Safe AI and autonomous systems research

The Centre for Assuring Autonomy is at the forefront of pioneering research and innovation in the field of safe AI and AI-enabled autonomous systems.

We are wholly focused on assuring the safety of AI-enabled autonomous systems. Our work is an continuation of a long heritage of research and innovation in safety-critical systems at the University of York, which works to advance novel assurance methods, policy and practice, and collaborate in diverse domains.

Our research approach

Our research takes a whole-systems perspective and is deliberately sector- agnostic, providing conceptually sound and empirically evaluated safety assurance frameworks. With that in mind, our research is split into three distinct areas: research priorities, frameworks, and projects.

CfAA Research Priorities

Our research priorities are focused on three main themes:

Lifelong safety assurance of AI-enabled autonomous systems
Human-centric design and assurance
Informed governance

Learn more about our research priorities

Professor McDermid, a man wearing glasses and a suit is standing in front of an unseen audience presenting a slide on the CfAA. There is a pull up banner with CfAA branding on the left of the screen.

CfAA Research Frameworks

One of the defining features of our research is how we have used what we've learnt to develop frameworks which support real-world decision making. You can view our existing frameworks below:

CfAA Research Projects

We are advocates of collaborative and cross-disciplinary research projects. We work with researchers and academics across such disciplines as law, ethics, and philosophy to produce well-rounded, validated research.

We can work with you on research projects ranging from:

Directly funded research
Collaborative research partnerships
PhD Studentships

Two people in hi-vis vests one on a computer with back to the camera and another closer to the camera holding a control pad for a robotic arm which is in the background