mlsanityData to 14 Oct 2026

Constrained Reinforcement Learning for Unstable Point-Feet Bipedal Locomotion Applied to the Bolt Robot

arXiv 2508.02194 ↗First posted 4 Aug 2025cs.ROcited by 1

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

Abstract (arXiv)

Bipedal locomotion is a key challenge in robotics, particularly for robots like Bolt, which have a point-foot design. This study explores the control of such underactuated robots using constrained reinforcement learning, addressing their inherent instability, lack of arms, and limited foot actuation. We present a methodology that leverages Constraints-as-Terminations and domain randomization techniques to enable sim-to-real transfer. Through a series of qualitative and quantitative experiments, we evaluate our approach in terms of balance maintenance, velocity control, and responses to slip and push disturbances. Additionally, we analyze autonomy through metrics like the cost of transport and ground reaction force. Our method advances robust control strategies for point-foot bipedal robots, offering insights into broader locomotion.

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 32 of its 53 references that are in the map. First posted on arXiv 4 Aug 2025.

Builds on

32 of 53 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Reinforcement Learning from Wild Animal Videos5 Dec
  2. 2024SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experience20 Sep
  3. 2024CTS: Concurrent Teacher-Student Reinforcement Learning for Legged Locomotion17 May
  4. 2024CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learning27 Mar
  5. 2024Reinforcement Learning for Blind Stair Climbing with Legged and Wheeled-Legged Robots9 Feb
  6. 2024Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control30 Jan

Other references · 26

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 512
  3. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 508
  4. 2023Orbit: A Unified Simulation Framework for Interactive Robot Learning Environmentscited by 295
  5. 2023Real-World Humanoid Locomotion with Reinforcement Learningcited by 187
  6. 2023Extreme Parkour with Legged Robotscited by 164
  7. 2025ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skillscited by 130
  8. 2022Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotioncited by 88
  9. 2023Not Only Rewards But Also Constraints: Applications on Legged Robot Locomotioncited by 47
  10. 2022Optimization-Based Control for Dynamic Legged Robotscited by 35
  11. 2019Crocoddyl: An Efficient and Versatile Framework for Multi-Contact Optimal Controlcited by 34
  12. 2019An Open Torque-Controlled Modular Robot Architecture for Legged Locomotion Researchcited by 22
14 more
  1. 2023Controlling the Solo12 Quadruped Robot with Deep Reinforcement Learningcited by 16
  2. 2023Learning Agile Bipedal Motions on a Quadrupedal Robotcited by 15
  3. 2025Bridging the Sim-to-Real Gap for Athletic Loco-Manipulationcited by 13
  4. 2018Using Deep Reinforcement Learning to Learn High-Level Policies on the ATRIAS Bipedcited by 10
  5. 2023Imitating and Finetuning Model Predictive Control for Robust and Symmetric Quadrupedal Locomotioncited by 10
  6. 2024Cafe-Mpc: A Cascaded-Fidelity Model Predictive Control Framework with Tuning-Free Whole-Body Controlcited by 10
  7. 2021Zero Dynamics, Pendulum Models, and Angular Momentum in Feedback Control of Bipedal Locomotioncited by 6
  8. 2017Walking Control Based on Step Timing Adaptationcited by 4
  9. 2021On the Emergence of Whole-body Strategies from Humanoid Robot Push-recovery Learningcited by 3
  10. 2021A unified framework for walking and running of bipedal robotscited by 3
  11. 2023A Real-World Quadrupedal Locomotion Benchmark for Offline Reinforcement Learningcited by 3
  12. 2023Stoch BiRo: Design and Control of a low cost bipedal robotcited by 2
  13. 2024Whole-body MPC and sensitivity analysis of a real time foot step sequencer for a biped robot Boltcited by 2
  14. 2024Dynamic Walking on Highly Underactuated Point Foot Humanoids: Closing the Loop between HZD and HLIPcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Direct Dynamic Retargeting for Humanoid Imitation Learning from Videoscited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2025Whole-Body Constrained Learning for Legged Locomotion via Hierarchical Optimization
  2. 2026Walk the PLANC: Physics-Guided RL for Agile Humanoid Locomotion on Constrained Footholds
  3. 2025Robust RL Control for Bipedal Locomotion with Closed Kinematic Chains
  4. 2024Agile and versatile bipedal robot tracking control through reinforcement learning
  5. 2026Hierarchical Reinforcement Learning for Collision-Free Locomotion of an Underactuated Biped
  6. 2025Bipedalism for Quadrupedal Robots: Versatile Loco-Manipulation through Risk-Adaptive Reinforcement Learning
  7. 2026MARCH: Model-Assisted Reinforcement Learning for the Perceptive Control of Humanoids over Sparse Footholds
  8. 2024A Learning Framework for Diverse Legged Robot Locomotion Using Barrier-Based Style Rewards