Neural Networks for Safety‐Critical Applications ‐ Challenges, Experiments and Perspectives
Chih‐Hong Cheng, Frederik Diehl, Gereon Hinz, Yassine Hamza, Georg Nuehrenberg, Markus Rickert, Harald Ruess and Michael Truong‐Le
Landesforschungsinstitut des Freistaats Bayern, Germany
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.
Keywords: Autonomous driving, neural network, dependability, certification, formal verification, research challenges.
