Obstacle Avoidance Scheme Based Elite Opposition Bat Algorithm for Unmanned Ground Vehicles

Abstract

Unmanned Ground Vehicles (UGVs) are intelligent vehicles that operate in an obstacle environment without an onboard human operator but can be controlled autonomously using an obstacle avoidance system or by a human operator from a remote location. In this research, an obstacle avoidance scheme-based elite opposition bat algorithm (EOBA) for UGVs was developed. The obstacle avoidance system comprises a simulation map, a perception system for obstacle detection, and the implementation of EOBA for generating an optimal collision-free path that led the UGV to the goal location. Three distance thresholds of 0.1 m, 0.2 m, and 0.3 m was used in the obstacle detection stage to determine the optimal distance threshold for obstacle avoidance. The performance of the obstacle avoidance scheme was compared with that of bat algorithm (BA) and particle swarm optimization (PSO) techniques. The simulation results show that the distance threshold of 0.3 m is the optimal threshold for obstacle avoidance provided that the size of the obstacle does not exceed the size of the UGV. The EOBA based scheme when compared with BA and PSO schemes obtained an average percentage reduction of 21.82% in terms of path length and 60% in terms of time taken to reach the target destination. The uniqueness of this approach is that the UGV avoid collision with an obstacle at a distance of 0.3 m from nearby obstacles as against taking three steps backward before avoiding obstacle