Optimized Robot Mapping and Obstacle Avoidance using Stereo Vision

Abstract

Robot Mapping for an unknown environment with no priori map by using computer vision was developed. In this paper, stereo vision is used and applied to Autonomous Guided Vehicle (AGV) to perform range finding and extract surrounding features. A region in the rectified image pair is selected as Region of Interest (RDI) for optimization and the RDI is processed to obtain disparity map which helps to estimate distance from obstacles. For real-time robot application, the image processing time must be reduced to be competitive with other active sensors. For obstacle avoidance, the mobile robot with the system implemented able to avoid obstacles within the test field. A 2D occupancy map is able to be constructed using the depth information obtained through stereo vision. The processing time of the system is optimized by the RDI implementation. The time taken is reduced for image processing and the final processing time per frame is 0.2143 s.