Hubert Weisser

Autonomous driving on vehicle test tracks: overview, implementation and vehicle diagnosis

This article describes the implementation of the Autonomous Driving project. Furthermore, it shows the concept of the vehicle diagnosis in detail. The vehicle diagnosis monitors a test car on a proving ground and substitutes the surveillance of a human test driver. Therefore, the human diagnostics capabilities have to be replaced by measuring equipment in order to automate the detection of malfunctions. The components of the vehicle diagnosis system and its operating principle are shown. Two test vehicles were equipped with sensors, computers and actuators (driving robots). The vehicles can be driven by a robot while the sensor system observes the entire surroundings in order to be able to avoid obstacles. Furthermore, the vehicle control can be overruled by an electronic copilot in case of an emergency.

Measurement and modeling of infrared imaging systems at conditions of reduced visibility (fog) for traffic applications

This paper addresses the feasibility and operational application of different infrared (IR) imaging systems in road traffic to improve security of individual motor vehicles at conditions of low visibility, especially in fog. Extensive field measurements were carried out at different weather conditions, mainly fog and haze, utilizing three IR imaging sensors in different spectral bands in the near and thermal infrared. Additionally, a CCD camera in the visible band was used for comparison purposes. Measurements were performed on public roads and a test road which was equipped with heated and unheated radiation reference sources and thermal beacons. Furthermore, the atmospheric spectral transmission and relevant meteorological and aerosol parameters were measured. A mathematical model, SIMIS (simulation model for IR scenes), was developed and applied to generate and analyze thermal images of the test road. The spectral dependencies and radiation properties of fog and haze were modelled with LOWTRAN 7. Apparent radiances, temperatures, and contrasts of the references sources were simulated as a function of distance. The contrast transmission and effective IR visibility was derived and compared to the measured IR-imaging sensor data. From the analysis an assessment of the performance of IR-imaging sensors at fog conditions has been deduced.

Driver face recognition as a security and safety feature

We present a driver face recognition system for comfortable access control and individual settings of automobiles. The primary goals are the prevention of car thefts and heavy accidents caused by unauthorized use (joy-riders), as well as the increase of safety through optimal settings, e.g. of the mirrors and the seat position. The person sitting on the drivers seat is observed automatically by a small video camera in the dashboard. All he has to do is to behave cooperatively, i.e. to look into the camera. A classification system validates his access. Only after a positive identification, the car can be used and the driver-specific environment (e.g. seat position, mirrors, etc.) may be set up to ensure the drivers comfort and safety. The driver identification system has been integrated in a Volkswagen research car. Recognition results are presented.

Autonome Führung von Serienfahrzeugen

Dieser Beitrag stellt ein Autonomes Robotersystem zur autonomen Fuhrung von Serienfahrzeugen vor. Das Systemkonzept ist in den wesentlichen Modulen redundant ausgelegt, um ein Hochstmas an Zuverlassigkeit zu gewahrleisten. Eine aus verschiedenartigen Sensoren, Prazisionsortung und digitaler Karte aufgebaute Rundumsicht- und Informationsplattform ermittelt den Fahrbahnverlauf sowie die Lage von Objekten. Diese redundante Information wird fusioniert und in einer vorausschauenden Bahnplanung und Regelung umgesetzt. Ein ‘elektronischer Copilot’ uberwacht die Fahrt und bringt das Fahrzeug in unplausiblen Situationen gezielt zum Stillstand. Die gesamte Aktorik findet auf dem Fahrersitz Platz und bedient Lenkung, Bremse, Gas, Kupplung und Schaltung ahnlich einem menschlichen Fahrer. Durch den Verzicht auf Sondereinbauten kann das Robotersystem in kurzester Zeit in Serienfahrzeuge eingebaut werden. Fahrergebnisse auf extremen Teststrecken demonstrieren die Leistungsfahigkeit des Systems.

Autonomous Driving on Vehicle Test Tracks: Overview, Implementation and First Results

This paper presents results from the Autonomous Driving project in which automated driving took place on the Volkswagen proving ground. It first gives a system overview, followed by a discussion of how the system was implemented. Tests were conducted with two vehicles equipped with sensors, computers and actuators. The vehicles are driven by robots while the sensor system is designed to avoid obstacles. Vehicle guidance takes place through DGPS satellite navigation and through visual lane detection. In case of emergencies vehicle control can be overruled by an electronic copilot.