Abstract
The aim of the present paper is to propose that the adoption of a framework of biological development is suitable for the construction of artificial systems. We will argue that a developmental approach does provide unique insights on how to build highly complex and adaptable artificial systems. To illustrate our point, we will use as an example the acquisition of goal-directed reaching. In the initial part of the paper we will outline (a) how mechanisms of biological development can be adapted to the artificial world, and (b) how this artificial development differs from traditional engineering approaches to robotics. An experiment performed on an artificial system initially controlled by motor reflexes is presented, showing the acquisition of visuo-motor maps for ballistic control of reaching without explicit knowledge of the system's kinematic parameters.
Original language | English (US) |
---|---|
Pages (from-to) | 1413-1427 |
Number of pages | 15 |
Journal | Neural Networks |
Volume | 12 |
Issue number | 10 |
DOIs | |
State | Published - Dec 1999 |
Externally published | Yes |
Bibliographical note
Funding Information:The research described here is supported in part by a National Project of the Italian Ministry of Scientific and Technological Research (MURST), by Italian Space Agency (ASI) and in part by the EU-TMR project Virgo.
Keywords
- Artificial systems
- Development
- Human infants
- Learning
- Motor control
- Robotics