Towards Robot Vision Module Development

In this paper we present a thrust in three directions of visual development using supervised and semi-supervised techniques. The first is an implementation of semi-supervised object detection and recognition using the principles of Soft Attention and Generative Adversarial Networks (GANs). The second and the third are supervised networks that learn basic concepts of spatial locality and quantity respectively using Convolutional Neural Networks (CNNs). The three thrusts together are based on the approach of Experiential Robot Learning, introduced in previous publication. While the results are unripe for implementation, we believe they constitute a stepping stone towards autonomous development of robotic visual modules.