A Fail-safe Architecture for Automated Driving
Sebastian vom Dorff1,3,a, Bert Böddeker2,c, Maximilian Kneissl1,b and Martin Fränzle3,d
1Corporate R&D department of DENSO Automotive Deutschland GmbH, Freisinger Str. 21-23, 85386 Eching,
Germany
2Autonomous Intelligent Driving GmbH, Ungererstr. 69, 80805 München, Germany
3Carl von Ossietzky University, Department of Computing Science, 26111 Oldenburg, Germany
as.vomdorff@denso-auto.de
bm.kneissl@denso-auto.de
cbert.boeddeker@aid-driving.eu
dfraenzle@informatik.uni-oldenburg.de
ABSTRACT
The development of autonomous vehicles has gained a rapid pace. Along with the promising possibilities of such automated systems, the question of how to ensure their safety arises. With increasing levels of automation the need for failoperational systems, not relying on a back-up driver, poses new challenges in system design. In this paper we propose a lightweight architecture addressing the challenge of a verifiable, fail-safe safety implementation for trajectory planning. It offers a distributed design and the ability to comply with the requirements of ISO26262, while avoiding an overly redundant setup. Furthermore, we show an example with low-level prediction models applied to a real world situation.
