An Upgraded Particle Swarm Optimization Framework for highly Efficient Robot Navigation

A main issue in autonomous driving was robot path planning, but traditional optimization method faces the shortcoming of the complexity and dynamic in the real-world environments. Hence, this study introduces a boosted Particle Swarm Optimization (PSO) for addressing the problems in the traditional. This algorithm introduces a new particle update mechanism by using the personal best positions of previous particles to boost global search ability and search diversity. The results show that the boosted PSO algorithm has more strength than standard PSO in terms of path length, obstacle avoidance, and computational efficiency. Besides, this mechanism avoids premature convergence in local optima of standard PSO. Our work provides a new pathway to import the PSO algorithm for autonomous driving.