A Hybrid Multi-objective Heuristic Algorithm for Automated Guided Vehicle Path Planning

With the development of automated guided vehicle (AGV) technology, there is an increasing trend of AGV replacing manual labor across various fields. Efficient and safe path planning, as one of the key elements in ensuring the successful completion of tasks by AGV, has long been a focal point of academic research. This paper models the path planning problem with the objectives of minimizing the path length and energy consumption of the AGV, and proposes a hybrid heuristic algorithm for its resolution. Specifically, the hybrid algorithm first involves generating the path with the shortest length using the improved $A^{*}$, serving as a basis for optimizing the initial pheromone of the ant colony optimization (ACO) algorithm. Then, we construct a new heuristic function by combining the two objectives of path length and energy consumption to avoid local optima. Further, this paper improves pheromone update rule. Ultimately, the adaptive particle swarm optimization algorithm is used to finely tune the parameters of the ACO. The hybrid algorithm is compared with the other six algorithms in a grid map scene of size $20 \times 20$, and the simulation results fully verify that the proposed algorithm can obtain the optimal path that takes into account the path length and the energy consumption of the robot motion.