ACTIVE - Autonomous Car to Infrastructure Communication Mastering Adverse Environments

Abstract

Precise localization is crucial for autonomous navigation, especially for autonomous driving. GNSS localization is prone to a number of errors and is not sufficient to provide reliable positional data in all situations. Most existing approaches for fine-grained positioning are not working reliably in difficult weather conditions. In this paper we present a method to tackle that problem by performing precise localization by exploiting the angle-of-arrival of V2X communications. During a 30-months project, we built an unmanned vehicle capable of determining its precise location via V2X communication. In order to safely navigate in the environment and detect obstacles in its path, the robot is also equipped with environmental perception sensors (time-of-flight and radar). We evaluated the proposed localization method during a test-drive on a precisely mapped parking lot. The resulting localization precision was improved by over 60 percent compared to the standard GPS localization.