2013 IEEE International Conference on Computer Vision Workshops Making Bertha See Uwe Franke, David Pfeiffer, Clemens Rabe, Carsten Knoeppel, Markus Enzweiler, Fridtjof Stein, and Ralf G. Herrtwich Daimler AG - Research & Development, 71059 Sindelfingen, Germany
[email protected] Abstract With the market introduction of the 2014 Mercedes-Benz S-Class vehicle equipped with a stereo camera system, au- tonomous driving has become a reality, at least in low speed highway scenarios. This raises hope for a fast evolution of autonomous driving that also extends to rural and ur- ban traffic situations. In August 2013, an S-Class vehi- cle with close-to-production sensors drove completely au- tonomously for about 100 km from Mannheim to Pforzheim, Germany, following the well-known historic Bertha Benz Memorial Route. Next-generation stereo vision was the main sensing component and as such formed the basis for Figure 1: Autonomous vehicle ”Bertha”, a 2014 Mercedes- the indispensable comprehensive understanding of com- Benz S-Class with well-integrated close-to-production sen- plex traffic situations, which are typical for narrow Eu- sors driving fully autonomously on open public roads. ropean villages. This successful experiment has proved both the maturity and the significance of machine vision for autonomous driving. This paper presents details of villages in the Black Forest. It stopped in front of red traffic the employed vision algorithms for object recognition and lights, made its way through a lot of roundabouts, planned tracking, free-space analysis, traffic light recognition, lane its path through narrow passages with oncoming vehicles recognition, as well as self-localization. and numerous cars parked on the road, and gave the right of way to crossing pedestrians.