The Community for Technology Leaders
Green Image
<p>Classical artificial intelligence systems presuppose that all knowledge is stored in a central database of logical assertions or other symbolic representations and that reasoning consists largely of searching and sequentially updating that database. Although this model has been successful for disembodied reasoning systems, it is problematic for robots. Robots are distributed systems; multiple sensory, reasoning, and motor control processes run in parallel, often on separate processors that are only loosely coupled with one another. Each of these processes necessarily maintains its own separate, limited representation of the world and task; requiring them to constantly synchronize with the central knowledge base is probably unrealistic. This article discusses an alternative class of architectures-tagged behavior-based systems-that support a large subset of the capabilities of classical AI architectures, including limited quantified inference, forward and backward chaining, simple natural language question answering and command following, reification, and computational reflection, while allowing object representations to remain distributed across multiple sensory and representational modalities. Although limited, they also support extremely fast, parallel inference.</p>

I. Horswill, "Tagged Behavior-Based Systems: Integrating Cognition with Embodied Activity," in IEEE Intelligent Systems, vol. 16, no. , pp. 30-37, 2001.
81 ms
(Ver 3.3 (11022016))