Take a look at the new version of this page: [ beta version ]. Tell us what you think.

ABSTRACT

A central tenet of embodied artificial intelligence is that intelligent behavior arises out of the coupled dynamics between an agent's body, brain and environment. It follows that the complexity of an agents's controller and morphology must match the complexity of a given task. However, more complex task environments require the agent to exhibit different behaviors, which raises the question as to how to distribute responsibility for these behaviors across the agents's controller and morphology. In this work a robot is trained to locomote and manipulate an object, but the assumption of functional specialization is relaxed: the robot has a segmented body plan in which the front segment may participate in locomotion and object manipulation, or it may specialize to only participate in object manipulation. In this way, selection pressure dictates the presence and degree of functional specialization rather than such specialization being enforced a priori. It is shown that for the given task, evolution tends to produce functionally specialized controllers, even though successful generalized controllers can also be evolved. Moreover, the robot's initial conditions and training order have little effect on the frequency of finding specialized controllers, while the inclusion of additional proprioceptive feedback increases this frequency.

REFERENCES

• 1: Michael L. Anderson, Embodied cognition: a field guide, Artificial Intelligence, v.149 n.1, p.91-130, September 2003 [doi>10.1016/S0004-3702(03)00054-7]
• 2: J. Auerbach and J. C. Bongard. How robot morphology and training order affect the learning of multiple behaviors. In Proceedings of the IEEE Congress on Evolutionary Computation, 2009. To Appear.
• 3: R. Beer. The Dynamics of Active Categorical Perception in an Evolved Model Agent. Adaptive Behavior, 11(4):209, 2003.
• 4: Randall D. Beer, Parameter space structure of continuous-time recurrent neural networks, Neural Computation, v.18 n.12, p.3009-3051, December 2006 [doi>10.1162/neco.2006.18.12.3009]
• 5: R. D. Beer. The dynamics of brain-body-environment systems: A status report. In P. Calvo and A. Gomila, editors, Handbook of Cognitive Science: An Embodied Approach, pages 99--120. Elsevier, 2008.
• 6: J. Bongard. Behavior chaining: incremental behavioral integration for evolutionary robotics. In S. Bullock, J. Noble, R. Watson, and M. A. Bedau, editors, Artificial Life XI: Proceedings of the Eleventh International Conference on the Simulation and Synthesis of Living Systems, pages 64--71. MIT Press, Cambridge, MA, 2008.
• 7: R. Brooks. A robust layered control system for a mobile robot. Robotics and Automation, IEEE Journal of {legacy, pre - 1988}, 2(1):14--23, 1986.
• 8: Rodney A. Brooks, Cambrian intelligence: the early history of the new AI, MIT Press, Cambridge, MA, 1999
• 9: Raffaele Calabretta , Stefano Nolfi , Domenico Parisi , Günter P. Wagner, Emergence of functional modularity in robots, Proceedings of the fifth international conference on simulation of adaptive behavior on From animals to animats 5, p.497-504, September 1998, Univ. of Zurich, Zurich, Switzerland
• 10: Raffaele Calabretta , Stefano Nolfi , Domenico Parisi , Günter P. Wagner, Duplication of modules facilitates the evolution of functional specialization, Artificial Life, v.6 n.1, p.69-84, Dec. 1999 [doi>10.1162/106454600568320]
• 11: Marco Dorigo , Marco Colombetti, Robot shaping: developing autonomous agents through learning, Artificial Intelligence, v.71 n.2, p.321-370, Dec. 1994 [doi>10.1016/0004-3702(94)90047-7]
• 12: E. Izquierdo and T. Buhrmann. Analysis of a dynamical recurrent neural network evolved for two qualitatively different tasks: walking and chemotaxis. In S. Bullock, J. Noble, R. Watson, and M. A. Bedau, editors, Artificial Life XI: Proceedings of the Eleventh International Conference on the Simulation and Synthesis of Living Systems, pages 257--264. MIT Press, Cambridge, MA, 2008.
• 13: N. Kashtan and U. Alon. Spontaneous evolution of modularity and network motifs. Proc Natl Acad Sci U S A, September 2005.
• 14: H. Lipson, J. Pollack, and N. Suh. On The Origin of Modular Variation. Evolution, 56(8):1549--1556, 2002.
• 15: A. Noe. Action In Perception. MIT Press, 2004.
• 16: Rolf Pfeifer , Josh C. Bongard, How the Body Shapes the Way We Think: A New View of Intelligence (Bradford Books), The MIT Press, 2006
• 17: Stuart J. Russell , Peter Norvig, Artificial intelligence: a modern approach, Prentice-Hall, Inc., Upper Saddle River, NJ, 1995
• 18: L. Saksida, S. Raymond, and D. S. Touretzky. Shaping robot behavior using principles from instrumental conditioning. Robotics and Autonomous Systems, 22:231--249, 1997.
• 19: Satinder Pal Singh, Transfer of Learning by Composing Solutions of Elemental Sequential Tasks, Machine Learning, v.8 n.3-4, p.323-339, May 1992 [doi>10.1007/BF00992700]
• 20: N. P. Suh. The Principles of Design (Oxford Series on Advanced Manufacturing). Oxford University Press, March 1990.
• 21: G. Wagner and L. Altenberg. Perspective: Complex adaptations and the evolution of evolvability. Evolution, 50(3):967--976, 1996.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.9 Robotics

General Terms:
Experimentation

Keywords:
artificial intelligence, embodied cognition, evolutionary robotics