The projects will look into the use of radar and video sensing to interpret the external environment, road conditions and other road users; how drivers will react to new autonomous systems; how systems can be designed to adapt to the personal characteristics of users; investigate how the transition between human control and automated systems can be designed to best effect; how distributed control systems and cloud computing can be integrated with vehicles; and how data from intelligent infrastructure, drivers and automated vehicles can be used to aid interaction.

To realize the future potential for fully autonomous vehicles, we need to give drivers, pedestrians and other road users the confidence that a car driving around with little or no human input is a safe, viable and rewarding experience. These collaborative projects will bring some of the UK’s leading academics together with our autonomous driving team to address the fundamental real-world challenges that are part of our journey towards autonomous driving.

—Dr. Wolfgang Epple, Director of Research and Technology, Jaguar Land Rover

The five projects are:

Pervasive low-TeraHz and Video Sensing for Car Autonomy and Driver Assistance (PATH CAD). Led by Dr. Marina Gashinova, the project combines novel low-THz (LTHz) sensor development with advanced video analysis, fusion and cross learning. Using the two streams integrated within the sensing, information and control systems of a modern automobile, it aims to map terrain and identify hazards such as potholes and surface texture changes in all weathers, and to detect and classify other road users (pedestrians, car, cyclists etc.).

The project is a collaboration between the three academic institutions: the University of Birmingham with its long-standing excellence in automotive radar research and radar technologies; the University of Edinburgh with world class expertise in signal processing and radar imaging; and Heriot-Watt University with equivalent skill in video analytics, LiDAR and accelerated algorithms.

Human Interaction: Designing Autonomy in Vehicles (HI:DAV). Led by Professor Neville Stanton at the University of Southampton, the project, with the University of Cambridge as a partner, will study a wide range of drivers with different driving experience in simulators, or test-tracks and in road going vehicles to investigate how drivers will react to this new technology and how best to design the driver-automation interaction.

The studies will progress from the simulator to the test-track, as interaction and interface designs evolve with testing. On the test-track, driver behavior physiological and psychological states will be recorded to see what further changes are needed and whether the automation can be even more highly tailored. As the research progresses revised designs will be taken into road-going vehicles for the final set of tests.

The team will start by modeling driver behaviour in laboratories to help design inclusive, user-centered, interfaces with vehicle automation. Then they will test the designs out in a driving simulator (which comprises a Jaguar XJ connected to computers with large projectors and screens).

They will test drivers of different ages, gender, experience and capabilities, in a range of scenarios (eg, different road types and environmental conditions) with different automation systems (eg, autonomous driving, auto valet parking, adaptive vehicle personalization, off-road assistance) and different interfaces.

The design approach will aim to personalize the driver interfaces to the widest range of drivers possible so that the system adapts to the driver, rather than the driver having to adapt to the system.

Driver-Cognition-Oriented Optimal Control Authority Shifting for Adaptive Automated Driving (CogShift). Led by Dr. Dongpu Cao at Cranfield University, with UCL as a partner, this project aims to achieve a safe engagement and smooth and swift control-authority shift between the driver and the vehicle controller during adaptive automated driving.

The team will first conduct a comprehensive study of driver attention and cognitive control characteristics when interacting with the vehicle controller. An optimal control authority shifting system which considers driver cognition will then be systematically developed and validated.

This cross-disciplinary research challenge will be addressed using a combination of researchers from engineering, cognitive neuroscience and human factors. The research will not only contribute to technology innovations in automated driving, but will also advance the science of human attention and cognitive control when interacting with automation.

Secure Cloud-based Distributed Control (SCDC) Systems for Connected Autonomous Cars. Led by Dr. Mehrdad Dianati at the University of Surrey, this project also involves Imperial College London, University of Warwick, and the UK’s Transport Research Laboratory.

Modern cars are expected to become intelligent agents that learn from their environments and exploit various sources of information to become increasingly autonomous systems that relieve the driver from tedious tasks, such as parking, and improve safety, efficiency, and desirability of the future cars.

This project will design and validate a framework that combines the power of the connected vehicles concept with the notion of autonomous systems and build a novel platform for cost-effective deployment of autonomous features and ultimately realization of connected and fully autonomous cars.

This will rely on modern wireless technologies and the power of cloud computing that allows sharing expensive computing resources (hence, reducing costs per vehicle) and provides access to information that are only available on the cloud.

To realize the ambition of the project, a number of key challenges in the areas of ultra-low-latency wireless technologies, cloud computing, distributed control systems, and human interaction issues will be addressed. In addition, potential security threats will be identified and analysed to assess the possible risks for the public and reputational damage for car manufacturers should such technologies be commercialized.

The long-term objective is to enable affordable driver-less cars; in the short term, the project aims to enable a number of demonstrable autonomous features in a test environment.

The Cooperative Car. Led by Dr. Nathan Griffiths at the University of Warwick, this project will will develop intelligent driver systems, and cooperation and behaviour modelling techniques that learn about drivers, enabling vehicles to cooperate with each other and with urban transport infrastructures.

This will entail developing software algorithms, applying experimental methods from behavioral sciences and processing information from connected cars, to understand driver habits, and to develop strategies to encourage behavior modifications—for example, to design adaptive pricing to reduce parking and congestion.

The project will also investigate how best human drivers and autonomous cars can interact, for example when taking or handing-over control, or when interacting and negotiating with other road users.

Modern vehicles are equipped with hundreds of micro-computers and sensors, including cameras, radar, GPS, and telemetry measuring everything from speed, braking, and steering to environmental conditions.

Many vehicles have wireless communications (from 2018, new EU cars will have data communication for automated emergency calls) enabling data to be uploaded in real-time to the cloud to be later analysed and used. Current vehicle features operate relatively independently, however such data gives the potential for a vehicle to learn about its driver and environment, and paves the way for integrated intelligent features and eventually for autonomous cars.

Jaguar Land Rover has a vision of a self-learning car (SLC) that will minimize driver distractions, enhance safety, and deliver a personalized driving experience. This project will apply advanced research techniques in machine learning and the processing and mining of large data streams to make the SLC a reality.

For example, it will use telemetry and information about the occupants, such as their cognitive load; to personalize the driving experience; to predict the destination; adaptively to configure safety systems; and to advise on congestion avoidance and parking opportunities.