Bi-objective optimisation for intelligent warehouse scheduling based on student psychology mechanism

Addressing the issue that traditional methods do not fully consider the workload balance among robots, this paper proposes a dual-objective optimisation model aimed at simultaneously minimising the total task completion time for all robots and reducing the disparity in working hours among them. To tackle this optimisation problem, the paper introduces an improved non-dominated sorting genetic algorithm II (NSGA-II) based on student psychology optimisation (SPM-NSGAII). This algorithm incorporates a student psychology optimisation strategy to classify the population and implement differentiated evolution strategies, thereby enhancing population diversity and improving global search capabilities. Experimental data demonstrate that the SPM-NSGAII algorithm performs excellently across various types of datasets, with a reduction in total task completion time ranging from 10.91% to 18.84%, and a decrease in the disparity of working hours among robots ranging from 55.43% to 87.61%. These results fully validate its effectiveness in practical intelligent warehouse scheduling problems.