An international conference connecting people
in CAD research, education and business
Bookmark and Share
Copyright (C) CAD Solutions, LLC. All rights reserved.
Proceedings of CAD'17, 2017, 170-175
Sensor and Object Recognition Technologies for Self-driving Cars

Mario Hirz, Bernhard Walzel, Graz University of Technology

Abstract. Assisted and automated driving technologies are one of the most intensive researched and investigated fields in automotive industry today. Nearly all car manufacturer and several well-known player from the electronics and communication industry push forward knowhow for self-driving cars. Scientific and non-scientific community intensively discusses the introduction of automated driving functions in cars on worldwide markets as well as the potentials, benefits and risks of this technology for humans and environment. In this way, it is expected that vehicles with driving assistance functions and even autonomous vehicles for passenger and goods transportation will have an increasingly share in daily traffic. This requires an integration of diverse types of technologies into existing traffic systems. According to SAE there are different levels of autonomous driving. Level “0” represents the old-fashioned car that is thoroughly controlled by a human driver. Most of the cars today are in this level. With raising SAE level, the share of automated driving functions is increasing. Level “1” and “2” include driving assistance supporting the chauffeur in certain traffic situations, e.g. automated cruise control, lane assistant, highway assistant. In these technology levels, the car driver has to keep an eye on the driving situations continuously to be able to perform interventions. From level “3” on, the car takes over control in certain traffic conditions, e.g. highway chauffeur or traffic jam assistant.

Keywords. Autonomous driving, sensor technology, object recognition, image-based modelling

DOI: 10.14733/cadconfP.2017.170-175