Handling Occlusions in Automated Driving Using a Multiaccess Edge Computing Server-Based Environment Model From Infrastructure Sensors
Michael Buchholz, Johannes Müller, Martin Herrmann, Jan Strohbeck, Benjamin Völz, Matthias Maier, Jonas Paczia, Oliver Stein, Hubert Rehborn, Rüdiger-Walter Henn
Abstract
Sensors in an automated vehicle (AV) can encounter occlusions caused by other traffic, buildings, and vegetation, especially in urban areas. Information from infrastructure sensors sent via vehicle-to-anything communication can help. We have developed and prototypically implemented an infrastructure environment model generated from infrastructure sensors on a multi-access edge computing server on an LTE/5G mobile network. This extends an AV’s field of view and is integrated into the vehicle’s motion planning schemes. In this article, after a description of our approach, we present and discuss real-world results from a pilot site at a public junction that were obtained using prototype AVs.