Multi-Objective Multi-Picking-Robot Task Allocation: Mathematical Model and Discrete Artificial Bee Colony Algorithm
Lou-Lei Dai, Quan-Ke Pan, Zhonghua Miao, Ponnuthurai Nagaratnam Suganthan, Kaizhou Gao
Abstract
With the advent of agriculture 4.0 era, the combination of agriculture and unmanned technology has promoted the development of intelligent agriculture. However, there are relatively few studies on the agricultural robot task allocation problem to optimize the cost and efficiency of smart farms. To make up this deficiency, this paper addresses a multi-picking-robot task allocation (MPRTA) problem with two objectives of minimizing the maximum completion time and minimizing the total travel length of all robots. An effective multi-objective discrete artificial bee colony (MODABC) algorithm is proposed to solve this problem. At first, a heuristic allocation method based on robot load balancing is designed to generate high-quality initial solutions. And then, a multi-objective self-adaptive strategy is proposed to enhance the exploitation and exploration of the algorithm. In addition, a multi-objective local search strategy for the non-dominated solutions is presented to help the population find better solutions. At last, extensive experiments based on different task sizes and robot scales of an intelligent orchard demonstrate the effectiveness and high performance of the proposed algorithm for solving the MPRTA problem.