When and Where Will AI Meet Robotics?

Because perception-action systems are necessarily constrained by the physics of time and space, robotocists often assume they are best described using differential equations, a language that is specialized for describing the evolution of variables that represent physical quantities. However, when it comes to decision making, where the representations involved refer to goals, strategies, and preferences, AI offers a diverse range of formalisms to the modeler. However, the relationship between these two levels of representation--signal and symbol--are not well understood. If we are to achieve success in modeling intelligent physical agents, robotics and AI must reach a new consensus on how to integrate perception-action systems with systems designed for abstract reasoning. All our major AI laboratories had research programs in robotics in the late 1960s and early 1970s.