Purdue Experiments in Model Based Vision for

In the Robot Vision Laboratory of Purdue Univer sity we have developed two robust architectures for vision guided mobile robot navigation in indoor en vironments The rst approach FINALE enables the robot to autonomously navigate in hallways at speeds around m min through vision based position updating utilizing a geometrical map model based rea soning and Kalman ltering The performance of the navigation is not impaired by the presence of sta tionary or moving obstacles The second approach FUZZY NAV performs vision based navigation in a more human friendly manner utilizing simply a topo logical map and the combination of neural networks and fuzzy logic This approach also allows the robot to simultaneously navigate and avoid obstacles both static and dynamic In this paper we describe the above two approaches and show experimental results to demonstrate the e ectiveness and the robustness of our approaches