Mobile Robot Navigation Using Sonar and Range Measurements from Uncalibrated Cameras

A novel, simple and efficient method for vision based range measurements with uncalibrated cameras is presented. Required parameters are the image size, the relative distance between two different image frames of the same scene and the field of view of the camera(s). Range measurements acquired using ultrasonic sensors and a vision system have been used to navigate a mobile robot around known colored obstacles in an indoor environment. Both sonar sensors and cameras are activated and they operate simultaneously in parallel to obtain range measurements from common search areas located in the front of the mobile robot. Experimental results using a parallel stereoscopic, rotated and monocular vision system with uncalibrated cameras confirm that the maximum computational error (as well as the normalized root mean square error) of range measurements using the vision system for obstacles lying at a distance of 27–800 cm from the robot, is smaller compared to other similar, even more advanced and state-of-the-art existing approaches, reported in Rajagopalan (IEEE Trans. Pattern Anal. Mach. Intell., 28(11): 1521–1525, 2004), Mudenagudi and Chaudhuri (Proceedings of IEEE International Conference on Computer Vision, 1: 483–488, 1999), Umeda and Takahashi (Proceedings of IEEE ICRA, pp. 3215–3220, April 2000), Jiang and Weymouth (Proceedings of IEEE CVPR, pp. 250–255, June 1989), Lai, Fu, and Chang (IEEE Trans. Pattern Anal. Mach. Intell., 14(4):405–411, 1992), Malis and Rives (Proceedings of IEEE ICRA, pp. 1056–1061, 2003), Derrouich, Izumida, and Shiiya (IEEE Annual Conference on IECON, 3: 2191–2196, Nov. 2002).