Federated Socio-Cognitive Systems
Keywords: Hybrid Intelligence, Collective Learning, Human-Machine Collaboration, Joint Cognitive Systems, Socio-Cognitive Engineering
Humans are social adaptive beings, collaborating at work and socializing at relaxation. More and more, Artificial Intelligence (AI) is entering their work and leisure environments as a substantive actor. A major challenge is to develop AI-actors that become partners of the humans in joint activities. However, human and artificial intelligence differ in a fundamental way on all aspects, such as the empirical foundation of associative (or implicit) learning and the knowledge-base for symbolic (or explicit) reasoning. In hybrid human-AI systems, the different components have to be harmonized to establish the envisioned collective intelligence with the desired behavior patterns. We are working on federated socio-cognitive systems that incorporate models and methods for establishing joint objectives, for coping with value tensions via work agreements, for sharing experiences to co-learn, and for mutual feedback and explanations that support learning and trust calibration. Furthermore, the envisioned systems develop competencies to identify beneficial and destructive team patterns (i.e., showing (in)effective collaboration or partnership), and mechanisms to support or mitigate such patterns.
- Personal Assistant for a Healthy Lifestyle (PAL) project http://www.pal4u.eu/
- TRADR project http://www.tradr-project.eu/
Related tracks: ST, DST
- CS4235 Socio-Cognitive Engineering
- CS4015 Behaviour Change Support Systems
- CS4125 Seminar Research Methodology for Data Science
Related key publications:
- Harbers, M., & Neerincx, M.A. (2017). Value sensitive design of a virtual assistant for workload harmonization in teams. Cognition, Technology & Work, 19(2-3), 329-343.
- Johnson, M., Bradshaw, J. M., Feltovich, P. J., Jonker, C. M., Van Riemsdijk, M. B., & Sierhuis, M. (2014). Coactive design: Designing support for interdependence in joint activity. Journal of Human-Robot Interaction, 3(1), 43-69.
- Kayal, A., Brinkman, W.P., Neerincx, M.A. and Van Riemsdijk, M.B. (2018). Automatic Resolution of Normative Conflicts in Supportive Technology Based on User Values. ACM Trans. Internet Technol. 18, 4, Article 41 (May 2018), 21 pages
- Neerincx, M. A., van der Waa, J., Kaptein, F., & van Diggelen, J. (2018, July). Using perceptual and cognitive explanations for enhanced human-agent team performance. In International Conference on Engineering Psychology and Cognitive Ergonomics (pp. 204-214). Springer, Cham.
- Neerincx, M.A., van Vught, W., Blanson Henkemans, O. Oleari, E. Broekens, J., Peters, R., Kaptein, F. Demiris, Y., Kiefer, B,. Fumagalli, M. and Bierman, B. (to appear). Socio-Cognitive Engineering of a Robotic Partner for Child’s Diabetes Self-Management.
- Pereira, A., Oertel, C., Fermoselle, L., Mendelson, J. & Gustafson, J.(2019, November). Responsive Joint Attention in Human-Robot Interaction. Accepted in 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE.
- Oertel, C., & Salvi, G. (2013, December). A gaze-based method for relating group involvement to individual engagement in multimodal multiparty dialogue. In Proceedings of the 15th ACM on International conference on multimodal interaction (pp. 99-106). ACM.