交通オントロジーと説明生成に基づく交通危険予測

Abstract

We develop an Advanced Driver Assistance System (ADAS) that can recognize potential risks in traffic scenes and provide the reasoning for its prediction. In this study, we extend our previous risk prediction model combining logic-based reasoning with physics simulation, based on ontology-based traffic scene understanding research. Our evaluation on a real-life traffic incident database demonstrates the potentiality of our approach.

Publication
人工知能学会第30回全国大会予稿集
Date