EBSCO Logo
Connecting you to content on EBSCOhost
Results
Title

Learning agility and adaptive legged locomotion via curricular hindsight reinforcement learning.

Authors

Li, Sicen; Wang, Gang; Pang, Yiming; Bai, Panju; Hu, Shihao; Liu, Zhaojin; Wang, Liquan; Li, Jiawei

Abstract

Agile and adaptive maneuvers such as fall recovery, high-speed turning, and sprinting in the wild are challenging for legged systems. We propose a Curricular Hindsight Reinforcement Learning (CHRL) that learns an end-to-end tracking controller that achieves powerful agility and adaptation for the legged robot. The two key components are (i) a novel automatic curriculum strategy on task difficulty and (ii) a Hindsight Experience Replay strategy adapted to legged locomotion tasks. We demonstrated successful agile and adaptive locomotion on a real quadruped robot that performed fall recovery autonomously, coherent trotting, sustained outdoor running speeds up to 3.45 m/s, and a maximum yaw rate of 3.2 rad/s. This system produces adaptive behaviors responding to changing situations and unexpected disturbances on natural terrains like grass and dirt.

Subjects

REINFORCEMENT learning; RUNNING speed; ROBOTS; GRASSES; CURRICULUM

Publication

Scientific Reports, 2024, Vol 14, Issue 1, p1

ISSN

2045-2322

Publication type

Academic Journal

DOI

10.1038/s41598-024-79292-4

EBSCO Connect | Privacy policy | Terms of use | Copyright | Manage my cookies
Journals | Subjects | Sitemap
© 2025 EBSCO Industries, Inc. All rights reserved