Current research



Automated driving technology has matured to a level motivating a final phase of road tests which can answer key questions before the market introduction of the systems. The European research project L3Pilot tests the viability of automated driving as a safe and efficient means of transportation on public roads. It will focus on large-scale piloting of SAE Level 3 functions, with additional assessment of some Level 4 functions. The functionality of the systems will be exposed to variable conditions with 1,000 drivers and 100 cars across ten European countries, including cross-border routes.

The technologies being tested cover a wide range of driving situations, including parking, overtaking on highways and driving through urban intersections. The tests will provide valuable data for evaluating technical aspects, user acceptance, driving and travel behaviour, as well as the impact on traffic and safety. With the comprehensive piloting of automated driving functions in test vehicles, L3Pilot will pave the way for large-scale field tests of series cars on public roads.


As Automated Vehicles (AVs) will be deployed in mixed traffic, they need to interact safely and efficiently with other traffic participants. The interACT project will be working towards the safe integration of AVs into mixed traffic environments. In order to do so, interACT will analyse today’s human-human interaction strategies, and implement and evaluate solutions for safe, cooperative, and intuitive interactions between AVs and both their onboard driver and other traffic participants.

Across three European countries (Germany, Greece, & the UK), data will be collected about how human traffic participants interact in real traffic conditions. Specific situations will be identified to enable meaningful comparisons. This data will inform the development of interaction models that identify the main communication needs of road users in future traffic scenarios incorporating AVs. These interaction models will then be used to improve software algorithms and sensor capabilities for recognising the intentions of surrounding road users, and predicting their behaviours, enabling real cooperation between AVs and other road users. On the vehicle side, the AV itself will be controlled by a newly developed Cooperation and Communication Planning Unit that integrates the planning algorithms, provides synchronized and integrated interaction protocols for the AV, and includes a safety layer that is based on an easy-to-verify software with novel methods for fail-safe trajectory planning. In addition, the interACT project team will use a user-centred design process to develop, implement and evaluate novel Human-Machine Interaction elements for communicating with surrounding road users.

interACT results will be demonstrated using driving and pedestrian simulators and two vehicle demonstrators.

COMMOTIONS: Computational Models of Traffic Interactions for Testing of Automated Vehicles

As automated vehicles (AVs) are being developed for driving in increasingly complex and diverse traffic environments, it becomes increasingly difficult to comprehensively test that the AVs always behave in ways that are safe and acceptable to human road users. There is wide consensus that a key part of the solution to this problem will be the use of virtual traffic simulations, where simulated versions of an AV under development can meet simulated surrounding traffic. Such simulations could in theory cover vast ranges of possible scenarios, including both routine and more safety-critical interactions. However, the current understanding and models of human road user behaviour are not good enough to permit realistic simulations of traffic interactions at the level of detail needed for such testing to be meaningful. This fellowship aims to develop the missing simulation models of human behaviour, to ensure that development of the future automated transport system can be carried out in a responsible, human-centric way.

The behaviour of car drivers and pedestrians will be observed both in real traffic as well as in controlled studies in driving and pedestrian simulators, in some cases complementing behavioural data with neurophysiological (EEG) data, since several candidate component models make specific predictions about brain activity. The fellowship will then build on existing models of driver and pedestrian behaviour in routine and safety-critical situations, and extend these with state of the art neuroscientific models of specific phenomena like perceptual judgments, beliefs about others’ intentions, and communication, to create an integrated cognitive modelling framework allowing simulations of traffic interactions across a variety of targeted scenarios.

Such cognitive interaction models, based on well-understood underlying mechanisms, will be one main contribution from the fellowship. Some researchers have suggested the use of another type of model altogether, instead obtained directly by applying machine learning (ML) methods to large datasets of human road user behaviour, i.e., without an ambition to correctly model underlying mechanisms. This fellowship hypothesises that to achieve reliable virtual testing of AVs, both types of modelling approaches will be needed, and methods for combining them will be researched. Not least, due to their “black box” nature, ML models need to be investigated and benchmarked, to for example determine their ability to generalise to rare, safety-critical events.


The HumanDrive project will develop a prototype autonomous vehicle with the aim of successfully demonstrating a lengthy end-to-end journey in a variety of settings.

Including country roads, A-roads and motorways inlive traffic and different environmental conditions. Before being introduced to UK roads, the system will be developed and subjected to a robust testing process using a range of facilities, including simulation, hardware in the loop, private test track and small sections of public roads.

One of the key innovative aspects of the project will be the development of an advanced vehicle control system.

Designed to allow the vehicle to emulate a ‘natural’ human driving style using machine learning and developing an Artificial Intelligence to enhance the user comfort and experience.


Project TRANSITION, led by Professor Richard Wilkie in the School of Psychology, will use sophisticated laboratory-based measures (including the UoLDS) to examine drivers re-engaging with the vehicle after a period of AV control. We will determine the capability of drivers regaining steering control under conditions that simulate various types of visual and cognitive load (e.g. driving at night, and/or when looking away at a satellite navigation system). These findings will be used to identify situations where drivers are particularly vulnerable to making steering errors and develop the TRANSITION model of AV-Human transitions that will inform improvements to the design and implementation of AV systems.

Multi-Disciplinary Pedestrian-in-the-Loop Simulator

Pedestrians represented roughly 24% of road fatalities and 22% of the seriously injured in the UK in 2015 (Department for Transport, Reported Road Casualties Great Britain: 2015, Annual Report). The most commonly recorded factors were: “in accidents where a pedestrian was killed or injured; pedestrian failed to look properly was reported in 59 per cent of accidents. Failed to judge other person’s path or speed was the most typical secondary cause.” (DfT, 2015)

In this context, the increased use of Autonomous Vehicles (AVs) and new urban warning systems that can help monitor and assist pedestrians and their interactions with vehicles has the potential to dramatically reduce road deaths. A major concern, however, is that the AVs and warning systems must be designed to take into account the capabilities and limitations of pedestrians.

This project will develop a new pedestrian laboratory to support safe experimental research in a repeatable fashion in which a variety of variables with respect to AV design, warning system design, and intersection configuration can be studied. The experiments can also look at the impacts of a wide range of human factors including age, vision and mobility.

The pedestrian laboratory (PEDSIM) will consist of a Virtual Reality (VR) simulator that will allow a participant to experience a variety of urban configurations and interact with new vehicles and urban robots. The pedestrian laboratory will track the participant’s performance in a variety of tasks to compare the effectiveness of various designs.

What makes the PEDSIM unique in the world is its very high resolution displays combined with its large walkable environment (9 metres by 4 metres) and its integration with driving simulators to test interactions between pedestrians and drivers.

As automated and autonomous vehicles get closer to deployment, research into their design and impact has rapidly increased. There are several studies currently funded by the EPSRC that can take immediate advantage of the new research capabilities of the PEDSIM. These include research to evaluate solutions for cooperative interaction of automated vehicles and urban robots with pedestrians and research that will test various lighting conditions and its impact on visibility, trip hazards, and understanding intentions of other pedestrians and vehicles.

VeriCAV: Using simulation to put Connected and Autonomous Vehicles to the test

The VeriCAV project will develop an integrated platform to allow Automated Driving Systems (ADS) to be tested in simulation.

As Connected and Autonomous Vehicles technology becomes increasingly sophisticated (and the UK more prepared for driverless cars on public roads), the industry needs to explore ways to ensure autonomous vehicles operate safely. However, safety evaluation is laborious and complex, and real-world testing can be impractical and incomplete – simulation gets around these problems and opens the doors to evaluating multi-layered and uncommon situations.

Delivered by a world-class consortium of industry and academic experts, and starting in November 2018, VeriCAV is a 2-year project that will open the door to evaluating complex and uncommon CAV situations in a simulated environment.