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.

People:
Holger Bernigau
Collaborations:
Tim Schröder
Further Information:
A Theory of Cheap Control in Embodied Systems
Workshop on Guided Self-Organisation
(1st , 2nd, 3rd , 4th )
Open positions:
Master Thesis
Bachelor Thesis
Internship
Contact: Keyan Zahedi
Related Group Publications:
Krakauer, D. C. ; Bertschinger, N. ; Olbrich, E. ; Flack, J. C. and N. Ay: The information theory of individuality. Theory in biosciences, 139 (2020) 2, p. 209-223 Bibtex [DOI] [ARXIV] [FREELINK]

Ay, N. ; Rauh, J. and G. Montúfar: A continuity result for optimal memoryless planning in POMDPs. RLDM 2019 : 4th multidisciplinary conference on reinforcement learning and decision making ; July 7-10, 2019 ; Montréal, Canada University, 2019. - P. 362-365 Bibtex [FREELINK]

Ghazi-Zahedi, K.: Morphological intelligence : measuring the body's contribution to intelligence. Springer, 2019. - XIII, 180 p. ISBN 978-3-030-20620-8 Bibtex [DOI]

Montúfar, G. ; Rauh, J. and N. Ay: Task-agnostic constraining in average reward POMDPs. Task-agnostic reinforcement learning : workshop at ICLR, 06 May 2019, New Orleans ICLR, 2019 Bibtex [FREELINK]

Sokoloski, S.: Implementing Bayesian inference with neural networks. Dissertation, Univeristät Leipzig, 2019 Bibtex [FREELINK]

Ghazi-Zahedi, K.: Morphological intelligence : information-theoretic quantifications of the morphological contribution to intelligence. Habilitation, Univeristät Leipzig, 2018 Bibtex

Ghazi-Zahedi, K. ; Langer, C. and N. Ay: Morphological computation : synergy of body and brain [Entropy, 19 (2017) 9, 456]. Information decomposition of target effects from multi-source interactions : [collected articles from the special issue published in Entropy] / J. T. Lizier... (eds.). MDPI, 2018. - P. 267-281 Bibtex [DOI]

Montúfar, G. ; Rauh, J. and N. Ay: Uncertainty and stochasticity of optimal policies. Proceedings of the 11th workshop on uncertainty processing WUPES '18, June 6-9, 2018 / V. Kratochvíl (ed.). MatfyzPress, 2018. - P. 133-140 Bibtex [FREELINK]

Muiños-Landin, S. ; Ghazi-Zahedi, K. and F. Cichos: Reinforcement learning of artificial microswimmers. Bibtex [ARXIV]

Der, R. and G. Martius: Self-organized behavior generation for musculoskeletal robots. Frontiers in neurorobotics, 11 (2017), 8 Bibtex [DOI] [ARXIV]

Ghazi-Zahedi, K.: NMODE - Neuro-MODule evolution. Bibtex [ARXIV]

Ghazi-Zahedi, K. ; Deimel, R. ; Montúfar, G. ; Wall, V. and O. Brock: Morphological computation : the good, the bad, and the ugly. 2017 IEEE/RSJ international conference on intelligent robots and systems (IROS) : Vancouver, BC, Canada ; September 24-28, 2017 IEEE, 2017. - P. 464-469 Bibtex [DOI] [FREELINK]

Ghazi-Zahedi, K. ; Langer, C. and N. Ay: Morphological computation : synergy of body and brain. Entropy, 19 (2017) 9, 456 Bibtex [DOI]

Montúfar, G. ; Ghazi-Zahedi, K. and N. Ay: Stochasticity of optimal policies for POMDPs. RLDM 2017 : 3rd multidisciplinary conference on reinforcement learning and decision making ; June 11-14, 2017 ; Ann Arbor, Michigan, USA University, 2017 Bibtex [FREELINK]

Der, R.: In search for the neural mechanisms of individual development : behavior-driven differential Hebbian learning. Frontiers in robotics and AI, 2 (2016), 37 Bibtex [DOI]

Ghazi-Zahedi, K. ; Haeufle, D. F. B. ; Montúfar, G. ; Schmitt, S. and N. Ay: Evaluating morphological computation in muscle and DC-motor driven models of hopping movements. Frontiers in robotics and AI, 3 (2016), 42 Bibtex [DOI] [ARXIV]

Martius, G. ; Hostettler, R. ; Knoll, A. and R. Der: Compliant control for soft robots : emergent behavior of a tendon driven anthropomorphic arm. 2016 IEEE/RSJ international conference on intelligent robots and systems (IROS) : October 9-14 2016 ; Daejeon, Korea IEEE, 2016. - P. 767-773 Bibtex [DOI]

Montúfar, G. ; Ghazi-Zahedi, K. and N. Ay: Information theoretically aided reinforcement learning for embodied agents. Bibtex [ARXIV]

Ay, N. and W. Löhr: The Umwelt of an embodied agent : a measure-theoretic definition. Theory in biosciences, 134 (2015) 3-4, p. 105-116 Bibtex MIS-Preprint: 74/2015 [DOI] [ARXIV]

Bernigau, H.: Causal models over infinite graphs and their application to the sensorimotor loop : general stochastic aspects and gradient methods for optimal control. Dissertation, Universität Leipzig, 2015 Bibtex [FREELINK]

Der, R. and G. Martius: Novel plasticity rule can explain the development of sensorimotor intelligence. Proceedings of the National Academy of Sciences of the United States of America, 112 (2015) 45, p. E6224-E6232 Bibtex [DOI] [ARXIV]

Ghazi-Zahedi, K. and J. Rauh: Quantifying morphological computation based on an information decomposition of the sensorimotor loop. Proceedings of the european conference on artificial life 2015, ECAL 2015 / P. Andrews... (eds.). MIT Press, 2015. - P. 70-77 Bibtex MIS-Preprint: 21/2015 [DOI] [ARXIV] [FREELINK]

Montúfar, G. ; Ghazi-Zahedi, K. and N. Ay: A theory of cheap control in embodied systems. PLoS computational biology, 11 (2015) 9, e1004427 Bibtex MIS-Preprint: 70/2014 [DOI] [ARXIV]

Ay, N. and K. Ghazi-Zahedi: On the causal structure of the sensorimotor loop. Guided self-organization : inception / M. Prokopenko (ed.). Springer, 2014. - P. 261-294 (Emergence, complexity, and computation) Bibtex [DOI]

Der, R.: On the role of embodiment for self-organizing robots : behavior as broken symmetry. Guided self-organization : inception / M. Prokopenko (ed.). Springer, 2014. - P. 193-221 (Emergence, complexity, and computation) Bibtex [DOI]

Martius, G. ; Der, R. and J. M. Herrmann: Robot learning by guided self-organization. Guided self-organization : inception / M. Prokopenko (ed.). Springer, 2014. - P. 223-260 (Emergence, complexity, and computation) Bibtex [DOI]

Martius, G. ; Jahn, L. ; Hauser, H. and V. V. Hafner: Self-exploration of the Stumpy robot with predictive information maximization. From Animals to Animats 13 : 13th International Conference on Simulation of Adaptive Behavior, SAB 2014, Castellón, Spain, July 22-25, 2014 ; proceedings / A. P. Del Pobil... (eds.). Springer, 2014. - P. 32-42 (Lecture notes in computer science ; 8575) Bibtex [DOI] [FREELINK]

Prokopenko, M. ; Polani, D. and N. Ay: On the cross-disciplinary nature of guided self-organisation. Guided self-organization : inception / M. Prokopenko (ed.). Springer, 2014. - P. 3-15 (Emergence, complexity, and computation) Bibtex [DOI]

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) Bibtex MIS-Preprint: 22/2011 [DOI]

Ay, N. and W. Löhr: A measure-theoretic description of the intrinsic view of embodied agents. Bibtex [FREELINK]

Der, R. and G. Martius: Behavior as broken symmetry in embodied self-organizing robots. Advances in Artificial Life, ECAL 2013 : Proceedings of the Twelfth European Conference on the Synthesis and Simulation of Living Systems / P. Lio... (eds.). MIT Press, 2013. - P. 601-608 Bibtex [DOI]

Ghazi-Zahedi, K. and N. Ay: Quantifying morphological computation. Entropy, 15 (2013) 5, p. 1887-1915 Bibtex 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 Bibtex MIS-Preprint: 60/2013 [DOI] [ARXIV]

Martius, G. ; Der, R. and N. Ay: Information driven self-organization of complex robotic behaviors. PLOS ONE, 8 (2013) 5, e63400 Bibtex MIS-Preprint: 15/2013 [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 Bibtex [DOI]

Ay, N. ; Der, R. and M. Prokopenko: Guided self-organization : perception-action loops of embodied systems. Theory in biosciences, 131 (2012) 3, p. 125-127 Bibtex [DOI]

Der, R. and G. Martius: The playful machine : theoretical foundation and practical realization of self-organizing robots. Springer, 2011. - XIII, 333 p. (Cognitive systems monographs ; 15) ISBN 978-3-642-20253-7 Bibtex [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 Bibtex [DOI] [ARXIV]

Güttler, F. ; Rabe, W. ; Hoffmann, J. ; Bogdan, M. and R. Der: Transposing simulated self-organizing robots into reality using the plug and learn architecture. Proceedings of the International Conference on Fuzzy Computation and International Conference on Neural Computation : Valencia, Spain, October 24 - 26, 2010 SciTePress - Science and Techn. Publ., 2010. - P. 350-357 Bibtex [DOI]

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 Bibtex [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 Bibtex

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) Bibtex [DOI]

Ghazi-Zahedi, K. and F. Pasemann: Adaptive behavior control by self-regulating neurons. 50 years of artificial intelligence : essays dedicated to the 50th aniversary of artificial intelligence / M. Lungarella... (eds.). Springer, 2007. - P. 196-205 (Lecture notes in computer science ; 4850 : Lecture notes in artificial intelligence) Bibtex [DOI]

Pasemann, F. ; Steinmetz, U. and R. Der: Homeokinesis : a new principle to back up evolution with learning. Computational Intelligence for Modelling, Control and Automation / M. Mohammadian (ed.). IOS Press, 1999. - P. 43 - 47 (Concurrent Systems Engineering Series ; 55) Bibtex MIS-Preprint: 14/1999