CaltechAUTHORS
  A Caltech Library Service

Bootstrapping bilinear models of robotic sensorimotor cascades

Censi, Andrea and Murray, Richard M. (2010) Bootstrapping bilinear models of robotic sensorimotor cascades. California Institute of Technology , Pasadena, CA. (Unpublished) http://resolver.caltech.edu/CaltechCDSTR:2010.003a

This is the latest version of this item.

[img]
Preview
PDF
See Usage Policy.

7Mb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechCDSTR:2010.003a

Abstract

We consider the bootstrapping problem, which consists in learning a model of the agent's sensors and actuators starting from zero prior information, and we take the problem of servoing as a cross-modal task to validate the learned models. We study the class of bilinear dynamics sensors, in which the derivative of the observations are a bilinear form of the control commands and the observations themselves. This class of models is simple yet general enough to represent the main phenomena of three representative robotics sensors (field sampler, camera, and range-finder), apparently very different from one another. It also allows a bootstrapping algorithm based on hebbian learning, and that leads to a simple and bioplausible control strategy. The convergence properties of learning and control are demonstrated with extensive simulations and by analytical arguments.


Item Type:Report or Paper (Technical Report)
Group:Control and Dynamical Systems Technical Reports
Record Number:CaltechCDSTR:2010.003a
Persistent URL:http://resolver.caltech.edu/CaltechCDSTR:2010.003a
Usage Policy:You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.
ID Code:28142
Collection:CaltechCDSTR
Deposited By: Imported from CaltechCDSTR
Deposited On:20 Sep 2010
Last Modified:26 Dec 2012 14:31

Available Versions of this Item

Repository Staff Only: item control page