University of Warwick: Joint European effort boosts automated driving

From 11 to 15 October the European research project L3Pilot, which WMG at the University of Warwick have worked on led by Volkswagen AG and co-funded by the European Commission, showcases automated driving functions in the City of Hamburg and on motorways nearby. The four-year project will now come to its successful end with performing its Final Event in conjunction with the ITS World Congress in Hamburg 2021.Caption: WMG, at the University of Warwick demonstrating their technical achievement at ITS World Congress. Credit: WMG, University of Warwick

Running from 2017 to 2021, the project consortium brought together stakeholders from the whole value chain, including car manufacturers, suppliers, academia, research institutes, infrastructure and governmental agencies, user groups and the insurance sector.

The experience of the partners in large-scale testing intelligent vehicle technologies made it possible to create a pan-European testing environment. The Code of Practice for the Development of Automated Driving Functions (CoP-ADF) is one of the major achievements of L3Pilot. It provides comprehensive guidelines for supporting the design, development, verification and validation of automated driving technologies.

Fourteen partners focused on testing automated driving functions in normal motorway driving, traffic jams, urban driving and parking. The pilots, running from April 2019 until February 2021, involved seven countries: Belgium, Germany, France, Italy, Luxemburg, Sweden and the United Kingdom and included two cross-border activities between Germany and Luxemburg as well as Germany, Belgium and the United Kingdom.

WMG, at the University of Warwick focussed on the development of a proof-of-concept prototype and a real-world demonstration of a cutting-edge technology for cooperative perception, using WMG’s state-of-the-art Open Innovation Vehicle Platform and mobile roadside units. The technology developed by WMG aims to enable safe automated driving at complex driving scenarios, such as roundabouts and T-junctions.

However WMG also contributed to a variety of key project activities including: Cyber Security Analysis of highly automated driving functions in highway environments, known as highway chauffeur, and the development of a Consolidated Database (CDB) to store large datasets acquired in the project during the experimental phase, which also included designing and implementing a web-based User Interface (UI) to provide access to CDB for L3pilot users, for example, partners and data analysts.

Prof. Mehrdad Dianati, from WMG at the University of Warwick comments:
“A major challenge for the safety of automated vehicles is how they will navigate through complex road segments, a part of our role in L3Pilot was to demonstrate how this challenge can be addressed using state-of-the-art cooperative automated driving technology we have developed at WMG.

L3Pilot Coordinator Aria Etemad, Volkswagen AG comments:
“Automated driving has a huge potential to make mobility safer, more efficient and more comfortable. The L3Pilot partners made great efforts to pursue piloting and met the project goals – despite the tremendous pandemic crisis. This shows the outstanding commitment of our Europe-wide partner network. One of our major achievements is a Code of Practice for the Development of Automated Driving Functions. It provides guidelines that will support the development of safe and reliable automated driving systems.”Caption: WMG, at the University of Warwick demonstrating their technical achievement at ITS World Congress. Credit: WMG, University of Warwick

The project equipped 70 vehicles and the test fleet comprised 13 different vehicle brands, from a passenger car to a SUV. More than 400,000 kilometres were driven on motorways including 200,000 km in an automated mode and 200,000 km in a manual mode as a baseline for comparison of the user experience and evaluation of the impacts. More than 24,000 km were travelled in the automated mode in urban traffic. With the aim to put the focus on the user experience of automated driving functions, over 1,000 persons participated in piloting and complementary virtual environment tests.

The project focused on SAE Level 3 automated driving functions on motorways and in urban traffic, while SAE Level 4 functions targeted exclusively parking and close-distance scenarios. The SAE Level 3 features Conditional Automation which requires the driver to respond appropriately to a request to take-over the vehicle control for manual driving. In case the driver is not responding properly to a take-over request, the vehicle performs an automatic minimum risk manoeuvre to safely stop the vehicle.

Moreover, L3Pilot carried out extensive supplementary tests to also research user experiences that were difficult to address in large-scale piloting due to safety requirements and legal issues. Therefore, supplementary studies were performed in addition to the on-road piloting to be able to study system usage and other relevant user experiences with ordinary, non-professional drivers in safe and virtual environments. The extensive studies comprised some 600 subjects.

Research evaluation results have shown that increased safety is the main benefit of SAE Level 3 automated driving systems. They also show that an automated driving system consisting of motorway, urban and parking functions for robust hands-off driving will generate a social benefit that is higher than the social costs of installing it.

L3Pilot paved the way for scaled-up driving tests with automated series vehicles in real-life traffic. This underscores the leadership of Europe’s automotive industry in developing reliable, thoroughly tested and user-friendly technology.