Home About Browse Search

Learning multiobjective rough terrain traversability

Wallin, Erik and Wiberg, Viktor and Vesterlund, Folke and Holmgren, Johan and Persson, Henrik and Servin, Martin (2022). Learning multiobjective rough terrain traversability. Journal of Terramechanics. 102 , 17-26
[Research article]

[img] PDF


We present a method that uses high-resolution topography data of rough terrain, and ground vehicle simulation, to predict traversability. Traversability is expressed as three independent measures: the abil-ity to traverse the terrain at a target speed, energy consumption, and acceleration. The measures are con-tinuous and reflect different objectives for planning that go beyond binary classification. A deep neural network is trained to predict the traversability measures from the local heightmap and target speed. To produce training data, we use an articulated vehicle with wheeled bogie suspensions and procedurally generated terrains. We evaluate the model on laser-scanned forest terrains, previously unseen by the model. The model predicts traversability with an accuracy of 90%. Predictions rely on features from the high-dimensional terrain data that surpass local roughness and slope relative to the heading. Correlations show that the three traversability measures are complementary to each other. With an infer-ence speed 3000 times faster than the ground truth simulation and trivially parallelizable, the model is well suited for traversability analysis and optimal path planning over large areas. (c) 2022 The Authors. Published by Elsevier Ltd on behalf of ISTVS. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Authors/Creators:Wallin, Erik and Wiberg, Viktor and Vesterlund, Folke and Holmgren, Johan and Persson, Henrik and Servin, Martin
Title:Learning multiobjective rough terrain traversability
Series Name/Journal:Journal of Terramechanics
Year of publishing :2022
Page range:17-26
Number of Pages:10
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 > 203 Mechanical Engineering > Vehicle Engineering
Keywords:Traversability, Rough terrain vehicle, Multibody simulation, Laser scan, Deep learning
Permanent URL:
Additional ID:
Type of IDID
Web of Science (WoS)000805039700001
ID Code:28474
Faculty:S - Faculty of Forest Sciences
Department:(S) > Dept. of Forest Resource Management
(NL, NJ) > Dept. of Forest Resource Management
Deposited By: SLUpub Connector
Deposited On:18 Aug 2022 15:09
Metadata Last Modified:18 Aug 2022 15:11

Repository Staff Only: item control page


Downloads per year (since September 2012)

View more statistics