Rapid locomotion via reinforcement learning

Agile maneuvers such as sprinting and high-speed turning in the wild are challenging for legged robots. We present an end-to-end learned controller that achieves record agility for the MIT Mini Cheetah, sustaining speeds up to 3.9 m/s. This system runs and turns fast on natural terrains like grass,...

Full description

Saved in:
Bibliographic Details
Published in:The International journal of robotics research 2024-04, Vol.43 (4), p.572-587
Main Authors: Margolis, Gabriel B., Yang, Ge, Paigwar, Kartik, Chen, Tao, Agrawal, Pulkit
Format: Article
Language:English
Subjects:
Controllers
Locomotion
Neural networks
On-line systems
Robots
System identification
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!