Neural Networks for Safety-Critical Applications - Challenges, Experiments and Perspectives

Chih-Hong Cheng, Frederik Diehl, Gereon Michael Hinz, Yassine Hamza, Georg Nührenberg, Markus Rickert, Harald Rueß and Michael Truong Le

Proceedings of the Design, Automation & Test in Europe Conference & Exhibition (DATE), pp. 1005–1006

March 2018 · Dresden, Germany · doi:10.23919/DATE.2018.8342158

abstract

We propose a methodology for designing dependable Artificial Neural Networks (ANNs) by extending the concepts of understandability, correctness, and validity that are crucial ingredients in existing certification standards. We apply the concept in a concrete case study for designing a highway ANN-based motion predictor to guarantee safety properties such as impossibility for the ego vehicle to suggest moving to the right lane if there exists another vehicle on its right.

subject terms:autonomous driving, robotics, neural networks, safety