Abstract
We introduce a technique that allows a robot to increase its resiliency and learning skills by exploiting a process akin to self-reflection. A robot contains two controllers: A pure reactive innate controller, and a reflective controller that can observe, model and control the innate controller. The reflective controller adapts the innate controller without access to the innate controller’s internal state or architecture; Instead, it models it and then synthesizes filters that exploit its existing capabilities for new situations. In this paper we explore a number of scenarios where the innate controller is a recurrent neural network. We demonstrate significant adaptation ability with relatively few physical trials.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Cox, M.T.: Metacognition in Computation: A selected research review. Artificial Intelligence 169(2), 104–141 (2005)
Foote, A., Crystal, J.: Metacognition in the Rat. Current Biology 17(6), 551–555 (2007)
Hampton, R.: Rhesus monkeys know when they remember. Proceedings of the National Academy of Sciences 98(9), 5359 (2001)
Bongard, J.C., Zykov, V., Lipson, H.: Resilient Machines through Continuous Self-Modeling. Science 314(5802), 1118–1121 (2006)
Brooks, R.A.: Intelligence Without Representation. Artificial Intelligence 47(1-3), 139–159 (1991)
Minsky, M.: The Society of Mind. Simon & Chuster Inc., New York (1986)
Minsky, M.: Interior grounding, reflection, and self-consciousness. In: Proceedings of International Conference on Brain, Mind and Society. Tohoku University, Japan (2005)
Minsky, M.: The Emotion Machine. Simon & Schuster Inc., New York (2007)
Nelson, T., Narens, L.: Metamemory: A theoretical framework and new findings. The Psychology of Learning and Motivation 26, 125–141 (1990)
Smith, J., Shields, W., Washburn, D.: The comparative psychology of uncertainty monitoring and metacognition. Behavioral and Brain Sciences 26(03), 317–339 (2004)
Zagal, J.C., Lipson, H.: Self-Reflection in Evolutionary Robotics: Resilient Adaptation with a Minimum of Physical Exploration. In: Proceedings of the Genetic and Evolutionary Computation Conference, Late Breaking Papers, GECCO (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zagal, J.C., Lipson, H. (2011). Towards Self-reflecting Machines: Two-Minds in One Robot. In: Kampis, G., Karsai, I., Szathmáry, E. (eds) Advances in Artificial Life. Darwin Meets von Neumann. ECAL 2009. Lecture Notes in Computer Science(), vol 5777. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21283-3_20
Download citation
DOI: https://doi.org/10.1007/978-3-642-21283-3_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21282-6
Online ISBN: 978-3-642-21283-3
eBook Packages: Computer ScienceComputer Science (R0)