Navigation Based on Vision and DGPS Information for Mobile Robots
Shinji Kotani*, Ken’ichi Kaneko**, Tatsuya Shinoda* and Hideo Mori*
*Faculty of Engineering, Yamanashi University, 4-3-11, Takeda, Kofu, Yamanashi 400-8511, Japan
**CANON Ltd., 3-16-1, Shimonoge, Takatsu, Kawasaki, Kanagawa 213-8512, Japan
This paper describes a navigation system for an autonomous mobile robot in outdoors. The robot uses vision to detect landmarks and DGPS information to determine its initial position and orientation. The vision system detects landmarks in the environment by referring to an environmental model. As the robot moves, it calculates its position by conventional dead reckoning, and matches landmarks to the environmental model to reduce error in position calculation. The robot’s initial position and orientation are calculated from coordinates of the first and second locations acquired by DGPS. Subsequent orientations and positions are derived by map matching. We implemented the system on a mobile robot, Harunobu 6. Experiments in real environments verified the effectiveness of our proposed navigation.