CE33 - Interaction, robotique

Multi-Level Decision-Making with Interactive Systems – NEUROHCI

Submission summary

This project is in Human-Computer Interaction (HCI) and aims at designing interactive systems developing user expertise by establishing a human-machine partnership. Interacting with these systems can be seen as a multi-scale decision-making problem: 1) Task, i.e choosing the right medical treatment or business strategy based on visualisations or AI-based recommendations; 2) Method, i.e. choosing among different devices or modalities to achieve a task; 3) Object, i.e. which physical or virtual object users will interact with; 4) Movement, i.e. which trajectory to reach the target object ;
The theoretical objective is to predict users' decisions at these four scales and how user expertise influences how users make decisions. The originality of this pluridisciplinary project is to transpose theories, models and methods from Neuroscience to HCI. Neuroscience studies phenomena involving both decision-making and learning with humans, but did not receive attention in the HCI community.
The practical objective is to develop adaptive systems that empower humans by allowing a human-machine partnership. We argue that the scientific bottleneck is the lack of robust HCI models of decision-making and learning, a problem that we address by building on Neuroscience. We demonstrate the benefits of this approach through 3 applications, for which platforms already exist and maintained by the partners, but scientifical challenges remain for real-world adoption. The three applications are 1) Intelligent Graphical User Interfaces including AI-based Recommendation systems; 2) Immersive simulation systems providing rich haptic feedback and 3) Medical Cobotic interfaces that aim at restoring or enhancing the capability of humans to interact with objects in the real world. These three applications require advanced computational models (and interaction design) capable of predicting users behavior to adapt the interfaces accordingly.

Project coordination

Gilles BAILLY (Sorbonne Université)

The author of this summary is the project coordinator, who is responsible for the content of this summary. The ANR declines any responsibility as for its contents.

Partner

ISIR Sorbonne Université

Help of the ANR 609,719 euros
Beginning and duration of the scientific project: December 2022 - 48 Months

Useful links

Explorez notre base de projets financés

 

 

ANR makes available its datasets on funded projects, click here to find more.

Sign up for the latest news:
Subscribe to our newsletter