When Can Planning Benefit from Common-Sense Knowledge?

To improve the quality of plans and ensure their alignment with the real-world environment, existing works have explored the integration of external knowledge with AI planning. <br/>Most of these approaches are motivated with examples from real-world scenarios and evaluated on a subset of domains, with a focus on household environments. The collective choice of certain tasks for evaluation suggests that some tasks can further benefit from external knowledge than others. However, the choice of environment in integration methods is rarely rationalised or justified, and the generalisability of approaches across domains is not often discussed. <br/>In this paper, we examine the characteristics that influence when planning tasks benefit from integrating external knowledge, such as semantic and common-sense knowledge, into decision-making within AI planning. We provide a systematic classification of these characteristics according to their scope (spanning the task, domain, problem, and plan) and relate them to the specific stages of the planning process in which they play a role -- the task description, the search process, post-planning analysis, and plan execution.