Autonomous and connected vehicle technologies are rapidly emerging and being introduced to society. Traditional vehicles are becoming more sophisticated with integrated driver-assist features incorporating AI algorithms, control systems, and communication interfaces. Modern vehicles are tightly-coupled into a system of systems more robust than the commonly leveraged physical world simulations used in the research community and industry today. This means that components beyond just the AI model effect the safety and security of operating vehicles. It is imperative to consider the complex and interconnected nature of these systems during pre-deployment development and testing. In this paper, we discuss our preliminary work on a multi-level simulation and hardware-in-the-loop (HITL) testbed capable of evaluating vehicle reactions to diverse driving situations based on virtually constructed worlds. Our framework is able to evaluate vehicle behavior at scale in a simulated world while seamlessly integrating physical hardware via a digital-twin approach.
Live Virtual Constructive Environment for Assuring the Safety and Security of Complex Autonomous Vehicles
2023-06-01
2268627 byte
Conference paper
Electronic Resource
English
Assuring Responsible Driving of Autonomous Vehicles
IEEE | 2022
|Scenario-Based Risk Quantification Approach for Assuring Safety in Autonomous Vehicles
British Library Conference Proceedings | 2023
|Scenario-Based Risk Quantification Approach for Assuring Safety in Autonomous Vehicles
SAE Technical Papers | 2023
|Safety mechanism for assuring driver engagement during autonomous drive
European Patent Office | 2023
|