Anti Intelligent Mine Unmanned Ground Vehicle Based on Reinforcement Learning

Xiaoyao Tong; Yuxi Ma; Yuan Xue; Quanxin Zhang; Yuanzhang Li; Yu an Tan

doi:10.1007/978-981-16-7502-7_7

Anti Intelligent Mine Unmanned Ground Vehicle Based on Reinforcement Learning

Xiaoyao Tong, Yuxi Ma, Yuan Xue^*, Quanxin Zhang, Yuanzhang Li, Yu an Tan

^*Corresponding author for this work

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

Abstract

In recent years, with the rapid development of military technology and the evolution of battlefield mines, intelligent mines are the important embodiment of active attack mines. In the future, unmanned vehicles need to chase and capture intelligent mines, improve the efficiency of mine clearance, and reduce the casualties of soldiers. Therefore, it is necessary to study how to improve the efficiency of unmanned ground vehicle pursuit. Among them, the game method of pursuit and evasion between intelligent mines and unmanned ground vehicles based on reinforcement learning in the 2D simulation environment can effectively achieve this goal. The trained intelligent mines have active attack ability, unmanned ground vehicles have basic mine clearance ability, and the success rate of intelligent mine blasting is as high as 90%. In addition, unmanned ground vehicles can also effectively defend against the active attack of intelligent mines, and the defense success rate is also as high as 90%.

Original language	English
Title of host publication	Data Mining and Big Data - 6th International Conference, DMBD 2021, Proceedings
Editors	Ying Tan, Yuhui Shi, Albert Zomaya, Hongyang Yan, Jun Cai
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	61-68
Number of pages	8
ISBN (Print)	9789811675010
DOIs	https://doi.org/10.1007/978-981-16-7502-7_7
Publication status	Published - 2021
Event	6th International Conference on Data Mining and Big Data, DMBD 2021 - Guangzhou, China Duration: 20 Oct 2021 → 22 Oct 2021

Publication series

Name	Communications in Computer and Information Science
Volume	1454 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	6th International Conference on Data Mining and Big Data, DMBD 2021
Country/Territory	China
City	Guangzhou
Period	20/10/21 → 22/10/21

Keywords

Intelligent mine
Reinforcement learning
Unmanned vehicle

Access to Document

10.1007/978-981-16-7502-7_7

Cite this

Tong, X., Ma, Y., Xue, Y., Zhang, Q., Li, Y., & Tan, Y. A. (2021). Anti Intelligent Mine Unmanned Ground Vehicle Based on Reinforcement Learning. In Y. Tan, Y. Shi, A. Zomaya, H. Yan, & J. Cai (Eds.), Data Mining and Big Data - 6th International Conference, DMBD 2021, Proceedings (pp. 61-68). (Communications in Computer and Information Science; Vol. 1454 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-16-7502-7_7

Tong, Xiaoyao ; Ma, Yuxi ; Xue, Yuan et al. / Anti Intelligent Mine Unmanned Ground Vehicle Based on Reinforcement Learning. Data Mining and Big Data - 6th International Conference, DMBD 2021, Proceedings. editor / Ying Tan ; Yuhui Shi ; Albert Zomaya ; Hongyang Yan ; Jun Cai. Springer Science and Business Media Deutschland GmbH, 2021. pp. 61-68 (Communications in Computer and Information Science).

@inproceedings{0104debe976b4ed5942acccde48c4aac,

title = "Anti Intelligent Mine Unmanned Ground Vehicle Based on Reinforcement Learning",

abstract = "In recent years, with the rapid development of military technology and the evolution of battlefield mines, intelligent mines are the important embodiment of active attack mines. In the future, unmanned vehicles need to chase and capture intelligent mines, improve the efficiency of mine clearance, and reduce the casualties of soldiers. Therefore, it is necessary to study how to improve the efficiency of unmanned ground vehicle pursuit. Among them, the game method of pursuit and evasion between intelligent mines and unmanned ground vehicles based on reinforcement learning in the 2D simulation environment can effectively achieve this goal. The trained intelligent mines have active attack ability, unmanned ground vehicles have basic mine clearance ability, and the success rate of intelligent mine blasting is as high as 90%. In addition, unmanned ground vehicles can also effectively defend against the active attack of intelligent mines, and the defense success rate is also as high as 90%.",

keywords = "Intelligent mine, Reinforcement learning, Unmanned vehicle",

author = "Xiaoyao Tong and Yuxi Ma and Yuan Xue and Quanxin Zhang and Yuanzhang Li and Tan, {Yu an}",

note = "Publisher Copyright: {\textcopyright} 2021, Springer Nature Singapore Pte Ltd.; 6th International Conference on Data Mining and Big Data, DMBD 2021 ; Conference date: 20-10-2021 Through 22-10-2021",

year = "2021",

doi = "10.1007/978-981-16-7502-7_7",

language = "English",

isbn = "9789811675010",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "61--68",

editor = "Ying Tan and Yuhui Shi and Albert Zomaya and Hongyang Yan and Jun Cai",

booktitle = "Data Mining and Big Data - 6th International Conference, DMBD 2021, Proceedings",

address = "Germany",

}

Tong, X, Ma, Y, Xue, Y, Zhang, Q , Li, Y & Tan, YA 2021, Anti Intelligent Mine Unmanned Ground Vehicle Based on Reinforcement Learning. in Y Tan, Y Shi, A Zomaya, H Yan & J Cai (eds), Data Mining and Big Data - 6th International Conference, DMBD 2021, Proceedings. Communications in Computer and Information Science, vol. 1454 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 61-68, 6th International Conference on Data Mining and Big Data, DMBD 2021, Guangzhou, China, 20/10/21. https://doi.org/10.1007/978-981-16-7502-7_7

Anti Intelligent Mine Unmanned Ground Vehicle Based on Reinforcement Learning. / Tong, Xiaoyao; Ma, Yuxi; Xue, Yuan et al.
Data Mining and Big Data - 6th International Conference, DMBD 2021, Proceedings. ed. / Ying Tan; Yuhui Shi; Albert Zomaya; Hongyang Yan; Jun Cai. Springer Science and Business Media Deutschland GmbH, 2021. p. 61-68 (Communications in Computer and Information Science; Vol. 1454 CCIS).

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

TY - GEN

T1 - Anti Intelligent Mine Unmanned Ground Vehicle Based on Reinforcement Learning

AU - Tong, Xiaoyao

AU - Ma, Yuxi

AU - Xue, Yuan

AU - Zhang, Quanxin

AU - Li, Yuanzhang

AU - Tan, Yu an

PY - 2021

Y1 - 2021

N2 - In recent years, with the rapid development of military technology and the evolution of battlefield mines, intelligent mines are the important embodiment of active attack mines. In the future, unmanned vehicles need to chase and capture intelligent mines, improve the efficiency of mine clearance, and reduce the casualties of soldiers. Therefore, it is necessary to study how to improve the efficiency of unmanned ground vehicle pursuit. Among them, the game method of pursuit and evasion between intelligent mines and unmanned ground vehicles based on reinforcement learning in the 2D simulation environment can effectively achieve this goal. The trained intelligent mines have active attack ability, unmanned ground vehicles have basic mine clearance ability, and the success rate of intelligent mine blasting is as high as 90%. In addition, unmanned ground vehicles can also effectively defend against the active attack of intelligent mines, and the defense success rate is also as high as 90%.

AB - In recent years, with the rapid development of military technology and the evolution of battlefield mines, intelligent mines are the important embodiment of active attack mines. In the future, unmanned vehicles need to chase and capture intelligent mines, improve the efficiency of mine clearance, and reduce the casualties of soldiers. Therefore, it is necessary to study how to improve the efficiency of unmanned ground vehicle pursuit. Among them, the game method of pursuit and evasion between intelligent mines and unmanned ground vehicles based on reinforcement learning in the 2D simulation environment can effectively achieve this goal. The trained intelligent mines have active attack ability, unmanned ground vehicles have basic mine clearance ability, and the success rate of intelligent mine blasting is as high as 90%. In addition, unmanned ground vehicles can also effectively defend against the active attack of intelligent mines, and the defense success rate is also as high as 90%.

KW - Intelligent mine

KW - Reinforcement learning

KW - Unmanned vehicle

UR - http://www.scopus.com/inward/record.url?scp=85119626906&partnerID=8YFLogxK

U2 - 10.1007/978-981-16-7502-7_7

DO - 10.1007/978-981-16-7502-7_7

M3 - Conference contribution

AN - SCOPUS:85119626906

SN - 9789811675010

T3 - Communications in Computer and Information Science

SP - 61

EP - 68

BT - Data Mining and Big Data - 6th International Conference, DMBD 2021, Proceedings

A2 - Tan, Ying

A2 - Shi, Yuhui

A2 - Zomaya, Albert

A2 - Yan, Hongyang

A2 - Cai, Jun

PB - Springer Science and Business Media Deutschland GmbH

T2 - 6th International Conference on Data Mining and Big Data, DMBD 2021

Y2 - 20 October 2021 through 22 October 2021

ER -

Tong X, Ma Y, Xue Y, Zhang Q , Li Y , Tan YA. Anti Intelligent Mine Unmanned Ground Vehicle Based on Reinforcement Learning. In Tan Y, Shi Y, Zomaya A, Yan H, Cai J, editors, Data Mining and Big Data - 6th International Conference, DMBD 2021, Proceedings. Springer Science and Business Media Deutschland GmbH. 2021. p. 61-68. (Communications in Computer and Information Science). doi: 10.1007/978-981-16-7502-7_7

Anti Intelligent Mine Unmanned Ground Vehicle Based on Reinforcement Learning

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this