Automated Process Planning Based on a Semantic Capability Model and SMT
This addresses the challenge of reducing the high effort in creating planning problem descriptions for AI planning in heterogeneous manufacturing and robotic systems, though it appears incremental as it combines existing models and methods.
The paper tackles the problem of automated process planning for manufacturing and autonomous robots by automatically generating AI planning problems from a semantic capability model, using Satisfiability Modulo Theories (SMT) to find valid capability sequences with required parameter values.
In research of manufacturing systems and autonomous robots, the term capability is used for a machine-interpretable specification of a system function. Approaches in this research area develop information models that capture all information relevant to interpret the requirements, effects and behavior of functions. These approaches are intended to overcome the heterogeneity resulting from the various types of processes and from the large number of different vendors. However, these models and associated methods do not offer solutions for automated process planning, i.e. finding a sequence of individual capabilities required to manufacture a certain product or to accomplish a mission using autonomous robots. Instead, this is a typical task for AI planning approaches, which unfortunately require a high effort to create the respective planning problem descriptions. In this paper, we present an approach that combines these two topics: Starting from a semantic capability model, an AI planning problem is automatically generated. The planning problem is encoded using Satisfiability Modulo Theories and uses an existing solver to find valid capability sequences including required parameter values. The approach also offers possibilities to integrate existing human expertise and to provide explanations for human operators in order to help understand planning decisions.