mlsanityData to 14 Oct 2026

Constraint-Grounded Reinforcement Learning for Variable Impedance Control in Contact-Rich Robotic Insertion

arXiv 2609.13516 ↗First posted 11 Sep 2026cs.ROcited by 1

On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation

Abstract (arXiv)

In robotic insertion under uncertain contact, the axial force limit and the appropriate controller gain vary across tasks. As a result, a single fixed gain is unlikely to remain suitable across different task conditions, making conventional impedance controllers reliant on manual retuning. To eliminate manual retuning, we propose Constraint-Grounded Reinforcement Learning (CG-RL), a variable impedance framework for online gain adaptation. Conditioned on the force limit and contact feedback, the policy outputs a residual motion, an insertion rate, and a requested gain. The controller projects this gain into the admissible range without exposing the range itself to the policy. This separation allows a single policy to operate under different force limits without retraining or manual retuning. We evaluate CG-RL on simulated oblique insertion across five training seeds. CG-RL achieves an 85.8±7.7% (mean ± SD) success rate of insertions without violating the force limit, while keeping the applied gain within the admissible range. As a comparison, a fixed-gain baseline using the midpoint gain achieves a success rate of 50.1%. The policy adapts its insertion rate continuously to the specified force limit and further generalizes to more permissive force limits above the training range. In contrast, the same actor without force-limit input does not exhibit this adaptation. The applied gain is guaranteed to remain within the admissible range, while force-limit satisfaction is validated empirically rather than guaranteed formally.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 26 of its 50 references that are in the map. First posted on arXiv 11 Sep 2026.

Builds on

26 of 50 references.

References · 26

  1. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  2. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  3. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  4. 2018Learning Dexterous In-Hand Manipulationcited by 687
  5. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 672
  6. 2021Implicit Behavioral Cloningcited by 452
  7. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 389
  8. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 371
  9. 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 289
  10. 2017A General Safety Framework for Learning-Based Control in Uncertain Robotic Systemscited by 163
  11. 2018Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Taskscited by 154
  12. 2022ObjectFolder 2.0: A Multisensory Object Dataset for Sim2Real Transfercited by 75
14 more
  1. 2019Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Taskscited by 67
  2. 2023IndustReal: Transferring Contact-Rich Assembly Tasks from Simulation to Realitycited by 53
  3. 2019Reinforcement Learning on Variable Impedance Controller for High-Precision Robotic Assemblycited by 39
  4. 2020Meta-Reinforcement Learning for Robotic Industrial Insertion Taskscited by 34
  5. 2021Robust Multi-Modal Policies for Industrial Assembly via Reinforcement Learning and Demonstrations: A Large-Scale Studycited by 30
  6. 2020Variable Compliance Control for Robotic Peg-in-Hole Assembly: A Deep Reinforcement Learning Approachcited by 29
  7. 2021A Survey of Robot Manipulation in Contactcited by 28
  8. 2024AutoMate: Specialist and Generalist Assembly Policies over Diverse Geometriescited by 26
  9. 2024FORGE: Force-Guided Exploration for Robust Contact-Rich Manipulation under Uncertaintycited by 23
  10. 2023Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learningcited by 18
  11. 2020Variable impedance control and learning -- A reviewcited by 17
  12. 2025Integrating LLMs and Digital Twins for Adaptive Multi-Robot Task Allocation in Constructioncited by 3
  13. 2026From Perception to Symbolic Task Planning: Vision-Language Guided Human-Robot Collaborative Structured Assemblycited by 2
  14. 2025Learning Diffusion Policies for Robotic Manipulation of Timber Joinery under Fabrication Uncertaintycited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026From Documented Strengths to Force Limits: Material-Informed Robotic Insertion for Construction Assemblycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Impedance Primitive-augmented Hierarchical Reinforcement Learning for Sequential Tasks
  2. 2026VIDP: Variable Impedance Diffusion Policy for Compliant Robot Manipulation from Diverse Demonstrations
  3. 2024SRL-VIC: A Variable Stiffness-Based Safe Reinforcement Learning for Contact-Rich Robotic Tasks
  4. 2026Impedance Cloning: Learning Equilibrium Point Parameters for Contact-Rich Manipulation ↗
  5. 2026Potential-Field Action Representation for Reinforcement Learning in Contact-Rich Manipulation
  6. 2021Learning Variable Impedance Control via Inverse Reinforcement Learning for Force-Related Tasks
  7. 2025Safe and Optimal Variable Impedance Control via Certified Reinforcement Learning
  8. 2025Diffusion-Based Impedance Learning for Contact-Rich Manipulation Tasks