Explainable Planning

TL;DR

This paper discusses how to improve human-AI interaction in planning systems by leveraging model-based representations to enhance explainability and build trust, despite the complexity of underlying algorithms.

Contribution

It explores the potential of using model-based representations in AI planning to make decision processes more transparent and understandable to users.

Findings

Model-based representations can facilitate better communication with users.

Explainability in planning enhances trust and cooperation.

Challenges remain in bridging the gap between algorithms and human understanding.

Abstract

As AI is increasingly being adopted into application solutions, the challenge of supporting interaction with humans is becoming more apparent. Partly this is to support integrated working styles, in which humans and intelligent systems cooperate in problem-solving, but also it is a necessary step in the process of building trust as humans migrate greater responsibility to such systems. The challenge is to find effective ways to communicate the foundations of AI-driven behaviour, when the algorithms that drive it are far from transparent to humans. In this paper we consider the opportunities that arise in AI planning, exploiting the model-based representations that form a familiar and common basis for communication with users, while acknowledging the gap between planning algorithms and human problem-solving.