Belief state planning for autonomously navigating urban intersections

Maxime Bouton; Akansel Cosgun; Mykel J. Kochenderfer

doi:10.1109/IVS.2017.7995818

Belief state planning for autonomously navigating urban intersections

Maxime Bouton, Akansel Cosgun, Mykel J. Kochenderfer

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

75 Citations (Scopus)

Abstract

Urban intersections represent a complex environment for autonomous vehicles with many sources of uncertainty. The vehicle must plan in a stochastic environment with potentially rapid changes in driver behavior. Providing an efficient strategy to navigate through urban intersections is a difficult task. This paper frames the problem of navigating unsignalized intersections as a partially observable Markov decision process (POMDP) and solves it using a Monte Carlo sampling method. Empirical results in simulation show that the resulting policy outperforms a threshold-based heuristic strategy on several relevant metrics that measure both safety and efficiency.

Original language	English
Title of host publication	2017 IEEE Intelligent Vehicles Symposium (IV 2017)
Editors	Wei-Bin Zhang, Arnaud de La Fortelle, Tankut Acarman, Ming Yang
Place of Publication	Piscataway NJ USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	825-830
Number of pages	6
ISBN (Electronic)	9781509048045, 9781509048038
ISBN (Print)	9781509048052
DOIs	https://doi.org/10.1109/IVS.2017.7995818
Publication status	Published - 28 Jul 2017
Externally published	Yes
Event	Intelligent Vehicles Symposium 2017 - Redondo Beach, United States of America Duration: 11 Jun 2017 → 14 Jun 2017 Conference number: 28th http://iv2017.org/ https://ieeexplore.ieee.org/xpl/conhome/7987634/proceeding (Proceedings)

Conference

Conference	Intelligent Vehicles Symposium 2017
Abbreviated title	IEEE IV 2017
Country/Territory	United States of America
City	Redondo Beach
Period	11/06/17 → 14/06/17
Internet address	http://iv2017.org/ https://ieeexplore.ieee.org/xpl/conhome/7987634/proceeding (Proceedings)

Access to Document

10.1109/IVS.2017.7995818

Cite this

@inproceedings{89692c8da32640d7a2317117a6033b5b,

title = "Belief state planning for autonomously navigating urban intersections",

abstract = "Urban intersections represent a complex environment for autonomous vehicles with many sources of uncertainty. The vehicle must plan in a stochastic environment with potentially rapid changes in driver behavior. Providing an efficient strategy to navigate through urban intersections is a difficult task. This paper frames the problem of navigating unsignalized intersections as a partially observable Markov decision process (POMDP) and solves it using a Monte Carlo sampling method. Empirical results in simulation show that the resulting policy outperforms a threshold-based heuristic strategy on several relevant metrics that measure both safety and efficiency.",

author = "Maxime Bouton and Akansel Cosgun and Kochenderfer, \{Mykel J.\}",

year = "2017",

month = jul,

day = "28",

doi = "10.1109/IVS.2017.7995818",

language = "English",

isbn = "9781509048052",

pages = "825--830",

editor = "Wei-Bin Zhang and \{de La Fortelle\}, Arnaud and Tankut Acarman and Ming Yang",

booktitle = "2017 IEEE Intelligent Vehicles Symposium (IV 2017)",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

note = "Intelligent Vehicles Symposium 2017, IEEE IV 2017 ; Conference date: 11-06-2017 Through 14-06-2017",

url = "http://iv2017.org/, https://ieeexplore.ieee.org/xpl/conhome/7987634/proceeding",

}

Bouton, M, Cosgun, A & Kochenderfer, MJ 2017, Belief state planning for autonomously navigating urban intersections. in W-B Zhang, A de La Fortelle, T Acarman & M Yang (eds), 2017 IEEE Intelligent Vehicles Symposium (IV 2017). IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 825-830, Intelligent Vehicles Symposium 2017, Redondo Beach, California, United States of America, 11/06/17. https://doi.org/10.1109/IVS.2017.7995818

Belief state planning for autonomously navigating urban intersections. / Bouton, Maxime; Cosgun, Akansel; Kochenderfer, Mykel J.
2017 IEEE Intelligent Vehicles Symposium (IV 2017). ed. / Wei-Bin Zhang; Arnaud de La Fortelle; Tankut Acarman; Ming Yang. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers, 2017. p. 825-830.

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

TY - GEN

T1 - Belief state planning for autonomously navigating urban intersections

AU - Bouton, Maxime

AU - Cosgun, Akansel

AU - Kochenderfer, Mykel J.

N1 - Conference code: 28th

PY - 2017/7/28

Y1 - 2017/7/28

N2 - Urban intersections represent a complex environment for autonomous vehicles with many sources of uncertainty. The vehicle must plan in a stochastic environment with potentially rapid changes in driver behavior. Providing an efficient strategy to navigate through urban intersections is a difficult task. This paper frames the problem of navigating unsignalized intersections as a partially observable Markov decision process (POMDP) and solves it using a Monte Carlo sampling method. Empirical results in simulation show that the resulting policy outperforms a threshold-based heuristic strategy on several relevant metrics that measure both safety and efficiency.

AB - Urban intersections represent a complex environment for autonomous vehicles with many sources of uncertainty. The vehicle must plan in a stochastic environment with potentially rapid changes in driver behavior. Providing an efficient strategy to navigate through urban intersections is a difficult task. This paper frames the problem of navigating unsignalized intersections as a partially observable Markov decision process (POMDP) and solves it using a Monte Carlo sampling method. Empirical results in simulation show that the resulting policy outperforms a threshold-based heuristic strategy on several relevant metrics that measure both safety and efficiency.

UR - http://www.scopus.com/inward/record.url?scp=85028029272&partnerID=8YFLogxK

U2 - 10.1109/IVS.2017.7995818

DO - 10.1109/IVS.2017.7995818

M3 - Conference Paper

AN - SCOPUS:85028029272

SN - 9781509048052

SP - 825

EP - 830

BT - 2017 IEEE Intelligent Vehicles Symposium (IV 2017)

A2 - Zhang, Wei-Bin

A2 - de La Fortelle, Arnaud

A2 - Acarman, Tankut

A2 - Yang, Ming

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

T2 - Intelligent Vehicles Symposium 2017

Y2 - 11 June 2017 through 14 June 2017

ER -

Belief state planning for autonomously navigating urban intersections

Abstract

Conference

Access to Document

Other files and links

Cite this