TERRAIN ESTIMATION USING INTERNAL SENSORS

摘要: The US Army designed Experimental Unmanned Vehicle (XUV) [1], shown in Figure 1, is a semi-autonomous unmanned ground vehicle (UGV) that uses high fidelity sensors for reconnaissance, surveillance, and target acquisition. One of the goals XUV research to develop autonomous mobility enables maneuver over rugged terrain as part mixed manned group. As this goal, must be able autonomously navigate different terrains at speeds. performance navigation improves when vehicle’s control system takes into account type on which traveling. For example, if covered with snow reduction acceleration necessary avoid wheel slip. Previous researchers have developed algorithms based vision digital signal processing categorize traversability terrain. Others used classical terramechanics equations identify key parameters. This paper presents novel algorithm internal qualitatively real-time. was successful identifying gravel, packed dirt, grass.