Interactive Intelligence Group
Responsible Intelligent agents & Intelligent human/agent-agent interaction
Our mission is to understand and engineer collaboration between humans & agents. We develop theories, models and methods of interactive intelligence by combining methods from AI and the social sciences.
The Interactive Intelligence (II) section focusses on socially interactive, intelligent agents. We research the intelligence that underlies and co-evolves during the repeated interactions of human and technology “agents” who cooperate to achieve a joint goal. Our research program aims for synergy and social interaction between humans and technology, to empower humans in their social context. The new technological challenges we face arise from the need to integrate Artificial Intelligence, Cognitive Engineering, and behavioural sciences. In particular, the technological challenge is to develop socially aware agents that in interaction with humans co-adapt and co-learn over time. Social awareness implies context-awareness with the knowledge to interpret the physical situation in social terms and the knowledge to behave in a distinctive individual way that is personalized towards those the agent interacts with. In this manner, we endeavour to develop the interactive agent technology that empowers humans and groups of humans to deal with the societal and individual challenges such as the increasing need for sustained self-management for healthy ageing, safety and life-long education.
Behaviour modelling, Mental models/ToM, Responsible AI/EXAI, Intelligent agents, Multi-modal perception systems, Knowledge representation x ML, Socio-cognitive engineering, Humane/Hybrid AI, Long-term interaction, Situated awareness.
We are part of the Department of Intelligent Systems.
We are participating in:
26 oktober 2020
Robot en mens leren van elkaar
In this month's issue of AG Connect, dr. Catharine Oertel and dr. Myrthe Tielman contributed to an article on how AI can align more closely with human behavior. In it, they discuss how both data-driven and knowledge-based methods can help AI become better interaction partners.
01 oktober 2020
Three papers from the Interactive Intelligence group to appear at the NeurIPS 2020 Conference
Frans Oliehoek, whose research focuses on interactive learning and decision making, is the coauthor of three accepted papers at the NeurIPS 2020 Conference.
30 september 2020
Algoritme helpt ontwerpteams effectiever samenwerken
Computerwetenschapper Catharine Oertel onderzoekt hoe een kunstmatig systeem, misschien een robot, een team kan versterken. 'Het moet horen wat er gezegd wordt, alleen onthouden wat belangrijk is, zien hoe mensen bewegen en waar ze naar kijken.
23 september 2020
AI moet geen pijn doen
In the NRC newspaper of September 18, 2020, professor Catholijn Jonker contributed to an article about AI in the series "Met machines meer mens" (dutch)
14 september 2020
Synthesising Reinforcement Learning Policies through Set-Valued Inductive Rule Learning
Youri Coppens presents joint work on Machine Learning & Knowledge Representation at the TAILOR 2020 Workshop.
05 augustus 2020
TU Delft AI labs are launching
Myrthe Tielman recently appeared on the (Dutch) Radio 1 program 'Goed ingelichte kringen', to talk about the launch of the TU Delft AI labs.
17 juni 2020
Going transcendental in the Electrical Engineering Faculty
Gurus and other spiritual counsellors of mind and soul might just as well pack up. Willem-Paul Brinkman and Ding Ding elevated transcendental experience to the next level.
16 juni 2020
Mark Neerincx is giving a keynote at spring conference
Mark Neerincx is giving a keynote presentation at the Spring Conference of the Dutch Association of Psychiatry on June 17th. He will discuss the development of virtual or physical agents, like avatars and robots, that gradually enter into a symbiotic relationship with the people in (“blended”) healthcare systems (i.e., clients, doctors, caregivers, …). The proposition is that the development of symbiotic, artificial and human, intelligence can advance healthcare substantially. In nature, symbiosis advances the overall performance and resilience of the concerning species.
04 juni 2020
Virtuele innerlijke stem voor ontwikkelen sociale vaardigheden
Sociale vaardigheden zijn onmisbaar in het leven, maar ze komen niet altijd aangewaaid. Er is dan ook een groot aanbod aan cursussen en zelfhelpboeken om ze te ontwikkelen. Tegenwoordig kan dat ook met digitale ondersteuning, zoals virtual reality (VR).
02 juni 2020
AI labs & talent recruitment
Over the course of 2020-2021 we are establishing a total of 24 TU Delft AI-labs where experts in AI foundations work together with experts in AI challenges. Through these Delft AI-labs, expertise and innovation in AI, Data & Digitalisation is used to advance expertise and innovation with AI, Data & Digitalisation, thereby increasing the impact of AI at TU Delft in science, design engineering and society.