Next Generation Decision Support Tools
How to talk to algorithms? How to explain them if they are wrong? How they should talk to us? These are some of the questions we are investigating in the NextGenDST project.
The overall goal of the NextGenDST project is to improve performance within time-critical complex domains, such as emergency management, Air Traffic Management (ATM), maritime and train dispatching, by developing a new generation decision support tool (NextGenDST). The tool will enable better human/automation collaboration during decision-making activities by: i) enabling humans to communicate their intentions, preferences and priorities to the tool, ii) enabling negotiation between humans and the tool, iii) identifying decisions that are close to the optimal ones but that humans can control, understand and execute, iv) intervening only if the potential for improvement is high, v) explaining the rationale behind the proposed decisions in a way understandable for humans, and vi) presenting impacts of the proposed decisions on the global performance of the system.
Different topics and approaches are possible within this project. One option is explore trust within this context. How design can increase trust? Another option is to explore benefits of virtual reality for decision support. More about project: http://bit.ly/204d497
This project will enable you to combine a good theoretical understanding of human-computer interaction with a hands-on experience to technology design and collaboration with industrial partners. You will be a member of the NextGenDST project team and have access to a wide variety of experts.
For this master thesis, it is mandatory that you take INF2260/4060 - Interaction Design.