A5071518251- Multi-Agent Systems and Negotiation
- Logic, Reasoning, and Knowledge
- Social Robot Interaction and HRI
- Semantic Web and Ontologies
- AI-based Problem Solving and Planning
- Auction Theory and Applications
- AI in Service Interactions
- Reinforcement Learning in Robotics
- Business Process Modeling and Analysis
- Robotics and Automated Systems
- Mobile Agent-Based Network Management
- Artificial Intelligence in Law
- Game Theory and Applications
- Emotion and Mood Recognition
- Innovative Human-Technology Interaction
- Speech and dialogue systems
- Artificial Intelligence in Games
- Game Theory and Voting Systems
- Constraint Satisfaction and Optimization
- Robot Manipulation and Learning
- Topic Modeling
- Ethics and Social Impacts of AI
- Software Engineering Research
- Formal Methods in Verification
- Advanced Software Engineering Methodologies
Vrije Universiteit Amsterdam
2019-2024
University of Amsterdam
2022
Delft University of Technology
2011-2021
Shell (Netherlands)
2018
Robotics Research (United States)
2014
Radboud University Nijmegen
2006-2007
Accenture (Switzerland)
2002
Utrecht University
1998-2001
We define hybrid intelligence (HI) as the combination of human and machine intelligence, augmenting intellect capabilities instead replacing them achieving goals that were unreachable by either humans or machines. HI is an important new research focus for artificial we set a agenda formulating four challenges.
The design of automated negotiators has been the focus abundant research in recent years. However, due to difficulties involved creating generalized agents that can negotiate several domains and against human counterparts, many are domain specific their behavior cannot be for other domains. Some these arise from differences inherent within domains, need understand learn negotiators’ diverse preferences concerning issues domain, different strategies undertake. In this paper we present a...
The efficiency of automated multi-issue negotiation depends on the availability and quality knowledge about an opponent. We present a generic framework based Bayesian learning to learn opponent model, i.e. issue preferences as well priorities algorithm proposed is able effectively from bid exchanges by making some assumptions preference structure rationality bidding process. used are general consist among others independency topology functions that model such preferences. Additionally,...
The past years have seen increasing cooperation between psychology and computer science in the field of computational modeling emotion. However, to realize its potential, exchange two disciplines, as well intradisciplinary coordination, should be further improved. We make three proposals for how this could achieved. refer to: 1) systematizing classifying assumptions psychological emotion theories; 2) formalizing theories implementation-independent formal languages (set theory, agent logics);...
A negotiation between agents is typically an incomplete information game, where the initially do not know their opponent's preferences or strategy. This poses a challenge, as efficient and effective requires bidding agent to take other's wishes future behavior into account when deciding on proposal. Therefore, in order reach better earlier agreements, can apply learning techniques construct model of opponent. There mature body research that focuses modeling opponent, but there exists no...
In this paper we specify and validate three interaction design patterns for an interactive storytelling experience with autonomous social robot. The enable the child to make decisions about story by talking robot, reenact parts of together recording self-made sound effects. successfully support children's engagement agency. A user study (N = 27, 8-10 y.o.) showed that children paid more attention enjoyed more, could recall story, when were employed robot during storytelling. All aspects are...
When a negotiating agent is presented with an offer by its opponent, it faced decision: can accept the that currently on table, or reject and continue negotiation. Both options involve inherent risk: continuing negotiation carries risk of forgoing possibly optimal offer, whereas accepting runs missing out even better future offer. We approach decision whether to as sequential problem, modeling bids received stochastic process. argue this natural choice in context incomplete information,...
The annual International Automated Negotiating Agents Competition (ANAC) is used by the automated negotiation research community to benchmark and evaluate its work andto challenge itself. problems evaluation results protocols strategies developed are available wider community.
Serious games and gamification is a popular growing field, commercially for academic research. This paper aims to give an overview of specific domain within the field serious gaming gamification; empower vulnerable target groups. contributes better understanding this by identifying different groups empowerment methods with their own characteristics. From gap in existing research can be identified: complex, more indirect, vulnerabilities are not covered Moreover, opportunities lie creating...
When encountering a robot in the wild, it is not inherently clear to human users what robot's capabilities are. misunderstandings or problems spoken interaction, robots often just apologize and move on, without additional effort make sure user understands happened. We set out compare effect of two speech based capability communication strategies (proactive, reactive) such strategy, regard user's rating their behavior during interaction. For this, we conducted an in-person study with 120...