首页|A decomposition-based constrained multi-objective evolutionary algorithm with a local infeasibility utilization mechanism for UAV path planning
A decomposition-based constrained multi-objective evolutionary algorithm with a local infeasibility utilization mechanism for UAV path planning
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NSTL
Elsevier
Unmanned Aerial Vehicle (UAV) path planning problems can be treated as constrained multi-objective optimization problems, which often have complicated constraints in real-world scenarios. Algorithms for solving them require a powerful constraint-handling technique to utilize infeasible information. However, this has seldom been explored in this field. To remedy this issue, this paper proposes a decomposition-based constrained multi-objective evolutionary algorithm (M2M-DW) with a local infeasibility utilization mechanism for UAV path planning. Therein, M2M-DW is adopted as a solution optimizer since it can utilize infeasible individuals. However, this may result in poor performance due to the arbitrary use of infeasible individuals. To solve this issue, a local infeasibility utilization mechanism is proposed to effectively utilize the infeasible information. Besides, an improved mutation scheme is designed to further explore the promising regions. Experimental studies are conducted on three sets of UAV path planning problems with different difficulties, and the results highlight the effectiveness of the proposed algorithm in terms of reliability and stability in finding a set of feasible optimal solutions.
NSTL
Elsevier
