Skip to content
printicon

Socially Intelligent Autonomous Systems

Research project This project is part of a larger research initiative at Umeå University of 8 postdoc projects on autonomous systems for the future of industry and society. To further strengthen the effort on socially intelligent systems, three PhD student projects are also ongoing.

The future intelligent environments will be socio-technical systems where autonomous software agents and people are cooperating to reach different goals.

Head of project

Project overview

Project period

2017-08-01 2019-07-31

Funding

Kempe foundations, 600.000 kr.

Research subject

Computing science

Project description

The software agents will need social capacity similar to a human, i.e. be socially intelligent, both when collaborating with professionals in a work environment e.g. in the mining industry, and in the form of social robots and ambient assisted living environments for older adults. Such systems that aim to reinforce the human's capacity, ability and wellbeing are sometimes denoted digital companions. Such socially intelligent systems will in the future aggregate dynamic computational models of the human actor's capacity, goal-driven activities, needs, motives, norms and preferences, and integrate methods for cooperative reasoning and decision making in interaction with the human actors.

Agreement technologies, computational social norms and methods for personalisation are key ingredients in future socially intelligent digital companions, and will be in focus for research. Scientific methods from different fields within artificial intelligence need to be developed and combined as part of this project in order to generate a more sophisticated socially intelligent autonomous behaviour in software agents, e.g. methods for planning, learning, reasoning and decision making.