An Embodied Approach for Evolving Robust Visual Classifiers

Karol Zieba, Josh Bongard
2015 Proceedings of the 2015 on Genetic and Evolutionary Computation Conference - GECCO '15  
From the very creation of the term by Czech writer Karel Čapek 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
more » ... ine 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.
doi:10.1145/2739480.2754788 dblp:conf/gecco/ZiebaB15 fatcat:gr3jbmycd5gatgb254kfbkwjdu