What is it about?
We propose a contrastive explanation paradigm for plans in hybrid systems, as done for their discrete counterparts, by highlighting the contrasts of the original plan with an alternate one. We aim to explain a plan by a contrastive explanation framework that provides answers to contrastive questions posed by a plan user. Through such answers, a user gains insights as to why a particular plan can be trusted and deployed, or on the other hand, why there may be a need for re-planing. Our framework works by generating alternate plans to the planning problem by constructing a hypothetical planning problem and this construction is such that any valid plan for the hypothetical problem will meet the user expectation phrased in the contrastive question.
Featured Image
Why is it important?
In artificial intelligence planning, having an explanation of a plan given by a planner is often desirable. The ability to explain various aspects of a synthesized plan to an end-user not only brings in trust on the planner but also reveals insights into the planning domain and the planning process.
Perspectives
With the advent of automated planning being applied in safety-critical systems, the need for plan explanation, to a human expert responsible for implementing the plan, has become ever more important. Before accepting and executing the plan, the human expert ought to be convinced about the safety and rationality of the plan. Recently, with the advent of Cyber-Physical Systems (CPS) and Internet-of-Things, there has been a renewed research interest in planning for hybrid systems that exhibit an interplay of discrete and continuous dynamics. Planning in hybrid systems poses particular challenges to classical AI planners, due to the interplay of continuous and discrete dynamics. These reasons have inspired and worked as motivation for this work.
MIR MD SAJID SARWAR
Indian Association for the Cultivation of Science
Read the Original
This page is a summary of: A Contrastive Plan Explanation Framework for Hybrid System Models, ACM Transactions on Embedded Computing Systems, January 2023, ACM (Association for Computing Machinery),
DOI: 10.1145/3561532.
You can read the full text:
Contributors
The following have contributed to this page
