Autonomous Intelligent Systems
Autonomous Intelligent Systems are AI software systems that act independently of direct human supervision, e.g., self-driving cars, UAVs, smart manufacturing robots, care robots for the elderly and virtual agents for training or support. Such systems need to be able to make safe, rational and human values-compatible decisions in unforeseen circumstances. Their decision making should be understandable by human users and collaborators, to ensure the necessary trust on behalf of the human users.
There are multiple challenges in this area, some of them are common to all interest groups of the focus area on human-centered AI, in particular, Knowledge Representation and Reasoning, and AI, Ethics and Law.
In order to be able to make reasonable and efficient decisions in unforeseen circumstances, autonomous intelligent systems need to be capable of learning, representing and (common sense) reasoning about, e.g., (probabilistic) knowledge and beliefs, utilities, preferences, goals, actions and plans, norms and emotions. On the other hand, in order for regulatory authorities and human users to trust autonomous intelligent systems, their decision-making behavior should be transparent and explainable to humans if necessary.
This SIG aims at investigating symbolic and sub-symbolic models, software tools, and computational techniques to specify, design and develop Autonomous Intelligent Systems. In particular, the main research questions in the area of SIG are:
- Developing efficient algorithms for various AI components of intelligent autonomous systems
- Designing and programming autonomous intelligent systems
- Ensuring the resulting programs do the right thing, especially when components of the system are learnt
- Designing algorithmic approaches for explaining and verifying decision making behavior of intelligent autonomous systems
Our researchers are active in the following departments:
|Faculty of Science|
Researchers of the Department of Information and Computing Sciences, working on knowledge representation, machine learning, algorithms, human interaction
|Faculty of Humanities|
Researchers of the Department of Philosophy and Religious Studies, working on logic and reasoning
|Faculty of Social and Behavioral Sciences|
Researchers of the Department of Psychology, working on autonomy
We invite Utrecht University researchers to register their interest in the SIG by filling in the form.
Twice a year a call for activity proposals will be distributed UU-wide, and a selection of them will receive financial support. The SIG supports any activities in its area of research, in particular:
- Increasing the impact of current research and developing new research proposals (e.g., data collection, software development)
- Collaboration with leading researchers in the SIG area (e.g., funding for visitors)