Verification and Validation for Autonomous Vehicles
02/22/2023
Validation and Verification (V&V) of AI based cyber-physical systems is a vexing problem with limited signs of significant progress. Despite the billions spent on the development of AI systems, currently no clear methodology exists for a structured process of the V&V of these systems. For V&V researchers, it is exceedingly difficult to advance the state of art because of the massive infrastructure requirements to demonstrate the viability of any solution. PolyVerif provides an AI design and verification environment consisting of the digital twin creation process, an open-source AV engine, access to several open-source physics based simulators, symbolic test generation engine, example test scenarios from documented AV accidents, and native design-for-experiment layer for each of the major subsystems of an AV (detection, perception, localization, and path planning). PolyVerif’s objective is to arm V&V researchers to perform research which extends the state-of-the-art on any one of the major axes of interest and use the remainder of the infrastructure to quickly demonstrate the viability of their solution. Given its open-source nature, researchers can also contribute their innovations to the project. Using this critical property of open-source environments, the innovative potential of the whole research community to solve these vexing issues is greatly accelerated. In addition to the framework, two live demonstration projects from active AV shuttle projects will also be presented.
Rahul Razdan
Rahul Razdan, CEO, Razdan Research Institute: Rahul is a seasoned scientist and business executive who has had significant roles in the world of academia, startups, and fortune 500 companies. Active projects for the institute include avvc.net in the area of autonomous vehicles, nextgenedu.net in the area of STEM education, and anew-da.com in the area of EDA for long life products.