Automated Process Planning for CNC Machining
This article describes our application of AI planning to the problem of automated process planning for machining parts, given raw stock and a CAD file describing the desired part geometry. We have found that existing planners from the AI community were falling short on several requirements, most importantly regarding the expressivity of state and action representations, and the ability to exploit domain-specific knowledge to prune the search space. In this article we describe the requirements we had in this application and what kind of results from the planning community helped us most. Overall, in this project as well as others, we found that even significant results from domain-independent planning may not be relevant in practice.