Recent advances in deep learning have enabled data-driven controller design for autonomous systems. However, verifying safety of such controllers, which are often hard-to …
Deep Neural Networks (DNN) will emerge as a cornerstone in automotive software engineering. However, developing systems with DNNs introduces novel challenges for …
In this paper, we consider the problem of formally verifying a Neural Network (NN) based autonomous landing system. In such a system, a NN controller processes images from a …
S Manivasagam, IA Bârsan, J Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Testing the full autonomy system in simulation is the safest and most scalable way to evaluate autonomous vehicle performance before deployment. This requires simulating …
We demonstrate a unified approach to rigorous design of safety-critical autonomous systems using the VerifAI toolkit for formal analysis of AI-based systems. VerifAI provides an …
Deep neural networks (DNNs) are increasingly being employed in safety-critical systems, and there is an urgent need to guarantee their correctness. Consequently, the verification …
Urban driving simulators, such as CARLA, provide 3-D environments and useful tools to easily simulate sensorimotor control systems in scenarios with complex multi-agent …
This paper proposes a new forward reachability analysis approach to verify safety of cyber- physical systems (CPS) with reinforcement learning controllers. The foundation of our …
Deep reinforcement learning (DRL) has become a dominant deep-learning paradigm for tasks where complex policies are learned within reactive systems. Unfortunately, these …