Using 4D/RCS to Address AI Knowledge Integration

In this article, we show how 4D/RCS incorporates and integrates multiple types of disparate knowledge representation techniques into a common, unifying architecture. The 4D/RCS architecture is based on the supposition that different knowledge representation techniques offer different advantages, and 4D/RCS is designed in such a way as to combine the strengths of all of these techniques into a common unifying architecture in order to exploit the advantages of each. In the context of applying the architecture to the control of autonomous vehicles, we describe the procedural and declarative types of knowledge that have been developed and applied and the value that each brings to achieving the ultimate goal of autonomous navigation. We also look at symbolic versus iconic knowledge representation and show how 4D/RCS accommodates both of these types of representations and uses the strengths of each to strive towards achieving human-level intelligence in autonomous systems. Neuroanatomy has described the structure and function of the basic computational element of the brain--the neuron--and produced extensive maps of the computational modules and interconnecting data flow pathways making up the anatomy of the brain. Behavioral psychology provides information about stimulus-response behavior and instrumental conditioning. Cognitive psychology is exploring how the brain represents knowledge; how it perceives objects, events, situations, and relationships; how it analyzes the past and plans for the future; and how it selects and controls behavior that satisfies desires and achieves goals Over the last five decades, the invention of the electronic computer has brought rapid advances in computational power, making it feasible to launch serious attempts at building intelligent systems. Artificial intelligence and robotics have produced significant results in planning, problem solving, rule-based reasoning, image analysis, and speech understanding. Autonomous vehicle research has produced advances in real-time sensory processing, world modeling, navigation, path planning, and obstacle avoidance. Research in industrial automation and process control has produced hierarchical control systems, distributed databases, and models for representing processes and products. Modern control theory has developed precise understanding of stability, adaptability, and controllability under various conditions of uncertainty and noise. Progress is rapid in each of the above fields, and there exists an enormous and rapidly growing body of literature in all of these areas.