The AMHA (Automatic Mental Health Assistant) project is part of the Mars-500 experiment to be carried out at the Institute for Biomedical Problems (IBMP) in Moscow. The European Space Agency (ESA) and the Russian Academy of Sciences jointly plan and conduct this experiment in order to simulate a manned mission to Mars. It will provide the unique opportunity to study interactions between crew members while collecting data about their health and performance during experimental isolation. The confinement study will imitate all key peculiarities expected to be present during future missions to Mars (i.e. ultra long duration flight, need for autonomy, complicated communication due to signal delay, and limited stock of expendables).
ESA prepares for a human mission to Mars (credits: ESA)
The isolated space environment during ultra long space flights affects a number of psychosocial and mental processes critically involved in human performance. Latent and overt stress factors are mental strain, interpersonal problems, lack of capability to rescue crew members, isolation, monotony, and tedium of life aboard an autonomous shuttle.
In this project, we explore the use of strategic multi-player games to alleviate stress, and more importantly as an unintrusive tool to monitor the mental capacity of astronauts as well as the development of different social interaction patterns within the crew.
Colored Trails: A 3-player negotiation game
For the first iteration of the Mars-500 experiment, a 105 day pretest, we are primarily interested in games that feature the following properties:
Game theory studies strategic interactions, where multiple players act rational in order to maximize their expected payoffs. In this work, we leverage the profound mathematical foundation of game theory and evolutionary game theory (EGT) to model and study crew member interactions. Traditional game theory provides means to analyze rational decision making, while EGT describes adaptation and learning. Both, the ability to think rational and to adapt to changing situations, are deciding factors for mission success.
Automatic monitoring of face expression, voice intonation and body movements were proven to be useful techniques for monitoring of emotional states of subjects. These techniques are important since humans naturally express their emotions throw nonverbal behavior. In our study we use records of facial expressions during the time people are playing the Colored Trails Game. Facial expressions give important clues about emotions. In contrast to self assessment techniques, the tracking of nonverbal behavior provides information about emotions and psychological state unconscious. It would allow to get more objective data compare to results of questionnaires.
Matthias Rauterberg
Professor 1
Emilia Barakova
Assistant Professor 1
Rene Ahn
Assistant Professor 1
Roman Gorbunov
Ph.D. Candidate 1
Mark Neerincx
Professor 2
Karl Tuyls
Associate professor 3
Daniel Hennes
Ph.D. Candidate 3
Natalia Voynarovskaya
Postmaster Student 1
AMHA experiment: Colored Trails Game Online watch the video...
Mars500 (ESA Human Spaceflight)
Colored Trails (Harvard University - School of Engineering and Applied Sciences)
June 02, 2010
ESA: "Mars500 gaming helps develop electronic helpers for deep space crews" read more...
July 14, 2009
Business News Radio BNR.nl: "End of the MARS-105 experiment" listen the radio...
March 31, 2009
tagesschau.de: "Mars Flugsimulation: Mars-WG" watch the video...
March 30, 2009
Cyrille Fournier: "We also tried an ESA experiment proposed by a Dutch team which requires the participation of three crewmembers..." read more... watch the video...
Gorbunov, R., Barakova E., Rauterberg, G.W.M. Interpretation of Time Dependent Facial Expressions in Terms of Emotional Stimuli International Conference on Evolutionary Computation Theory and Applications, 2012. [pdf]
Gorbunov, R., Barakova E., Rauterberg, G.W.M. Design of Social Agents Accepted for publication in Neurocomputing Journal [pdf]
Gorbunov, R., Barakova, E., Ahn, R., Rauterberg, G.W.M. Monitoring Facial Expressions during the Mars-500 Isolation Experiment The 8th International Conference on Methods and Techniques in Behavioral Research, 2012 [pdf]
Gorbunov, R., Barakova, E., Ahn, R., Rauterberg, G.W.M. Adaptive Properties and Memory of a System of Interactive Agents: A Game Theoretic Approach The Fourth International Conference on Adaptive and Self-Adaptive Systems and Applications, 2012 [pdf]
Gorbunov, R., Barakova, E., Ahn, R., Rauterberg, G.W.M. Generalized Utility Describing Cooperation and Fairness The 8th Spain-Italy-Netherlands Meeting on Game Theory, 2012, ask for reprint.
Gorbunov, R., Barakova, E., Ahn, R., Rauterberg, G.W.M. Monitoring Interpersonal Relationships through Games with Social Dilemma Proceedings of International Conference on Evolutionary Computation Theory and Applications. pp. 5-12, Paris, France, October 2011. [Best Paper Award] [pdf]
Gorbunov, R., Barakova, E., Rauterberg, G.W.M. Design of Social Agents Lecture Notes in Computer Science, Volume 6686, pp. 192-201, 2011 [pdf]
Voynarovskaya, N., Gorbunov, R., Barakova, E., Ahn, R., Rauterberg, G.W.M. Nonverbal Behavior Observation: Collaborative Gaming Method for Prediction of Conflicts during Long-term Missions. In H.S. Yang et al. (Eds.): ICEC 2010, LNCS 6243, pp. 103-114, 2010. [pdf]
Voynarovskaya, N., Gorbunov, R., Barakova, E., Rauterberg, G.W.M. Automatic Mental Heath Assistant: Monitoring and Measuring Nonverbal Behavior of the Crew During Long-Term Missions. Extended abstracts in Proceedings of 7th International Conference on Methods and Techniques in Behavioral Research. Eindhoven, the Netherlands, 2010. [pdf]
Daniel Hennes, Karl Tuyls, Mark Neerincx and Matthias Rauterberg. Micro-scale Social Network Analysis for Ultra-long Space Flights. To appear in Proceedings of the IJCAI-09/SMC-IT-09/IWPSS-09 Workshop on Artificial Intelligence in Space, Pasadena, USA, July 2009. [pdf]
Daniel Hennes, Karl Tuyls and Matthias Rauterberg. State-Coupled Replicator Dynamics. In Proceedings of the 8th International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2009), pp. 789-796, Budapest, Hungary, May 2009. [pdf]
Daniel Hennes, Karl Tuyls and Matthias Rauterberg. Formalizing Multi-state Learning Dynamics. In Proceedings of the IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (IAT 2008), Volume 2, pp. 266-272, Sydney, Australia, December 2008. [pdf]
Matthias Rauterberg, Mark Neerincx, Karl Tuyls and Jack van Loon. Entertainment computing in the Orbit. In Proceedings of New Frontiers for Entertainment Computing. (IFIP Conference Proceedings, Vol. 279, pp. 59-70). Boston: Springer, 2008. [pdf]