The Community for Technology Leaders
Green Image
<p>This article illustrates the complexities of real-world planning and how we can create AI planning systems to address them. Our system, IMACS (Interactive Manufacturability Analysis and Critiquing System), an automated designer's aid, evaluates the manufacturability of machined parts and suggests design modifications to improve manufacturability. </p> <p>Over the course of our efforts on IMACS, the manufacturing domain has continually challenged us to come up with working solutions that would scale to realistic problems. This article compares and contrasts IMACS's planning techniques with those used in classical AI planning systems and describes (1) how some of IMACS's planning techniques may be useful for AI planning in general, and (2) what challenges need to be overcome by AI planners so that they can be successfully used in manufacturing process planning. </p> <p>Similarities between AI and IMACS planning techniques indicate the large unrealized potential of AI planning techniques in solving real-world manufacturing problems. On the other hand, differences seem to indicate the need for domain-specific planning techniques. In particular, our experience suggests that process planning for complex machined parts cannot be easily accomplished by populating a general purpose planner with domain-specific knowledge. Instead, we needed to integrate the domain-specific knowledge into the planning algorithms themselves.</p>
William C. Regli, Dana S. Nau, Satyandra K. Gupta, "IMACS: A Case Study in Real-World Planning", IEEE Intelligent Systems, vol. 13, no. , pp. 49-60, May/June 1998, doi:10.1109/5254.683210
89 ms
(Ver 3.3 (11022016))