RLOC: Terrain-Aware Legged Locomotion Using Reinforcement Learning and Optimal Control

We present a unified model-based and data-driven approach for quadrupedal planning and control to achieve dynamic locomotion over uneven terrain. We utilize on-board proprioceptive and exteroceptive feedback to map sensory information and desired base velocity commands into footstep plans using a re...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on robotics Vol. 38; no. 5; pp. 2908 - 2927
Main Authors: Gangapurwala, Siddhant, Geisert, Mathieu, Orsolino, Romeo, Fallon, Maurice, Havoutis, Ioannis
Format: Journal Article
Language:English
Published: New York IEEE 01.10.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
AI-based methods
Computational modeling
deep learning in robotics and automation
Learning
Legged locomotion
legged robots
Locomotion
Optimal control
Perturbation
Physical properties
Planning
Policies
Quadrupedal robots
Robots
robust/adaptive control of robotic systems
Terrain
Tracking
Tracking control
Training
ISSN:1552-3098, 1941-0468
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a unified model-based and data-driven approach for quadrupedal planning and control to achieve dynamic locomotion over uneven terrain. We utilize on-board proprioceptive and exteroceptive feedback to map sensory information and desired base velocity commands into footstep plans using a reinforcement learning (RL) policy. This RL policy is trained in simulation over a wide range of procedurally generated terrains. When run online, the system tracks the generated footstep plans using a model-based motion controller. We evaluate the robustness of our method over a wide variety of complex terrains. It exhibits behaviors that prioritize stability over aggressive locomotion. Additionally, we introduce two ancillary RL policies for corrective whole-body motion tracking and recovery control. These policies account for changes in physical parameters and external perturbations. We train and evaluate our framework on a complex quadrupedal system, ANYmal version B, and demonstrate transferability to a larger and heavier robot, ANYmal C, without requiring retraining.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1552-3098
1941-0468
DOI:10.1109/TRO.2022.3172469