Towards Providing Explanations for AI Planner Decisions
This addresses the need for trust and transparency in AI systems, particularly in planning domains, but is incremental as it builds on existing explanation techniques.
The paper tackles the problem of making AI planner decisions understandable to users by developing a methodology that generates explanations through user-suggested alternative actions and plan comparisons, implemented in the XAI-Plan framework.
In order to engender trust in AI, humans must understand what an AI system is trying to achieve, and why. To overcome this problem, the underlying AI process must produce justifications and explanations that are both transparent and comprehensible to the user. AI Planning is well placed to be able to address this challenge. In this paper we present a methodology to provide initial explanations for the decisions made by the planner. Explanations are created by allowing the user to suggest alternative actions in plans and then compare the resulting plans with the one found by the planner. The methodology is implemented in the new XAI-Plan framework.