Humanoid robot moves agilely using one learning framework
FORGE: Feasible Online Reduced-Order Reference Generation and Whole-Body Execution for Agile Humanoid Locomotion
RoboticsMachine Learning
Summary
Making humanoid robots walk and move quickly with many different steps and turns is hard. The authors created a two-step learning method where a simpler model plans the movement, and then a detailed robot model learns to follow those plans. This helps the robot handle many walking styles and speeds using just one computer program. They tested it on a real humanoid robot that could run, hop on one leg, and turn smoothly.
What this means in practice
- •For robotics engineers: Enable humanoid robots to perform diverse agile motions with one unified control framework for walking, running, and hopping.
- •For robotics hardware developers: Design whole-body control systems that leverage reduced-order planning for improved real-time robot balancing and motion.
Authors
Adrian B. Ghansah, Yujin An, Jeeseop Kim, Soon-Jo Chung
Abstract
This paper presents a two-stage learning framework for versatile and agile humanoid locomotion that couples online reduced-order model (ROM) reference generation with whole-body tracking control. In the first stage, we train a command-conditioned whole-body reference generator using single rigid body dynamics combined with full humanoid kinematics. In the second stage, the frozen ROM policy is rolled out online to generate references for training a whole-body tracking policy on the full-order dynamics model. Learning a kino-dynamically consistent reference generator in the simplified ROM space enables us to generate references over a broad command space and over multiple locomotion strategies using a single unified framework. We demonstrate the approach on a Unitree G1 humanoid robot, achieving longitudinal velocities from -2.0 m/s to 2.8 m/s, lateral velocities up to +-1.0 m/s, angular velocities up to +-3.0 rad/s, one-legged hopping, and continuous transitions across the commands, all using one unified reference policy and one whole-body tracking policy.