Hazard-Anticipative Driving Method for Automated Driving in Urban Area

2018 Fiscal Year Final Research Report

• Project/Area Number: 16K06162
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Dynamics/Control
• Research Institution: Tokyo University of Science
• Principal Investigator: Hayashi Ryuzo 東京理科大学, 工学部機械工学科, 准教授 (80505868)
• Project Period (FY): 2016-04-01 – 2019-03-31
• Keywords: 交通機械制御 / 自動車 / 予防安全 / 自動運転

Outline of Final Research Achievements

This study focuses on accidents when a vehicle overtake a pedestrian. It is an important problem to be solved to realize automated driving in urban areas. This study proposes an automated driving method which can overtake a pedestrian in a small street safely and smoothly. Potential field method, which is used in robotics, is utilized. It make a vehicle behave as if repulsive forces are applied to the vehicle, so that the vehicle evasively overtake the pedestrian. In the potential field method, it is important how to determine the values of parameters. In this study, the parameters are determined by using genetic algorithm to optimize the potential field.

Free Research Field

機械力学・制御

Academic Significance and Societal Importance of the Research Achievements

これまでポテンシャルフィールド法では，潜在的な危険に対していかに安全を確実に担保するかが課題であったが，本研究ではこの問題を解決する手法ができた．考え方自体は他の広範な自動運転の安全性問題に応用可能であることから，広く波及することが期待される．
本研究の成果は，まだまだ実用化は難しいとされる市街地自動運転の実現を一歩近づけるものであり，物流における人手不足や免許返納後の高齢者の移動問題に対して寄与するものである．