The Dynamic Drone Scheduling Delivery Problem

Giovanni Campuzano; Eduardo Lalla-Ruiz; Martijn Mes

doi:10.1007/978-3-031-16579-5_18

The Dynamic Drone Scheduling Delivery Problem

Giovanni Campuzano^*, Eduardo Lalla-Ruiz, Martijn Mes

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Logistics plays an important role in today’s last-mile economy. Therefore, companies constantly seek for improving their delivery system towards more efficient and sustainable management of parcel distribution. In this paper, we study the Dynamic Drone Scheduling Delivery Problem. The objective is to minimize the delayed deliveries by a fleet of drones located in a central drone station, taking into account the uncertain arrival of parcels, soft time windows, and energy requirements. We develop a Markov Decision Processes (MDP) formulation and solve it approximately by implementing a value-based Reinforcement Learning (RL) approach. We compare our approach with several heuristic dispatching policies and provide insights into the efficiency of our RL algorithm when facing different delivery scenarios.

Original language	English
Title of host publication	Computational Logistics - 13th International Conference, ICCL 2022, Proceedings
Editors	Jesica de Armas, Helena Ramalhinho, Stefan Voß
Place of Publication	Cham
Publisher	Springer Science + Business Media
Pages	260-274
Number of pages	15
ISBN (Electronic)	978-3-031-16579-5
ISBN (Print)	978-3-031-16578-8
DOIs	https://doi.org/10.1007/978-3-031-16579-5_18
Publication status	Published - 14 Sep 2022
Event	13th International Conference on Computational Logistics, ICCL 2022 - Barcelona, Spain Duration: 21 Sep 2022 → 23 Sep 2022 Conference number: 13

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	13557
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	13th International Conference on Computational Logistics, ICCL 2022
Abbreviated title	ICCL 2022
Country/Territory	Spain
City	Barcelona
Period	21/09/22 → 23/09/22

Keywords

Battery charging
Drone scheduling
Last mile
Reinforcement learning
UAV
22/4 OA procedure

Access to Document

10.1007/978-3-031-16579-5_18

ArticleFinal published version, 488 KBLicence: Taverne

Cite this

@inproceedings{58fdc33575914a7889ecbeb5989b67f4,

title = "The Dynamic Drone Scheduling Delivery Problem",

abstract = "Logistics plays an important role in today{\textquoteright}s last-mile economy. Therefore, companies constantly seek for improving their delivery system towards more efficient and sustainable management of parcel distribution. In this paper, we study the Dynamic Drone Scheduling Delivery Problem. The objective is to minimize the delayed deliveries by a fleet of drones located in a central drone station, taking into account the uncertain arrival of parcels, soft time windows, and energy requirements. We develop a Markov Decision Processes (MDP) formulation and solve it approximately by implementing a value-based Reinforcement Learning (RL) approach. We compare our approach with several heuristic dispatching policies and provide insights into the efficiency of our RL algorithm when facing different delivery scenarios.",

keywords = "Battery charging, Drone scheduling, Last mile, Reinforcement learning, UAV, 22/4 OA procedure",

author = "Giovanni Campuzano and Eduardo Lalla-Ruiz and Martijn Mes",

note = "Funding Information: This work was funded by the Chilean National Agency for Research and Development (ANID)/Scholarship Program/DOCTORADO BECAS CHILE/2019-72200288. Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 13th International Conference on Computational Logistics, ICCL 2022, ICCL 2022 ; Conference date: 21-09-2022 Through 23-09-2022",

year = "2022",

month = sep,

day = "14",

doi = "10.1007/978-3-031-16579-5_18",

language = "English",

isbn = "978-3-031-16578-8",

series = "Lecture Notes in Computer Science",

publisher = "Springer Science + Business Media",

pages = "260--274",

editor = "{de Armas}, Jesica and Helena Ramalhinho and Stefan Vo{\ss}",

booktitle = "Computational Logistics - 13th International Conference, ICCL 2022, Proceedings",

address = "United States",

}

Campuzano, G, Lalla-Ruiz, E & Mes, M 2022, The Dynamic Drone Scheduling Delivery Problem. in J de Armas, H Ramalhinho & S Voß (eds), Computational Logistics - 13th International Conference, ICCL 2022, Proceedings. Lecture Notes in Computer Science, vol. 13557, Springer Science + Business Media, Cham, pp. 260-274, 13th International Conference on Computational Logistics, ICCL 2022, Barcelona, Spain, 21/09/22. https://doi.org/10.1007/978-3-031-16579-5_18

The Dynamic Drone Scheduling Delivery Problem. / Campuzano, Giovanni; Lalla-Ruiz, Eduardo ; Mes, Martijn.

Computational Logistics - 13th International Conference, ICCL 2022, Proceedings. ed. / Jesica de Armas; Helena Ramalhinho; Stefan Voß. Cham : Springer Science + Business Media, 2022. p. 260-274 (Lecture Notes in Computer Science; Vol. 13557).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - The Dynamic Drone Scheduling Delivery Problem

AU - Campuzano, Giovanni

AU - Lalla-Ruiz, Eduardo

AU - Mes, Martijn

N1 - Conference code: 13

PY - 2022/9/14

Y1 - 2022/9/14

N2 - Logistics plays an important role in today’s last-mile economy. Therefore, companies constantly seek for improving their delivery system towards more efficient and sustainable management of parcel distribution. In this paper, we study the Dynamic Drone Scheduling Delivery Problem. The objective is to minimize the delayed deliveries by a fleet of drones located in a central drone station, taking into account the uncertain arrival of parcels, soft time windows, and energy requirements. We develop a Markov Decision Processes (MDP) formulation and solve it approximately by implementing a value-based Reinforcement Learning (RL) approach. We compare our approach with several heuristic dispatching policies and provide insights into the efficiency of our RL algorithm when facing different delivery scenarios.

AB - Logistics plays an important role in today’s last-mile economy. Therefore, companies constantly seek for improving their delivery system towards more efficient and sustainable management of parcel distribution. In this paper, we study the Dynamic Drone Scheduling Delivery Problem. The objective is to minimize the delayed deliveries by a fleet of drones located in a central drone station, taking into account the uncertain arrival of parcels, soft time windows, and energy requirements. We develop a Markov Decision Processes (MDP) formulation and solve it approximately by implementing a value-based Reinforcement Learning (RL) approach. We compare our approach with several heuristic dispatching policies and provide insights into the efficiency of our RL algorithm when facing different delivery scenarios.

KW - Battery charging

KW - Drone scheduling

KW - Last mile

KW - Reinforcement learning

KW - UAV

KW - 22/4 OA procedure

UR - http://www.scopus.com/inward/record.url?scp=85138802985&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-16579-5_18

DO - 10.1007/978-3-031-16579-5_18

M3 - Conference contribution

AN - SCOPUS:85138802985

SN - 978-3-031-16578-8

T3 - Lecture Notes in Computer Science

SP - 260

EP - 274

BT - Computational Logistics - 13th International Conference, ICCL 2022, Proceedings

A2 - de Armas, Jesica

A2 - Ramalhinho, Helena

A2 - Voß, Stefan

PB - Springer Science + Business Media

CY - Cham

T2 - 13th International Conference on Computational Logistics, ICCL 2022

Y2 - 21 September 2022 through 23 September 2022

ER -

The Dynamic Drone Scheduling Delivery Problem

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this