Intelligent path planning algorithm for cooperative traversal task of multiple unmanned ground vehicles

The task assignment of multiple constant-thrust unmanned ground vehicles in a warehouse has been studied in the paper. In order to reduce energy consumption, a set of dynamic multiple targets with fixed moving ways and different sensor demands are transported by vehicles with multiple customized sensors to complete the task while minimizing the total traveling distance. Firstly, considering the influence of the load brought by the weight of the carried sensor, a path planning model for dynamic targets was designed. Then, a co-evolutionary mixed population genetic algorithm (CMPGA) that combined virtual coding strategy, classical evolution method, and mixed crossover mechanism has been proposed, which was used to search for feasible solutions under the condition that the loading and endurance capacity of vehicles were limited. The simulation results showed that the proposed algorithm was feasible. Compared with the traditional simulated annealing algorithm (SA), particle swarm optimization algorithm (PSO) and the principle of proximity(Nearby), the proposed algorithm has better advantages in reducing energy consumption.