation on Mixed-Skill Robot Data

    Oct 28, 2026Jiuyi Xu, Meida Chen, Yang Ye +1Robot Imitation LearningLearning from Suboptimal Demonstrations

    Colorado School of Mines · University of Southern California – Institute for Creative Technologies · Northeastern University

  19. Embodied at Sea: Imitation Learning for Multi-Task Underwater Manipulation

    Oct 28, 2026Greta Perez-Haiek, Luca Macesanu, Kevin Angers +3Multi-Task Robotic ManipulationUnderwater Robotics

    New York University · University of Malta

  20. When, Where, and What to Correct: Human-Guided Adaptive Residual Correction for Robot Policies

    Oct 27, 2026Anukriti Singh, Maxime Caniot, Pratap Tokekar +1Robot Policy AdaptationResidual Policy Learning

    University of Maryland, College Park College Park, MD · Work done during internship at Enchanted Tools. · Enchanted Tools Paris, France

  21. From 12 to 200 Demonstrations: How ACT, Diffusion Policy, SmolVLA and π0.5π_{0.5} Scale on a Low-Cost Arm

    Oct 27, 2026Simon CowlingImitation LearningRobot Imitation Learning

    fysical.ai, Denmark

  22. RoboSTD: Zero-Shot Single-to-Dual Transfer via Sagittal Mirroring for Bimanual Learning

    Oct 27, 2026Hongyu Wu, Chong Liu, Shaoxuan Xie +4Bimanual Robotic ManipulationRobot Imitation Learning

    Beijing Academy of Artificial Intelligence · Beijing University of Posts and Telecommunications

  23. HIDRA: Hierarchical Dual-Routing Attention for Replay-Free Lifelong Imitation Learning

    Oct 26, 2026Fanqi Yu, Matteo Tiezzi, Cigdem Beyan +2Hierarchical AttentionRobot Imitation Learning

    AI for Good (AIGO) Research Unit, Istituto Italiano di Tecnologia, Genoa, Italy · DITEN, University of Genoa, Genoa, Italy · Pattern Analysis and Computer Vision (PAVIS), Istituto Italiano di Tecnologia, Genoa, Italy +1

  24. ElevateHead: Decide Once, Then Commit: When the Action Head Matters for Multimodal Imitation

    Oct 25, 2026Tsung-Lung YangRobot Policy LearningImitation Learning

    National University

  25. Learning Dexterous Manipulation: Hands, Simulators, Training, and Evaluation

    Oct 24, 2026Luai AbuelsamenRobotic ManipulationRL for Robotics

    Independent Researcher

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

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

    University of Cambridge, Cambridge, United Kingdom

  27. DexPort: A Hand-Held Skill Interface for Dexterous Hand Data Collection

    Oct 23, 2026Amber Xie, Jiawei Fu, Xiaofeng Guo +3Robotic Data CollectionRobotic Manipulation

    Amazon FAR (Frontier AI & Robotics) · Stanford University · UC San Diego

  28. Conditional Neural Processes for Self-Supervised Goal Discovery in Action Imitation

    Oct 23, 2026Marco Gabriele Fedozzi, Yukie Nagai, Francesco Rea +1Action Representation LearningRobot Imitation Learning

    DIBRIS Department, University of Genoa · CONTACT Unit, Italian Institute of Technology · International Research Center for Neurointelligence, The University of Tokyo

  29. Retiming Robot Demonstrations with a Learned Speed Prior

    Oct 23, 2026Seungyong Moon, Deokjae Lee, Hansang Lee +7Robot Policy LearningLearning from Demonstration

    Seoul National University

  30. From Tabletop to Walking Bot: Deploying a VLA Model on a Legged Manipulator Robot

    Oct 23, 2026Giovanni Minelli, Antonio Langella, Giovanni B. Dessy +4Loco-ManipulationVLA Model Adaptation

    Dynamic Legged Systems Lab, Istituto Italiano di Tecnologia (IIT)