Linear Policies are Sufficient to Realize Robust Bipedal Walking on Challenging Terrains

In this work, we demonstrate robust walking in the bipedal robot Digit on uneven terrains by just learning a single linear policy. In particular, we propose a new control pipeline, wherein the high-level trajectory modulator shapes the end-foot ellipsoidal trajectories, and the low-level gait contro...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE robotics and automation letters Jg. 7; H. 2; S. 2047 - 2054
Hauptverfasser: Krishna, Lokesh, Castillo, Guillermo A., Mishra, Utkarsh A., Hereid, Ayonga, Kolathaya, Shishir
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 01.04.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Control theory
Foot
Gait
Hip
Humanoid and bipedal locomotion
Learning
Legged locomotion
legged robots
machine learning for robot control
Neural networks
Policies
reinforcement learning
Robot kinematics
Robots
Robustness
Torso
Trajectory
Walking
ISSN:2377-3766, 2377-3766
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this work, we demonstrate robust walking in the bipedal robot Digit on uneven terrains by just learning a single linear policy. In particular, we propose a new control pipeline, wherein the high-level trajectory modulator shapes the end-foot ellipsoidal trajectories, and the low-level gait controller regulates the torso and ankle orientation. The foot-trajectory modulator uses a linear policy and the regulator uses a linear PD control law. As opposed to neural network based policies, the proposed linear policy has only 13 learnable parameters, thereby not only guaranteeing sample efficient learning but also enabling simplicity and interpretability of the policy. This is achieved with no loss of performance on challenging terrains like slopes, stairs and outdoor landscapes. We first demonstrate robust walking in the custom simulation environment, MuJoCo, and then directly transfer to hardware with no modification of the control pipeline. We subject the biped to a series of pushes and terrain height changes, both indoors and outdoors, thereby validating the presented work.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2022.3143227