Joint Infrastructure Planning and Order Assignment for On-Demand Food-Delivery Services with Coordinated Drones and Human Couriers

TL;DR

This paper tackles the problem of coordinating ground couriers and drones within a dense urban on-demand food-delivery network while simultaneously planning the locations of launchpads and kiosks. It develops a Mixed-Integer Nonlinear Program (MINLP) to jointly optimize infrastructure deployment and the allocation of orders between ground and air delivery, and then employs a neural-network-assisted linearization to transform the problem into a tractable MILP solvable by standard solvers. The authors introduce a detailed demand-modeling approach (logit-based mode choice), a double-ended-queue and queueing framework for the interactions at launchpads and kiosks, and a comprehensive bundling mechanism to improve efficiency; they validate the method with a Hong Kong case study and real-world data, demonstrating potential cost reductions and fleet-size reductions from drone delivery, alongside nuanced delivery-time implications that depend on order distance. The work provides actionable guidance for deploying coordinated drone-ground delivery in dense cities, revealing when and where air delivery offers the most value and highlighting the critical trade-offs introduced by intermodal transfer and waiting times.

Abstract

This paper investigates the optimal infrastructure planning and order assignment problem of an on-demand food-delivery platform with a mixed fleet of drones and human couriers. The platform has two delivery modes: (a) ground delivery and (b) drone-assisted delivery (i.e., air delivery). In ground delivery, couriers directly collect and transport orders from restaurants to destinations. For air delivery, the delivery process involves three legs: initially, a human courier picks up the order from the restaurant and transports it to a nearby launchpad, where personnel load the orders onto drones and replace batteries as needed. The loaded drone then transports the order from the launchpad to a kiosk, where another courier retrieves the order from the kiosk for final delivery. The platform must determine the optimal locations for launchpads and kiosks within a transportation network, and devise an order assignment strategy that allocates food-delivery orders between ground and air delivery considering the bundling probabilities of ground deliveries and the waiting times at launchpads and kiosks. We formulate the platform's problem as a mixed-integer nonlinear program and develop a novel neural network-assisted optimization method to obtain high-quality solutions. A case study in Hong Kong validates our model and algorithm, revealing that drone delivery reduces operational costs, minimizes courier fleet size, and increases order bundling opportunities. We also find that the expansion of air delivery services may entail larger delivery times due to the trade-off between the travel time savings induced by the faster air delivery and the associated detours incurred by intermodal transfer and extra waiting times at launchpads and kiosks, which crucially depends on the distance of the orders and the sequence of activating long-distance air delivery routes versus short-distance ones.

Figures (13)

• Figure 1: An illustrative figure for launchpads and kiosks for Meituan
• Figure 2: Delivery processes of ground delivery services and air delivery services
• Figure 3: An example of pickup and delivery process of a courier matched with two food-delivery orders.
• Figure 4: The state transitions across seeker and taker states and the corresponding probabilities (The "Matched" state signifies that the taker has completed matching with all seekers).
• Figure 5: Movement of courier in taker state $t_{(i,j,1)}^1$ from getting matched with the seeker to picking up all orders.

Theorems & Definitions (15)

• Remark 1
• Proposition 1
• proof
• Proposition 2
• proof
• Proposition 3
• proof
• Proposition 4
• Proposition 5
• proof