A Reactive Bearing Angle Only Obstacle Avoidance Technique for Unmanned Ground Vehicles

Abstract

In this paper, we present a reactive, vision based obstacle avoidance technique for Unmanned Ground Vehicles (UGVs) navigating with only visual electro-optic sensors in an indoor environment without Global Positioning System (GPS) signals. The presented work is unique in that, to the best of our knowledge, there was no other bearing angle only obstacle avoidance technique for ground vehicles reported in the literature. A Lyapunov-based sliding mode controller maintains the bearing angle of the UGV from obstacles, using a real-time image processing method. The proposed technique is implemented and tested with a Pioneer robot in an indoor environment, and the results demonstrate its effectiveness.