The quantity configuration and path optimization design of AGV considering energy consumption

Aiming at the collaborative optimization of energy efficiency and path planning for automated guided vehicles (AGV), a multi-mode collaborative optimization model is proposed to enhance system-level, energy-time, trade-offs and dynamic adaptability. Based on hierarchical reinforcement learning and dynamic task allocation strategy, a dynamic task allocation strategy is developed to reduce idle loss, which combines the enhanced ant colony optimization (ACO) and entropy-based weighting method to optimize energy consumption of the path. Compared with the benchmark genetic algorithm method, simulation results show that the energy consumption of AGV is reduced by 21.3% (p<0.05), and the task response time of AGV is shortened by 17.8% (p<0.05), to verify the effectiveness of the multi-mode collaborative optimization model. The proposed method provides theoretical support for the quantity configuration and path optimization design of AGV in intelligent manufacturing scenarios, avoiding path conflict-induced efficiency loss observed in high-density deployments.