On the Emergence of Whole-body Strategies from Humanoid Robot Push-recovery Learning

Abstract

Balancing and push-recovery are essential capabilities enabling humanoid robots to solve complex locomotion tasks. In this context, classical control systems tend to be based on simplified physical models and hard-coded strategies. Although successful in specific scenarios, this approach requires demanding tuning of parameters and switching logic between specifically-designed controllers for handling more general perturbations. We apply model-free Deep Reinforcement Learning for training a general and robust humanoid push-recovery policy in a simulation environment. Our method targets high-dimensional whole-body humanoid control and is validated on the iCub humanoid. Reward components incorporating expert knowledge on humanoid control enable fast learning of several robust behaviors by the same policy, spanning the entire body. We validate our method with extensive quantitative analyses in simulation, including out-of-sample tasks which demonstrate policy robustness and generalization, both key requirements towards real-world robot deployment.

Co-first authors: Diego Ferigo and Raffaello Camoriano; 8 pages

References in corpus (6)

• Learning agile and dynamic motor skills for legged robots
• AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control
• Learning natural locomotion behaviors for humanoid robots using human knowledge
• An empirical investigation of the challenges of real-world reinforcement learning
• Torque-Controlled Stepping-Strategy Push Recovery: Design and Implementation on the iCub Humanoid Robot
• Learning Whole-body Motor Skills for Humanoids

Cited by in corpus (2)

• Reactive Stepping for Humanoid Robots using Reinforcement Learning: Application to Standing Push Recovery on the Exoskeleton Atalante
• Bracing for Impact: Robust Humanoid Push Recovery and Locomotion with Reduced Order Models