Q
What is VeriCAV?

What is VeriCAV?

The VeriCAV (Verification of Connected and Autonomous Vehicles) project will develop an integrated platform to allow Automated Driving Systems (ADS) to be tested in simulation. As CAV 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. The VeriCAV simulation will also mean significantly improving test efficiency when evaluating countless driving scenarios, and at the same time it can replicate the behaviour and actions of obstacles in a realistic and consistent manner.
A
Q
What are the project’s main aims?

What are the project’s main aims?

The VeriCAV project is developing an integrated test framework to allow Automated Driving Systems (ADSs) to be validated in simulation, exposing them to large numbers of complex driving situations such that developers and regulators can have real confidence in their reliability and safety when deployed on the roads. The project will go beyond scenario-based testing to a paradigm where optimal test cases are generated from the space of all possible situations. VeriCAV is also aiming to improve the efficiency of testing by minimising human effort necessary to supervise the huge number of tests expected. As part of this approach, a test analyser (also known as test oracle) will automate the evaluation of an ADS’s performance during a test run and also aggregate information on the simulation setup in order to automatically create test coverage statistics. The project will also create realistic smart actors, representing other vehicles and pedestrians that interact with the ADS. Sophisticated decision-making actors within a virtual test environment do not currently exist in any commercial product, yet they are central to injecting real-world variability into tests that don’t rely on human involvement. Finally, the project will verify that the test framework performs correctly, by testing a real ADS as the system-under-test in the simulation framework, and additionally by performing physical tests with a vehicle running the same ADS to correlate performance with the simulation.
A
Q
Which organisations are part of VeriCAV and what are their roles?

Which organisations are part of VeriCAV and what are their roles?

The consortium is made up of seven members, all of whom have specific responsibilities and areas of expertise:
  • HORIBA MIRA is the industry lead partner and will deliver a proof-of concept for advanced test scenario generation and a state-of-art test oracle
  • Connected Places Catapult (CPC) is leading on project management and dissemination and will lead two technical areas; systems requirements and simulation platform selection, and, verification and validation of the test framework.
  • University of Leeds (UoL) and Latent Logic will provide machine-learning based agents to populate the simulation environment.
  • Aimsun will advise on architectural issues relating to the use of this framework in the context of wider micro-traffic simulation.
A
Q
Will the vehicles be used on public roads?

Will the vehicles be used on public roads?

At no point during the project will autonomous vehicles be trialled on public roads. All trials will take place at the HORIBA MIRA test track, in controlled conditions, in order to validate the accuracy of the simulation tool.
A