Fundamental Study on Risk Resilience Control for Autonomous Driving Based on Driving Environmental Risk Structuration

2023 Fiscal Year Final Research Report

• Project/Area Number: 21K03977
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 20020:Robotics and intelligent system-related
• Research Institution: Tokyo University of Agriculture and Technology
• Principal Investigator: Raksincharoensak Pongsathorn 東京農工大学, 工学(系)研究科(研究院), 教授 (30397012)
• Project Period (FY): 2021-04-01 – 2024-03-31
• Keywords: モビリティ / 運動制御 / 予防安全 / 自動運転

Outline of Final Research Achievements

This research aims to construct an automated driving technology for accident prevention and early avoidance, focusing on a fundamental research on risk resilience control methodology, which enables the risk level prediction in next few seconds ahead based on the driving environment and road context using risk potentials. The model determines normative driving to minimize risk, and guides the driver to safe driving behavior. Specifically, a motion planning and control system was constructed in the way that the behavior of surrounding vehicles, pedestrians, etc. are modeled based on driving data from the actual road driving. The control system calculates a trajectory and speed model based on the risk potential. Next, in the second step, a speed planning method adapted to road traffic context information was devised and its effectiveness was verified. This fundamental research aims to provide design guidelines for vehicle motion control systems to reasonably estimate the risk level.

Free Research Field

機械力学・制御工学

Academic Significance and Societal Importance of the Research Achievements

本研究課題は、従来の自動車運動力学・制御による物理モデルに加え、交通環境リスクの多様性に対応可能な情報科学モデルを融合させて、サイバーフィジカルシステムとして事故予防メカニズムを学術的に見出すものであり、交通事故ゼロに対する学術的研究である。また、自動車以外のモビリティを設計する上でも安全指針になりうる応用範囲の広い研究であり、社会的な波及効果も大きいと考える。