Multi-objective unmanned vehicle path planning based on whale optimization algorithm

Path planning is an important part of the research field of mobile robots. How to plan more suitable paths more quickly has become a challenging optimization problem that requires consideration of several constraints and performance metrics. Given the multitude of optimization objectives and the intricate nature of addressing the static path planning problem, it is usually converted into a single-objective optimization problem. However, this approach would lead to the algorithm being unable to thoroughly explore the solution space. To address this problem, a nondominated sorting whale optimization algorithm based on crowding degree and memory (NSWOACDM) is presented and applied to unmanned vehicle path planning in this paper. Both the length and curvature of path are optimized simultaneously. Experimental results on benchmark functions show that the proposed algorithm is more effective compared with other traditional multi-objective algorithms. The effects of different control points on the optimization results are analyzed through path planning experiments. The experimental results demonstrate that the NSWOACDM algorithm exhibits superior performance in comparison to similar algorithms. Furthermore, it is capable of identifying several viable paths within a reduced timeframe in the context of the multi-objective path planning issue.