Robust Autonomy and Decisions group

Our work focusses on building autonomous robots and other cyber-physical systems systems, capable of working robustly in application domains such as the following:

Human-robot collaborative work in customisable manufacturing, personal robotics, etc.
Active sensing, predictive modelling and decision making in energy and environmental systems.

This motivates us to develop new models and algorithms to address conceptial issues such as:

Compositional and incremental methods for model learning and learning to act in multi-scale, dynamic environments.
Mechanisms of extended interaction for model selection, structure learning and coordinated action in the face of unknown unknowns.