We investigate the theory behind safe, verifiable, and trustworthy autonomous systems. Our work looks at their use from smart cities to disaster response.
Our research
We address:
models of safety
responsibility and optimisation for artificial intelligence (AI) systems
reinforcement learning
game theory and negotiation
mechanism design
reasoning and learning under uncertainty
ethical and responsible AI
Human-in-the-loop interaction
Research challenges in this area include exploring how to build better human-in-the-loop AI systems which use AI o support and augment human performance. This both enhances interaction experiences for humans and uses human expertise to enhance AI performance.
Our research includes:
human-system/robot interaction
natural language processing
machine listening
human-agent collaboration
citizen centric AI
Autonomous systems
This area of research involves looking at how systems evolve, learn and adapt enable us to better understand complex networks of individual actors. Our research in this area spans:
