Evolving Plastic Neuromodulated Networks for Behavior Emergence of Autonomous Virtual Characters

This paper addresses the problem of generating natural behavior of autonomous virtual characters. Inspired by the fields of Embodied and Enactive Artificial Intelligence, we postulate that natural behavior is the result of a coupling between the agent and the world where it lives, which leads to a coherence between its actions and its surroundings. In this work, we present the tools that we have been using to study that idea: a controller based on a plastic neuromodulated neural network, which is capable of molding itself to received stimuli; and a simple novel method for genetic encoding of artificial neural networks. We show the capabilities of the controller in generating interesting foraging behavior of an autonomous virtual robot, and discuss the advantages of its emergent characteristics when compared with traditional approaches.

[1]  Dario Floreano,et al.  Evolving neuromodulatory topologies for reinforcement learning-like problems , 2007, 2007 IEEE Congress on Evolutionary Computation.

[2]  Michael L. Anderson Embodied Cognition: A field guide , 2003, Artif. Intell..

[3]  Francisco J. Serón,et al.  AI and virtual crowds: Populating the Colosseum , 2007 .

[4]  Joaquim B. Cavalcante Neto,et al.  A nervous system model for direct dynamics animation control based on evolutionary computation , 2008, SAC '08.

[5]  Demetri Terzopoulos,et al.  Autonomous pedestrians , 2005, SCA '05.

[6]  Dario Floreano,et al.  Evolutionary Advantages of Neuromodulated Plasticity in Dynamic, Reward-based Scenarios , 2008, ALIFE.

[7]  Daniel Thalmann,et al.  An action selection process to simulate the human behavior in virtual humans with real personality , 2011, The Visual Computer.

[8]  Marvin Oliver Schneider,et al.  Application and development of biologically plausible neural networks in a multiagent artificial life system , 2009, Neural Computing and Applications.

[9]  Karl Sims,et al.  Evolving 3D Morphology and Behavior by Competition , 1994, Artificial Life.

[10]  Francisco J. Serón,et al.  ALVW: an alife behaviour modelling system , 2006 .

[11]  Daniel Thalmann,et al.  Semantic Representation of Individualized Reaction Movements for Virtual Humans , 2007, Int. J. Virtual Real..

[12]  Jonathan Dinerstein,et al.  COGNITIVE AND BEHAVIORAL MODEL ENSEMBLES FOR AUTONOMOUS VIRTUAL CHARACTERS , 2010, Comput. Intell..

[13]  Tom Ziemke,et al.  Enactive artificial intelligence: Investigating the systemic organization of life and mind , 2009, Artif. Intell..

[14]  Hervé Luga,et al.  The Cortexionist architecture: behavioural intelligence of artificial creatures , 2010, The Visual Computer.

[15]  Christoph Adami,et al.  Evolving Virtual Creatures and Catapults , 2007, Artificial Life.

[16]  Michael E. Palmer,et al.  An artificial visual cortex drives behavioral evolution in co-evolved predator and prey robots , 2012, GECCO '12.

[17]  Randall D. Beer,et al.  On the Dynamics of Small Continuous-Time Recurrent Neural Networks , 1995, Adapt. Behav..

[18]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.

[19]  Klaus Mainzer,et al.  From embodied mind to embodied robotics: Humanities and system theoretical aspects , 2009, Journal of Physiology-Paris.

[20]  Dario Floreano,et al.  Analog Genetic Encoding for the Evolution of Circuits and Networks , 2007, IEEE Transactions on Evolutionary Computation.