タクティカルレベル入力に基づく自動運転システムとの協調運転

Abstract

This study develops a touchscreen-based human-machine interface prototype that allows the driver to use simple touch gestures to input vehicle control commands specifically in levels 2 and 3. The driver can instantly command a set of lateral inputs by location-based TLI, e.g., lane changing, by designating a desired location on the map, e.g., lane, by double tapping and swiping. Situational awareness is enhanced, for e.g., when approaching an intersection, by using visual and auditory prompts. We conducted experiments using a simulator to evaluate TLI method compared with the operational- (OLI, level 0) and strategic-level input (SLI, level 4) methods. The results show that TLI method offers both the flexibility of OLI as well as comfort of SLI, and drivers prefer to use all three methods depending on the driving environment.