Skip to main content Skip to navigation

News Contents

WMG academic helps identify the frameworks for the Government to enrol Autonomous Vehicles

When it comes to Autonomous Vehicles the question on everyone’s lips is when will they be on the roads? However for them to be safely deployed there must be a policy framework.

SiddarthaIn the report, ‘Safe Drive Initiative: SafeDI Scenario-Based AV Policy Framework - an overview for policymakers, published by the World Economic Forum, Dr Siddartha Khastgir from WMG, University of Warwick as part of the Technical Working Group of the Safe Drive Initiative, contributed to the technological aspects of the policy framework building on his UKRI Future Leaders Fellowship research outcomes.

In order to measure driving safely in the AV sector there are many challenges, especially how to evaluate the safety of AVs. In this report, the Forum along with industry, government and academic experts have developed guidance and tools to create a useful, practicable governance approach for safety assurance of AVs, based on how it behaves in the context of its operating environment, known as its Operational Design Domain (ODD).

The Safe Drive Initiative seeks to establish a high-level framework to enable regulators and AV developers to work collaboratively to demonstrate an AV system’s capability to operate without intervention from a driver. The initiative proposes a data-driven, scenario based assessment using a graduated approach to safety assurance. The framework’s approach is vehicle and solution-agnostic and builds upon existing national and international standards, where possible. The approach focusses on assessing AV in the context of its deployment ODD by demonstrating behaviour competence in a range of scenarios and covers using simulation, driving in controlled environments and naturalistic on-road driving for evaluation. This can then be adopted by a regulator or government entities, which are responsible for managing AV development and deployment.

The report has highlighted numerous points of testing that all bodies should follow, including:

1. Prepare - Convene necessary stakeholders to identify interim milestones as a function of the deployment ODD which can be defined using standard taxonomies e.g. BSI PAS 1883

2. Define - Specify qualitative scenarios for the interim milestones as behaviour competencies in each ODD sub-set

3. Measure – Using a scenario database (e.g. SafetyPool, UK’s National CAV Test Scenario Database), select scenarios based on ODD for simulation and corresponding success criteria

4. Execute – Conduct on-road tests and perform on going monitoring to evaluate scenario exposure to refine evaluation

The graduated approach enables defining interim milestones as a function of deployment ODD. After completing all steps of the assessment regulators should have a clear idea of which AV developers are ready to operate commercially in the deployment operational design domain. Ideally, the AV developer should demonstrate the vehicle’s capability to operate without a safety driver, but this depends on back-up on mechanisms such as minimal risk manoeuvres and remote operators to take control should they meet a rare situation it is not designed to handle, for example if an emergency vehicle is approaching.

Dr Siddartha Khastgir, from WMG, University of Warwick comments:

“Although this framework is for all regulators who want to implement an operational safety assessment within their jurisdiction, not one-size will fit all, different towns and cities all over the world will have different concerns based on their respective Operational Design Domains, and therefore each step should be customised for each community. Defining the interim milestones and qualitative scenarios as a function of deployment ODD, enables this framework to be used by wide variety of stakeholders like manufacturers, governments, local-authorities etc.

“We do however hope that this framework will help us see the safe development and deployment of CAVs, so that in the future we can see the benefits of safe, clean and inclusive mobility. WMG are already researching this in many ways, as we are leading the Midlands Future Mobility testbed, which sees autonomous vehicles being tested on real worlds, and have the facilities, such as the 3xD simulator to test AVs before they go on real world tests.”

Tim Dawkins from the World Economic Forum comments:

“By bringing together a multi-stakeholder community of industry, academia, safety organizations and regulators, we’ve developed a pro-active approach which will enables policymakers to structure a safety evaluation for AVs which reflects the challenges of their roads, and expects a common standard of safety across different types of vehicle. Partnering with research institutions like WMG is essential to building the knowledge base to empower regulators for success.”

11 NOVEMBER 2020

NOTES TO EDITORS:

High-res images available at:

- 3xD Simulator: https://warwick.ac.uk/services/communications/medialibrary/images/november_2020/3xd.jpg

- Dr Siddartha Khastgir: https://warwick.ac.uk/services/communications/medialibrary/images/november_2020/sid_42.jpg

Report available to view at: http://www3.weforum.org/docs/WEF_Safe_DI_AV_policy_framework_2020.pdf

More details about Siddartha’s UKRI Future Leadership can be seen at:

- https://warwick.ac.uk/fac/sci/wmg/research/cav/vandv/ukriflf/

- https://youtu.be/sjpL82E-JCQ

A TEDx talk by Siddartha can also be seen at: https://youtu.be/KrOOXE3SW-A

Tags
Autonomous Vehicles, Featured, Showcase

World’s largest public scenario database launched for testing and assuring safe Autonomous Vehicles

Picture Ego vehicle (in black) is overtaking agent vehicle (red) on a motorway in a sunset condition.

It’s been widely stated that for Autonomous vehicles to be road-ready they have to be tested for at least 11 billion miles.

For this to be viable virtual road scenarios must contribute towards these miles, and WMG at the University of Warwick and Deepen AI have made a globally accessible database of scenarios for Governments, manufacturers and researchers to test their autonomous vehicle technology.

The Safety PoolTM Scenario Database and its role in enabling efficient testing will not only provide insights into the safety and readiness of Advanced Driver Assistance Systems (ADAS) and Automated Driving Systems (ADS), but will also help speed up the adoption of autonomous vehicles globally by providing the largest public scenario database in the world.

The Safety PoolTM Scenario Database, the largest public repository of scenarios for testing autonomous vehicles in the world, has been launched today by WMG at the University of Warwick, and Deepen AI.

The database provides a diverse set of scenarios in different operational design domains (ODDs i.e. operating conditions) that can be leveraged by governments, industry and academia alike to test and benchmark Automated Driving Systems (ADSs) and use insights to inform policy and regulatory guidelines.

Initial scenarios have been generated using a novel hybrid methodology developed by WMG, at the University of Warwick, using both knowledge-based and data-based approaches. The Safety PoolTM Scenario Database will allow organisations to create scenarios in their own libraries, collaborate with other organisations via both shared and public libraries and enable the public to submit challenging real world scenarios.

Enabling scenarios to be matched to specific environments and operating conditions means that trials and tests can be undertaken in the simulated environment, controlled test facilities and on public roads, with evidence from each environment being used to inform our understanding of safe behaviours, bringing Autonomous Vehicles closer to market at pace.

It is becoming ever more apparent that Autonomous Vehicles and the Connected and Automated Mobility (CAM) that they enable are one of today’s most exciting technological advances with industry, academia and governments investing in the research and development of safe and secure Autonomous Vehicles.

CAM will provide a once in a lifetime opportunity to have a global impact on societal issues around road safety, traffic efficiency and emissions.

However, to ensure that Autonomous Vehicles are road-ready and will be safer than the average human driver, it has been suggested that they must be tested on 11 billion miles of roads, an insurmountable goal in the real world. Therefore, the ability to test on virtual roads in simulation environments is paramount for manufacturers and government bodies to ensure safe behaviours and assure that Autonomous Vehicles are a positive influence on road safety. The true test of an Autonomous Vehicles will not be in just the number of miles driven, but also the quality and complexity of those miles, leading to a wide spread industry adoption of a scenario-based testing approach to ensure that the Autonomous Vehicle’s behaviours and capabilities are ready for the real world.

Dr Siddartha Khastgir, from WMG, University of Warwick, holds a UKRI Future Leaders Fellowship enabling him to create methods to test autonomous vehicles over a seven year programme, having already worked on the UK Government’s Centre for Connected and Autonomous Vehicles and Innovate UK funded Midlands Future Mobility, which offers a real-world ecosystem for development and trialling of Connected and Automated Technology as part of the Zenzic coordinated CAM Testbed UK capability and was fundamental in the development of the scenario database which forms the core of Safety PoolTM initiative Siddartha stresses the importance of a global database of scenarios:

“Safety of automated driving systems is a hard research challenge and can only to solved by national and international collaboration and knowledge sharing. With the launch of Safety PoolTM Scenario Database, we are inching closer to seeing automated driving systems on the roads. Testing and validating automated driving systems transparently in an integrated simulation-based framework and in real-world scenarios will not only provide insights into the readiness of ADS, but also speed up the adoption globally. WMG and MFM are grateful for the support of CCAV and Innovate UK in developing the database and we are excited to be at the forefront of this revolution.”

“The Safety PoolTM Scenario Database lays a key foundation stone for autonomous vehicle safety” said Mohammad Musa, CEO & Co-founder of DeepenAgent vehicle (red on the left) is cutting into ego vehicle's (grey) lane, while another agent vehicle (red on the right) is at front right position, on a motorway in a sunset condition AI. “We are working closely with governments across the world to create a framework for ADS certification that will bring vehicle manufacturers one giant step closer to deploying safe and secure autonomous vehicles on the roads.”

Scenarios in Safety PoolTM Database can be applied to a range of different autonomous vehicle systems, such as Automated Lane Keeping Systems (ALKS), which would see cars drive in an automated manner on motorways by adapting to speed and traffic around them, to trucking, to fully autonomous vehicles and even pods that could be used in town centres and pedestrianised areas as a ‘last mile’ mode of transport.

Safety PoolTM Initiative invites stakeholders to share learnings in the form of scenarios to expedite validation, testing and certification for the entire community.

Safety PoolTM Initiative is a global multi-stakeholder initiative with the mission of bringing transparent, certifiable safety to ADSs, uniting the autonomous vehicle community around standardised certification programs for ADSs worldwide.

Michelle Avary, Head of Automotive from World Economic Forum, comments:
“We are thrilled to work closely with Deepen AI & WMG, University of Warwick, to launch the Safety PoolTM Scenario Database. We believe Safety PoolTM Initiative is going to play a crucial role in standardising and bring transparency to ADS certification globally. We are already in advanced talks with many countries to adopt ADS certification frameworks based on Safety PoolTM database scenarios.”

Richard Morris, Innovation Lead for CAV at Innovate UK, comments:

“I am very pleased that the effort and hard work of producing this scenario database has been so successful and is now gaining the recognition it deserves. Scenario testing, both in simulation and physical tests, is widely recognised as the practical route to verifying the safety of ADS, and a comprehensive scenario database is crucial for that, and we are proud to have supported this work.”

Safety PoolTM initiative is welcoming government and industry stakeholders from all over the world to join the initiative and take the front row in bringing safety standards and certifications to their country. Members of the autonomous vehicle industry can also join the Safety PoolTM community and access safety scenarios to transparently test, validate and benchmark ADS. Visit http://www.safetypool.ai for more information.

ENDS

31 MARCH 2021

NOTES TO EDITORS

Images - credit WMG, University of Warwick.

Image scenario 1: Agent vehicle (red on the left) is cutting into ego vehicle's (grey) lane, while another agent vehicle (red on the right) is at front right position, on a motorway in a sunset condition.

Image scenario 2: Ego vehicle (in black) is overtaking agent vehicle (red) on a motorway in a sunset condition.

Video available at: https://www.youtube.com/watch?v=YjO28ode6mU (credit WMG, University of Warwick)

Please visit https://www.safetypool.ai/ for more information.

About WMG, University of Warwick

WMG is an academic department at the University of Warwick and is the leading international role model for successful collaboration between academia and the public and private sectors, driving innovation in science, technology and engineering, to develop the brightest ideas and talent that will shape our future.

www.warwick.ac.uk/fac/sci/wmg 

About Deepen

Deepen AI is a Silicon Valley based startup and the only safety-first data lifecycle tools and services company focused on machine learning and AI for autonomous systems. With tools and services that are customizable to suit the needs of enterprises as well as start-ups they have happy customers of every size across the globe. Visit Deepen.ai for more information.

About the Centre for Connected and Autonomous Vehicles

CCAV is a joint Department for Business, Energy & Industrial Strategy (BEIS) and Department for Transport (DfT) unit. Established in 2015, CCAV is an expert unit that is working with industry and academia to make everyday journeys greener, safer, more flexible and more reliable by shaping the safe and secure emergence of connected and self-driving vehicles in the UK.

Innovate UK

Innovate UK drives productivity and economic growth by supporting businesses to develop and realise the potential of new ideas, including those from the UK’s world-class research base. They connect businesses to the partners, customers and investors that can help them turn these ideas into commercially successful products and services, and business growth.

Date
Wednesday, 31 March 2021
Tags
Autonomous Vehicles, Featured, Showcase

Autonomous Vehicle safety standards to be set by Warwick academic

Siddartha Khastgir, Head of Verification and Validation, Intelligent Vehicles at WMG. UKRI Future Leaders Fellow.

Autonomous Vehicles safety will be tested by researchers at WMG, University of Warwick – thanks to a seven year UKRI Future Leader Fellowship awarded to Dr Siddartha Khastgir, worth £1.2m.

Connected autonomous vehicle technology prototypes have existed for some time, however questions around the safety of this technology from the public and industry who want to commercialise these technologies has blocked it from developing.

The future with CAV has to be more reliable, more efficient and less risky. So safety testing is essential to informing people’s opinion about this new technology.

In order to prove that CAVs are safer than human drivers, it’s been suggested they need to be driven for more than 11 billion miles. However, instead of the number of miles, it more important to focus on the experiences of the CAV in those miles to identify any smart miles which expose failures in CAV.

Dr Khastgir’s fellowship will therefore develop pioneering testing methodologies and international standards to enable robust and safe use of CAV, particularly focusing on creating both fundamental knowledge and applied research methods and tools.

WMG, University of Warwick, has created a concept of the “evaluation continuum” for CAV, which involves using various environment like digital world, simulated environment, test track testing and real-world for testing.

There are two aspects which are common to each of the evaluation continuum environments and also the focus areas of the fellowship research

1) Test Scenarios: exposing failures of the CAV

2) Safety Evidence: establishing how safe is safe enough?

As a part of this fellowship, three approaches will be explored to identify the smart miles which expose any CAV failures including:

· Using Machine Learning (ML) based methods including Bayesian Optimisation to create test cases for test scenarios

· Safety Of The Intended Functionality (SOTIF) (Innovative safety analysis of CAV) based test scenarios using Systems Theoretic Process Process Analysis (STPA)

· Translating real-world data into executable test scenarios for a simulation tool.

All these approaches will together contribute to the creation of a UK’s National CAV Test Scenario Database. Dr Khastgir has previously written about enabling British CAV deployment and the role of standards for the BSI (British Standards Institute), and hopes to build on the Fellowship research outcomes to build standards for national and international purposes.

Dr Siddartha Khastgir, from WMG, University of Warwick comments:

“The global Connected and Autonomous Vehicles (CAV) industry is estimated to be worth over £50bn by 2035, with the UK CAV industry comprising over £3billion of this, however questions around safety are always raised, by the automotive industry and the public.

“This hinders the process of commercialising CAVs, however my UKRI Future Leaders Fellowship to research the safety of CAVs can help Department for Transport, the automotive industry and the public to be reassured that they are safer than human drivers.

“I am incredibly grateful for the UKRI Future Leader Fellowship, as it puts the UK and the University at the forefront for research and development into the safety of CAVs.”

Margot James, Executive Chair at WMG, University of Warwick adds:

“WMG is very proud that Dr Siddartha Khastgir has been awarded a prestigious UKRI Future Leaders Fellowship (FLF). Through Siddartha’s research we can enable the UK to become a world leader in safe CAV deployment.”

Kirsty Grainger, Director, Future Leaders Fellowship Scheme adds:

“Dr Siddartha Khastgir is taking forward a really exciting project that supports the government’s Future of Mobility grand challenge. Through the Future Leaders Fellowships we’re not only delivering cutting edge research like this, but also investing in the individuals who have the potential be leading researchers and innovators in years to come. I am delighted that Dr Khastgir is part of the programme.”

Date
Tuesday, 22 September 2020
Tags
Autonomous Vehicles, Featured, Showcase