한국정보처리학회:학술대회논문집 (Proceedings of the Korea Information Processing Society Conference)
- 한국정보처리학회 2019년도 춘계학술발표대회
- /
- Pages.485-486
- /
- 2019
- /
- 2005-0011(pISSN)
- /
- 2671-7298(eISSN)
DOI QR Code
Active learning 기반 운전자 행동 모방 학습 기법 연구
A Study on a Driving Behavior Imitation Learning Method Based on Active Learning
- 황카이스 (동국대학교 멀티미디어공학과) ;
- 문명운 (동국대학교 멀티미디어공학과) ;
- 박지선 (동국대학교 멀티미디어공학과) ;
- 성연식 (동국대학교 멀티미디어공학과) ;
- 조경은 (동국대학교 멀티미디어공학과)
- Huang, Kaisi (Department of Multimedia Engineering, Dongguk University) ;
- Wen, Mingyun (Department of Multimedia Engineering, Dongguk University) ;
- Park, Jisun (Department of Multimedia Engineering, Dongguk University) ;
- Sung, Yunsick (Department of Multimedia Engineering, Dongguk University) ;
- Cho, Kyungeun (Department of Multimedia Engineering, Dongguk University)
- 발행 : 2019.05.10
초록
Simulated driving behavior is an important aspect of realistic simulation systems. To simulate natural driving behavior, this paper proposes an imitation learning method based on active learning that combines demonstration and experience. Driving demonstrations are collected from human drivers in a driving simulator. A driving behavior policy is learned from these demonstrations. The driving demonstration dataset is augmented with new demonstrations that the original demonstrations did not contain, in the form of behaviors from another driving behavior policy learned from experience. The final driving behavior policy is learned from an augmented demonstration dataset.
키워드