- Evolutionary robotics
Evolutionary Robotics (ER) is a methodology that uses
evolutionary computationto develop controllers for autonomous robots. Algorithmsin ER frequently operate on populations of candidate controllers,initially selected from some distribution. This population is then repeatedlymodified according to a fitness function. In the case of genetic algorithms (or "GAs"), a common method in evolutionary computation, the populationof candidate controllers is repeatedly grown according to crossover, mutation and other GA operatorsand then culled according to the fitness function.The candidate controllers used in ER applications may be drawn from some subset of the set of artificial neural networks, although some applications (including SAMUEL, developed at the Naval Center for Applied Research in Artificial Intelligence) use collections of "IF THEN ELSE" rules as the constituent parts of an individual controller. It is theoretically possible to use any set of symbolic formulations of a control laws (sometimes called a policies in the machine learningcommunity) as the space of possible candidate controllers.It is worth noting that artificial neural networks can also be used for robot learningoutside of the context of evolutionary robotics. In particular, other forms of reinforcement learningcan be used for learning robot controllers. Developmental roboticsis related to, but differs from, evolutionary robotics. ER uses populations of robots that evolve over time, whereas DevRob is interested in the organization of a single robot's control system develops through experience, over time
The foundation of ER was laid with work at the national research council in Rome in the 90s, but the initial idea of encoding a robot control system into a genome and have
artificial evolutionimprove on it dates back to the late 80s.
The term "evolutionary robotics" was introduced in 1993 by Cliff, Harvey and Husbands at the
University of SussexFact|date=November 2007. In 1992 and 1993 two teams, a team surrounding Floreano and Mondada at the EPFLin Lausanneand a research group at the COGS at the University of Sussexreported the first experiments on artificial evolution of autonomous robots. The success of this early research triggered a wave of activity in labs around the world trying to harness the potential of the approach.
Lately, the difficulty in "scaling up" the complexity of the robot tasks has shifted attention somewhat towards the theoretical end of the field rather than the engineering end.
Evolutionary robotics is done with many different objectives, often at the same time. These include creating useful controllers for real-world robot tasks, exploring the intricacies of evolutionary theory (such as the
Baldwin effect), reproducing psychological phenomena, and finding out about biological neural networks by studying artificial ones. Creating controllers via artificial evolution requires a large number of evaluations of a large population. This is very time consuming, which is one of the reasons why controller evolution is usually done in software. Also, initial random controllers may exhibit potentially harmful behaviour, such as repeatedly crashing into a wall, which may damage the robot. Transferring controllers evolved in simulation to physical robots is very difficult and a major challenge in using the ER approach. The reason is that evolution is free to explore all possibilities to obtain a high fitness, including any inaccuracies of the simulation Fact|date=January 2008.This need for a large number of evaluations, requiring fast yet accurate computer simulations, is one of the limiting factors of the ER approach Fact|date=January 2008.
In rare cases, evolutionary computation may be used to design the physical structure of the robot, in addition to the controller. One of the most notable examples of this was
Karl Sims' demo for Thinking Machinescorporation.
Motivation for Evolutionary Robotics
Many of the commonly used
machine learningalgorithms require a set of training examples consisting of both a hypothetical input and a desired answer. In many robot learningapplications the desired answer is an action for the robot to take.These actions are usually not known explicitly a priori, instead the robotcan, at best, receive a value indicating the success or failure of a given action taken. Evolutionary algorithms are natural solutions to this sort of problem framework, as the fitness function need only encode the success or failure of a given controller, rather than the precise actions the controller should have taken. An alternative to the use of evolutionary computation in robot learningis the use of other forms of reinforcement learning, such as q-learning, to learn the fitness of any particular action, and then use predicted fitness values indirectly to create a controller.
Conferences and Institutes
* Evolutionary Robotics
IEEE Congress on Evolutionary Computation
European Conference on Artificial Life
Academic institutes and researchers
Chalmers University of Technology: Peter Nordin, [http://humanoid.fy.chalmers.se/ The Humanoid Project]
University of Sussex: Inman Harvey, Phil Husbands, Ezequiel Di Paolo, Eric Vaughan, Thomas Buehrmann
Stefano Nolfi, Raffaele Calabretta
EPFL: Dario Floreano
University of Zürich: Rolf Pfeifer
Cornell University: Hod Lipson, Josh Bongard
* Indiana University:
* [http://crim.ece.ncsu.edu/index.php Center for Robotics and Intelligent Machines] ,
North Carolina State University: Eddie Grant, [http://www.nelsonrobotics.org/ Andrew Nelson]
University College London: Peter Bentley, Siavash Haroun Mahdavi
University of Essex: Simon Lucas
Brandeis University: Jordan Pollack
IDSIAand Technical University of Munich: Juergen Schmidhuber's [http://www.idsia.ch/~juergen/cogbotlab.html Robot Lab]
University College of Skövde: Tom Ziemke
U.S. Naval Research Laboratory's, [http://www.nrl.navy.mil/aic/iss/aas/ Navy Center for Applied Research In Artificial Intelligence] : Alan C. Schultz, Mitchell A. Potter, Kenneth De Jong
* [http://www.ais.fraunhofer.de/INDY Fraunhofer AiS, Intelligent Dynamics Dep.] : [http://www.ais.fraunhofer.de/INDY/fpas/index_empty.html Frank Pasemann]
* [http://www.genarts.com/karl/evolved-virtual-creatures.html Evolved Virtual Creatures] by
Karl Sims( GenArts)
* [http://www.kenrinaldo.com Ken Rinaldo artificial life robotics] .
* [http://lsi.vc.ehu.es/pablogn/ University of the Basque Country (UPV-EHU): Robótica Evolutiva, Pablo González-Nalda (in Spanish)] [http://lsi.vc.ehu.es/pablogn/topos/investig/ficheros/NeurocompTopos.pdf PDF (in English)] .
* "Evolutionary Robotics" by
Stefano Nolfiand Dario Floreano. ISBN 0-262-14070-5
* "Advances in the Evolutionary Synthesis of Intelligent Agents" by Mukesh Patel,
Vasant Honavarand Karthik Balakrishnan (Ed). Cambridge, MA: MIT Press. 2001. ISBN 0-262-16201-6
* [http://mensnewsdaily.com/2007/05/16/robobusiness-robots-with-imagination/ RoboBusiness: Robots that Dream of Being Better]
* [http://www.irobis.com/ Institute of Robotics in Scandinavia AB (iRobis)]
* [http://humanoid.fy.chalmers.se/text/cuba.pdf An Evolutionary Architecture for a Humanoid Robot]
* [http://www.evolutionaryrobotics.org/ An introduction to Evolutionary Robotics with annotated bibliography]
* [http://laral.istc.cnr.it/evorobot/ The Evolutionary Robotics Homepage]
* [http://lis.epfl.ch/resources/documentation/EvolutionaryRobotics/index.php A gentle introduction to ER]
Wikimedia Foundation. 2010.
Look at other dictionaries:
Evolutionary algorithm — In artificial intelligence, an evolutionary algorithm (EA) is a subset of evolutionary computation, a generic population based metaheuristic optimization algorithm. An EA uses some mechanisms inspired by biological evolution: reproduction,… … Wikipedia
Evolutionary computation — For the journal, see Evolutionary Computation (journal). In computer science, evolutionary computation is a subfield of artificial intelligence (more particularly computational intelligence) that involves combinatorial optimization problems.… … Wikipedia
Robotics conventions — There are many conventions used in the robotics research field. This article summarises these conventions. Contents 1 Line representations 2 Non minimal vector coordinates 2.1 Plücker coordinates … Wikipedia
Evolutionary Virtual Agent — EVA Apparu en 2000 Auteur Jean Claude Heudin Dialectes Lisp, Scheme … Wikipédia en Français
Topic outline of robotics — Robotics is the science and technology of designing, making, and applying robots, including theory from many contributing fields. A robot is a mechanical or virtual, artificial . It is usually an electromechanical system, which, by its appearance … Wikipedia
Morphogenetic robotics —  generally refers to the methodologies that address challenges in robotics inspired by biological morphogenesis. The term morphogenetic robotics was first coined in a project discussion in 2009 by Yaochu Jin and his colleague who first… … Wikipedia
Outline of robotics — See also: Index of robotics articles The following outline is provided as an overview of and topical guide to robotics: Robotics – branch of technology that deals with the design, construction, operation, structural disposition, manufacture and… … Wikipedia
Developmental robotics — (DevRob), sometimes called epigenetic robotics, is a methodology that uses metaphors from neural development and developmental psychology to develop the mind for autonomous robots. The focus is on a single or multiple robots going through stages… … Wikipedia
Cognitive robotics — a robot is a robot device that is built from inanimate matter. Its behavior in response to the environment is deterministic, based on how the robot was designed. Cognition is the process of acquiring and using knowledge about the world for goal… … Wikipedia
Institute of Robotics in Scandinavia AB — Infobox Company company name = Institute of Robotics in Scandinavia AB company type = Private company slogan = foundation = 2007 location = Gothenburg, Sweden key people = Staffan Hillberg, CEO; Peter Nordin num employees = 6 (2007) industry =… … Wikipedia