Access the full text.
Sign up today, get DeepDyve free for 14 days.
D. Parisi, F. Cecconi, S. Nolfi (1990)
Econets: Neural networks that learn in an environmentNetwork: Computation In Neural Systems, 1
(1994)
Evolution of robot behavior with finite state automata and neural nets — Is the neutral evolution observed in big jumps ?
S. Nolfi, D. Parisi, J. Elman (1994)
Learning and Evolution in Neural NetworksAdaptive Behavior, 3
D. Cliff, P. Husbands, I. Harvey (1993)
Explorations in Evolutionary RoboticsAdaptive Behavior, 2
J. Smith (1975)
Evolution of sexNature, 254
D. Floreano, F. Mondada (1994)
Automatic creation of an autonomous agent: genetic evolution of a neural-network driven robot
J. Elman (1990)
Finding Structure in TimeCogn. Sci., 14
D. Goldberg (1988)
Genetic Algorithms in Search Optimization and Machine Learning
F. Menczer, D. Parisi (1992)
Recombination and unsupervised learning: effects of crossover in the genetic optimization of neural networksNetwork: Computation In Neural Systems, 3
(1992)
The Micro-C 68HC11 Cross Compiler
Cedric Smith, D. Falconer (1962)
Introduction to Quantitative Genetics.Biometrika, 49
R. Bagrodia, Chien-Chung Shen (1991)
MIDAS: Integrated Design and Simulation of Distributed SystemsIEEE Trans. Software Eng., 17
J. Holland (1975)
Adaptation in natural and artificial systems
S. Gould, N. Eldredge (1993)
Punctuated equilibrium comes of ageNature, 366
Joe Jones, A. Flynn (1993)
Mobile robots: inspiration to implementationLeonardo, 27
S. Nolfi, D. Floreano, O. Miglino, F. Mondada (1994)
How to Evolve Autonomous Robots: Different Approaches in Evolutionary Robotics
J. Koza (1993)
Evolution of Subsumption Using Genetic Programming
(1991)
Course Notes from "6.270": The Autonomous Robot Design Competition
(1992)
Miniboard 2.0 Technical Reference
R. Collins, D. Jefferson (1991)
Representations for artificial organisms
Proceedings of the Simulation of Adaptive Behavior
R. Brooks (1991)
New Approaches to RoboticsScience, 253
R. Brooks (1992)
Artificial Life and Real Robots
M. Minsky (1967)
Computation: Finite and Infinite Machines
We have evolved artificial neural networks to control the wandering behavior of small robots. The task and environment were very simple—to touch as many squares in a grid as possible during a fixed period of time. A number of the simulated robots were embodied in a small Lego™ robot, controlled by a Motorola™ 6811 processor; and their performance was compared to the simulations. We observed that: (a) evolution was an effective means to program the robot's behavior; (b) progress was characterized by sharply stepped periods of improvement, separated by periods of stasis that corresponded to levels of behavioral/computational complexity; and (c) the simulated and realized robots behaved quite similarly, the realized robots in some cases outperforming the simulated ones. Introducing random noise to the simulations improved the fit somewhat (from r = 0.73 to 0.79). Hybrid simulated/embodied selection regimes for evolutionary robots are discussed.
Artificial Life – MIT Press
Published: Jan 1, 1994
Keywords: Artificial Life; robots; evolution; genetic algorithms; evolutionary robotics; mobile autonomous vehicles
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.