Testing learning-enabled cyber-physical systems with Large-Language Models: A Formal Approach
The integration of machine learning (ML) into cyber-physical systems (CPS) offers significant benefits, including enhanced efficiency, predictive capabilities, real-time responsiveness, and the enabling of autonomous operations. This convergence has accelerated the development and deployment of a range of real-world applications, such as autonomous vehicles, delivery drones, service robots, and telemedicine procedures. However, the software development life cycle (SDLC) for AI-infused CPS diverges significantly from traditional approaches, featuring data and learning as two critical components. Existing verification and validation techniques are often inadequate for these new paradigms. In this study, we pinpoint the main challenges in ensuring formal safety for learningenabled CPS.We begin by examining testing as the most pragmatic method for verification and validation, summarizing the current state-of-the-art methodologies. Recognizing the limitations in current testing approaches to provide formal safety guarantees, we propose a roadmap to transition from foundational probabilistic testing to a more rigorous approach capable of delivering formal assurance.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous VehiclesMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
"Active Neighbour": A Novel Monitoring Model for Cyber-Physical Systems
Over the past decade, advancements in technology have enabled Cyber-Physical Systems (CPS) to monitor sensor networks through various methodologies. However, these developments have concurrently introduced significant se…
Detection of Dataset Shifts in Learning-Enabled Cyber-Physical Systems using Variational Autoencoder for Regression
Cyber-physical systems (CPSs) use learning-enabled components (LECs) extensively to cope with various complex tasks under high-uncertainty environments. However, the dataset shifts between the training and testing phase …
Anomaly DetectionregressionSelf-Driving CarsMany-Objective Reinforcement Learning for Online Testing of DNN-Enabled Systems
Deep Neural Networks (DNNs) have been widely used to perform real-world tasks in cyber-physical systems such as Autonomous Driving Systems (ADS). Ensuring the correct behavior of such DNN-Enabled Systems (DES) is a cruci…
Autonomous Drivingreinforcement-learningReinforcement Learning (RL)Towards Developing Safety Assurance Cases for Learning-Enabled Medical Cyber-Physical Systems
Machine Learning (ML) technologies have been increasingly adopted in Medical Cyber-Physical Systems (MCPS) to enable smart healthcare. Assuring the safety and effectiveness of learning-enabled MCPS is challenging, as suc…
Monitor and Recover: A Paradigm for Future Research on Distribution Shift in Learning-Enabled Cyber-Physical Systems
With the known vulnerability of neural networks to distribution shift, maintaining reliability in learning-enabled cyber-physical systems poses a salient challenge. In response, many existing methods adopt a detect and a…
Decision MakingPhilosophy