FHG-CO-DRIVER - FROM MAP-GUIDED AUTOMATIC DRIVING BY MACHINE VISION TO A COOPERATIVE DRIVER SUPPORT

A digital road map provides partial knowledge about the operating envi ronment for a road vehicle. If a road vehicle is equipped with a video camera, machine vision approaches can provide knowledge about the act ual traffic environment around the vehicle. Experiences with a combina tion of two such approaches during the commissioning of a van for auto matic driving on a private road network are reported, including experi ences gathered during subsequent driving experiments on public roads a nd several improvement cycles for hardware and software. Based on thes e experiences, a second generation vehicle for automatic driving-a sed an-has been designed and commissioned. It is currently evaluated on pu blic roads. This equipment provides an experimental platform for study ing driver-vehicle interactions with the option to automatically evalu ate actual traffic situations around the vehicle in real-time. Our equ ipment thus offers an approach to record and disentangle the multitude of factors which influence the-often subconscious-reactions of a driv er. It is our working hypothesis that only an automatic, in-depth unde rstanding of the actual traffic situation facilitates the design of a driver support system which is competent and flexible enough to win ac ceptance by a wide spectrum of users.