Saliency of Robotic Tasks Using Soar

Saliency of Robotic Tasks With Soar

Soar utilizes a match-based attention mechanism which arises naturally out of the interactions of the productions of long-term memory and the attribute-value representation of working memory. In a perceptual system, many inputs may compete for attention and cognitive resources. In Soar, these demands are represented by recognitional productions which match to the input. However, simply matching to the input may not be enough to cause the production to fire; the current context is relevant as well. Thus, the context and input drive the knowledge that is brought to bear and the subsequent action of the decision procedure, resulting in actions that are appropriate for the current situation (based on the knowledge available to Soar).


To go to the Soar capabilities list, press UP

To return, press HOME. To go to the next document, press NEXT.