Generalized Animal Imitator: Agile Locomotion with Versatile Motion Prior

TL;DR

This paper presents VIM, a reinforcement learning framework enabling legged robots to learn and smoothly transition between diverse agile locomotion skills by imitating animal and designed motions, applicable in simulation and real-world scenarios.

Contribution

The introduction of VIM, a versatile RL-based framework that allows simultaneous learning of multiple agile locomotion behaviors with smooth transitions for legged robots.

Findings

Robots can learn multiple skills concurrently in simulation.

Robots successfully transfer learned skills to real-world environments.

VIM achieves smooth skill transitions during locomotion.

Abstract

The agility of animals, particularly in complex activities such as running, turning, jumping, and backflipping, stands as an exemplar for robotic system design. Transferring this suite of behaviors to legged robotic systems introduces essential inquiries: How can a robot learn multiple locomotion behaviors simultaneously? How can the robot execute these tasks with a smooth transition? How to integrate these skills for wide-range applications? This paper introduces the Versatile Instructable Motion prior (VIM) - a Reinforcement Learning framework designed to incorporate a range of agile locomotion tasks suitable for advanced robotic applications. Our framework enables legged robots to learn diverse agile low-level skills by imitating animal motions and manually designed motions. Our Functionality reward guides the robot's ability to adopt varied skills, and our Stylization reward ensures that robot motions align with reference motions. Our evaluations of the VIM framework span both simulation and the real world. Our framework allows a robot to concurrently learn diverse agile locomotion skills using a single learning-based controller in the real world. Videos can be found on our website: https://rchalyang.github.io/VIM/