Abstract— This paper introduces a novel approach to representing and learning tool affordances by a robot. The tool representation described here uses a behavior-based approach t...
In this paper we propose a novel computational method to infer visual saliency in images. The method is based on the idea that salient objects should have local characteristics tha...
A system based on a neural network framework is considered. We used two neural networks, an Elman network [1][2] and a Kohonen (concurrent) network [3], for a categorization task....
—Three dimensional vision applications, such as robot vision, require modeling of the relationship between the two-dimensional images and the three-dimensional world. Camera cali...
: Several species of animals use whiskers to accurately navigate and explore objects in the absence of vision. We have developed inexpensive arrays of artificial whiskers based on ...
Aimee Schultz, Joseph Solomon, Michael A. Peshkin,...