My research goal is to achieve long-term human-agent robot teamwork, which requires agents and robots with empathy and interactive intelligence. I am aiming for co-evolution between humans, agents and robots to a sustainable use of our planet with a comfortable life style for all. All my research lines adopt a value-sensitive approach to develop intelligent agents that can interact with their users in value-conflicting situations when also meta-values no longer solve the situation.
Building on a background in logic and multi-agent simulation, my research focusses on intelligent support systems for decision making in complex situations. I initiated and continuously develop GENIUS, the internationally most used platform to support research into negotiation mechanisms, protocols, and intelligent negotiating agents. The Pocket Negotiator is currently the only general purpose negotiation support system that assists users in all phases of the negotiation process. Click here for an experimental version of the Pocket Negotiator.
In my vision, agents and robots should explain their behaviour and decisions in a context-sensitive and engaging way. Our research on the embedding of artificial intelligence in social settings has focused on negotiation in various forms: automated negotiation, and negotiation support. For all applications in which agents and robots have to work closely together with humans, agents and robots must be able to deliberate about the social situation to determine their actions, and be able to form a mental model about their human team mates. I intend to support both agents and humans in their deliberative processes. Mass deliberation support will help citizens and policy makers to take informed decisions in democratic processes. In this endeavour, my aim is to engage people in lasting interests in the policy making of their environments.
In Delft, I work with an interdisciplinary team to create synergy between humans and technology by understanding, shaping and using fundamentals of intelligence and interaction. My initiative to start the annual international Automated Negotiating Agents Competition (ANAC) has made a significant change to the research in automated negotiation agents.
Over the years I learned most about the following application areas
- Lifestyle and Personalized Care
- Cybernetic Incident Management & International Peace Keeping Missions
- Animal behaviour
The negotiation environment GENIUS is by used top groups in the world for developing the best negotiation strategies in automated negotiations.
VRAPT - Virtual Reality Aggression Prevention Training is a project to that focuses on building a Virtual Reality therapy system that facilitates treatment. The patients have to interact with avatars in a virtual world. Our role in the project is part of the effort to make the experience real. To increase presence, the avatar has to respond appropriately and fast. This is facilitated by two main components: behaviour recognition and behaviour generation. We focus on behaviour recognition. Multiple modalities are used for the behaviour recognition component, such as audio, kinect and physiological data, to predict negative arousal and aggressive tendencies.
Socially Adaptive Electronic Partners (SAEP). The overall aim of this VIDI project of Birna van Riemsdijk is to develop a reasoning framework that combines logic and quantitative techniques for Socially Adaptive Electronic Partners (SAEPs) that adapt their behavior to norms and values of people. This becomes more and more important as technology becomes an integral part of our daily lives. The computational reasoning techniques are aimed at determining when and to what extent norm-compliance can be guaranteed, and deciding what to do if in exceptional situations a norm cannot or should not be complied with. We are working on this project together with Pietro Pasotti by studying how to help people with their habits and habit formation.
Sensing Heterogeneous Information Network Environment (SHINE). Research theme: How can heterogeneous resources (people, mobile sensors, fixed sensors, social media, information systems, ...) self-organize for answering information needs? My contribution is in the field of negotiation and of organisation-aware agents.
Smart M2M Grids the M2M Internet for dynamic M2M Information Business ecosystem. Our contribution in that project focuses on multi-party negotation, where we study protocols, bidding and search heuristics and human-in-the-loop automated negotations.
IQmulus which is a EU project to create a High-volume Fusion and Analysis Platform for Geospatial Point Clouds, Coverages and Volumetric Data Sets. Our contribution focuses on human-computer interaction. We employ value-sensitive design methods and focus group interviews to support the design of IQmulus.
Shared Mental Models is a project that studies what human and artificial actors should know about each other to get the best experience and task performance. A research questions is, how to formalize that knowledge in what is known as shared mental models. A related question is how to quantifiably measure sharedness and develop agents that work to improve sharedness.