.png){kind=icon}
.png){kind=icon}
Return
An effective multi-objective evolutionary algorithm for multiple spraying robots task assignment problem
.png){kind=icon}
PRE
AI
DOI：10.1016/j.swevo.2024.101558.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper addresses a multiple agricultural spraying robots task assignment problem in the greenhouse environment. The objective of the problem is to obtain a set of Pareto solutions that simultaneously optimize the total travel distance and maximum completion time of all robots. To solve this problem, an effective multi-objective evolutionary algorithm is proposed. In the proposed algorithm, an initial population with high quality and diversity is generated by a heuristic allocation strategy based on robot capacity constraints. During the evolutionary phase, a crossover strategy based on information in the non-dominated solution set is designed for exploration in the global scope. A multi-objective local search with an iterated greedy idea is introduced to improve the exploration ability of the algorithm. Meanwhile, a restart operator based on the ideal point is presented to jump out of the local optimum. Finally, extensive experiments based on different scales are conducted. The results show that the proposed algorithm significantly outperforms several state-of-the-art multiobjective algorithms in the literature.
Keywords:
Agricultural spraying robots
Task assignment
Multi-objective evolutionary algorithm
Heuristic
Journal
IF:
8.5
Papers:
2.2K
Citations:
1.0W