Automatic creation of an autonomous agent: genetic evolution of a neural-network driven robot
Dario Floreano,Francesco Mondada +1 more
- pp 421-430
TLDR
The paper describes the results of the evolutionary development of a real, neural-network driven mobile robot, and shows a number of emergent phenomena that are characteristic of autonomous agents.Abstract:
The paper describes the results of the evolutionary development of a real, neural-network driven mobile robot. The evolutionary approach to the development of neural controllers for autonomous agents has been successfully used by many researchers, but most - if not all - studies have been carried out with computer simulations. Instead, in this research the whole evolutionary process takes places entirely on a real robot without human intervention. Although the experiments described here tackle a simple task of navigation and obstacle avoidance, we show a number of emergent phenomena that are characteristic of autonomous agents. The neural controllers of the evolved best individuals display a full exploitation of non-linear and recurrent connections that make them more efficient than analogous man-designed agents. In order to fully understand and describe the robot behavior, we have also employed quantitative ethological tools [13], and showed that the adaptation dynamics conform to predictions made for animals.read more
Citations
More filters
BookDOI
Genetic and Evolutionary Computation - GECCO 2004
Kalyanmoy Deb,Riccardo Poli,Wolfgang Banzhaf,H-G Beyer,Edmund K. Burke,PJ Darwen,Dipankar Dasgupta,Dario Floreano +7 more
TL;DR: The two volume set LNCS 3102/3103 constitutes the refereed proceedings of the Genetic and Evolutionary Computation Conference, GECCO 2004, held in Seattle, WA, USA, in June 2004.
Journal ArticleDOI
Automatic design and manufacture of robotic lifeforms
Hod Lipson,Jordan Pollack +1 more
TL;DR: A combined computational and experimental approach is reported in which simple electromechanical systems are evolved through simulations from basic building blocks, and the ‘fittest’ machines are then fabricated robotically using rapid manufacturing technology.
Book ChapterDOI
Noise and the Reality Gap: The Use of Simulation in Evolutionary Robotics
TL;DR: It has been demonstrated that it is possible to develop successful robot controllers in simulation that generate almost identical behaviours in reality, at least for a particular class of robot-environment interaction dynamics.
Journal ArticleDOI
Evolution of homing navigation in a real mobile robot
Dario Floreano,Francesco Mondada +1 more
TL;DR: The evolution of a discrete-time recurrent neural network to control a real mobile robot and it is shown that the autonomous development of a set of behaviors for locating a battery charger and periodically returning to it can be achieved by lifting constraints in the design of the robot/environment interactions.
Journal ArticleDOI
On the dynamics of small continuous-time recurrent neural networks
TL;DR: This article begins a systematic examination of the dynamics of continuous-time recurrent neural networks with a fairly complete description of the possible dynamical behavior and bifurcations of one- and two-neuron circuits.
References
More filters
Proceedings Article
Adding "foveal vision'' to Wilson's animat
Dave Cliff,Seth Bullock +1 more
TL;DR: The animat's observed behavior can be explained by the animat cautiously moving in a manner that attempts to maximize the generation of new information from the environment over time, and similar explanations can be offered for behavioral patterns in real animals.
Journal ArticleDOI
Adding “foveal vision” to Wilson's animat
Dave Cliff,Seth Bullock +1 more
TL;DR: In this paper, the effects of variations in patterns of sensory sampling were explored in a minimal system for investigating the effects on the behavior of an animat's sensory field and the environment within which it resides.