mlsanityData to 14 Oct 2026

Learning Bipedal Walking for Humanoids with Current Feedback

arXiv 2303.03724 ↗First posted 7 Mar 2023cs.RO cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

Recent advances in deep reinforcement learning (RL) based techniques combined with training in simulation have offered a new approach to developing robust controllers for legged robots. However, the application of such approaches to real hardware has largely been limited to quadrupedal robots with direct-drive actuators and light-weight bipedal robots with low gear-ratio transmission systems. Application to real, life-sized humanoid robots has been less common arguably due to a large sim2real gap. In this paper, we present an approach for effectively overcoming the sim2real gap issue for humanoid robots arising from inaccurate torque-tracking at the actuator level. Our key idea is to utilize the current feedback from the actuators on the real robot, after training the policy in a simulation environment artificially degraded with poor torque-tracking. Our approach successfully trains a unified, end-to-end policy in simulation that can be deployed on a real HRP-5P humanoid robot to achieve bipedal locomotion. Through ablations, we also show that a feedforward policy architecture combined with targeted dynamics randomization is sufficient for zero-shot sim2real success, thus eliminating the need for computationally expensive, memory-based network architectures. Finally, we validate the robustness of the proposed RL policy by comparing its performance against a conventional model-based controller for walking on uneven terrain with the real robot.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 22 of its 37 references that are in the map. First posted on arXiv 7 Mar 2023.

Builds on

22 of 37 references.

References · 22

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 604
  3. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 508
  4. 2019Learning agile and dynamic motor skills for legged robotscited by 504
  5. 2018Sim-to-Real: Learning Agile Locomotion For Quadruped Robotscited by 319
  6. 2020Learning Agile Robotic Locomotion Skills by Imitating Animalscited by 251
  7. 2023Real-World Humanoid Locomotion with Reinforcement Learningcited by 187
  8. 2022Rapid Locomotion via Reinforcement Learningcited by 168
  9. 2020Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Compositioncited by 96
  10. 2021Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learningcited by 92
  11. 2020Multi-expert learning of adaptive legged locomotioncited by 67
  12. 2019Sim-to-Real Transfer for Biped Locomotioncited by 56
10 more
  1. 2022Adapting Rapid Motor Adaptation for Bipedal Robotscited by 54
  2. 2020Learning Memory-Based Control for Human-Scale Bipedal Locomotioncited by 28
  3. 2021DeepWalk: Omnidirectional Bipedal Gait by Deep Reinforcement Learningcited by 21
  4. 2022Learning Bipedal Walking On Planned Footsteps For Humanoid Robotscited by 12
  5. 2018Stair Climbing Stabilization of the HRP-4 Humanoid Robot using Whole-body Admittance Controlcited by 9
  6. 2022Online Non-linear Centroidal MPC for Humanoid Robot Locomotion with Step Adjustmentcited by 8
  7. 2020Learning Whole-body Motor Skills for Humanoidscited by 6
  8. 2022mc-mujoco: Simulating Articulated Robots with FSM Controllers in MuJoCocited by 5
  9. 2022Sim-to-Real Transfer of Compliant Bipedal Locomotion on Torque Sensor-Less Gear-Driven Humanoidcited by 4
  10. 2021Learning Linear Policies for Robust Bipedal Locomotion on Terrains with Varying Slopescited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 8; 2025: 5; 2026: 4.

18 papers.

Sort:

By area:

  1. 2024HumanPlus: Humanoid Shadowing and Imitation from Humanscited by 185
  2. 2023Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learningcited by 133
  3. 2024Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Controlcited by 99
  4. 2024PDP: Physics-Based Character Animation via Diffusion Policycited by 31
  5. 2024Whole-body Humanoid Robot Locomotion with Human Referencecited by 29
  6. 2025Distillation-PPO: A Novel Two-Stage Reinforcement Learning Framework for Humanoid Robot Perceptive Locomotioncited by 10
  7. 2024Deep Reinforcement Learning for Bipedal Locomotion: A Brief Surveycited by 7
  8. 2024Enhancing Model-Based Step Adaptation for Push Recovery through Reinforcement Learning of Step Timing and Regioncited by 3
  9. 2025Robust Humanoid Walking on Compliant and Uneven Terrain with Deep Reinforcement Learningcited by 3
  10. 2025Learning Bipedal Locomotion on Gear-Driven Humanoid Robot Using Foot-Mounted IMUscited by 2
  11. 2026Efficiently Learning Robust Torque-based Locomotion Through Reinforcement with Model-Based Supervisioncited by 2
  12. 2026Training and Evaluating Diffusion Policies with Long Context Lengthscited by 2
6 more
  1. 2024Learning Skateboarding for Humanoid Robots through Massively Parallel Reinforcement Learningcited by 1
  2. 2024Learning to enhance multi-legged robot on rugged landscapescited by 1
  3. 2025Achieving Precise and Reliable Locomotion with Differentiable Simulation-Based System Identificationcited by 1
  4. 2026ECO: Energy-Constrained Optimization with Reinforcement Learning for Humanoid Walkingcited by 1
  5. 2025HuMam: Humanoid Motion Control via End-to-End Deep Reinforcement Learning with Mambacited by 0
  6. 2026GaitSpan: Growing Humanoid Locomotion from Walking to Runningcited by 0