DeepAI AI Chat
Log In Sign Up

Learning Bipedal Walking for Humanoids with Current Feedback

by   Rohan Pratap Singh, et al.
National Institute of Advanced Industrial Science and Technology

Recent advances in deep reinforcement learning (RL) based techniques combined with training in simulation have offered a new approach to developing control policies 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 life-sized humanoid robots has been elusive due to the large sim-to-real gap arising from their large size, heavier limbs, and a high gear-ratio transmission systems. In this paper, we present an approach for effectively overcoming the sim-to-real 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 motors on the real robot, after training the policy in a simulation environment artificially degraded with poor torque tracking. Our approach successfully trains an end-to-end policy in simulation that can be deployed on a real HRP-5P humanoid robot for bipedal locomotion on challenging terrain. We also perform robustness tests on the RL policy and compare its performance against a conventional model-based controller for walking on uneven terrain. YouTube video:


page 1

page 5

page 6


Learning Bipedal Walking On Planned Footsteps For Humanoid Robots

Deep reinforcement learning (RL) based controllers for legged robots hav...

Reinforcement Learning Meets Hybrid Zero Dynamics: A Case Study for RABBIT

The design of feedback controllers for bipedal robots is challenging due...

Reinforcement Learning of a CPG-regulated Locomotion Controller for a Soft Snake Robot

In this work, we present a learning-based goal-tracking control method f...

Optimal Stroke Learning with Policy Gradient Approach for Robotic Table Tennis

Learning to play table tennis is a challenging task for robots, due to t...

End-to-end grasping policies for human-in-the-loop robots via deep reinforcement learning

State-of-the-art human-in-the-loop robot grasping is hugely suffered by ...

Training in Task Space to Speed Up and Guide Reinforcement Learning

Recent breakthroughs in the reinforcement learning (RL) community have m...

Code Repositories


Training a humanoid robot for locomotion using Reinforcement Learning

view repo