Skip to main content

Single & Multi-Modal Video-Based Human-AI Collaboration

Single & Multi-Modal Video-Based Human-Machine Collaboration

The overarching goal of this work package is to investigate technical approaches that advance knowledge in AI-assistive technology for healthcare imaging systems that work as assistants or peers. To date we have been focussing on dynamic multimodal ultrasound guidance models and human-AI systems that can determine when and how to appropriately defer to either the human expert or the AI model. The later extends to the design of collaborative frameworks for shared human–AI tasks.

Ultimately, the goal is to develop adaptive AI systems that can evolve the human–AI collaboration relationship over time, tailoring interactions to individual users.

 

This research is funded by UKRI Engineering and Physical Science Research Council (EPSRC) Programme Grant Scheme under the reference number EP/X040186/1