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

04/29/2021
by   Diego Ferigo, et al.
10

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.

READ FULL TEXT

page 1

page 7

research
02/07/2020

Learning Whole-body Motor Skills for Humanoids

This paper presents a hierarchical framework for Deep Reinforcement Lear...
research
03/02/2022

Reactive Stepping for Humanoid Robots using Reinforcement Learning: Application to Standing Push Recovery on the Exoskeleton Atalante

State-of-the-art reinforcement learning is now able to learn versatile l...
research
06/22/2023

Robust Recovery Motion Control for Quadrupedal Robots via Learned Terrain Imagination

Quadrupedal robots have emerged as a cutting-edge platform for assisting...
research
09/06/2018

Emergence of Human-comparable Balancing Behaviors by Deep Reinforcement Learning

This paper presents a hierarchical framework based on deep reinforcement...
research
10/18/2017

Data Driven Computational Model for Bipedal Walking and Push Recovery

In this research, we have developed the data driven computational walkin...
research
10/07/2022

Integration of Riemannian Motion Policy and Whole-Body Control for Dynamic Legged Locomotion

In this paper, we present a novel Riemannian Motion Policy (RMP)flow-bas...
research
03/03/2020

Scaling MAP-Elites to Deep Neuroevolution

Quality-Diversity (QD) algorithms, and MAP-Elites (ME) in particular, ha...

Please sign up or login with your details

Forgot password? Click here to reset