On-Road Motion Planning for Automated Vehicles at Ulm University

TL;DR

This paper discusses the development and testing of on-road motion planning algorithms for autonomous vehicles at Ulm University, emphasizing safety, comfort, and real-world scenario handling.

Contribution

It presents the motion planning system, its functionalities, and real-world testing results in diverse traffic scenarios, including roundabouts and intersections.

Findings

Successful real-world testing in public traffic

Effective handling of complex scenarios like roundabouts

Demonstrated safety and comfort in autonomous driving

Abstract

The Institute of Measurement, Control and Microtechnology at Ulm University investigates advanced driver assistance systems for decades and concentrates in large parts on autonomous driving. It is well known that motion planning is a key technology for autonomous driving. It is first and foremost responsible for the safety of the vehicle passengers as well as of all surrounding traffic participants. However, a further task consists in providing a smooth and comfortable driving behavior. In Ulm, we have the grateful opportunity to test our algorithms under real conditions in public traffic and diversified scenarios. In this paper, we would like to give the readers an insight of our work, about the vehicle, the test track, as well as of the related problems, challenges and solutions. Therefore, we will describe the motion planning system and explain the implemented functionalities. Furthermore, we will show how our vehicle moves through public road traffic and how it deals with challenging scenarios like e.g. driving through roundabouts and intersections.