Neural Learning of Embodied Interaction Dynamics

Kuniyoshi, Yasuo and Berthouze, Luc (1998) Neural Learning of Embodied Interaction Dynamics. [Journal (Paginated)]

Full text available as:

[img] PDF


This paper presents our approach towards realizing a robot which can bootstrap itself towards higher complexity through embodied interaction dynamics with the environment including other agents. First, the elements of interaction dynamics are extracted from conceptual analysis of embodied interaction and its emergence, especially of behavioral imitation. Then three case studies are made, presenting our neural architecture and the robotic experiments on some of the important elements discussed above: self exploration and entrainment, emergent coordination, and categorizing self behavior. Finally we propose that integrating all these elements will be the important step towards realizing the bootstrapping agent envisaged above.

Item Type:Journal (Paginated)
Keywords:embodiment, dynamical systems, imitation, development, spiking neurons, emergence, exploration, categorization, coordination, active vision
Subjects:Computer Science > Artificial Intelligence
Computer Science > Machine Learning
Computer Science > Neural Nets
ID Code:1495
Deposited By: Berthouze, Dr Luc
Deposited On:10 May 2001
Last Modified:11 Mar 2011 08:54


Repository Staff Only: item control page