Research on Navigation for Search and Rescue Robot Based on Traversability

摘要

This paper presents a navigation algorithm based on traversability for search and rescue robot. The traversability includes pre-traversability and realtime traversability. The pre-traversability is calculated using terrain roughness and roll and pitch change. The terrain roughness is based on the texture information from the image captured by the on-board camera. An artificial neural network has been trained to find the relationship between roll and pitch changes and image characters. In order to avoid the localization that the intransitable region could not be completely identified just using the image process method, the real-time traversability with slip element has been adopted to correct the error in pre-traversability. The fuzzy logic approach has been developed for the traversability integration. The experiment demonstrates that the navigation algorithm is effective.