Evolving robots able to integrate sensory-motor information over time

Authors:
Stefano Nolfi;Davide Marocco
Affiliations:
Division of Neural Systems and Artificial Life, Institute of Psychology, National Research Council (CNR), Viale Marx, 15, 00137, Rome, Italy;University of Calabria, "Centro Interdipartimentale della Comunicazione", Cosenza, Italy and Division of Neural Systems and Artificial Life, Institute of Psychology, (CNR), Rome, Italy
Venue:
Biologically inspired robot behavior engineering
Year:
2003

Citing 11
Cited 0

Learning to Perceive and Act by Trial and Error

Machine Learning
Evolving dynamical neural networks for adaptive behavior

Adaptive Behavior
Seeing the light: artificial evolution, real vision

SAB94 Proceedings of the third international conference on Simulation of adaptive behavior : from animals to animats 3: from animals to animats 3
A dynamical systems perspective on agent-environment interaction

Artificial Intelligence - Special volume on computational research on interaction and agency, part 1
Understanding intelligence

Understanding intelligence
Being There: Putting Brain, Body, and World Together Again

Being There: Putting Brain, Body, and World Together Again
Catching Ourselves in the Act: Situated Activity, Interactive Emergence, Evolution, and Human Thought

Catching Ourselves in the Act: Situated Activity, Interactive Emergence, Evolution, and Human Thought
Evolutionary Robotics: The Biology,Intelligence,and Technology

Evolutionary Robotics: The Biology,Intelligence,and Technology
Mobile Robot Miniaturisation: A Tool for Investigation in Control Algorithms

The 3rd International Symposium on Experimental Robotics III
Landscapes, learning costs, and genetic assimilation

Evolutionary Computation
Evolution of homing navigation in a real mobile robot

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Quantified Score

Hi-index	0.00

Visualization

Abstract

By acting, agents which are embodied and situated, partially determine the sensory patterns they receive from the environment. In this paper we will discuss in which conditions we can expect the emergence of systems able to integrate sensory-motor information over time and later use this information to modulate their behavior accordingly. In doing so we will discuss the problems that these systems should be able to solve and the processes that might lead to a transition from simple agents that only rely on sensory information or on their internal dynamic to systems that are also able to integrate information over time.