Pointwise-in-Time Explanation for Linear Temporal Logic Rules

TL;DR

This paper introduces Rule Status Assessment (RSA), a framework for analyzing the behavior of autonomous agents at specific time points using Linear Temporal Logic rules, aiding in post-hoc diagnostics.

Contribution

The paper presents a novel pointwise-in-time explanation framework for LTL rules, enabling detailed trajectory analysis and rule status classification at individual time steps.

Findings

RSA effectively classifies rule status at each time step

Enables systematic tracking of agent behavior

Useful for post-hoc diagnostics

Abstract

The new field of Explainable Planning (XAIP) has produced a variety of approaches to explain and describe the behavior of autonomous agents to human observers. Many summarize agent behavior in terms of the constraints, or ''rules,'' which the agent adheres to during its trajectories. In this work, we narrow the focus from summary to specific moments in individual trajectories, offering a ''pointwise-in-time'' view. Our novel framework, which we define on Linear Temporal Logic (LTL) rules, assigns an intuitive status to any rule in order to describe the trajectory progress at individual time steps; here, a rule is classified as active, satisfied, inactive, or violated. Given a trajectory, a user may query for status of specific LTL rules at individual trajectory time steps. In this paper, we present this novel framework, named Rule Status Assessment (RSA), and provide an example of its implementation. We find that pointwise-in-time status assessment is useful as a post-hoc diagnostic, enabling a user to systematically track the agent's behavior with respect to a set of rules.