mlsanityData to 14 Oct 2026

Robust RL Control for Bipedal Locomotion with Closed Kinematic Chains

arXiv 2507.10164 ↗First posted 14 Jul 2025cs.ROcited by 0

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

Abstract (arXiv)

Developing robust locomotion controllers for bipedal robots with closed kinematic chains presents unique challenges, particularly since most reinforcement learning (RL) approaches simplify these parallel mechanisms into serial models during training. We demonstrate that this simplification significantly impairs sim-to-real transfer by failing to capture essential aspects such as joint coupling, friction dynamics, and motor-space control characteristics. In this work, we present an RL framework that explicitly incorporates closed-chain dynamics and validate it on our custom-built robot TopA. Our approach enhances policy robustness through symmetry-aware loss functions, adversarial training, and targeted network regularization. Experimental results demonstrate that our integrated approach achieves stable locomotion across diverse terrains, significantly outperforming methods based on simplified kinematic models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 15 of its 17 references that are in the map. First posted on arXiv 14 Jul 2025.

Builds on

15 of 17 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Humanoid Whole-Body Locomotion on Narrow Terrain via Dynamic Balance and Reinforcement Learning24 Feb
  2. 2025HiLo: Learning Whole-Body Human-like Locomotion with Motion Tracking Controller5 Feb
  3. 2024Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllers21 May

Other references · 12

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2022Robot Operating System 2: Design, Architecture, and Uses In The Wildcited by 199
  3. 2023Real-World Humanoid Locomotion with Reinforcement Learningcited by 187
  4. 2022Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behaviorcited by 138
  5. 2024ExBody2: Advanced Expressive Humanoid Whole-Body Controlcited by 88
  6. 2024Learning Humanoid Locomotion with Perceptive Internal Modelcited by 50
  7. 2018Feedback Control For Cassie With Deep Reinforcement Learningcited by 45
  8. 2024Learning Humanoid Locomotion over Challenging Terraincited by 26
  9. 2024Berkeley Humanoid: A Research Platform for Learning-based Controlcited by 24
  10. 2024Revisiting Reward Design and Evaluation for Robust Humanoid Standing and Walkingcited by 21
  11. 2025Design and Control of a Bipedal Robotic Charactercited by 18
  12. 2023On discrete symmetries of robotics systems: A group-theoretic and data-driven analysiscited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control
  2. 2025RL-augmented Adaptive Model Predictive Control for Bipedal Locomotion over Challenging Terrain
  3. 2026Efficiently Learning Robust Torque-based Locomotion Through Reinforcement with Model-Based Supervision
  4. 2025Robust Humanoid Walking on Compliant and Uneven Terrain with Deep Reinforcement Learning
  5. 2024Deep Reinforcement Learning for Bipedal Locomotion: A Brief Survey
  6. 2025Constrained Reinforcement Learning for Unstable Point-Feet Bipedal Locomotion Applied to the Bolt Robot
  7. 2026Walk the PLANC: Physics-Guided RL for Agile Humanoid Locomotion on Constrained Footholds
  8. 2025NaviGait: Navigating Dynamically Feasible Gait Libraries using Deep Reinforcement Learning