Bootstrap Learning of Foundational Representations. (2005)
To be autonomous, intelligent robots must learn the foundations of commonsense knowledge from their own sensorimotor experience in the world. We describe four recent research results that show how a robot learning agent can bootstrap from the ``blooming buzzing confusion'' of the pixel level to a higher-level ontology including distinctive states, places, actions, and objects.
View:
PDF
Citation:
In Developmental Robotics, AAAI Spring Symposium Series, 2005.
Bibtex:

Patrick Beeson pbeeson [at] traclabs com
Benjamin Kuipers kuipers [at] cs utexas edu
Joseph Modayil modayil [at] cs utexas edu
Jefferson Provost Ph.D. Alumni jefferson provost [at] gmail com