Construction of risk map system

Because the proactive braking intervention system developed in our previous study refers to only node-link information from digital map, the system uniformly decelerates during approaching to all intersections with occlusion. However, because actual risk on intersections with occlusion depends on the situation of each intersection, uniform deceleration sometimes decreases user acceptance. Thus, grasping the risk-related information of each intersection is important for improving the acceptance for the proactive braking intervention system. For this purpose, we proposed a risk map generation system via data-driven approach.

Left side: Conceptual schematic of intersections with various risk level.

Right side: Conceptual schematic of estimating risk level from accumulated driving data.

Related Paper

Takuma Ito, Masatsugu Soya, Kyoichi Tohriyama, Minoru Kamata, “Risk map generation system for intelligent vehicles on community roads via data-driven approach ”, Mechanical Engineering Journal, 7(1) 1-18, Feb 15, 2020, doi: 10.1299/mej.19-00119 .

Evaluation of adaptive proactive braking intervention system based on risk map

For improving the acceptance of proactive braking intervention system developed in our previous study, we proposed an adaptive proactive braking intervention system based on risk map. Field operation test in which actual drivers participated on public roads revealed that the adaptation using risk information reduced the impatient feeling and improve the acceptance to a certain degree.

Left side: Conceptual schematic of proactive braking intervention situation.

Right side: Conceptual schematic of deceleration by proactive braking intervention.

Related Paper

Takuma Ito, Masatsugu Soya, Kyoichi Tohriyama, Yuichi Saito, Tsukasa Shimizu, Akito Yamasaki, Masao Nagai, Hideo Inoue, Minoru Kamata, “Evaluation of Acceptability of Adaptive Proactive Braking Intervention System Based on Risk Map for Elderly Drivers" , International Journal of Automotive Engineering, 11(2) 40-48, 2020, doi: 10.20485/jsaeijae.11.2_40.