Automatic creation of an autonomous agent: genetic evolution of a neural-network driven robot
Dario Floreano,Francesco Mondada +1 more
- pp 421-430
Reads0
Chats0
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
Journal ArticleDOI
Evolved Transistor Array Robot Controllers.
TL;DR: For the first time, a field programmable transistor array (FPTA) was used to evolve robot control circuits directly in analog hardware and a methodology was developed to analyse the evolved circuits which provided insights into their operation.
A Model for Programmability and Virtuality in Dynamical Neural Networks
TL;DR: In this dissertation a fixed-weight architecture for Continuous Time Recurrent Neural Networks (CTRNNs) is proposed in order to give an account for biological phenomena, controlled by neuronal activity, in which changes of behavior occur so fast that presumably no changes in the involved neuronal connectivity are possible.
Journal ArticleDOI
Multiphase genetic programming: a case study in sumo maneuver evolution
Jiming Liu,Shiwu Zhang +1 more
TL;DR: An overview of the MP GP approach is provided as well as details on how the sumo maneuver evolution experiments are carried out and how the MPGP-based case study differs from others.
Posted Content
Training Deep Fourier Neural Networks To Fit Time-Series Data
TL;DR: In this paper, a method for training a deep neural network containing sinusoidal activation functions to fit to time-series data is presented, where weights are initialized using a fast Fourier transform, then trained with regularization to improve generalization.
Mechanistic and ecological explanations in agent-based models of cognition
Jason Noble,M. de Pinedo +1 more
TL;DR: It is argued that two styles of explanation — mechanistic and ecological — are needed in accounting for the behaviour of synthetic agents, and that mechanistic explanations cannot stand alone.
References
More filters
Book
Genetic algorithms in search, optimization, and machine learning
TL;DR: In this article, the authors present the computer techniques, mathematical tools, and research results that will enable both students and practitioners to apply genetic algorithms to problems in many fields, including computer programming and mathematics.
Book
Adaptation in natural and artificial systems
TL;DR: Names of founding work in the area of Adaptation and modiication, which aims to mimic biological optimization, and some (Non-GA) branches of AI.
Intelligence without Representation
TL;DR: Brooks et al. as mentioned in this paper decompose an intelligent system into independent and parallel activity producers which all interface directly to the world through perception and action, rather than interface to each other particularly much.
Journal ArticleDOI
Intelligence without representation
TL;DR: Brooks et al. as discussed by the authors decompose an intelligent system into independent and parallel activity producers which all interface directly to the world through perception and action, rather than interface to each other particularly much.