Welcome to the website of the Robots, Agents, and Interaction (RAI) group at the Department of Data Science & Knowledge Engineering at Maastricht University.
RAI has strong experience in the design and implementation of machine learning, data mining, computer vision, and robotics. This includes broad know-how in research involving learning and coordination among autonomous agents (software or robots), human-robot interaction, human activity & emotion recognition in HCI/HRI (Human-Computer/Robot Interaction), swarm and modular robotics, automated negotiation, and AI knowledge transfer.
The University of Maastricht (UM) and Dimokritos (NCSR) are co-organizing the SMAP 2017 Special Session on Multimodal Affective Analysis for Human-Machine Interfaces and Learning Environments (see this link for more information about the SS), which will be part of the SMAP 2017 (smap2017.org) conference in Bratislava, 9th-10th July 2017. The special session will focus on signal analysis and machine learning techniques on affective knowledge from auditory, visual and textual information, employed in human-machine interaction and learning applications and it is organized in collaboration with MaTHiSiS.
Recently, our paper titled “High-performance and Lightweight Real-time Deep Face Emotion Recognition” has been accepted for publication at the SMAP2017 – 12th International Workshop on Semantic and Social Media Adaptation and Personalization. This paper will be included as part of the Special Session on Multimodal affective analysis for human-machine interfaces and learning environments.
This paper (J. Schwan, E. Ghaleb, E. Hortal and S. Asteriadis) is the outcome of a student internship and presents a method for facial analysis in the wild based on Convolutional Neural Networks. This system will be applied in learning enviroments in the context of MaTHiSiS project.
Our paper titled “Multi-Agent Parking Place Simulation” is accepted for publication at the 15th International Conference on Practical Applications of Agents and multi-agents systems (PAAMS’17) (as a full paper and a demo paper).
This paper was authored by four of our Master in Artificial Intelligence students and their supervisors (Thomas Vrancken, Daniel Tenbrock, Sebastian Reick, Dejan Bozhinovski, Gerhard Weiss and Gerasimos Spanakis) as part of a semester research project and explored how multi-agent simulations can be utilized in parking dynamic pricing for the city of Maastricht.
Our paper titled “Machine learning techniques in eating behavior e-coaching: Balancing between generalization and personalization” (G. Spanakis, G. Weiss, B. Boh, L. Lemmens, A.Roefs) has been accepted for publication.
RAI, in collaboration with the Polytechnic University of Madrid and the Centre of Research and Technology, Hellas in Greece, are organizing the international Smart Indoor Event and Activity Recognition Workshop. Paper Submission deadline: 20th of May. For more information, click here
Some members of RAI (Stelios Asteriadis, Enrique Hortal and Dimitris Koutsoukos) attended the first review meeting of MaTHiSiS project on February 10 in Luxembourg. During the review, the consortium shows a live demo of the learning platform including the use of computers, mobile devices (an Android tablet) and robots (NaO robot and TurtleBot).
Two papers were accepted for publication in the proceedings of the 9th International Conference on Computer Supported Education (CSEDU-2017).
The first one is titled: “Personalized, affect and performance-driven Computer-based Learning”, authored by C. Athanasiadis, C.Z. Lens, D. Koutsoukos, E. Hortal and S. Asteriadis and the second one is titled: “A Course Recommender System based on Graduating Attributes” and is authored by B. Bakhshinategh, G. Spanakis, O. Zaiane and S. ElAtia
RAI participates in IMPACT (International Meeting in Performing Arts & Creative Technologies), a project supported by Interreg (Euregio Meuse-Rhin) and officially launched on Tuesday, January 31st in Théâtre de Liège. In this project our Artificial Intelligence/Machine Learning experts together with artist Marie van Vollenhoven will explore whether computers can learn concepts like “harmony” and “balance”.
First findings of this research project will be presented during Cross Currents festival organized by Jazz Maastricht (also a participant in IMPACT) on May 13th 2017.
See below the video/interview from the official launch event with Dr. Gerasimos (Jerry) Spanakis and the artist Marie van Vollenhoven
Our paper “Multimodal Fusion Based on Information Gain for Emotion Recognition in the Wild” (E. Ghaleb, M. Popa, E. Hortal, S. Asteriadis) has been accepted for publication in the IEEE Technically Sponsored Intelligent Systems Conference (IntelliSys) 2017. This conference will take place in London, United Kingdom from 7 to 8 September 2017.