Home About Browse Search

Control of Rough Terrain Vehicles Using Deep Reinforcement Learning

Wiberg, Viktor and Wallin, Erik and Nordfjell, Tomas and Servin, Martin (2022). Control of Rough Terrain Vehicles Using Deep Reinforcement Learning. IEEE Robotics and Automation Letters. 7 , 390-397
[Research article]

[img] PDF


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.

Authors/Creators:Wiberg, Viktor and Wallin, Erik and Nordfjell, Tomas and Servin, Martin
Title:Control of Rough Terrain Vehicles Using Deep Reinforcement Learning
Series Name/Journal:IEEE Robotics and Automation Letters
Year of publishing :2022
Page range:390-397
Number of Pages:8
Publication Type:Research article
Article category:Scientific peer reviewed
Version:Published version
Copyright:Creative Commons: Attribution-Noncommercial-No Derivative Works 4.0
Full Text Status:Public
Subjects:(A) Swedish standard research categories 2011 > 2 Engineering and Technology > 202 Electrical Engineering, Electronic Engineering, Information Engineering > Robotics
Keywords:Deep learning methods, reinforcement learning, autonomous vehicle navigation, model learning for control, robotics and automation in agriculture and forestry
Permanent URL:
Additional ID:
Type of IDID
Web of Science (WoS)000721999500008
ID Code:26262
Faculty:S - Faculty of Forest Sciences
Department:(S) > Department of Forest Biomaterials and Technology
Deposited By: SLUpub Connector
Deposited On:02 Dec 2021 13:25
Metadata Last Modified:02 Dec 2021 13:31

Repository Staff Only: item control page


Downloads per year (since September 2012)

View more statistics