Feature Fusion Attention-Based Deep Reinforcement Learning for Multidepot O2O Food Delivery Route Optimization

The online-to-offline (O2O) business model has facilitated millions of daily transactions on popular online food ordering platforms. Online food delivery route planning presents a complex multidepot vehicle routing problem (VRP) with capacity limits, pickup–delivery, and time-window constraints. However, the vast volume of transactions and computational complexities of delivery routes pose significant challenges. This paper proposes a novel feature fusion attention-based deep reinforcement learning model to address such constrained routing problems. The innovative encoding and masking scheme with a self-attention-guided order relocation operator efficiently handles multidepot and multiconstraint scenarios. Additionally, incorporating self-attention with a graph neural network (GNN) framework extends existing research from static unit square environments to dynamic real road networks. Computational experiments demonstrate that our proposed route solver outperforms state-of-the-art heuristics and reinforcement learning methods regarding solution quality and computation time across unit square environments and real road networks. Exploratory analysis using real-world delivery data^a illustrates the applicability of our approach to practical online ordering platforms.