Connected and Autonomous Vehicles (CAVs) are an emerging technology that offer huge potential benefits, including improved safety, lower emissions, inclusive mobility and more efficient journey times. However, to unlock this potential, it is essential that CAVs are introduced safely and are also accepted and used by society. It is essential to have a strong regulatory environment to enable this journey.

With the UK government committing to delivering safer, cleaner transport and enabling more innovation in the Transport Bill in the Queen’s Speech, there has never been more of a focus on ensuring autonomous vehicles are implemented safely.

A RAND corporation study suggested that CAVs would need to be driven 11 billion miles to prove they are even 20% safer than human drivers. Achieving this form of regulatory approval therefore poses a new challenge, one that cannot be solved through distance driven alone.

Research at WMG, University of Warwick led by Professor Paul Jennings addresses this problem by posing alternate methods and standards for autonomous vehicle safety and roadworthiness. The research has been critical to the development of international standards and regulatory policy for CAVs and has accelerated the commercial development of driverless pods around the world in addition to increasing societal trust in CAVs.

Developing a testing approach

While prototype CAV technologies have existed for some time, ensuring the level of safety of these technologies has been a barrier to the commercialisation and adoption of CAVs. This is due to the challenges of testing automated driving systems in all the complex scenarios they may face in public environments. There are five fundamental and intrinsically linked stages required for a new testing approach.

1. Create – the identification of test scenarios
2. Format – the articulation of test scenarios in appropriate form
3. Store – the central repository of test scenarios enabling sharing and contribution
4. Execute – the running of test scenarios in suitable environments
5. Use – the usage of results in safety evaluation

Researchers at WMG, University of Warwick have been focusing on the all the stages of this testing approach which are key to the development of regulatory impact and standards. WMG’s work includes the development of a Hazard Based Testing approach which focuses on understanding the different scenarios that the CAV experiences during its journey, rather than the number of miles travelled. The research team have also developed a Scenario Description Language (SDL) to meet the differing levels of detail required by regulators and users of simulation-based testing, as well as the Safety Pool^TM Scenario Database – world’s largest public scenario database for exchange of scenarios. By utilising a unique 3D simulator for Intelligent Vehicles, the team were able to learn more about simulation-based testing to bridge the gap between virtual and real-world testing.

 Influencing policy and regulation

CAV research at WMG has directly fed into 13 national and international standards in total, including the international standards for both low speed automated driving ISO 22737 and for Operational Design Domain (ODD) (BSI PAS 1883 and ASAM OpenODD).  

Dr Siddartha Khastgir, Head of Verification and Validation at WMG commented: “Defining the ODD, or the operating conditions of a driverless vehicle, is fundamental to ensuring its roadworthiness. Our research has helped to remove a key barrier to worldwide uptake of these greener and more inclusive transport systems, and regulators across the globe have been given the confidence that this emerging technology can be used safely.”

WMG has further contributed to CAV policy and regulations, supporting the Law Commission, The Department for Transport in the UK and with Transport Canada on implementing CAV standards in real-world environments.

Discussing the benefits of the standard, Transport Canada’s Chief of Human Factors & Crash Avoidance explained, “ISO 22737 has accomplished exactly what international standards are designed for – providing a framework of guidance designed by experts which can be applied ubiquitously to its subject area. Simply put, these trials, which are at the forefront of autonomous driving in Canada, would have been fundamentally impossible without ISO 22737 being in place. ISO 22737 provided the means to collect the evidence to help determine if the shuttles were roadworthy.”

WMG’s research has also played a vital role in the Centre for Connected and Autonomous Vehicles (CCAV), a joint policy unit between the Department for Transport and BEIS which acts as a point of contact for industry and academia for CAV technologies.

Social and commercial impact

Beyond influencing expenditure for multiple government agencies in the millions, the standards have also enabled pilot schemes in Canada, Japan and the UK, with over 23,000 members of the public travelling a combined distance of more than 20,000km.

The development of a novel methodology to create test scenarios and environments for testing has also accelerated the safe roll-out of automated driving pods by two leading manufacturers – Aurrigo (UK) and Yamaha (Japan).

Aurrigo’s CTO commented: “The novel virtual testing environment Warwick has developed has enabled us to accelerate the development and capability of our automated driving system. This will also allow us in the future to reduce the expected cost of our automated vehicles by 55% and allow our potential customers to save an estimated 70% in deploying the vehicles at scale by enabling one supervisor to supervise multiple vehicles. WMG is critical in enabling the safe deployment of our technology as we move to real-world applications and future scale up.”

Professor Paul Jennings concluded: “Working with both national and international partners, we are using the learning from our research to help create a regulatory environment that enables commercial innovation, which drives investment and creates new job opportunities, whilst crucially preventing the introduction of unsafe technologies.”

For more information about this research visit: https://warwick.ac.uk/fac/sci/wmg/research/cav/