Certifying a synthetic environment for CAV validation and verification

A key element supporting the introduction of Level 4/5 Connected and Autonomous Vehicles (CAVs) will be the ability to independently certify that such systems are safe, reliable and secure. Not only must system developers and service providers have methodologies for demonstrating that consumer products are safe, but the public must also have confidence in these vehicles and systems. While testing and development of CAVs has begun across many countries in Europe and globally, a certification approach is required to underpin widespread adoption of CAVs. Among the options for delivering certification cost-effectively and faster, is the use of synthetic environments, including CAV simulators. Conducting validation of vehicles in simulators enables the creation of an almost limitless number of testing scenarios that are flexible, repeatable and safe. Compared to real-world testing, simulated validation using simulators will enable vehicles to be tested rapidly and against a challenging set of conditions that would be difficult and costly to replicate in real life. This paper will examine the conditions required for creating such a testing environment, as well as prerequisites for developing a methodology for a simulator to be independently certified as an appropriate means of evaluating the safety of CAVs. This paper presents the identification and analysis of twelve existing standards for CAV testing as a pre-requisite for creating a simulator certification methodology