TriDeliver: Cooperative Air-Ground Instant Delivery with UAVs, Couriers, and Crowdsourced Ground Vehicles

TL;DR

TriDeliver is a hierarchical cooperative framework that integrates couriers, UAVs, and crowdsourced ground vehicles, utilizing transfer learning to optimize instant delivery efficiency and significantly reduce costs and delivery times.

Contribution

It introduces the first hierarchical cooperative system combining multiple delivery agents with a transfer learning approach for improved dispatching and efficiency.

Findings

Reduces delivery cost by 65.8% compared to state-of-the-art methods.

Achieves 17.7% faster delivery times and 9.8% lower costs.

Decreases impact on crowdsourced ground vehicles by 43.6%.

Abstract

Instant delivery, shipping items before critical deadlines, is essential in daily life. While multiple delivery agents, such as couriers, Unmanned Aerial Vehicles (UAVs), and crowdsourced agents, have been widely employed, each of them faces inherent limitations (e.g., low efficiency/labor shortages, flight control, and dynamic capabilities, respectively), preventing them from meeting the surging demands alone. This paper proposes TriDeliver, the first hierarchical cooperative framework, integrating human couriers, UAVs, and crowdsourced ground vehicles (GVs) for efficient instant delivery. To obtain the initial scheduling knowledge for GVs and UAVs as well as improve the cooperative delivery performance, we design a Transfer Learning (TL)-based algorithm to extract delivery knowledge from couriers' behavioral history and transfer their knowledge to UAVs and GVs with fine-tunings, which is then used to dispatch parcels for efficient delivery. Evaluated on one-month real-world trajectory and delivery datasets, it has been demonstrated that 1) by integrating couriers, UAVs, and crowdsourced GVs, TriDeliver reduces the delivery cost by $65.8\%$ versus state-of-the-art cooperative delivery by UAVs and couriers; 2) TriDeliver achieves further improvements in terms of delivery time ($-17.7\%$), delivery cost ($-9.8\%$), and impacts on original tasks of crowdsourced GVs ($-43.6\%$), even with the representation of the transferred knowledge by simple neural networks, respectively.