Research on vehicle path planning of automated guided vehicle with simultaneous pickup and delivery with mixed time windows

The authors investigate new Automated Guided Vehicle (AGV) Routing Problem with Simultaneous Pickup and Delivery with Mixed Time Windows (VRPSPDMTW) in smart workshops, a variation of the classic Vehicle Routing Problem (VRP). A mixed time window vehicle routing model was developed for simultaneous deliveries. This model reduces the cost of AGVs used and distribution cost, along with time window penalties. To address this complex challenge, a Hybrid Adaptive Genetic Algorithm using Variable Neighbourhood Search (AGA‐VNS) is proposed. This algorithm enhances the genetic algorithm's local search capabilities while preserving solution diversity, thereby improving both efficiency and quality of solutions. Comprehensive computational experiments are conducted, which include both VRPSPDTW test benchmark and real‐world smart factory instance studies. The outcomes reveal that the AGA‐VNS algorithm outperforms both professional solver software and advanced heuristic methods significantly. Moreover, the newly developed mixed time window model is more aligned with the requirements of real‐world production processes compared to the traditional time window model. Thus, this research not only presents novel insights into the domain of vehicle routing problems but also demonstrates its significant applicability and potential in the background of intelligent workshops. The authors introduce a new Automated Guided Vehicle (AGV) Routing Problem with Simultaneous Pickup and Delivery with Mixed Time Windows (VRPSPDMTW) for smart workshops. A novel Hybrid Adaptive Genetic Algorithm using Variable Neighbourhood Search (AGA‐VNS) is proposed, showing significant improvements over existing methods in computational experiments and real‐world applications. The research highlights the model's practical relevance to real‐world production processes and its potential in intelligent workshop settings.