mlsanityData to 7 Oct 2026

Residual Learning from Demonstration: Adapting DMPs for Contact-rich Manipulation

arXiv 2008.07682 ↗First posted 18 Aug 2020cs.RO cs.AIcited by 22

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

Abstract (arXiv)

Manipulation skills involving contact and friction are inherent to many robotics tasks. Using the class of motor primitives for peg-in-hole like insertions, we study how robots can learn such skills. Dynamic Movement Primitives (DMP) are a popular way of extracting such policies through behaviour cloning (BC) but can struggle in the context of insertion. Policy adaptation strategies such as residual learning can help improve the overall performance of policies in the context of contact-rich manipulation. However, it is not clear how to best do this with DMPs. As a result, we consider several possible ways for adapting a DMP formulation and propose ``residual Learning from Demonstration`` (rLfD), a framework that combines DMPs with Reinforcement Learning (RL) to learn a residual correction policy. Our evaluations suggest that applying residual learning directly in task space and operating on the full pose of the robot can significantly improve the overall performance of DMPs. We show that rLfD offers a gentle to the joints solution that improves the task success and generalisation of DMPs rband enables transfer to different geometries and frictions through few-shot task adaptation. The proposed framework is evaluated on a set of tasks. A simulated robot and a physical robot have to successfully insert pegs, gears and plugs into their respective sockets. Other material and videos accompanying this paper are provided at https://sites.google.com/view/rlfd/.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Placed in Robot learning from demonstration, one of 13 directions in Offline RL and imitation learning from data. Builds on 12 of its 39 references that are in the map. First posted on arXiv 18 Aug 2020.

Builds on

12 of 39 references.

Closest ancestors · 1

Same direction, newest first

  1. 2019Towards Orientation Learning and Adaptation in Cartesian Space9 Jul

Other references · 11

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2017Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewardscited by 302
  4. 2018Residual Reinforcement Learning for Robot Controlcited by 242
  5. 2019A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithmscited by 136
  6. 2019TossingBot: Learning to Throw Arbitrary Objects with Residual Physicscited by 131
  7. 2019Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewardscited by 58
  8. 2017Deep Reinforcement Learning for High Precision Assembly Taskscited by 37
  9. 2019Reinforcement Learning on Variable Impedance Controller for High-Precision Robotic Assemblycited by 33
  10. 2020Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learningcited by 22
  11. 2017Learning Sensor Feedback Models from Demonstrations via Phase-Modulated Neural Networkscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 1; 2023: 3; 2024: 6; 2025: 7; 2026: 4.

22 papers.

Sort:

By area:

  1. 2025ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skillscited by 104
  2. 2024From Imitation to Refinement -- Residual RL for Precise Assemblycited by 80
  3. 2025ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learningcited by 56
  4. 2022Factory: Fast Contact for Robotic Assemblycited by 49
  5. 2024JUICER: Data-Efficient Imitation Learning for Robotic Assemblycited by 36
  6. 2023DEFT: Dexterous Fine-Tuning for Real-World Hand Policiescited by 15
  7. 2021Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulationcited by 13
  8. 2025A Survey on Imitation Learning for Contact-Rich Tasks in Roboticscited by 12
  9. 2026RFS: Reinforcement Learning with Residual Flow Steering for Dexterous Manipulationcited by 10
  10. 2024GenCHiP: Generating Robot Policy Code for High-Precision and Contact-Rich Manipulation Taskscited by 9
  11. 2024Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous Graspingcited by 8
  12. 2023Few-Shot Learning of Force-Based Motions From Demonstration Through Pre-training of Haptic Representationcited by 5
10 more
  1. 2024Fast Ergodic Search with Kernel Functionscited by 5
  2. 2024Fusion Dynamical Systems with Machine Learning in Imitation Learning: A Comprehensive Overviewcited by 3
  3. 2023Efficient Skill Acquisition for Complex Manipulation Tasks in Obstructed Environmentscited by 2
  4. 2025CHEQ-ing the Box: Safe Variable Impedance Learning for Robotic Polishingcited by 1
  5. 2025Dynamic Action Interpolation: A Universal Approach for Accelerating Reinforcement Learning with Expert Guidancecited by 0
  6. 2025Knowledge capture, adaptation and composition (KCAC): A framework for cross-task curriculum learning in robotic manipulationcited by 0
  7. 2025MoRe-ERL: Learning Motion Residuals using Episodic Reinforcement Learningcited by 0
  8. 2026V2P-Manip: Learning Dexterous Manipulation from Monocular Human Videoscited by 0
  9. 2026Learning Residual Kinematic Corrections for Continuous Neural Decoding via Reinforcement Learningcited by 0
  10. 2026Potential-Field Action Representation for Reinforcement Learning in Contact-Rich Manipulationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026DynaForge: Planning-Guided Residual Learning for Dynamic Manipulation Demonstration Generation ↗
  2. 2026Learning Forward & Reverse Skills from a Single Unfinished Demonstration for Constrained Manipulation Tasks
  3. 2026One-Shot Learning from Demonstration of Contact-Rich Robotic Manipulation by Identifying Physical Interactions
  4. 2021Residual Reinforcement Learning from Demonstrations
  5. 2026Res-HIL: Human-Guided Residual Reinforcement Learning for Sample-Efficient Dexterous Manipulation
  6. 2026Learning Diffusion Policy from Primitive Skills for Robot Manipulation
  7. 2025FLEX: A Framework for Learning Robot-Agnostic Force-based Skills Involving Sustained Contact Object Manipulation
  8. 2026Decompose and Reorganize: Planning with Primitives and Visuomotor Policies Learned from Demonstrations ↗