The MOVE_UK project was jointly funded by government and industry, trailing a new ‘connected validation’ methodology for Advanced Driver Assistance Systems (ADAS). The work will sought to achieve more efficient validation of ADAS, without compromising safety, all while assessing how this method could be used in the type-approval of autonomous vehicles.
Business and Energy Secretary Greg Clark said: “Low carbon and self-driving vehicles are the future and the UK is determined to be one of the leaders in this technological revolution. Through our Industrial Strategy, the Government is laying the foundations to ensure the UK seizes the opportunities presented by the development of our next generation of vehicles.
“Government investment, through our Intelligent Mobility Fund, in the MOVE_UK programme is helping deliver this pioneering research into the ‘real world’ application of this technology. It is a collaboration between Government and industry that is building our expertise and reputation in self-driving technology and support our clean growth, low-carbon agenda.”
The technological race to develop and launch automated driving systems is gathering speed, but traditional methods for developing, testing and validating vehicle safety systems are not keeping pace with the increasing complexity of these systems. It is not possible to design physical tests for every situation that a car might encounter on the road.
To respond to this challenge, the MOVE_UK consortium came together to develop innovative solutions and methodologies designed to speed up the validation, evaluation and approval process for automated driving systems by analysing data sourced from vehicles in the real world.
TRL, together with partners Bosch, Jaguar Land Rover, Direct Line Group, The Floow and the Royal Borough of Greenwich, conducted live trials of automated driving systems using a fleet of five Land Rover passenger vehicles.
Sensor and automated driving data was transmitted to TRL’s data hub, where partners will evaluated the performance of the driving system and model changes to the control software. The work was carried out in the UK Smart Mobility Living Lab, London.
The project’s data was gathered from sensors installed on a fleet of Land Rover vehicles that completed more than 30,000 miles of driving on public roads in Greenwich by council workers from their fleet services department. As part of the new validation method, data was selected and recorded intelligently which helped to reduce the total volume of data collected and speed up validation of the automated driving functions in the real world. The data was then automatically transferred to a central cloud, allowing researchers to analyse it remotely, using newly developed tools. As a result, the consortium partners were able to analyse how automated driving functions respond in the real world, helping to ensure that future autonomous vehicles drive in a natural way, retaining the positive driving characteristics of a good driver.
Taking place in the Royal Borough of Greenwich – one of the UK’s leading ‘smart cities’ and a global reference point for mobility innovation – the project has enabled the MOVE_UK consortium to develop a new validation method that will reduce the time taken to test automated driving systems and bring them to market.
At the same time, TRL started to use the “Big Data” resource to develop a UK framework for regulatory and type approval safety requirements for automated driving technologies.
Richard Cuerden, Academy Director at TRL commented: “This project brings us another step closer to seeing autonomous vehicles on UK roads. Through MOVE_UK we are able to compare the behaviour of the automated driving systems with the behaviour of human drivers, which, in turn, will help to improve the safety and validation of automation systems.”
A defining feature of MOVE_UK Phase 2 was the addition of front radar sensors to all trial vehicles, which extended the vehicles’ sensor perception and allowed experimentation with methods for validating different sensor modalities. The integration of the radar sensors in the vehicles required both hardware and software adaptions. The project’s data recording and analysis tools were also updated and extended to allow easy access to statistics and visualisations of the radar data collected.
The primary focus of this report is set on the four new use cases, which make use of the Phase 2 radar capabilities: Lead Vehicle Statistics (LVS), Radar-based Autonomous Emergency Braking (ARB), Cut-in Scenarios (CIN) and further telematics (Telematics 2).
The ultimate aim of the telematics use case is to construct a method through which a comprehensive and synoptic description of risk can be computed. To achieve this, the MOVE_UK team is seeking to combine knowledge of telemetry, driver behaviour, the conduct of surrounding vehicles and geographical factors into a single parameterisation.
However, to obtain such an understanding will require continued studies to obtain more data using a greater number of vehicles, ideally with the ability to distinguish between specific drivers.
However, data collected during Phase 2 can be used to reach a good understanding of vehicles-in-front for incorporating into models of risk. Knowledge of the traffic context in which the vehicle is driving is clearly important, letting us observe not just how the driver is driving, but whether the observed behaviour is normal.
The defining feature of MOVE_UK Phase 3 was the addition of corner radar sensors to two of the trial vehicles. This additional hardware extended these vehicles’ sensor perception yet further and allowed experimentation with new use cases which rely on a full 360-degree understanding of surrounding objects; something that is vital for the successful development and validation of more complex automated driving features. The project’s data recording and analysis tools were updated and extended to allow recording and visualisation of the additional corner radar data. These improvements are described in Section 2.
The primary focus of this report is on three new use cases, which make use of the Phase 3 corner radar capabilities: Surround sensing of Cut-In situations (SUR-CIN), Surround sensing of Cross-traffic situations (SUR-CROSS), and further telematics (Telematics 3). Figure 1 illustrates the role of these use cases within the previously defined framework of capabilities which MOVE_UK aims to demonstrate, and the applications that are envisaged for the developed methodologies. The Phase 3 use cases and related capabilities are described in more detail in Section 4. Finally, Section 5 captures our final conclusions from all Phases of MOVE_UK.