A learning model for personalized adaptive cruise control

Xin Chen; Yong Zhai; Chao Lu; Jianwei Gong; Gang Wang

doi:10.1109/IVS.2017.7995748

A learning model for personalized adaptive cruise control

Xin Chen, Yong Zhai, Chao Lu, Jianwei Gong, Gang Wang

School of Mechanical Engineering

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

33 Citations (Scopus)

Abstract

This paper develops a learning model for personalized adaptive cruise control that can learn from human demonstration online and mimic a human driver's driving strategies in the dynamic traffic environment. Under the framework of the proposed model, reinforcement learning is used to capture the human-desired driving strategy, and the proportion-integration-differentiation controller is adopted to convert the learning strategy to low-level control commands. The performance of the learning model is tested in the simulation environment built in a driving simulator using PreScan. Experimental results show that the learning model can duplicate human driving strategies with acceptable errors. Moreover, compared with the traditional adaptive cruise control, the proposed model can provide better driving comfort and smoothness in the dynamic situation.

Original language	English
Title of host publication	IV 2017 - 28th IEEE Intelligent Vehicles Symposium
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	379-384
Number of pages	6
ISBN (Electronic)	9781509048045
DOIs	https://doi.org/10.1109/IVS.2017.7995748
Publication status	Published - 28 Jul 2017
Event	28th IEEE Intelligent Vehicles Symposium, IV 2017 - Redondo Beach, United States Duration: 11 Jun 2017 → 14 Jun 2017

Publication series

Name	IEEE Intelligent Vehicles Symposium, Proceedings

Conference

Conference	28th IEEE Intelligent Vehicles Symposium, IV 2017
Country/Territory	United States
City	Redondo Beach
Period	11/06/17 → 14/06/17

Access to Document

10.1109/IVS.2017.7995748

Cite this

Chen, X., Zhai, Y., Lu, C., Gong, J., & Wang, G. (2017). A learning model for personalized adaptive cruise control. In IV 2017 - 28th IEEE Intelligent Vehicles Symposium (pp. 379-384). Article 7995748 (IEEE Intelligent Vehicles Symposium, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IVS.2017.7995748

@inproceedings{48fda6736e524d8ba087ccb90a38ffa0,

title = "A learning model for personalized adaptive cruise control",

abstract = "This paper develops a learning model for personalized adaptive cruise control that can learn from human demonstration online and mimic a human driver's driving strategies in the dynamic traffic environment. Under the framework of the proposed model, reinforcement learning is used to capture the human-desired driving strategy, and the proportion-integration-differentiation controller is adopted to convert the learning strategy to low-level control commands. The performance of the learning model is tested in the simulation environment built in a driving simulator using PreScan. Experimental results show that the learning model can duplicate human driving strategies with acceptable errors. Moreover, compared with the traditional adaptive cruise control, the proposed model can provide better driving comfort and smoothness in the dynamic situation.",

author = "Xin Chen and Yong Zhai and Chao Lu and Jianwei Gong and Gang Wang",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 28th IEEE Intelligent Vehicles Symposium, IV 2017 ; Conference date: 11-06-2017 Through 14-06-2017",

year = "2017",

month = jul,

day = "28",

doi = "10.1109/IVS.2017.7995748",

language = "English",

series = "IEEE Intelligent Vehicles Symposium, Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "379--384",

booktitle = "IV 2017 - 28th IEEE Intelligent Vehicles Symposium",

address = "United States",

}

Chen, X, Zhai, Y, Lu, C, Gong, J & Wang, G 2017, A learning model for personalized adaptive cruise control. in IV 2017 - 28th IEEE Intelligent Vehicles Symposium., 7995748, IEEE Intelligent Vehicles Symposium, Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 379-384, 28th IEEE Intelligent Vehicles Symposium, IV 2017, Redondo Beach, United States, 11/06/17. https://doi.org/10.1109/IVS.2017.7995748

A learning model for personalized adaptive cruise control. / Chen, Xin; Zhai, Yong; Lu, Chao et al.
IV 2017 - 28th IEEE Intelligent Vehicles Symposium. Institute of Electrical and Electronics Engineers Inc., 2017. p. 379-384 7995748 (IEEE Intelligent Vehicles Symposium, Proceedings).

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

TY - GEN

T1 - A learning model for personalized adaptive cruise control

AU - Chen, Xin

AU - Zhai, Yong

AU - Lu, Chao

AU - Gong, Jianwei

AU - Wang, Gang

PY - 2017/7/28

Y1 - 2017/7/28

N2 - This paper develops a learning model for personalized adaptive cruise control that can learn from human demonstration online and mimic a human driver's driving strategies in the dynamic traffic environment. Under the framework of the proposed model, reinforcement learning is used to capture the human-desired driving strategy, and the proportion-integration-differentiation controller is adopted to convert the learning strategy to low-level control commands. The performance of the learning model is tested in the simulation environment built in a driving simulator using PreScan. Experimental results show that the learning model can duplicate human driving strategies with acceptable errors. Moreover, compared with the traditional adaptive cruise control, the proposed model can provide better driving comfort and smoothness in the dynamic situation.

AB - This paper develops a learning model for personalized adaptive cruise control that can learn from human demonstration online and mimic a human driver's driving strategies in the dynamic traffic environment. Under the framework of the proposed model, reinforcement learning is used to capture the human-desired driving strategy, and the proportion-integration-differentiation controller is adopted to convert the learning strategy to low-level control commands. The performance of the learning model is tested in the simulation environment built in a driving simulator using PreScan. Experimental results show that the learning model can duplicate human driving strategies with acceptable errors. Moreover, compared with the traditional adaptive cruise control, the proposed model can provide better driving comfort and smoothness in the dynamic situation.

UR - http://www.scopus.com/inward/record.url?scp=85028054739&partnerID=8YFLogxK

U2 - 10.1109/IVS.2017.7995748

DO - 10.1109/IVS.2017.7995748

M3 - Conference contribution

AN - SCOPUS:85028054739

T3 - IEEE Intelligent Vehicles Symposium, Proceedings

SP - 379

EP - 384

BT - IV 2017 - 28th IEEE Intelligent Vehicles Symposium

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 28th IEEE Intelligent Vehicles Symposium, IV 2017

Y2 - 11 June 2017 through 14 June 2017

ER -

A learning model for personalized adaptive cruise control

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this