Learning Temporal Logic Predicates from Data with Statistical Guarantees
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915260319924224 |
|---|---|
| author | Soroka, Emi Sinha, Rohan Lall, Sanjay |
| author_facet | Soroka, Emi Sinha, Rohan Lall, Sanjay |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_10449 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning Temporal Logic Predicates from Data with Statistical Guarantees Soroka, Emi Sinha, Rohan Lall, Sanjay Machine Learning Artificial Intelligence Logic in Computer Science 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. |
| title | Learning Temporal Logic Predicates from Data with Statistical Guarantees |
| topic | Machine Learning Artificial Intelligence Logic in Computer Science |
| url | https://arxiv.org/abs/2406.10449 |