Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviors

03/31/2022
by   Steven Bohez, et al.
0

We investigate the use of prior knowledge of human and animal movement to learn reusable locomotion skills for real legged robots. Our approach builds upon previous work on imitating human or dog Motion Capture (MoCap) data to learn a movement skill module. Once learned, this skill module can be reused for complex downstream tasks. Importantly, due to the prior imposed by the MoCap data, our approach does not require extensive reward engineering to produce sensible and natural looking behavior at the time of reuse. This makes it easy to create well-regularized, task-oriented controllers that are suitable for deployment on real robots. We demonstrate how our skill module can be used for imitation, and train controllable walking and ball dribbling policies for both the ANYmal quadruped and OP3 humanoid. These policies are then deployed on hardware via zero-shot simulation-to-reality transfer. Accompanying videos are available at https://bit.ly/robot-npmp.

READ FULL TEXT

page 1

page 3

page 5

page 7

page 9

11/24/2020

CoMic: Complementary Task Learning & Mimicry for Reusable Skills

Learning to control complex bodies and reuse learned behaviors is a long...
04/02/2020

Learning Agile Robotic Locomotion Skills by Imitating Animals

Reproducing the diverse and agile locomotion skills of animals has been ...
02/02/2022

Lipschitz-constrained Unsupervised Skill Discovery

We study the problem of unsupervised skill discovery, whose goal is to l...
11/15/2019

Reusable neural skill embeddings for vision-guided whole body movement and object manipulation

Both in simulation settings and robotics, there is an ambition to produc...
08/02/2022

Learning Skill-based Industrial Robot Tasks with User Priors

Robot skills systems are meant to reduce robot setup time for new manufa...
10/21/2019

Adversarial Skill Networks: Unsupervised Robot Skill Learning from Video

Key challenges for the deployment of reinforcement learning (RL) agents ...
09/27/2021

Model-based Motion Imitation for Agile, Diverse and Generalizable Quadupedal Locomotion

Robots operating in human environments need a variety of skills, like sl...