Applications

Case study Robotic Surgery: The aim is to create a Hybrid Intelligent system in which a robotic microscope and a surgeon complement each other’s skills on the level of micrometre surgery. The robotic microscope has to learn how best to align its angle and zoom of vision with the activities of the human surgeon. This requires a mutual understanding of each upcoming surgical procedure, which is to be acquired during practice sessions. The scientific challenges are human-robot dialogues, theory of mind, shared mental models, shared planning, and collaborative ontology determination.

Scenario

 

Case study Education: The aim is to develop a Hybrid AI robot tutor and to evaluate this tutor in field experiments at schools with teachers and students. The robot tutor should engage and motivate, using techniques such as interactive storytelling and mental models. A key challenge is to create long term personalised interactions, using a memory and retrieval mechanisms that should adapt to students, provide explanations and give feedback in a responsible way. 

Scenario

A child with learning difficulties is supported by a team in which her remedial teacher, an educational therapist and a Nao robot collaborate. Together they design a targeted learning programme, monitors progress, and provide encouragement. The robot combines expertise from the humans with its own observations, and advises on possible adjusments of the programme. Interacting with the Nao robot helps the child to stay concentrated and have fun for a longer time, for which the human experts lack time and perseverance (click here for an early example of our work).

Case study Health – Diabetes: Diabetes is a chronic lifestyle related disease. A change of lifestyle requires intensive, personalised support involving both the patient and their social environment. A hybrid intelligent coach should help diabetes patients to adopt a healthier lifestyle while at the same time lowering the workload of healthcare professionals. A key challenge is the creation of multi-party dialogues between HI system, patient and healthcare professional that create long-term engagement. Explainability is crucial in this domain. 

Scenario

 

Case study Scientific Assistant: The aim of the scientific assistant is to support one or more steps in the scientific method cycle: formulating research questions, analysing the literature, formulating a hypothesis, designing an experiment, analysing data, and drawing conclusions. This will require a combination of symbolic and subsymbolic AI techniques, ranging from domain ontologies to deep learning, as well as theory of mind and shared planning to support the collaboration. 

Scenario

A scientist in a pharmaceutical company is testing a compound for an inhibitory effect on neurodegeneration. Overwhelmed by the enormous amounts of available online data, she turns to the lab’s virtual agent. It searches through dozens of databases, scans the literature, sends emails to authors of relevant papers avoiding scientists working for competing companies, and consults the HI system of the sister lab in China. The scientist and her HI agent analyse the findings and conclude that the compound has been investigated before, and failed to show the required inhibitory activity. Thanks to HI, this took a day, not weeks (click here for an early example of our work).