The Proceedings of Mechanical Engineering Congress, Japan
Online ISSN : 2424-2667
ISSN-L : 2424-2667
2022
Session ID : J161-03
Conference information

AI Prediction System for ITS Skilled Level in Development of ITS Active-Manual
*Yuya KITONaoki NISHIMURAHitoshi SOMA
Author information
CONFERENCE PROCEEDINGS RESTRICTED ACCESS

Details
Abstract

We are developing “Active Manual” that provides appropriate quality and quantity of information through optimum processes to drivers. To realize “Active Manual” ITS Skilled Level of driver assistance system and autonomous driving system is defined and predicted. We are considering the method to use AI (Deep Learning) technology for this prediction. For the prediction, driving data from a driving simulator is used. The driving data is obtained from level 3 autonomous driving system that will be scenes of daily driving. Several neural network models are created to try the prediction, and the best prediction accuracy shows 83.3%.

Content from these authors
© 2022 The Japan Society of Mechanical Engineers
Previous article Next article
feedback
Top