AbstractMost animals have significant behavioral expertise built in without having to explicitly learn it all from scratch. This expertise is a product of evolution of the organism; it can be viewed as a very long term form of learning which provides a structured system within which individuals might learn more specialized skills or abilities. This paper suggests one possible mechanism for analagous robot evolution by describing a carefully designed series of networks, each one being a strict augmentation of the previous one, which control a six legged walking machine capable of walking over rough terrain and following a person passively sensed in the infrared spectrum. As the completely decentralized networks are augmented. the robot’s performance and behavior repetoire demonstrably improve. The rationale for such demonstrations is that they may provide a hint as to the requirements for automatically building massive networks to carry out complex sensory-motor tasks. The experiments with an actual robot ensure that an essence of reality is maintained and that no critical disabling problems have been ignored.
Similar books and articles
Can You Kill a Robot Nanny?: Ethological Approach to the Effect of Robot Caregivers on Child Development and Human Evolution.Enikő Kubinyi, P. Pongrácz & Ádám Miklósi - 2010 - Interaction Studies 11 (2):214-219.
Infinitely Complex Machines.Eric Steinhart - 2007 - In Intelligent Computing Everywhere. Springer. pp. 25-43.
There is No 'I' in 'Robot': Robots and Utilitarianism (Expanded & Revised).Christopher Grau - 2011 - In Susan Anderson & Michael Anderson (eds.), Machine Ethics. Cambridge University Press. pp. 451.
The Cog Project: Building a Humanoid Robot.Rodney A. Brooks, Cynthia Breazeal, Matthew Marjanovic, Brian Scassellati & Matthew Williamson - 1999 - Lecture Notes in Computer Science 1562:52-87.
Are Self-Organizing Biochemical Networks Emergent?Christophe Malaterre - 2009 - In Maryvonne Gérin & Marie-Christine Maurel (eds.), Origins of Life: Self-Organization and/or Biological Evolution? EDP Sciences. pp. 117--123.
Added to PP
Historical graph of downloads
Citations of this work
A Dynamical Systems Perspective on Agent-Environment Interaction.Randall D. Beer - 1995 - Artificial Intelligence 72 (1-2):173-215.
Ways of Coloring: Comparative Color Vision as a Case Study for Cognitive Science.Evan Thompson, Adrian Palacios & Francisco J. Varela - 1992 - Behavioral and Brain Sciences 15 (1):1-26.
Implications of Action-Oriented Paradigm Shifts in Cognitive Science.Peter F. Dominey, Tony J. Prescott, Jeannette Bohg, Andreas K. Engel, Shaun Gallagher, Tobias Heed, Matej Hoffmann, Gunther Knoblich, Wolfgang Prinz & Andrew Schwartz - 2016 - In Andreas K. Engel, Karl J. Friston & Danica Kragic (eds.), The Pragmatic Turn: Toward Action-Oriented Views in Cognitive Science. MIT Press. pp. 333-356.
Conclusions From Color Vision of Insects.Werner Backhaus & Randolf Menzel - 1992 - Behavioral and Brain Sciences 15 (1):28-30.
References found in this work
No references found.