Pointwise-in-Time Explanation for Linear Temporal Logic Rules
This provides a diagnostic tool for users to understand specific moments in agent trajectories, but it is incremental as it builds on existing explainable planning methods.
The paper tackles the problem of explaining autonomous agent behavior by introducing a pointwise-in-time framework for Linear Temporal Logic rules, which classifies rules as active, satisfied, inactive, or violated at individual time steps to enable systematic tracking of agent behavior.
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.