Research article - Peer-reviewed, 2022
Control of Rough Terrain Vehicles Using Deep Reinforcement Learning
Wiberg, Viktor; Wallin, Erik; Nordfjell, Tomas; Servin, MartinAbstract
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 degrees, 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.Keywords
Deep learning methods; reinforcement learning; autonomous vehicle navigation; model learning for control; robotics and automation in agriculture and forestryPublished in
IEEE Robotics and Automation Letters2022, volume: 7, number: 1, pages: 390-397
Publisher: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Authors' information
Wiberg, Viktor
Umea University
Wallin, Erik
Umea University
Swedish University of Agricultural Sciences, Department of Forest Biomaterials and Technology
Servin, Martin
Umea University
Sustainable Development Goals
SDG9 Build resilient infrastructure, promote inclusive and sustainable industrialization and foster innovation
UKÄ Subject classification
Robotics
Publication Identifiers
DOI: https://doi.org/10.1109/LRA.2021.3126904
URI (permanent link to this page)
https://res.slu.se/id/publ/114522