Learning Temporal Logic Predicates from Data with Statistical Guarantees

Emi Soroka, Rohan Sinha, Sanjay Lall
Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, PMLR 283:86-98, 2025.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v283-soroka25a, title = {Learning Temporal Logic Predicates from Data with Statistical Guarantees}, author = {Soroka, Emi and Sinha, Rohan and Lall, Sanjay}, booktitle = {Proceedings of the 7th Annual Learning for Dynamics \& Control Conference}, pages = {86--98}, year = {2025}, editor = {Ozay, Necmiye and Balzano, Laura and Panagou, Dimitra and Abate, Alessandro}, volume = {283}, series = {Proceedings of Machine Learning Research}, month = {04--06 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v283/main/assets/soroka25a/soroka25a.pdf}, url = {https://proceedings.mlr.press/v283/soroka25a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Learning Temporal Logic Predicates from Data with Statistical Guarantees %A Emi Soroka %A Rohan Sinha %A Sanjay Lall %B Proceedings of the 7th Annual Learning for Dynamics \& Control Conference %C Proceedings of Machine Learning Research %D 2025 %E Necmiye Ozay %E Laura Balzano %E Dimitra Panagou %E Alessandro Abate %F pmlr-v283-soroka25a %I PMLR %P 86--98 %U https://proceedings.mlr.press/v283/soroka25a.html %V 283 %X 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.
APA
Soroka, E., Sinha, R. & Lall, S.. (2025). Learning Temporal Logic Predicates from Data with Statistical Guarantees. Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, in Proceedings of Machine Learning Research 283:86-98 Available from https://proceedings.mlr.press/v283/soroka25a.html.

Related Material