Host: The Japan Society of Mechanical Engineers
Name : [in Japanese]
Date : June 08, 2016 - June 11, 2016
This manuscript describes a robot interaction for driving assist system of an Ultra-Compact Electric Vehicle (UCEV). It is important to improve driving skill for safety and comfortable drive. A driver should recognize about a relationship between the operation and car behavior. We propose a robotic driving support system which a robot in a UCEV interacts with driver. As a first step, we propose a driving evaluation system applying a simplified fuzzy inference, and an interaction timing estimation method applying a spiking neural network. Through offline simulation experiment by using real driving data, we verity the effectivity of our proposed method.