详情

原文传递 Automated Terrain Classification for Vehicle Mobility in Off-Road Conditions.

题名：	Automated Terrain Classification for Vehicle Mobility in Off-Road Conditions.
作者：	Hodgdon, T. S; Fuentes, A. J; Olivier, J. L; Quinn, B. G; Shoop, S. A.
关键词：	Army corps of engineers##Artificial intelligence##Artificial intelligence software##Artificial satellites##Autonomous vehicles
摘要：	The U.S. Army is increasingly interested in autonomous vehicle opera-tions, including off-road autonomous ground maneuver. Unlike on-road,off-road terrain can vary drastically, especially with the effects of seasonal-ity. As such, vehicles operating in off-road environments need to be in-formed about the changing terrain prior to departure or en route for suc-cessful maneuver to the mission end point. The purpose of this report is toassess machine learning algorithms used on various remotely sensed da-tasets to see which combinations are useful for identifying different ter-rain. The study collected data from several types of winter conditions byusing both active and passive, satellite and vehicle-based sensor platformsand both supervised and unsupervised machine learning algorithms. Toclassify specific terrain types, supervised algorithms must be used in tan-dem with large training datasets, which are time consuming to create.However, unsupervised segmentation algorithms can be used to help labelthe training data. More work is required gathering training data to includea wider variety of terrain types. While classification is a good first step,more detailed information about the terrain properties will be needed foroff-road autonomy.
总页数：	35 pages