This paper presents a method to forecast terrain trafficability from visual appearance. During training, the system identifies a set of image chips (or exemplars) that span the range of terrain appearance. Each chip is assigned a vector tag of vehicle-terrain interaction characteristics that are obtained from on-board sensors and simple performance models, as the vehicle traverses the terrain. The system uses the exemplars to segment images into regions, based on visual similarity to the terrain patches observed during training, and assigns the appropriate vehicle-terrain interaction tag to them. This methodology will therefore allow the online forecasting of vehicle performance on upcoming terrain. Currently, we are using fuzzy c-means clustering and exploring a number of different features for characterizing the visual appearance of the terrain.
Terrain Understanding for Robot Navigation
2007
7 pages
Report
Keine Angabe
Englisch
Transportation , Navigation Systems , Trafficability , Autonomous navigation , Ground vehicles , Detectors , Navigation , Robots , Terrain , Chips(Electronics) , Soils , Unmanned , Onboard , Forecasting , Cognition , Military vehicles , Performance(Engineering) , Interactions , Models , Reprints , Detection , Unmanned ground vehicles , Vehicle-terrain interactions , Teleoperation , Terrain understanding , Theoretical models , Terrain properties , Homogeneous soils , Moisture gradients , Natural terrain , Video cameras
Terrain Perception for Robot Navigation
NTIS | 2007
|Terrain perception for robot navigation [6561-09]
British Library Conference Proceedings | 2007
|Weaver: hexapod robot for autonomous navigation on unstructured terrain
British Library Online Contents | 2018
|Tema Archiv | 1990
|