Self-localization technology and the role of digital map for urban automated driving

Abstract

Automated vehicle technology is rapidly growing with the aim of practical applications as the next generation of transportation systems. In order to achieve fully-automated driving on public roads, a common approach is to implement digital map based robust perception and decision-making systems. It is a challenging task of self-localization to stably estimate ego-vehicle position with decimeter-level accuracy even under adverse conditions such as rain and snow. This paper describes overviews of the digital map generation based on SLAM technology and self-localization technology based on map matching for robust urban automated driving.