Multi-Objective Teaching-Learning-Based Optimizer for a Multi-Weeding Robot Task Assignment Problem

With the emergence of the artificial intelligence era, all kinds of robots are traditionally used in agricultural production. However, studies concerning the robot task assignment problem in the agriculture field, which is closely related to the cost and efficiency of a smart farm, are limited. Therefore, a Multi-Weeding Robot Task Assignment (MWRTA) problem is addressed in this paper to minimize the maximum completion time and residual herbicide. A mathematical model is set up, and a Multi-Objective Teaching-Learning-Based Optimization (MOTLBO) algorithm is presented to solve the problem. In the MOTLBO algorithm, a heuristic-based initialization comprising an improved Nawaz Enscore, and Ham (NEH) heuristic and maximum load-based heuristic is used to generate an initial population with a high level of quality and diversity. An effective teaching-learning-based optimization process is designed with a dynamic grouping mechanism and a redefined individual updating rule. A multi-neighborhood-based local search strategy is provided to balance the exploitation and exploration of the algorithm. Finally, a comprehensive experiment is conducted to compare the proposed algorithm with several state-of-the-art algorithms in the literature. Experimental results demonstrate the significant superiority of the proposed algorithm for solving the problem under consideration.