Delay Independent Safe Control with Neural Networks: Positive Lur'e Certificates for Risk Aware Autonomy
This provides scalable safety guarantees for risk-aware autonomous systems, though it is incremental as it builds on existing verification methods.
The paper tackled the problem of ensuring safety in autonomous control systems with neural networks under delays and uncertainties, by developing a positivity-based certification method that runs orders of magnitude faster than existing approaches and certifies regimes they cannot.
We present a risk-aware safety certification method for autonomous, learning enabled control systems. Focusing on two realistic risks, state/input delays and interval matrix uncertainty, we model the neural network (NN) controller with local sector bounds and exploit positivity structure to derive linear, delay-independent certificates that guarantee local exponential stability across admissible uncertainties. To benchmark performance, we adopt and implement a state-of-the-art IQC NN verification pipeline. On representative cases, our positivity-based tests run orders of magnitude faster than SDP-based IQC while certifying regimes the latter cannot-providing scalable safety guarantees that complement risk-aware control.