Verifiable Autonomy

In the next 20 years, we expect to see autonomous vehicles, aircraft, robots, devices, swarms, and software, all of which will (and must) be able to make their own decisions without human intervention.

This EPSRC funded project is concerned with building autonomous systems that are verifiably correct. It is a joint project with Liverpool (lead) and Sheffield, and the Bristol Robotics Laboratory contribution is to develop and build robots that can behave ethically.

In this project, we will build on internationally leading work on agent verification, control and learning, safety and ethics, and practical autonomous systems to advance the underlying verification techniques and so develop a framework allowing us to tackle questions such as the above. In developing autonomous systems for complex and unknown environments, being able to answer such questions is crucial.