Learning-based logistics planning and scheduling for crowdsourced parcel delivery

Yuncheol Kang, Seok Gi Lee, Byung Do Chung

Research output: Contribution to journalArticle

Abstract

Today many domains have begun dealing with more complex and practical problems thanks to advances in artificial intelligence. In this paper, we study the crowdsourced parcel delivery problem, a new type of transportation, with consideration of complex and practical cases, such as multiple delivery vehicles, just-in-time (JIT)pickup and delivery, minimum fuel consumption, and maximum profitability. For this we suggest a learning-based logistics planning and scheduling (LLPS)algorithm that controls admission of order requests and schedules the routes of multiple vehicles altogether. For the admission control, we utilize reinforcement learning (RL)with a function approximation using an artificial neural network (ANN). Also, we use a continuous-variable feedback control algorithm to schedule routes that minimize both JIT penalty and fuel consumption. Computational experiments show that the LLPS outperforms other similar approaches by 32% on average in terms of average reward earned from each delivery order. In addition, the LLPS is even more advantageous when the rate of order arrivals is high and the number of vehicles that transport parcels is low.

Original languageEnglish (US)
Pages (from-to)271-279
Number of pages9
JournalComputers and Industrial Engineering
Volume132
DOIs
StatePublished - Jun 1 2019

Fingerprint

Logistics
Scheduling
Access control
Planning
Fuel consumption
Pickups
Reinforcement learning
Scheduling algorithms
Feedback control
Artificial intelligence
Profitability
Neural networks
Experiments

Keywords

  • Admission control
  • Continuous feedback variable control
  • Crowdsourced parcel delivery
  • On-demand delivery service
  • Reinforcement learning

ASJC Scopus subject areas

  • Computer Science(all)
  • Engineering(all)

Cite this

Learning-based logistics planning and scheduling for crowdsourced parcel delivery. / Kang, Yuncheol; Lee, Seok Gi; Chung, Byung Do.

In: Computers and Industrial Engineering, Vol. 132, 01.06.2019, p. 271-279.

Research output: Contribution to journalArticle

@article{d87ce21f79cc45308571540e698f199d,
title = "Learning-based logistics planning and scheduling for crowdsourced parcel delivery",
abstract = "Today many domains have begun dealing with more complex and practical problems thanks to advances in artificial intelligence. In this paper, we study the crowdsourced parcel delivery problem, a new type of transportation, with consideration of complex and practical cases, such as multiple delivery vehicles, just-in-time (JIT)pickup and delivery, minimum fuel consumption, and maximum profitability. For this we suggest a learning-based logistics planning and scheduling (LLPS)algorithm that controls admission of order requests and schedules the routes of multiple vehicles altogether. For the admission control, we utilize reinforcement learning (RL)with a function approximation using an artificial neural network (ANN). Also, we use a continuous-variable feedback control algorithm to schedule routes that minimize both JIT penalty and fuel consumption. Computational experiments show that the LLPS outperforms other similar approaches by 32{\%} on average in terms of average reward earned from each delivery order. In addition, the LLPS is even more advantageous when the rate of order arrivals is high and the number of vehicles that transport parcels is low.",
keywords = "Admission control, Continuous feedback variable control, Crowdsourced parcel delivery, On-demand delivery service, Reinforcement learning",
author = "Yuncheol Kang and Lee, {Seok Gi} and Chung, {Byung Do}",
year = "2019",
month = "6",
day = "1",
doi = "10.1016/j.cie.2019.04.044",
language = "English (US)",
volume = "132",
pages = "271--279",
journal = "Computers and Industrial Engineering",
issn = "0360-8352",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Learning-based logistics planning and scheduling for crowdsourced parcel delivery

AU - Kang, Yuncheol

AU - Lee, Seok Gi

AU - Chung, Byung Do

PY - 2019/6/1

Y1 - 2019/6/1

N2 - Today many domains have begun dealing with more complex and practical problems thanks to advances in artificial intelligence. In this paper, we study the crowdsourced parcel delivery problem, a new type of transportation, with consideration of complex and practical cases, such as multiple delivery vehicles, just-in-time (JIT)pickup and delivery, minimum fuel consumption, and maximum profitability. For this we suggest a learning-based logistics planning and scheduling (LLPS)algorithm that controls admission of order requests and schedules the routes of multiple vehicles altogether. For the admission control, we utilize reinforcement learning (RL)with a function approximation using an artificial neural network (ANN). Also, we use a continuous-variable feedback control algorithm to schedule routes that minimize both JIT penalty and fuel consumption. Computational experiments show that the LLPS outperforms other similar approaches by 32% on average in terms of average reward earned from each delivery order. In addition, the LLPS is even more advantageous when the rate of order arrivals is high and the number of vehicles that transport parcels is low.

AB - Today many domains have begun dealing with more complex and practical problems thanks to advances in artificial intelligence. In this paper, we study the crowdsourced parcel delivery problem, a new type of transportation, with consideration of complex and practical cases, such as multiple delivery vehicles, just-in-time (JIT)pickup and delivery, minimum fuel consumption, and maximum profitability. For this we suggest a learning-based logistics planning and scheduling (LLPS)algorithm that controls admission of order requests and schedules the routes of multiple vehicles altogether. For the admission control, we utilize reinforcement learning (RL)with a function approximation using an artificial neural network (ANN). Also, we use a continuous-variable feedback control algorithm to schedule routes that minimize both JIT penalty and fuel consumption. Computational experiments show that the LLPS outperforms other similar approaches by 32% on average in terms of average reward earned from each delivery order. In addition, the LLPS is even more advantageous when the rate of order arrivals is high and the number of vehicles that transport parcels is low.

KW - Admission control

KW - Continuous feedback variable control

KW - Crowdsourced parcel delivery

KW - On-demand delivery service

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=85064740895&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064740895&partnerID=8YFLogxK

U2 - 10.1016/j.cie.2019.04.044

DO - 10.1016/j.cie.2019.04.044

M3 - Article

AN - SCOPUS:85064740895

VL - 132

SP - 271

EP - 279

JO - Computers and Industrial Engineering

JF - Computers and Industrial Engineering

SN - 0360-8352

ER -