Return to search

An embodied approach to evolving robust visual classifiers

From the very creation of the term by Czech writer Karel Capek in 1921, a "robot" has been synonymous with an artificial agent possessing a powerful body and cogitating mind. While the fields of Artificial Intelligence (AI) and Robotics have made progress into the creation of such an android, the goal of a cogitating robot remains firmly outside the reach of our technological capabilities. Cognition has proved to be far more complex than early AI practitioners envisioned. Current methods in Machine Learning have achieved remarkable successes in image categorization through the use of deep learning. However, when presented with novel or adversarial input, these methods can fail spectacularly. I postulate that a robot that is free to interact with objects should be capable of reducing spurious difference between objects of the same class. This thesis demonstrates and analyzes a robot that achieves more robust visual categorization when it first evolves to use proprioceptive sensors and is then trained to increasingly rely on vision, when compared to a robot that evolves with only visual sensors. My results suggest that embodied methods can scaffold the eventual achievement of robust visual classification.

Identiferoai:union.ndltd.org:uvm.edu/oai:scholarworks.uvm.edu:graddis-1422
Date01 January 2015
CreatorsZieba, Karol
PublisherScholarWorks @ UVM
Source SetsUniversity of Vermont
LanguageEnglish
Detected LanguageEnglish
Typetext
Formatapplication/pdf
SourceGraduate College Dissertations and Theses

Page generated in 0.0019 seconds