Josh C. Bongard
ABSTRACT
Embodied cognition emphasizes that intelligent behavior results from the coupled dynamics between an agent's body, brain and environment. In response to this, several projects have jointly evolved robot morphology and control to realize desired behaviors. However, which aspects of a robot's morphology should be placed under evolutionary control remains an open question. Here it is shown that subjugating more of the robot's body plan to selection pressure may either slow or increase the rate of evolution, depending on the desired behavior.
More specifically, it is shown that for the legged locomotion behavior evolved and described here, increasing the number of evolved morphological parameters slows adaptation. For a more complex behavior involving legged locomotion toward an object followed by manipulation of that object, increasing the number of evolved morphological parameters accelerates adaptation. This suggests that subjugating more of the robot's design to evolution may be of increasing utility for increasingly complex tasks.
- M. Anderson. Embodied cognition: A field guide. Artificial Intelligence, 149(1):91--130, 2003. Google Scholar
Digital Library
- 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.Google ScholarCross Ref
- 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, pages 64--71. MIT Press, Cambridge, MA, 2008.Google Scholar
- R. Brooks. Cambrian Intelligence: The Early History of the New AI. MIT Press, 1999. Google ScholarDigital Library
- R. Groß and M. Dorigo. Cooperative transport of objects of different shapes and sizes. In M. Dorigo, M. Birattari, C. Blum, L. M. Gambardella, F. Mondada, and T. Stutzle, editors, Ant colony optimization and swarm intelligence, pages 107--118. Berlin: Springer, 2004.Google Scholar
- S. Nolfi and D. Floreano. Evolutionary Robotics. MIT Press, Boston, MA, 2000.Google Scholar
- R. Pfeifer and J. Bongard. How the Body Shapes the Way We Think: A New View of Intelligence. MIT Press, 2006. Google ScholarDigital Library
Index Terms
- The impact of jointly evolving robot morphology and control on adaptation rate
Recommendations
The utility of evolving simulated robot morphology increases with task complexity for object manipulation
Embodied artificial intelligence argues that the body and brain play equally important roles in the generation of adaptive behavior. An increasingly common approach therefore is to evolve an agent's morphology along with its control in the hope that ...
Morphological and environmental scaffolding synergize when evolving robot controllers: artificial life/robotics/evolvable hardware
GECCO '11: Proceedings of the 13th annual conference on Genetic and evolutionary computationScaffolding---initially simplifying the task environment of autonomous robots---has been shown to increase the probability of evolving robots capable of performing in more complex task environments. Recently, it has been shown that changes to the body ...
The impact of different tasks on evolved robot morphologies
GECCO '21: Proceedings of the Genetic and Evolutionary Computation Conference CompanionA well-established fact in biology is that the environmental conditions have a paramount impact on the evolved life forms. In this paper we investigate this in an evolutionary robot system where morphologies and controllers evolve together. We evolve ...
Comments