Virtual Validation is a method to collect objective evidence of the reliability of the decision making that is built into the “brain” of an AV system.  It uses a powerful combination of 3D simulation of an AV, injected into a simulated environment, to see how the vehicle behaves when presented with precise conditions known to have caused an incident in the real world. With that data, it then becomes possible to evaluate the behaviour of the AV against agreed safety performance requirements.

 

This event will be hosted by James Long, Solution Architect at SMLL. Our guest presenters are Ceki Erginbas, CAV BIM Consultant at TRL and Dr David Hynd, Chief Scientist at TRL. They will explain the science behind this concept and demonstrate it in action.  They will put the technique into context in this fast-changing automotive sector, and identify its role and relevance to European R&D. Adam Barrow, Collision Data Consultant at TRL will join the panel for Q&A.

 

During this session they will show you firstly what it is and how it works

•  The multiple tools to be integrated, and techniques required to generate the evidence

•  With real examples to showcase the levels of detail possible, the integrity of the data, and the benefits of current capability

•  Suggesting future options for testing at scale

 

Virtual validation was brought to life in the STREETWISE project

Dr Hynd will share what we learned, and what this means for future projects seeking to validate new ADAS technologies, or whole new vehicle designs, or new connected infrastructure, or new operating service features.

 

>> Please register your interest using this Eventbrite link.

 

During the course of this session, you will discover

•   Why we need virtual validation as a component of the independent certification of automated vehicles

     - Part of the evidence base for safe operation in a complex road environment

     - To support public acceptance of and trust in automated vehicles

     - To ensure the localisation of AV training e.g. national road signs, driving norms …  and driving on the ‘wrong’ side of the road!

•    How to use real-world collision data to construct detailed test scenarios for automated vehicles

       - An exemplar tool-chain to go from national level collision data… Via in-depth collision reconstruction databases such as DfT’s RAIDS…To a full representation of the collision scenario

•    How to evaluate the performance of the AV in each test scenario

       - What is an acceptable AV behaviour in different scenarios?

       - How to rate/balance different approaches to safety

  • What next…?

 

We will leave as much time as possible for Q&As.

 

>> Please register your interest using this Eventbrite link.

 

This live event is by invitation only and will not be made available afterwards.

 

   

Register for our newsletter

Learn more about TRL with regular updates

Media membership

Our latest press releases and news

Get in touch

Have a question? Speak to one of our experts today.