Open AccessA CNN Based Vision-Proprioception Fusion Method for Robust UGV Terrain Classification
Author(s) -
Yu Chen,
Chirag Rastogi,
William R. Norris
Publication year - 2021
Publication title -
ieee robotics and automation letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.123
H-Index - 56
ISSN - 2377-3766
DOI - 10.1109/lra.2021.3101866
Subject(s) - robotics and control systems , computing and processing , components, circuits, devices and systems
The ability for ground vehicles to identify terrain types and characteristics can help provide more accurate localization and information-rich mapping solutions. Previous studies have shown the possibility of classifying terrain types based on proprioceptive sensors that monitor wheel-terrain interactions. However, most methods only work well when very strict motion restrictions are imposed including driving in a straight path with constant speed, making them difficult to be deployed on real-world field robotic missions. To lift this restriction, this letter proposes a fast, compact, and motion-robust, proprioception-based terrain classification method. This method uses common on-board UGV sensors and a 1D Convolutional Neural Network (CNN) model. The accuracy of this model was further improved by fusing it with a vision-based CNN that made classification based on the appearance of terrain. Experimental results indicated the final fusion models were highly robust with strong performance, with over 93% accuracy, under various lighting conditions and motion maneuvers.