2020 Fiscal Year Final Research Report
Risk Estimation of Group Pedestrians based on Stochastic Behavior Model
Project/Area Number |
18K04639
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Review Section |
Basic Section 25020:Safety engineering-related
|
Research Institution | Nihon University |
Principal Investigator |
|
Project Period (FY) |
2018-04-01 – 2021-03-31
|
Keywords | 確率的予測 / 予防安全 / 歩行者 / 危険度指標 |
Outline of Final Research Achievements |
The purpose of this study is to build a model that can predict the position of pedestrians in the next few seconds probabilistically. In order to protect pedestrians, it is necessary to analyze the behavior of individual pedestrians. In particular, the risk of contact with a vehicle increases when a pedestrian moves out of the way to avoid an obstacle in front of the walking path. In this study, we predict the walking path of a pedestrian by assuming the walking situations of a single pedestrian and group pedestrians, and modeling their walking behavior probabilistically. In addition, we identify pedestrians who are considered dangerous from among group pedestrians, and quantitatively evaluate the degree of risk. By quantitatively predicting the behavior of group pedestrians, the prediction can be used to plan the optimal route for a vehicle.
|
Free Research Field |
制御工学
|
Academic Significance and Societal Importance of the Research Achievements |
本研究で得られた成果は,運転支援システムの性能向上に寄与する.運転支援や自動運転においては,自車周辺の物体認識が重要であり,歩行者や自転車の行動を適切に捉え,より安全に接触を避けることが大切である.そのため,周辺歩行者を捉えた段階でその歩行者の行動を予測することで,接触しないような経路や速度選択を行うことが期待できる. また,将来的に人とロボットが共存する社会においては,ロボットが人と接触しない,あるいは適切な速度や距離を保って接近する場面が多々考えられる.そのような場面でも,人や障害物の動きを予測することが重要である.
|