Learning Robust and Agile Legged Locomotion Using Adversarial Motion Priors

Developing both robust and agile locomotion skills for legged robots is non-trivial. In this work, we present the first blind locomotion system capable of traversing challenging terrains robustly while moving rapidly over natural terrains. Our approach incorporates the Adversarial Motion Priors (AMP...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE robotics and automation letters Jg. 8; H. 8; S. 1 - 8
Hauptverfasser: Wu, Jinze, Xin, Guiyang, Qi, Chenkun, Xue, Yufei
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 01.08.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Behavioral sciences
Coders
Legged locomotion
Legged Robots
Locomotion
Machine Learning for Robot Control
Reinforcement Learning
Robot dynamics
Robot sensing systems
Robots
Robustness
Sensors
Task analysis
Training
ISSN:2377-3766, 2377-3766
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Developing both robust and agile locomotion skills for legged robots is non-trivial. In this work, we present the first blind locomotion system capable of traversing challenging terrains robustly while moving rapidly over natural terrains. Our approach incorporates the Adversarial Motion Priors (AMP) in locomotion policy training and demonstrates zero-shot generalization from the motion dataset on flat terrains to challenging terrains in the real world. We show this result on a quadruped robot Go1 using only proprioceptive sensors consisting of the IMU and joint encoders. Experiments on the Go1 demonstrate the robust and natural motion generated by the proposed method for traversing challenging terrains while moving rapidly over natural terrains.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2023.3290509