Belief state planning for autonomously navigating urban intersections

Maxime Bouton, Akansel Cosgun, Mykel J. Kochenderfer

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

61 Citations (Scopus)


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 languageEnglish
Title of host publication2017 IEEE Intelligent Vehicles Symposium (IV 2017)
EditorsWei-Bin Zhang, Arnaud de La Fortelle, Tankut Acarman, Ming Yang
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages6
ISBN (Electronic)9781509048045, 9781509048038
ISBN (Print)9781509048052
Publication statusPublished - 28 Jul 2017
Externally publishedYes
EventIntelligent Vehicles Symposium 2017 - Redondo Beach, United States of America
Duration: 11 Jun 201714 Jun 2017
Conference number: 28th (Proceedings)


ConferenceIntelligent Vehicles Symposium 2017
Abbreviated titleIEEE IV 2017
Country/TerritoryUnited States of America
CityRedondo Beach
Internet address

Cite this