Bootstrap learning of foundational representations

Benjamin Kuipers, Patrick Beeson, Joseph Modayil, and Jefferson Provost. Bootstrap learning of foundational representations. Connection Science, 18(2):145–158, June 2006.

Abstract

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 contribute to a theory of 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, objects, and actions. This is not a single learning problem, but a lattice of related learning tasks, each providing prerequisites for tasks to come later. Starting with completely uninterpreted sense and motor vectors, as well as an unknown environment, we show how a learning agent can separate the sense vector into modalities, learn the structure of individual modalities, learn natural primitives for the motor system, identify reliable relations between primitive actions and created sensory features, and can define useful control laws for homing and path-following. Building on this framework, we show how an agent can use to self-organizing maps to identify useful sensory featurs in the environment, and can learn effective hill-climbing control laws to define distinctive states in terms of thos features, and trajectoryfollowing control laws to move from one distinctive state to another. Moving on to place recognition, we show how an agent can combine unsupervised learning, map-learning, and supervised learning to achieve high-performance recognition of places from rich sensory input. And finally, we take the first steps toward learning an ontology of objects, showing tha a bootstrap learning robot can learn to individuate objects through motion, separating them from the static environment and from each other, and learning properties that will be useful for classification. These are four key steps in a much larger research enterprise that lays the foundation for human and robot commonsense knowledge.

BibTeX

@Article{Kuipers-connsci-06,
  author =       {Benjamin Kuipers and Patrick Beeson and Joseph Modayil and
                  Jefferson Provost},
  title =        {Bootstrap learning of foundational representations},
  journal =      {Connection Science},
  year =         2006,
  volume =       18,
  number =       2,
  pages =        {145--158},
  month =        {June},
  abstract =     {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 contribute to a theory of 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, objects, and
                  actions. This is not a single learning problem, but a
                  lattice of related learning tasks, each providing
                  prerequisites for tasks to come later. Starting with
                  completely uninterpreted sense and motor vectors, as well as
                  an unknown environment, we show how a learning agent can
                  separate the sense vector into modalities, learn the
                  structure of individual modalities, learn natural primitives
                  for the motor system, identify reliable relations between
                  primitive actions and created sensory features, and can
                  define useful control laws for homing and
                  path-following. Building on this framework, we show how an
                  agent can use to self-organizing maps to identify useful
                  sensory featurs in the environment, and can learn effective
                  hill-climbing control laws to define distinctive states in
                  terms of thos features, and trajectoryfollowing control laws
                  to move from one distinctive state to another. Moving on to
                  place recognition, we show how an agent can combine
                  unsupervised learning, map-learning, and supervised learning
                  to achieve high-performance recognition of places from rich
                  sensory input. And finally, we take the first steps toward
                  learning an ontology of objects, showing tha a bootstrap
                  learning robot can learn to individuate objects through
                  motion, separating them from the static environment and from
                  each other, and learning properties that will be useful for
                  classification. These are four key steps in a much larger
                  research enterprise that lays the foundation for human and
                  robot commonsense knowledge.},
  bib2html_pubtype ={Journal},
  bib2html_rescat ={Foundational Learning},
}

Download:

[206.1KB pdf]