Verification of Autonomous Systems

The overarching aim of the Verification of Autonomous Systems group is to develop novel computational methods and tools for providing safety guarantees to a wide range of autonomous systems, including autonomous vehicles, robotic systems, and swarm systems.

We are particularly active in the following topics:

  • Scalable methods and tools for the verification of neural networks, including CNNs, and RNNs.
  • Parameterised model checking methods for the verification of swarm systems.
  • AI-based specification languages and logic-based verification methods for reasoning about agent-based systems.
  • Safe reinforcement learning for agent-based systems.

Our work is guided by a passion for Artificial Intelligence and the belief that AI should be safe and secure for society to use.

We have a history of development and maintenance of open-source state-of-the-art toolkits for Safe AI and international collaboration both with academia and the industry.

We presently benefit from strong links with the Assured Autonomy DARPA program and the Centre for Doctoral Training in Safe and Trusted AI.


13 September 2021

Alexander Manta

19 July 2021

Verinet wins the Second Highest Score Award and is category winner for mnistfc at VNN-COMP'21

19 July 2021

Venus wins the Beat-Randgen Award at VNN-COMP'21

17 July 2021

VAS members have a paper accepted at FM 2021

15 June 2021

VAS members have a paper accepted at KR 2021

04 May 2021

Meet the new team member: Jianglin Lan

... see all News

Next Scheduled Seminar

There are currently no seminars planned.

... see other seminars