Leveraging Machine Learning for Terrain Traversability in Mobile Robotics

被引:0
|
作者
Cottiga, Simone [1 ]
Bonin, Lorenzo [1 ]
Giberna, Marco [1 ]
Caruso, Matteo [1 ]
Gorner, Martin [2 ]
Carabin, Giovanni [3 ]
Scalera, Lorenzo [4 ]
De Lorenzo, Andrea [1 ]
Seriani, Stefano [1 ]
机构
[1] Univ Trieste, Via A Valerio 6-1, Trieste, Italy
[2] German Aerosp Ctr DLR, Inst Robot & Mechatron, Muenchener Str 20, Wessling, Germany
[3] Free Univ Bozen Bolzano, Piazza Univ 1, I-39100 Bolzano, BZ, Italy
[4] Univ Udine, Via Sci 206, I-33100 Udine, Italy
关键词
mobile robots; rover; soft-terrain; terrain mechanics; machine learning; surrogate model; VEHICLES;
D O I
10.1007/978-3-031-67383-2_36
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
The problem of traversability of soft terrains is hard to solve due to both the inherent modeling complexity and the related computational cost. In this work a surrogate model is used to describe the behavior of soft soil, thus avoiding explicitly simulating it. We leverage machine learning to train a model on real-world data acquired with the "Archimede" robotic platform in DLR's Moon-Mars test area in Oberp-faffenhofen, Germany. The model is tested using the Gazebo simulation environment by injecting virtual forces that mimic the effect of drift. Results show that the surrogate model shows promise, but showing also noticeable variability, possibly ascribable to the early stage of the model and training dataset.
引用
收藏
页码:345 / 352
页数:8
相关论文
共 50 条
  • [1] Learning Terrain Traversability for a Mobile Robot based on Information Fusion
    Peralta-Lopez, Jose-Eleazar
    Antonio, Emmanuel
    Becerra, Israel
    Barranco-Gutierrez, Alejandro-Israel
    Murrieta-Cid, Rafael
    INTELIGENCIA ARTIFICIAL-IBEROAMERICAN JOURNAL OF ARTIFICIAL INTELLIGENCE, 2025, 28 (75): : 1 - 14
  • [2] Learning multiobjective rough terrain traversability
    Wallin, Erik
    Wiberg, Viktor
    Vesterlund, Folke
    Holmgren, Johan
    Persson, Henrik J.
    Servin, Martin
    JOURNAL OF TERRAMECHANICS, 2022, 102 : 17 - 26
  • [3] Learning multiobjective rough terrain traversability
    Wallin, Erik
    Wiberg, Viktor
    Vesterlund, Folke
    Holmgren, Johan
    Persson, Henrik J.
    Servin, Martin
    Journal of Terramechanics, 2022, 102 : 17 - 26
  • [4] Traversability Analysis by Semantic Terrain Segmentation for Mobile Robots
    Hosseinpoor, Sadegh
    Torresen, Jim
    Mantelli, Mathias
    Pitto, Diego
    Kolberg, Mariana
    Maffei, Renan
    Prestes, Edson
    2021 IEEE 17TH INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING (CASE), 2021, : 1407 - 1413
  • [5] Fuzzy Based Traversability Analysis for a Mobile Robot on Rough Terrain
    Tanaka, Yusuke
    Ji, Yonghoon
    Yamashita, Atsushi
    Asama, Hajime
    2015 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2015, : 3965 - 3970
  • [6] Adaptive Traversability of Unknown Complex Terrain with Obstacles for Mobile Robots
    Zimmermann, Karel
    Zuzanek, Petr
    Reinstein, Michal
    Hlavac, Vaclav
    2014 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2014, : 5177 - 5182
  • [7] Rough-terrain traversability for a cylindrical shaped mobile robot
    Reina, G
    Foglia, M
    Milella, A
    Gentile, A
    ICM '04: PROCEEDINGS OF THE IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS 2004, 2004, : 148 - 153
  • [8] 3D traversability awareness for rough terrain mobile robots
    Bellone, Mauro
    Reina, Giulio
    Giannoccaro, Nicola Ivan
    Spedicato, Luigi
    SENSOR REVIEW, 2014, 34 (02) : 220 - 232
  • [9] Learning traversability models for autonomous mobile vehicles
    Michael Shneier
    Tommy Chang
    Tsai Hong
    Will Shackleford
    Roger Bostelman
    James S. Albus
    Autonomous Robots, 2008, 24 : 69 - 86
  • [10] Learning traversability models for autonomous mobile vehicles
    Shneier, Michael
    Chang, Tommy
    Hong, Tsai
    Shackleford, Will
    Bostelman, Roger
    Albus, James S.
    AUTONOMOUS ROBOTS, 2008, 24 (01) : 69 - 86