Publication View

Feel the beat: using cross-modal rhythm to integrate perception of objects, others, and self (2004)

Abstract
For a robot to be capable of development, it must be able to explore its environment and learn from its experiences. It must find (or create) opportunities to experience the unfamiliar in ways that reveal properties valid beyond the immediate context. In this paper, we develop a novel method for using the rhythm of everyday actions as a basis for identifying the characteristic appearance and sounds associated with objects, people, and the robot itself. Our approach is to identify and segment groups of signals in individual modalities (sight, hearing, and proprioception) based on their rhythmic variation, then to identify and bind causally-related groups of signals across different modalities. By including proprioception as a modality, this cross-modal binding method applies to the robot itself, and we report a series of experiments in which the robot learns about the characteristics of its own body.

Publication details
Download http://cogprints.org/4062/
http://cogprints.org/4062/01/fitzpatrick.pdf
Repository Cogprints (United Kingdom)
Keywords Machine Vision, Machine Learning, Robotics
Type Conference Paper

Cited publications (6)
Foundations for a Theory of Mind for a Humanoid Robot (2001)
A Robot that Learns to Communicate with Human Caregivers (2002)
Object Lesson: discovering and learning to recognize objects (2003)
Computational Model for an Extendable Robot Body Schema (2003)
Binding in Models of Perception and Brain Function (1995)
The Whole World in Your Hand: Active and Interactive Segmentation (2003)