This report presents the results of a friendly competition for formal verification of continuous and hybrid systems with artificial intelligence (AI) components. Specifically, machine learning (ML) components in cyber-physical systems (CPS), such as feedforward neural networks used as feedback controllers in closed-loop systems are considered, which is a class of systems classically known as intelligent control systems, or in more modern and specific terms, neural network control systems (NNCS). For future iterations, we more broadly refer to this category as AI and NNCS (AINNCS). The friendly competition took place as part of the workshop Applied Verification for Continuous and Hybrid Systems (ARCH) in 2019. In the first edition of this AINNCS category at ARCH-COMP, three tools have been applied to solve five different benchmark problems, (in alphabetical order): NNV, Sherlock, and Verisig. This report is a snapshot of the current landscape of tools and the types of benchmarks for which these tools are suited. Due to the diversity of problems and that this is the first iteration of this category, we are not ranking tools in terms of performance, yet the presented results probably provide the most complete assessment of tools for the safety verification of NNCS.
Reachable Set Estimation for Neural Network Control Systems: A Simulation-Guided Approach
