Arjun B Krishnan and Jayaram Kollipara, Amrita Vishwa Vidyapeetham, India

The key component of a mobile robot system is the ability to localize itself accurately in an unknown environment and simultaneously build the map of the environment. Majority of the existing navigation systems are based on laser range finders, sonar sensors or artificial landmarks. Navigation systems using stereo vision are rapidly developing technique in the field of autonomous mobile robots. But they are less advisable in replacing the conventional approaches to build small scale autonomous robot because of their high implementation cost. This paper describes an experimental approach to build a cost- effective stereo vision system for autonomous mobile robots that avoid obstacles and navigate through indoor environments. The mechanical as well as the programming aspects of stereo vision system are documented in this paper. Stereo vision system adjunctively with ultrasound sensors was implemented on the mobile robot, which successfully navigated through different types of cluttered environments with static and dynamic obstacles. The robot was able to create two dimensional topological maps of unknown environments using the sensor data and three dimensional model of the same using stereo vision system.

Arduino, Disparity maps, Point clouds, Stereo vision, Triangulation