Self-reflection in evolutionary robotics: resilient adaptation with a minimum of physical exploration

ABSTRACT

Metacognition is the ability of a system to observe and self regulate its own cognitive processes. In this paper we explore the use of metacognitive processes to improve robot resiliency and learning skills. We examine a robot that contains two controllers: An innate controller that is directly connected to sensors and motors, and a meta controller that monitors and modulates the activity of the innate controller. We show how the meta controller can observe, model and control the innate controller without access to the innate controller's internal state or architecture. Quantitative comparisons of this method with traditional evolutionary robotics techniques show how this form of "self-reflection" is a promising alternative to traditional adaptation methods.

REFERENCES

• 1: J. Bongard and H. Lipson. Once more unto the breach: Co-evolving a robot and its simulator. In Artificial Life IX: Proceedings of the Ninth International Conference on the Simulation and Synthesis of Living Systems, pages 57--62, 2004.
• 2: J. Bongard, V. Zykov, and H. Lipson. Resilient Machines Through Continuous Self-Modeling. Science, 314(5802):1118--1121, 2006.
• 3: Michael T. Cox, Metacognition in computation: a selected research review, Artificial Intelligence, v.169 n.2, p.104-141, December 2005 [doi>10.1016/j.artint.2005.10.009]
• 4: A. Foote and J. Crystal. Metacognition in the Rat. Current Biology, 17(6):551--555, 2007.
• 5: R. Hampton. Rhesus monkeys know when they remember. Proceedings of the National Academy of Sciences, 98(9):5359, 2001.
• 6: Marvin Minsky, The society of mind, Simon & Schuster, Inc., New York, NY, 1986
• 7: T. Nelson and L. Narens. Metamemory: A theoretical framework and new findings. The psychology of learning and motivation, 26:125--141, 1990.
• 8: J. Smith, W. Shields, and D. Washburn. The comparative psychology of uncertainty monitoring and metacognition. Behavioral and Brain Sciences, 26(03):317--339, 2004.
• 9: J.C. Zagal, J. Ruiz-del-Solar, and P. Vallejos. Back-to-Reality: Crossing the reality gap in evolutionary robotics. In IAV 2004: Proceedings 5th IFAC Symposium on Intelligent Autonomous Vehicles. Elsevier Science Publishers B.V., 2004.
• 10: J.C. Zagal, J. Ruiz-del-Solar, A.G Palacios. Fitness based identification of a robot structure. In Artificial Life XI: Proceedings of the Eleventh International Conference on the Simulation and Synthesis of Living Systems, pages 733--740, 2008.
• 11: Zhong Zhang , Qiang Yang, Feature Weight Maintenance in Case Bases Using Introspective Learning, Journal of Intelligent Information Systems, v.16 n.2, p.95-116, March/April 2001 [doi>10.1023/A:1011208900462]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.9 Robotics
          Subjects: Autonomous vehicles

General Terms:
Algorithms

Keywords:
evolutionary robotics, learning, metacognition, self-modeling, self-reflection