REDE: Exploring Relay Transportation for Efficient Last-mile Delivery

Last-mile delivery from delivery stations to customers’ places is now mainly finished by dedicated couriers. In practice, each courier generally collects orders destined for one delivery area at the delivery station and delivers orders to customers. However, the long distance between the delivery station and the delivery area due to practical reasons, e.g., expensive delivery station rental fee in the downtown area, increases the delivery courier’s travel time and decreases the efficiency of the state-of-the-practice last-mile delivery scheme. In this paper, we solve the problem with relay transportation, where a relay courier collects orders at the delivery station and sends them to delivery couriers, and delivery couriers focus on the order delivery at corresponding delivery areas. We design a real-time relay courier scheduling system called REDE to minimize the average relay order delivery time (ARODT) considering the relay and delivery couriers’ mobility and the order destination distribution. First, a heterogeneous task aware route prediction algorithm is proposed to characterize the delivery courier’s mobility. Then a distance-aware greedy algorithm and an ARODT-constrained exchange algorithm are designed to generate the relay route, which is updated with real-time order pickup requests. Extensive evaluation results with real-world logistics data from 100 delivery stations in 38 cities show that REDE reduces ARODT by up to 8.4% compared to baseline methods. The online A/B tests show that compared to the state-of-the-practice method, REDE improves the delivery courier’s working efficiency and the daily number of pickup orders by 20.13% and 4.51%, respectively.

[1]  Yan Pan,et al.  Extending Delivery Range and Decelerating Battery Aging of Logistics UAVs Using Public Buses , 2023, IEEE Transactions on Mobile Computing.

[2]  Tianrui Li,et al.  Shortening Passengers’ Travel Time: A Dynamic Metro Train Scheduling Approach Using Deep Reinforcement Learning , 2023, IEEE Transactions on Knowledge and Data Engineering.

[3]  Guanfeng Liu,et al.  Drive Less but Finish More: Food Delivery based on Multi-Level Workers in Spatial Crowdsourcing , 2022, CIKM.

[4]  Jingwei Wang,et al.  RBG: Hierarchically Solving Large-Scale Routing Problems in Logistic Systems via Reinforcement Learning , 2022, KDD.

[5]  Zimu Zhou,et al.  Unified Route Planning for Shared Mobility: An Insertion-based Framework , 2022, ACM Trans. Database Syst..

[6]  Guang Wang,et al.  Concurrent Order Dispatch for Instant Delivery with Time-Constrained Actor-Critic Reinforcement Learning , 2021, 2021 IEEE Real-Time Systems Symposium (RTSS).

[7]  Sang Hyuk Son,et al.  A City-Wide Crowdsourcing Delivery System with Reinforcement Learning , 2021, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol..

[8]  Huijun Sun,et al.  Record: Joint Real-Time Repositioning and Charging for Electric Carsharing with Dynamic Deadlines , 2021, KDD.

[9]  Pan Hui,et al.  Hierarchical Reinforcement Learning for Scarce Medical Resource Allocation with Imperfect Information , 2021, KDD.

[10]  Guoren Wang,et al.  Energy-Efficient 3D Vehicular Crowdsourcing for Disaster Response by Distributed Deep Reinforcement Learning , 2021, KDD.

[11]  Donghai Shi,et al.  Dynamic Rebalancing Dockless Bike-Sharing System based on Station Community Discovery , 2021, IJCAI.

[12]  Desheng Zhang,et al.  Data-Driven Fairness-Aware Vehicle Displacement for Large-Scale Electric Taxi Fleets , 2021, 2021 IEEE 37th International Conference on Data Engineering (ICDE).

[13]  Fan Wu,et al.  Package Pick-up Route Prediction via Modeling Couriers’ Spatial-Temporal Behaviors , 2021, 2021 IEEE 37th International Conference on Data Engineering (ICDE).

[14]  Mingxuan Yuan,et al.  Learning to Optimize Industry-Scale Dynamic Pickup and Delivery Problems , 2021, 2021 IEEE 37th International Conference on Data Engineering (ICDE).

[15]  Shining Li,et al.  Efficient Schedule of Energy-Constrained UAV Using Crowdsourced Buses in Last-Mile Parcel Delivery , 2021, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol..

[16]  Wenjun Wang,et al.  Real-Time Ambulance Redeployment: A Data-Driven Approach , 2020, IEEE Transactions on Knowledge and Data Engineering.

[17]  Yu Zheng,et al.  Cooperative Multi-Agent Reinforcement Learning in Express System , 2020, CIKM.

[18]  Xike Xie,et al.  Large-Scale Intelligent Taxicab Scheduling: A Distributed and Future-Aware Approach , 2020, IEEE Transactions on Vehicular Technology.

[19]  Guilherme Fernandes,et al.  A realistic scooter rebalancing system via metaheuristics , 2020, GECCO Companion.

[20]  Kaishun Wu,et al.  Mobility-Aware Dynamic Taxi Ridesharing , 2020, 2020 IEEE 36th International Conference on Data Engineering (ICDE).

[21]  Yingcai Wu,et al.  Dynamic Public Resource Allocation Based on Human Mobility Prediction , 2020, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol..

[22]  Lei Chen,et al.  Last-Mile Delivery Made Practical: An Efficient Route Planning Framework with Theoretical Guarantees , 2019, Proc. VLDB Endow..

[23]  Yi Ding,et al.  Route Prediction for Instant Delivery , 2019, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol..

[24]  Qiang Yang,et al.  Efficient and Effective Express via Contextual Cooperative Reinforcement Learning , 2019, KDD.

[25]  Bin Guo,et al.  FooDNet: Toward an Optimized Food Delivery Network Based on Spatial Crowdsourcing , 2019, IEEE Transactions on Mobile Computing.

[26]  Tianrui Li,et al.  A Deep Reinforcement Learning-Enabled Dynamic Redeployment System for Mobile Ambulances , 2019, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol..

[27]  Deke Guo,et al.  Smart City-Wide Package Distribution Using Crowdsourced Public Transportation Systems , 2019, IEEE Internet of Things Journal.

[28]  Miguel A. Figliozzi,et al.  Maximum coverage capacitated facility location problem with range constrained drones , 2019, Transportation Research Part C: Emerging Technologies.

[29]  Fan Wu,et al.  DeepETA: A Spatial-Temporal Sequential Neural Network Model for Estimating Time of Arrival in Package Delivery System , 2019, AAAI.

[30]  Fan Zhang,et al.  bCharge: Data-Driven Real-Time Charging Scheduling for Large-Scale Electric Bus Fleets , 2018, 2018 IEEE Real-Time Systems Symposium (RTSS).

[31]  Guoming Tang,et al.  PPtaxi: Non-Stop Package Delivery via Multi-Hop Ridesharing , 2018, IEEE Transactions on Mobile Computing.

[32]  Daqing Zhang,et al.  CrowdExpress: A Probabilistic Framework for On-Time Crowdsourced Package Deliveries , 2018, IEEE Transactions on Big Data.

[33]  Daniel Aloise,et al.  Towards Station-Level Demand Prediction for Effective Rebalancing in Bike-Sharing Systems , 2018, KDD.

[34]  Jieping Ye,et al.  A Unified Approach to Route Planning for Shared Mobility , 2018, Proc. VLDB Endow..

[35]  Yanfeng Ouyang,et al.  Dynamic operations and pricing of electric unmanned aerial vehicle systems and power networks , 2018, Transportation Research Part C: Emerging Technologies.

[36]  Pin Lv,et al.  A Survey on Task and Participant Matching in Mobile Crowd Sensing , 2018, Journal of Computer Science and Technology.

[37]  Feng Wang,et al.  Ridesharing as a Service: Exploring Crowdsourced Connected Vehicle Information for Intelligent Package Delivery , 2018, 2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS).

[38]  T. He,et al.  BRAVO: Improving the Rebalancing Operation in Bike Sharing with Rebalancing Range Prediction , 2018, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol..

[39]  Max Welling,et al.  Attention, Learn to Solve Routing Problems! , 2018, ICLR.

[40]  Victor O. K. Li,et al.  Task Allocation in Spatial Crowdsourcing: Current State and Future Directions , 2018, IEEE Internet of Things Journal.

[41]  Cheng Li,et al.  Task Assignment in Mobile Crowdsensing: Present and Future Directions , 2018, IEEE Network.

[42]  Longbo Huang,et al.  A Deep Reinforcement Learning Framework for Rebalancing Dockless Bike Sharing Systems , 2018, AAAI.

[43]  Keld Helsgaun,et al.  An Extension of the Lin-Kernighan-Helsgaun TSP Solver for Constrained Traveling Salesman and Vehicle Routing Problems: Technical report , 2017 .

[44]  Daqing Zhang,et al.  crowddeliver: Planning City-Wide Package Delivery Paths Leveraging the Crowd of Taxis , 2017, IEEE Transactions on Intelligent Transportation Systems.

[45]  Samy Bengio,et al.  Neural Combinatorial Optimization with Reinforcement Learning , 2016, ICLR.

[46]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[47]  Yu Zheng,et al.  Effective and Efficient: Large-Scale Dynamic City Express , 2015, IEEE Transactions on Knowledge and Data Engineering.

[48]  Navdeep Jaitly,et al.  Pointer Networks , 2015, NIPS.

[49]  Eric Horvitz,et al.  Crowdphysics: Planned and Opportunistic Crowdsourcing for Physical Tasks , 2013, ICWSM.

[50]  Luca Bertazzi,et al.  Reoptimizing the traveling salesman problem , 2003, Networks.

[51]  Jianye Hao,et al.  A Hierarchical Reinforcement Learning Based Optimization Framework for Large-scale Dynamic Pickup and Delivery Problems , 2021, NeurIPS.

[52]  Washington Y. Ochieng,et al.  Optimal hub selection for rapid medical deliveries using unmanned aerial vehicles , 2020 .

[53]  Oriol Vinyals,et al.  Order Matters: Sequence to sequence for sets , 2016, ICLR 2016.