Related papers: Efficient Safety Verification of Autonomous Vehicl…
Neural networks achieve outstanding accuracy in classification and regression tasks. However, understanding their behavior still remains an open challenge that requires questions to be addressed on the robustness, explainability and…
This paper presents Verisig, a hybrid system approach to verifying safety properties of closed-loop systems using neural networks as controllers. Although techniques exist for verifying input/output properties of the neural network itself,…
This work in progress considers reachability-based safety analysis in the domain of autonomous driving in multi-agent systems. We formulate the safety problem for a car following scenario as a differential game and study how different…
Neural networks have recently become popular for a wide variety of uses, but have seen limited application in safety-critical domains such as robotics near and around humans. This is because it remains an open challenge to train a neural…
We present a new approach to automated scenario-based testing of the safety of autonomous vehicles, especially those using advanced artificial intelligence-based components, spanning both simulation-based evaluation as well as testing in…
Autonomous vehicles must navigate dynamically uncertain environments while balancing safety and efficiency. This challenge is exacerbated by unpredictable human-driven vehicle (HV) behaviors and perception inaccuracies, necessitating…
We present the first automated verification technique for confidence-based 2-safety properties, such as global robustness and global fairness, in deep neural networks (DNNs). Our approach combines self-composition to leverage existing…
Verifying correctness of deep neural networks (DNNs) is challenging. We study a generic reachability problem for feed-forward DNNs which, for a given set of inputs to the network and a Lipschitz-continuous function over its outputs,…
Virtual scenario-based testing methods to validate autonomous driving systems are predominantly centred around collision avoidance, and lack a comprehensive approach to evaluate optimal driving behaviour holistically. Furthermore, current…
To provide safety guarantees for learning-based control systems, recent work has developed formal verification methods to apply after training ends. However, if the trained policy does not meet the specifications, or there is conservatism…
Convolutional Neural Networks (CNN) for object detection, lane detection, and segmentation now sit at the head of most autonomy pipelines, and yet, their safety analysis remains an important challenge. Formal analysis of perception models…
Regulatory approval and safety guarantees for autonomous vehicles facing frequent functional updates and complex software stacks, including artificial intelligence, are a challenging topic. This paper proposes a concept and guideline for…
Over-approximating the reachable sets of dynamical systems is a fundamental problem in safety verification and robust control synthesis. The representation of these sets is a key factor that affects the computational complexity and the…
Intelligent mechanisms implemented in autonomous vehicles, such as proactive driving assist and collision alerts, reduce traffic accidents. However, verifying their correct functionality is difficult due to complex interactions with the…
Applying neural networks as controllers in dynamical systems has shown great promises. However, it is critical yet challenging to verify the safety of such control systems with neural-network controllers in the loop. Previous methods for…
The arising application of neural networks (NN) in robotic systems has driven the development of safety verification methods for neural network dynamical systems (NNDS). Recursive techniques for reachability analysis of dynamical systems in…
Autonomous driving vehicles provide a vast potential for realizing use cases in the on-road and off-road domains. Consequently, remarkable solutions exist to autonomous systems' environmental perception and control. Nevertheless, proof of…
Understanding human driving behavior is crucial to develop autonomous vehicles' algorithms. However, most low level automation, such as the one in advanced driving assistance systems (ADAS), is based on objective safety measures, which are…
The deployment of Large Language Models (LLMs) in robotic systems presents unique safety challenges, particularly in unpredictable environments. Although LLMs, leveraging zero-shot learning, enhance human-robot interaction and…
Increasing communication and self-driving capabilities for road vehicles lead to threats imposed by attackers. Especially attacks leading to safety violations have to be identified to address them by appropriate measures. The impact of an…