Driver modeling through deep reinforcement learning and behavioral game theory

Simple item page
buir.contributor.authorAlbaba, Berat Mert
buir.contributor.authorYıldız, Yıldıray
buir.contributor.orcidAlbaba, Berat Mert|0000-0002-3406-8412
buir.contributor.orcidYıldız, Yıldıray|0000-0001-6270-5354
dc.citation.epage892en_US
dc.citation.issueNumber2en_US
dc.citation.spage885en_US
dc.citation.volumeNumber30en_US
dc.contributor.authorAlbaba, Berat Mert
dc.contributor.authorYıldız, Yıldıray
dc.date.accessioned2022-03-04T08:11:24Z
dc.date.available2022-03-04T08:11:24Z
dc.date.issued2021-05-05
dc.departmentDepartment of Mechanical Engineeringen_US
dc.description.abstractIn this work, a synergistic combination of deep reinforcement learning and hierarchical game theory is proposed as a modeling framework for behavioral predictions of drivers in highway driving scenarios. The modeling framework presented in this work can be used in a high-fidelity traffic simulator consisting of multiple human decision-makers. This simulator can reduce the time and effort spent for testing autonomous vehicles by allowing safe and quick assessment of self-driving control algorithms. To demonstrate the fidelity of the proposed modeling framework, game-theoretical driver models are compared with real human driver behavior patterns extracted from two different sets of traffic data.en_US
dc.description.provenanceSubmitted by Dilan Ayverdi (dilan.ayverdi@bilkent.edu.tr) on 2022-03-04T08:11:24Z No. of bitstreams: 1 Driver_modeling_through_deep_reinforcement_learning_and_behavioral_game_theory.1.pdf: 1342198 bytes, checksum: 8a3d8fed9496abc20d354383c242113c (MD5)en
dc.description.provenanceMade available in DSpace on 2022-03-04T08:11:24Z (GMT). No. of bitstreams: 1 Driver_modeling_through_deep_reinforcement_learning_and_behavioral_game_theory.1.pdf: 1342198 bytes, checksum: 8a3d8fed9496abc20d354383c242113c (MD5) Previous issue date: 2021-05-05en
dc.identifier.doi10.1109/TCST.2021.3075557en_US
dc.identifier.eissn1558-0865
dc.identifier.issn1063-6536
dc.identifier.urihttp://hdl.handle.net/11693/77681
dc.language.isoEnglishen_US
dc.publisherInstitute of Electrical and Electronics Engineersen_US
dc.relation.isversionofhttps://doi.org/10.1109/TCST.2021.3075557en_US
dc.source.titleIEEE Transactions on Control Systems Technologyen_US
dc.subjectAutonomous vehicles (AVs)en_US
dc.subjectDeep learningen_US
dc.subjectDriver modelingen_US
dc.subjectGame theory (GT)en_US
dc.subjectReinforcement learning (RL)en_US
dc.titleDriver modeling through deep reinforcement learning and behavioral game theoryen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Driver_modeling_through_deep_reinforcement_learning_and_behavioral_game_theory.1.pdf
Size:
1.28 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.69 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Scholarly Publications - Mechanical Engineering