Collaborative path planning and task allocation for multiple agricultural machines

Abstract

Path planning and task allocation are critical concerns in multi-machine collaborative operations for unmanned farms. Nevertheless, several problems remain in the operation of agricultural machinery, such as the slow path planning algorithm, the omission of the working area, and the unreasonable scheduling of machines, resulting in low efficiency and wasted resources. Collaborative and complete coverage path planning was achieved to solve the problems of slow path planning algorithms and the omission of working areas. The farm’s electronic map was constructed using the topological map method. The improved Dijkstra algorithm based on priority queues was combined with three different complete coverage methods: the nested method, the reciprocating method, and the combination of nested and internal spiral path methods. The simulation results show that the improved Dijkstra method based on priority queues can effectively minimize the running time of the algorithm. The reciprocating method has a higher coverage index than the other two methods, with an average coverage rate of 94.73 %. To solve the problem of illogical scheduling of the same type of agricultural machines, an improved ant colony method was presented based on the whole working path to minimize the path cost. The simulation results show that the proposed method can allocate the task properly, and the path cost is reduced by 14 %–33 %. By combining the proposed path planning and task allocation methods, the whole-process path planning of a single agricultural machine and multiple agricultural machines of the same type was achieved, providing a technical solution for promoting the construction of unmanned farms.