Learning and prediction of vehicle-terrain interaction from 3D vision
- 20 June 2021
- conference paper
- conference paper
- Published by SPIE-Intl Soc Optical Eng
- Vol. 11785, 117850T
- https://doi.org/10.1117/12.2596021
Abstract
Wheel-terrain interaction plays a critical role for vehicle mobility on natural terrain, such as in agricultural, planetary exploration and off-road settings. Estimation of the terrain characteristics and the way they affect traversability is essential for the vehicle to better plan its safest and energy-efficient path. This work proposes a novel approach to learn and predict from a distance the motion resistance encountered by a robotic vehicle, while traversing natural soil, by using visual information from a stereovision device. To this end, terrain appearance and geometry information are first correlated to resistance torque measurements during a learning phase via two alternative regression approaches, namely Least-Squares Boosting and Long-Short Term Memory Recurrent Neural Network. Then, such a relationship is exploited to predict motion resistance remotely, based on visual data only. Results obtained in preliminary experimental tests on ploughed and compact terrain are presented to show the feasibility of the proposed method.Keywords
This publication has 9 references indexed in Scilit:
- Recurrent and convolutional neural networks for deep terrain classification by autonomous robotsJournal of Terramechanics, 2021
- IEEE Transactions on Intelligent VehiclesIEEE Transactions on Intelligent Vehicles, 2019
- A Deep Learning based Virtual Sensor for Vehicle Sideslip Angle Estimation: Experimental ResultsSAE International Journal of Advances and Current Practices in Mobility, 2018
- Terrain assessment for precision agriculture using vehicle dynamic modellingBiosystems Engineering, 2017
- Journal of Field RoboticsJournal of Field Robotics, 2013
- The FLEXnav precision dead-reckoning systemInternational Journal of Vehicle Autonomous Systems, 2006
- Rough-terrain traversability for a cylindrical shaped mobile robotPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Random ForestsMachine Learning, 2001
- Long Short-Term MemoryNeural Computation, 1997