The field of Embodied Artificial Intelligence highlights the significance of embodiment and situatedness. Agents sense and act within the sensori-motor loop, which defines the context of learning including their morphology. The development of cognitive capabilities cannot be understood detached from this context. In this project, we study the way in which learning principles for embodied agents shape behavioural patterns that reflect morphology and environmental constraints. Particular behaviours of interest are exploration and body coordination. The ultimate goal of the project is to develop an information-theoretic understanding of the sensori-motor loop. Causal aspects, such as causal effects of acting on sensing, and their role in the context of autonomy and control play a central role to this end.

Holger Bernigau
Tim Schröder
Further Information:
Workshop on Guided Self-Organisation
(1st , 2nd, 3rd , 4th )
Open positions:
Master Thesis
Bachelor Thesis
Contact: Keyan Zahedi
Related Group Publications:
Montufar, G. ; Ay, N. and K. Ghazi-Zahedi: A framework for cheap universal approximation in embodied systems. MIS-Preprint: 70/2014 [ARXIV]

Ay, N. and K. Ghazi-Zahedi: Causal effects for prediction and deliberative decision making of embodied systems. Advances in cognitive neurodynamics III : proceedings of the 3rd International Conference on Cognitive Neurodynamics 2011 ; [June 9-13, 2011, Hilton Niseko Village, Hokkaido, Japan] / Y. Yamaguchi (ed.). Springer, 2013. - P. 499-506 (Advances in cognitive neurodynamics) MIS-Preprint: 22/2011 [DOI]

Ghazi-Zahedi, K. and N. Ay: Quantifying morphological computation. Entropy, 15 (2013) 5, p. 1887-1915 MIS-Preprint: 11/2013 [DOI] [ARXIV]

Ghazi-Zahedi, K. ; Martius, G. and N. Ay: Linear combination of one-step predictive information with an external reward in an episodic policy gradient setting : a critical analysis. Frontiers in psychology / Frontiers in cognitive science, 4 (2013), 801 MIS-Preprint: 60/2013 [DOI] [ARXIV]

Ay, N. ; Bernigau, H. ; Der, R. and M. Prokopenko: Information-driven self-organization : the dynamical system approach to autonomous robot behavior. Theory in biosciences, 131 (2012) 3, p. 161-179 [DOI]

Ghazi-Zahedi, K. ; Ay, N. and R. Der: Higher coordination with less control : a result of information maximization in the sensorimotor loop. Adaptive behavior, 18 (2010) 3/4, p. 338-355 [DOI] [ARXIV]

Ay, N. ; Bertschinger, N. ; Der, R. ; Güttler, F. and E. Olbrich: Predictive information and explorative behavior of autonomous robots. The European physical journal / B, 63 (2008) 3, p. 329-339 [DOI]

Der, R. ; Güttler, F. and N. Ay: Predictive information and emergent cooperativity in a chain of mobile robots. Artificial Life XI : Proceedings of the Eleventh International Conference on the Simulation and Synthesis of Living Systems MIT Press, 2008. - P. 166-172

Ghazi-Zahedi, K. ; Twickel, A. v. and F. Pasemann: YARS : A physical 3D simulator for evolving controllers for real robots. Simulation, modeling, and programming for autonomous robots : first international conference, SIMPSR 2008 Venice, Italy, November 3-7, 2008 proceedings / S. Carpin... (eds.). Springer, 2008. - P. 75-86 (Lecture notes in artificial intelligence ; 5325) [DOI]