mlsanityData to 7 Oct 2026

Decoupling Skill Learning from Robotic Control for Generalizable Object Manipulation

arXiv 2303.04016 ↗First posted 7 Mar 2023cs.RO cs.CV cs.LGcited by 2

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

Abstract (arXiv)

Recent works in robotic manipulation through reinforcement learning (RL) or imitation learning (IL) have shown potential for tackling a range of tasks e.g., opening a drawer or a cupboard. However, these techniques generalize poorly to unseen objects. We conjecture that this is due to the high-dimensional action space for joint control. In this paper, we take an alternative approach and separate the task of learning 'what to do' from 'how to do it' i.e., whole-body control. We pose the RL problem as one of determining the skill dynamics for a disembodied virtual manipulator interacting with articulated objects. The whole-body robotic kinematic control is optimized to execute the high-dimensional joint motion to reach the goals in the workspace. It does so by solving a quadratic programming (QP) model with robotic singularity and kinematic constraints. Our experiments on manipulating complex articulated objects show that the proposed approach is more generalizable to unseen objects with large intra-class variations, outperforming previous approaches. The evaluation results indicate that our approach generates more compliant robotic motion and outperforms the pure RL and IL baselines in task success rates. Additional information and videos are available at https://kl-research.github.io/decoupskill

Key facts. Cited by 2 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 26 of its 33 references that are in the map. First posted on arXiv 7 Mar 2023.

Builds on

26 of 33 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Learning Category-Level Generalizable Object Manipulation Policy via Generative Adversarial Self-Imitation Learning from Demonstrations4 Mar
  2. 2021Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation11 Nov

Other references · 24

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  4. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 584
  5. 2021Habitat 2.0: Training Home Assistants to Rearrange their Habitatcited by 501
  6. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 484
  7. 2016Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updatescited by 342
  8. 2020ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulationcited by 249
  9. 2020Accelerating Reinforcement Learning with Learned Skill Priorscited by 220
  10. 2015Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hourscited by 208
  11. 2021ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrationscited by 193
  12. 2021Where2Act: From Pixels to Actions for Articulated 3D Objectscited by 179
12 more
  1. 2019A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithmscited by 136
  2. 2018Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learningcited by 121
  3. 2021ManipulaTHOR: A Framework for Visual Object Manipulationcited by 101
  4. 2022FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objectscited by 91
  5. 2019Interactive Gibson Benchmark (iGibson 0.5): A Benchmark for Interactive Navigation in Cluttered Environmentscited by 89
  6. 2021VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objectscited by 78
  7. 2021UMPNet: Universal Manipulation Policy Network for Articulated Objectscited by 64
  8. 2021Accelerating Robotic Reinforcement Learning via Parameterized Action Primitivescited by 63
  9. 2019Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Taskscited by 56
  10. 2021Articulated Object Interaction in Unknown Scenes with Whole-Body Mobile Manipulationcited by 44
  11. 2020Motion Planner Augmented Reinforcement Learning for Robot Manipulation in Obstructed Environmentscited by 19
  12. 2021OSCAR: Data-Driven Operational Space Control for Adaptive and Robust Robot Manipulationcited by 7

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2024Robotic Imitation of Human Actionscited by 2
  2. 2025FLEX: A Framework for Learning Robot-Agnostic Force-based Skills Involving Sustained Contact Object Manipulationcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025ArticuBot: Learning Universal Articulated Object Manipulation Policy via Large Scale Simulation
  2. 2025Kinematics-Aware Diffusion Policy with Consistent 3D Observation and Action Space for Whole-Arm Robotic Manipulation
  3. 2024A Survey of Embodied Learning for Object-Centric Robotic Manipulation
  4. 2024Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning
  5. 2023Plan-Guided Reinforcement Learning for Whole-Body Manipulation
  6. 2025RobotMover: Learning to Move Large Objects From Human Demonstrations
  7. 2023Kinematic-aware Prompting for Generalizable Articulated Object Manipulation with LLMs
  8. 2025ObjectVLA: End-to-End Open-World Object Manipulation Without Demonstration