Cited time in webofscience Cited time in scopus

A City-Wide Crowdsourcing Delivery System with Reinforcement Learning

A City-Wide Crowdsourcing Delivery System with Reinforcement Learning
Ding, YiGuo, BaoshenZheng, LinLu, MingmingZhang, DeshengWang, ShuaiSon, Sang HyukHe, Tian
Issued Date
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, v.5, no.3, pp.1 - 22
Author Keywords
Crowdsourced LaborCrowdsourcingReinforcement LearningSharing Economy
CrowdsourcingDecision makingLearning systemsProfitabilityDispatching problemOptimal order dispatchingPackage deliveryPublic transportationReinforcement learning modelsSequential decision makingTime constraintsUbiquitous computing infrastructureLearning algorithmsReinforcement learningUbiquitous computing
The revolution of online shopping in recent years demands corresponding evolution in delivery services in urban areas. To cater to this trend, delivery by the crowd has become an alternative to the traditional delivery services thanks to the advances in ubiquitous computing. Notably, some studies use public transportation for crowdsourcing delivery, given its low-cost delivery network with millions of passengers as potential couriers. However, multiple practical impact factors are not considered in existing public-transport-based crowdsourcing delivery studies due to a lack of data and limited ubiquitous computing infrastructures in the past. In this work, we design a crowdsourcing delivery system based on public transport, considering the practical factors of time constraints, multi-hop delivery, and profits. To incorporate the impact factors, we build a reinforcement learning model to learn the optimal order dispatching strategies from massive passenger data and package data. The order dispatching problem is formulated as a sequential decision making problem for the packages routing, i.e., select the next station for the package. A delivery time estimation module is designed to accelerate the training process and provide statistical delivery time guarantee. Three months of real-world public transportation data and one month of package delivery data from an on-demand delivery platform in Shenzhen are used in the evaluation. Compared with existing crowdsourcing delivery algorithms and widely used baselines, we achieve a 40% increase in profit rates and a 29% increase in delivery rates. Comparison with other reinforcement learning algorithms shows that we can improve the profit rate and the delivery rate by 9% and 8% by using time estimation in action filtering. We share the data used in the project to the community for other researchers to validate our results and conduct further research.1 [1]. © 2021 ACM.
Association for Computing Machinery (ACM)
Related Researcher
  • 손상혁 Son, Sang Hyuk 정보통신융합전공
  • Research Interests Real-time system; Wireless sensor network; Cyber-physical system; Data and event service; Information security; 실시간 임베디드 시스템
Files in This Item:

There are no files associated with this item.

Appears in Collections:
Department of Electrical Engineering and Computer Science RTCPS(Real-Time Cyber-Physical Systems) Lab 1. Journal Articles


  • twitter
  • facebook
  • mendeley

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.