mlsanityData to 7 Oct 2026

Grasping with Chopsticks: Combating Covariate Shift in Model-free Imitation Learning for Fine Manipulation

arXiv 2011.06719 ↗First posted 13 Nov 2020cs.RO cs.LGcited by 37

On the map: Offline RL and imitation learning from data → Robot manipulation imitation learning

Abstract (arXiv)

Billions of people use chopsticks, a simple yet versatile tool, for fine manipulation of everyday objects. The small, curved, and slippery tips of chopsticks pose a challenge for picking up small objects, making them a suitably complex test case. This paper leverages human demonstrations to develop an autonomous chopsticks-equipped robotic manipulator. Due to the lack of accurate models for fine manipulation, we explore model-free imitation learning, which traditionally suffers from the covariate shift phenomenon that causes poor generalization. We propose two approaches to reduce covariate shift, neither of which requires access to an interactive expert or a model, unlike previous approaches. First, we alleviate single-step prediction errors by applying an invariant operator to increase the data support at critical steps for grasping. Second, we generate synthetic corrective labels by adding bounded noise and combining parametric and non-parametric methods to prevent error accumulation. We demonstrate our methods on a real chopstick-equipped robot that we built, and observe the agent's success rate increase from 37.3% to 80%, which is comparable to the human expert performance of 82.6%.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 7 of its 37 references that are in the map. First posted on arXiv 13 Nov 2020.

Builds on

7 of 37 references.

References · 7

  1. 2018An Algorithmic Perspective on Imitation Learningcited by 455
  2. 2017Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperationcited by 286
  3. 2017DART: Noise Injection for Robust Imitation Learningcited by 187
  4. 2019Imitation Learning as f-Divergence Minimizationcited by 121
  5. 2016Model-Free Imitation Learning with Policy Optimizationcited by 52
  6. 2014Analyzing noise in autoencoders and deep networkscited by 25
  7. 2020Telemanipulation with Chopsticks: Analyzing Human Factors in User Demonstrationscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 4; 2023: 7; 2024: 12; 2025: 7; 2026: 6.

37 papers.

Sort:

By area:

  1. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  2. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 634
  3. 2023NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesiscited by 56
  4. 2022Motion Policy Networkscited by 53
  5. 2023Train Offline, Test Online: A Real Robot Learning Benchmarkcited by 47
  6. 2024Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Samplingcited by 46
  7. 2023Creative Robot Tool Use with Large Language Modelscited by 42
  8. 2024JUICER: Data-Efficient Imitation Learning for Robotic Assemblycited by 36
  9. 2024Diffusion Meets DAgger: Supercharging Eye-in-hand Imitation Learningcited by 34
  10. 2023Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behaviorcited by 33
  11. 2024Bi-ACT: Bilateral Control-Based Imitation Learning via Action Chunking with Transformercited by 27
  12. 2023CCIL: Continuity-based Data Augmentation for Corrective Imitation Learningcited by 26
25 more
  1. 2024Mitigating Covariate Shift in Imitation Learning for Autonomous Vehicles Using Latent Space Generative World Modelscited by 22
  2. 2022Learning Bimanual Scooping Policies for Food Acquisitioncited by 19
  3. 2025Dexterous Manipulation through Imitation Learning: A Surveycited by 18
  4. 2022Real World Offline Reinforcement Learning with Realistic Data Sourcecited by 16
  5. 2023Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregressioncited by 14
  6. 2024SAFE-GIL: SAFEty Guided Imitation Learning for Robotic Systemscited by 13
  7. 2022Distributionally Adaptive Meta Reinforcement Learningcited by 11
  8. 2024Learning from 10 Demos: Generalisable and Sample-Efficient Policy Learning with Oriented Affordance Framescited by 9
  9. 2024MILES: Making Imitation Learning Easy with Self-Supervisioncited by 9
  10. 2025SE(3)-Equivariant Diffusion Policy in Spherical Fourier Spacecited by 7
  11. 2024Multi-task real-robot data with gaze attention for dual-arm fine manipulationcited by 5
  12. 2025Elastic Motion Policy: An Adaptive Dynamical System for Robust and Efficient One-Shot Imitation Learningcited by 4
  13. 2025RobotSmith: Generative Robotic Tool Design for Acquisition of Complex Manipulation Skillscited by 4
  14. 2025Action Chunking with Transformers for Image-Based Spacecraft Guidance and Controlcited by 2
  15. 2021Imitation Learning via Simultaneous Optimization of Policies and Auxiliary Trajectoriescited by 1
  16. 2024Bridging the Resource Gap: Deploying Advanced Imitation Learning Models onto Affordable Embedded Platformscited by 1
  17. 2024Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloningcited by 1
  18. 2025Exploiting Policy Idling for Dexterous Manipulationcited by 1
  19. 2026See like a Robot: Robot-Centric Pointmaps for VLA Modelscited by 1
  20. 2025Denoising-based Contractive Imitation Learningcited by 0
  21. 2026Primary-Fine Decoupling for Action Generation in Robotic Imitationcited by 0
  22. 2026Imitation Learning from Human Motion Alone Does Not Guarantee Biomechanically Plausible Gait Kineticscited by 0
  23. 2026GROW2: Grounding Which and Where for Robot Tool Usecited by 0
  24. 2026Robustness of Robotic Manipulation: Foundations and Frontierscited by 0
  25. 2026Policy-Calibrated DAgger: Offline Calibrated Noise Injection for Imitation Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025RoboManipBaselines: A Unified Framework for Imitation Learning in Robotic Manipulation across Real and Simulation Environments
  2. 2025Robotic Manipulation via Imitation Learning: Taxonomy, Evolution, Benchmark, and Challenges
  3. 2021Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstration
  4. 2024Data Efficient Behavior Cloning for Fine Manipulation via Continuity-based Corrective Labels
  5. 2022Dexterous Imitation Made Easy: A Learning-Based Framework for Efficient Dexterous Manipulation
  6. 2025GrOMP: Grasped Object Manifold Projection for Multimodal Imitation Learning of Manipulation
  7. 2025Interactive Imitation Learning for Dexterous Robotic Manipulation: Challenges and Perspectives -- A Survey
  8. 2024A Comparison of Imitation Learning Algorithms for Bimanual Manipulation