차량간 상호작용이 고려된 멀티-헤드 어텐션 구조 기반 주변 차량 주행 경로 예측 알고리즘open accessProbabilistic vehicle trajectory prediction considering inter-vehicle interaction based on multi-head attention architecture
- Other Titles
- Probabilistic vehicle trajectory prediction considering inter-vehicle interaction based on multi-head attention architecture
- Authors
- Kim, Hayoung; Choi, Seungwon; Huh, Kunsoo
- Issue Date
- Aug-2020
- Publisher
- Korean Society of Automotive Engineers
- Keywords
- Deep learning; Interaction; Learning based model; Supervised learning; Trajectory prediction
- Citation
- Transactions of the Korean Society of Automotive Engineers, v.28, no.9, pp.645 - 652
- Indexed
- SCOPUS
KCI
- Journal Title
- Transactions of the Korean Society of Automotive Engineers
- Volume
- 28
- Number
- 9
- Start Page
- 645
- End Page
- 652
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/4445
- DOI
- 10.7467/KSAE.2020.28.9.645
- ISSN
- 1225-6382
- Abstract
- Predicting the trajectory of surrounding vehicles is important in developing safe and socially compliant self-driving cars. For this reason, interaction-aware vehicle trajectory prediction with uncertainty is essential before making a robust decision-making system and trajectory planner. In this paper, we present a probabilistic vehicle trajectory prediction algorithm, which is scalable, interpretable and accurate. Using past trajectory and the properties of the surrounding vehicles, the proposed model generates the distribution of the future predicted trajectory. Our model consists of a simple encoder-decoder architecture based on multi-head attention. Like human drivers, the model can learn which vehicles to focus on for accurate prediction without requiring supervision. Inter-vehicle interaction learning improves the interpretability of the prediction network. We demonstrate our model's performance using a challenging, naturalistic trajectory dataset, showing clear improvement in terms of positional error on both longitudinal and lateral directions.
- Files in This Item
-
- Appears in
Collections - 서울 공과대학 > 서울 미래자동차공학과 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/4445)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.