Siddartha Khastgir, Head of Verification and Validation, Intelligent Vehicles at WMG, discusses Connected and Autonomous Vehicles, achieving the long-term vision, and testing.

The vision

The global Connected and Autonomous Vehicles (CAV) industry is estimated to be worth over £50billion by 2035, with the UK CAV industry comprising over £3billion of this. Additionally, the UK Government's Industrial Strategy aims to bring fully autonomous cars without a human operator on the UK roads by 2021, which will make us one of the first countries in the world to achieve this vision. The CAV vision is motivated by a variety of potential benefits the technology has to offer – increasing safety by reducing accidents and minimising human error, decreasing traffic congestion, driving lower emissions and freeing up drivers’ time in vehicles - enabling individuals to be more productive during the work commute or the school run.

However, in order to realise this vision and the market potential, safe introduction of CAV is crucial. The diverse technological, legislative and societal barriers associated with public deployment of CAV will require significant research to overcome.

A safer way to travel

It is suggested that in order to prove that CAV are safer than human drivers, they will need to be driven for more than 11 billion miles. While this requirement has garnered a lot of publicity, the focus needs to be on what happens in those miles (i.e. smart miles which expose failures in CAV) and not on the number of miles themselves. One will not gain much information about the capabilities of a CAV system if we drive them up and down the sunny roads of a desert.

While prototype CAV technologies have existed for some time now, ensuring the safety level of these technologies has remained at the forefront of development decisions and considerations, and has emerged as a potential hindrance to the commercialisation of CAV technologies.

Presenting hard evidence-based data and trends efficiently will have a significant impact on public adoption of this new technology and the confidence levels invested. Safety is at the forefront of the case for why a future with CAV is more reliable, more efficient and less risky – But just saying this is not enough, people want to see objective insights and make their own informed decisions on how this new technology is safer.

The task of proving this is coupled with the challenge of requiring innovative testing and safety analysis methods, as interactions between large numbers of variables and the environment demand complex solutions and experimentation.

Positioning the UK as a world leader

WMG at the University of Warwick, facilitates collaboration between academia and the public and private sector to drive innovation in science, technology and engineering. Intelligent Vehicles research, at WMG, is focused on supporting the UK’s position as the world leader in CAV research and innovation for a long lasting societal and economic benefit.

Intelligent Vehicles research capability areas include Verification and Validation, Communications (i.e. 5G), Experiential Engineering, Supply Chains, Cyber Security and Cooperative Autonomy. Demonstrating safety, commercial viability and customer desirability pose three of the main challenges associated with realising the CAV vision. The “evaluation continuum” concept for CAV, at WMG, involves using digital technology to simulate various environments and conduct repeatable test track testing before launching trials in the “real-world”. WMG research is leading to the creation of international standards (ISO) for the safe deployment of CAV.

Testing in a virtual world

WMG’s 3D simulator for Intelligent Vehicles, funded by the Engineering and Physical Sciences Research Council (EPSRC), was launched in 2016 at WMG’s International Manufacturing Centre to test real-world robustness and usability of smart, CAV technology. The simulator creates virtual conditions for Intelligent Vehicles, replicating complex driving scenarios, changing lighting conditions, communications interference or unexpected events, all in a safe and repeatable environment.

The success of smart, CAV technologies, or Intelligent Vehicle technologies, will depend upon research and development, which can quickly demonstrate safety, security and robustness. Testing these technologies on-road in real-world driving situations is often complex, uncontrollable and potentially risky for early stage development. It is also reliant on the production of costly physical prototypes.

Industry trends in CAV suggest the widespread adoption of Machine Learning (ML) in the autonomous control systems. ML-systems by their structure are non-deterministic in nature, resulting in different behaviours and a lack of transparency around the CAV system. Therefore, it is often difficult to identify reasons for a particular failure in such ML-based systems and take the corrective measures.

Public road testing by mid-2020

WMG is involved in major research programmes like the £35m Midlands Future Mobility (real-world testbed), which focuses on “smart miles” by proving concepts and getting products to market with quick impact measures. Led by WMG, Midlands Future Mobility is an “on-road ecosystem” comprising nine partners from industry and local authorities all with a shared vision and objective - To launch the first service offering of public road testing by mid-2020.

WMG is also one of the seven centres in the High Value Manufacturing (HVM) Catapult and with “smart mobility” being one of the focus areas for the WMG HVM Catapult centre, their existing strong links and partnerships leave them well positioned to inform and respond to Government policy.

Achieving the Connected and Autonomous Vehicle vision

Past studies have indicated that only 50% of drivers tend to use Advanced Driver Assistance Systems (ADASs) like Lane Departure Warning. Increasing trust and acceptance of CAV technologies remains a challenge for the industrial and research community. Reaping the benefits of the CAV technologies will only happen when they are accepted by drivers and the wider public as a fundamental part of their everyday lives.

Challenges associated with realising the CAV vision are huge, but the benefits are even bigger. The only way we can achieve the CAV vision is through collaboration and knowledge exchange between various stakeholders – manufacturers, SMEs, suppliers, local councils and research organisations.

Search: WMG Intelligent Vehicles for more information.