Vision-based waypoint following using templates and artificial neural networks

详细信息    查看全文

• 作者：Jefferson R. Souza ; ^{jeffersonrodrigo.s@gmail.com} ; ^{jrsouza@icmc.usp.br}Author Vitae ; Gustavo Pessin ^{pessin@icmc.usp.br}Author Vitae ; Patrick Y. Shinzato ^{shinzato@icmc.usp.br}Author Vitae ; Fernando S. Osorio ^{fosorio@icmc.usp.br}Author Vitae ; Denis F. Wolf ^{denis@icmc.usp.br}Author Vitae
• 关键词：Robotic vehicle navigation ; Artificial neural networks ; Computer vision ; Compass ; GPS waypoints ; Templates
• 刊名：Neurocomputing
• 出版年：2013
• 出版时间：1 May, 2013
• 年：2013
• 卷：107
• 期：Complete
• 页码：77-86
• 全文大小：2704 K

文摘

This paper presents a learning-based vehicle control system capable of navigating autonomously. Our approach is based on image processing, road and navigable area recognition, template matching classification for navigation control, and trajectory selection based on GPS waypoints. The vehicle follows a trajectory defined by GPS points avoiding obstacles using a single monocular camera and maintaining the vehicle in the road lane. Different parts of the image, obtained from the camera, are classified into navigable and non-navigable regions of the environment using neural networks. They provide steering and velocity control to the vehicle. Several experimental tests have been carried out under different environmental conditions to evaluate the proposed techniques.