Control of Rough Terrain Vehicles Using Deep Reinforcement Learning

We explore the potential to control terrain vehicles using deep reinforcement in scenarios where human operators and traditional control methods are inadequate. This letter presents a controller that perceives, plans, and successfully controls a 16-tonne forestry vehicle with two frame articulation...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE robotics and automation letters Jg. 7; H. 1; S. 390 - 397
Hauptverfasser: Wiberg, Viktor, Wallin, Erik, Nordfjell, Tomas, Servin, Martin
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 01.01.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Artificial Intelligence
Automatic Control
autonomous vehicle navigation
Biomedical Engineering
Blocking
Computational modeling
Computer Science
Computer Science Applications
Computer Vision and Pattern Recognition
Control and Optimization
Control and Systems Engineering
Control methods
Controllers
datalogi
Deep learning
Deep learning methods
Forestry
fysik
Human-Computer Interaction
Joints
Mechanical Engineering
model learning for control
Operators
Physics
reglerteknik
Reinforcement learning
Robotics
robotics and automation in agriculture and forestry
Robotteknik och automation
Rough terrain
Skills
Solid modeling
Suspensions (mechanical systems)
Vehicles
Virtual environments
Wheels
ISSN:2377-3766, 2377-3766
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We explore the potential to control terrain vehicles using deep reinforcement in scenarios where human operators and traditional control methods are inadequate. This letter presents a controller that perceives, plans, and successfully controls a 16-tonne forestry vehicle with two frame articulation joints, six wheels, and their actively articulated suspensions to traverse rough terrain. The carefully shaped reward signal promotes safe, environmental, and efficient driving, which leads to the emergence of unprecedented driving skills. We test learned skills in a virtual environment, including terrains reconstructed from high-density laser scans of forest sites. The controller displays the ability to handle obstructing obstacles, slopes up to 27<inline-formula><tex-math notation="LaTeX">^\circ</tex-math></inline-formula>, and a variety of natural terrains, all with limited wheel slip, smooth, and upright traversal with intelligent use of the active suspensions. The results confirm that deep reinforcement learning has the potential to enhance control of vehicles with complex dynamics and high-dimensional observation data compared to human operators or traditional control methods, especially in rough terrain.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2021.3126904