Neural Networks for Safety-Critical Applications - Challenges, Experiments and Perspectives
This addresses the challenge of ensuring safety in neural networks for critical domains like autonomous driving, though it appears incremental by building on existing certification standards.
The paper tackles the problem of designing dependable artificial neural networks for safety-critical applications by proposing a methodology that extends certification concepts like understandability, correctness, and validity, applied in a case study for a highway motion predictor to guarantee safety properties such as preventing lane changes when vehicles are present.
We propose a methodology for designing dependable Artificial Neural Networks (ANN) 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 in designing a high-way 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.