Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
422621 | Electronic Notes in Theoretical Computer Science | 2007 | 13 Pages |
Abstract
We address the problem of verifying planning domains as used in model-based planning, for example in space missions. We propose a methodology for testing flight rules of planning domains which is self-contained, in the sense that flight rules are verified using a planner and no external tools are required. We review and analyse coverage conditions for requirements-based testing, and we reason in detail on "Unique First Cause" (UFC) coverage for test suites. We characterise flight rules using patterns, encoded using LTL, and we provide UFC coverage for them. We then present a translation of LTL formulae into planning goals, and illustrate our approach on a case study.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Computational Theory and Mathematics
Authors
Franco Raimondi, Charles Pecheur, Guillaume Brat,