Cognitive Patterns: An Architecture for Distributed Control of ChemBots
Today"s robots require a great deal of control and supervision, and are unable to intelligently respond to unanticipated and novel situations. To address this problem, we developed a preliminary architecture for Cognitive Patterns which includes Cognitive Patterns Knowledge Generation (CPKG) and has the ability to connect to various knowledge-based models, multiple sensors, and to a human operator. CPKG is a knowledge-based system that can understand, adapt to, and intelligently act in novel situations that are not accounted for by the knowledge base implementers, and can do so without much involvement from the human operator. The CPKG system comprises three major internal modules: Pattern Generation, Perception and Action via Vertical Blends and Adaptation via Horizontal Blends. These enable it to create situationally-relevant abstract patterns, match sensory input to a suitable abstract pattern in a multilayered top-down/bottom-up fashion, similar to the mechanisms used for visual perception in the brain, and generate new abstract patterns. The main benefit of Cognitive Patterns is that it will allow for a special class of robots that show a high flexibility in decision making and minimize the need for human effort and intervention.
Small Business Information at Submission:
12 Gill Street Suite 1400 Woburn, MA -
Number of Employees: