CaltechTHESIS
  A Caltech Library Service

Bootstrapping Vehicles: A Formal Approach to Unsupervised Sensorimotor Learning Based on Invariance

Citation

Censi, Andrea (2013) Bootstrapping Vehicles: A Formal Approach to Unsupervised Sensorimotor Learning Based on Invariance. Dissertation (Ph.D.), California Institute of Technology. doi:10.7907/PWVS-2Q74. https://resolver.caltech.edu/CaltechTHESIS:10282012-082208075

Abstract

Could a "brain in a jar" be able to control an unknown robotic body to which it is connected, and use it to achieve useful tasks, without any prior assumptions on the body's sensors and actuators? Other than of purely intellectual interest, this question is relevant to the medium-term challenges of robotics: as the complexity of robotics applications grows, automated learning techniques might reduce design effort and increase the robustness and reliability of the solutions. In this work, the problem of "bootstrapping" is studied in the context of the Vehicles universe, which is an idealization of simple mobile robots, after the work of Braitenberg. The first thread of results consists in analyzing such simple sensorimotor cascades and proposing models of varying complexity that can be learned from data. The second thread regards how to properly formalize the notions of "absence of assumptions", as a particular form of invariance that the bootstrapping agent must satisfy, and proposes some invariance-based design techniques.

Item Type:Thesis (Dissertation (Ph.D.))
Subject Keywords:Robotics; perception; learning; bootstrapping
Degree Grantor:California Institute of Technology
Division:Engineering and Applied Science
Major Option:Control and Dynamical Systems
Thesis Availability:Public (worldwide access)
Research Advisor(s):
  • Murray, Richard M.
Thesis Committee:
  • Murray, Richard M. (chair)
  • Soatto , Stefano
  • Burdick, Joel Wakeman
  • Abu-Mostafa, Yaser S.
Defense Date:26 June 2012
Record Number:CaltechTHESIS:10282012-082208075
Persistent URL:https://resolver.caltech.edu/CaltechTHESIS:10282012-082208075
DOI:10.7907/PWVS-2Q74
Default Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:7248
Collection:CaltechTHESIS
Deposited By: Andrea Censi
Deposited On:03 Dec 2013 21:52
Last Modified:18 Dec 2020 02:17

Thesis Files

[img]
Preview
PDF - Final Version
See Usage Policy.

24MB

Repository Staff Only: item control page