Ameliorated Particle Swarm Optimization Algorithm and Its Application in Robot Path Planning

Since particle swarm optimization (PSO) was put forward in 1995, it has been paid more and more attention in the research field because of its simple concept and easy implementation. This algorithm can simulate the mutual learning and cooperation behaviour of birds during foraging, and find the optimal solution of the population. However, there are some problems in the development of PSO, such as lack of theoretical basis, high computational cost, easy to fall into local optimums, and so on. This paper starts with the basic PSO algorithm and proposes an improved algorithm applied for robot path planning. In this algorithm, PSO and quantum computing are combined to simplify the search model. The weight factor's self-adjusting strategy is improved, and the convergence speed of the improved algorithm is better. The mutation operation is introduced to the global optimum, which increases the diversity of solutions in the search process. The improved algorithm is used in robot path planning simulation, and the results indicate that the planned path is more safe and reliable.