作者: C.F. Olson , L.H. Matthies
DOI: 10.1109/ROBOT.1998.676398
关键词:
摘要: This paper describes maximum likelihood estimation techniques for performing rover localization in natural terrain by matching range maps. An occupancy map of the local is first generated using stereo vision. The position with respect to a previously then computed comparing maps probabilistic formulation image techniques. Our motivation this work desire greater autonomy Mars rovers. These have been applied data obtained from Sojourner and run on-board Rocky 7 prototype.