Visualizations for an Explainable Planning Agent

TL;DR

This paper explores visualization techniques for an explainable AI planning agent to enhance transparency, trust, and human understanding by externalizing decision processes and visualizing plans within a smart assistant context.

Contribution

It introduces visualization methods for an XAIP agent, including internal decision process visualization and plan explanation, to improve transparency and human-agent collaboration.

Findings

Effective visualization of internal decision processes.

Plan visualization as a plan explanation problem.

Demonstration in a smart meeting assistant context.

Abstract

In this paper, we report on the visualization capabilities of an Explainable AI Planning (XAIP) agent that can support human in the loop decision making. Imposing transparency and explainability requirements on such agents is especially important in order to establish trust and common ground with the end-to-end automated planning system. Visualizing the agent's internal decision-making processes is a crucial step towards achieving this. This may include externalizing the "brain" of the agent -- starting from its sensory inputs, to progressively higher order decisions made by it in order to drive its planning components. We also show how the planner can bootstrap on the latest techniques in explainable planning to cast plan visualization as a plan explanation problem, and thus provide concise model-based visualization of its plans. We demonstrate these functionalities in the context of the automated planning components of a smart assistant in an instrumented meeting space.