Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Automated Process Planning Based on a Semantic Capability Model and SMT

Aljosha Köcher, Luis Miguel Vieira da Silva, Alexander Fay

TL;DR

The paper tackles the challenge of automating process planning for heterogeneous manufacturing and autonomous robot systems by unifying machine-interpretable capability models with SMT-based planning. It introduces the CaSk ontology to describe capabilities, constraints, and synonyms, and provides an automated method to transform this semantic model into an SMT encoding solved by an SMT solver to yield viable capability sequences. Key contributions include an OpenMath-driven capability constraint framework, mutex handling, and a solver-based pipeline (CaSkade Planner) that extracts plans with the smallest number of happenings. This approach reduces manual encoding efforts, supports explanations for planning decisions, and enables scalable planning across diverse capabilities and vendors, with future work on execution and human-centric explanations.

Abstract

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.

Automated Process Planning Based on a Semantic Capability Model and SMT

TL;DR

The paper tackles the challenge of automating process planning for heterogeneous manufacturing and autonomous robot systems by unifying machine-interpretable capability models with SMT-based planning. It introduces the CaSk ontology to describe capabilities, constraints, and synonyms, and provides an automated method to transform this semantic model into an SMT encoding solved by an SMT solver to yield viable capability sequences. Key contributions include an OpenMath-driven capability constraint framework, mutex handling, and a solver-based pipeline (CaSkade Planner) that extracts plans with the smallest number of happenings. This approach reduces manual encoding efforts, supports explanations for planning decisions, and enables scalable planning across diverse capabilities and vendors, with future work on execution and human-centric explanations.

Abstract

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.
Paper Structure (17 sections, 24 equations, 3 figures, 1 algorithm)

This paper contains 17 sections, 24 equations, 3 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Capability Modeling
  4. Capability Planning Approach
  5. SMT Encoding
  6. Synonymous Properties and Synonymous Capabilities
  7. Proposition Continuation across Layers
  8. Real Variable Continuation across Layers
  9. Capability Preconditions and Effects
  10. Capability Constraints
  11. Capability Mutexes
  12. Initial and Goal State Description
  13. Proposition Continuation across Happenings
  14. Real Variable Continuation across Happenings
  15. Implementation
  16. ...and 2 more sections

Figures (3)

  • Figure 1: Overview of the proposed planning approach. Required and provided capabilities in an ontology are transformed into an SMT planning problem. If the problem is satisfiable, the resulting model is a valid process plan.
  • Figure 2: Simplified representation of a transport capability and its properties modeled with the CaSk ontology.
  • Figure 3: Encoding a capability plan as a sequence of happenings. Adapted from CMZ_PlanningforHybridSystems_2020