Learning Temporal Logic Predicates from Data with Statistical Guarantees
This work addresses the need for reliable, interpretable rules in control and robotics, offering a solution with statistical guarantees, though it appears incremental by building on existing optimization and prediction techniques.
The paper tackles the problem of learning temporal logic predicates from data without correctness guarantees by introducing a method that provides finite-sample correctness assurances, achieving performance demonstrated on a simulated trajectory dataset.
Temporal logic rules are often used in control and robotics to provide structured, human-interpretable descriptions of trajectory data. These rules have numerous applications including safety validation using formal methods, constraining motion planning among autonomous agents, and classifying data. However, existing methods for learning temporal logic predicates from data do not provide assurances about the correctness of the resulting predicate. We present a novel method to learn temporal logic predicates from data with finite-sample correctness guarantees. Our approach leverages expression optimization and conformal prediction to learn predicates that correctly describe future trajectories under mild statistical assumptions. We provide experimental results showing the performance of our approach on a simulated trajectory dataset and perform ablation studies to understand how each component of our algorithm contributes to its performance.