Presentation
Provably Probabilistic Safe Controller Synthesis for Vision-Based Neural Network Control Systems
DescriptionThe prevalence of nonlinear systems in safety-critical domains calls for controllers with safety guarantees, while vision-based control relies on high-dimensional images complicates both decision-making and formal safety analysis under uncertainty. This paper proposes a provably safe controller synthesis method for vision-based neural network control systems. We first employ a conditional generative adversarial network (cGAN) to approximate the mapping from system states to visual observations and combine it with RL-based pretraining to build a verifiable closed-loop structure. A data-driven model quantifies uncertainties from environmental perturbations, while martingale theory guides the learning of a stochastic barrier certificate (SBC) to provide rigorous probabilistic safety bounds. Furthermore, counterexamples from verification are used to alternately refine both the controller and certificate networks, ultimately yielding a controller with formally provable probabilistic safety guarantees. Experimental results on widely studied benchmarks demonstrate the efficiency and effectiveness of our approach.
Event Type
Research Manuscript
TimeTuesday, July 2810:56am - 11:10am PDT
LocationMtg Room 202C