Backpropagation through signal temporal logic specifications: Infusing logical structure into gradient-based methods
The International Journal of Robotics Research · 2023-05 · 42 (6) · 356-370
DOI: 10.1177/02783649221082115 ↗Kurz gefasst
Fachartikel in der Zeitschrift The International Journal of Robotics Research, online erschienen am 28.05.2022. Verfasst von Karen Leung und 2 weiteren Autor:innen. Die Arbeit wurde bisher 56-mal zitiert (Crossref) und nennt 27 Literaturangaben. Gefördert von: Office of Naval Research, NASA University Leadership Initiative, Toyota Research Institute.
Abstract (Originalsprache)
This paper presents a technique, named STLCG, to compute the quantitative semantics of Signal Temporal Logic (STL) formulas using computation graphs. STLCG provides a platform which enables the incorporation of logical specifications into robotics problems that benefit from gradient-based solutions. Specifically, STL is a powerful and expressive formal language that can specify spatial and temporal properties of signals generated by both continuous and hybrid systems. The quantitative semantics of STL provide a robustness metric, that is, how much a signal satisfies or violates an STL specification. In this work, we devise a systematic methodology for translating STL robustness formulas into computation graphs. With this representation, and by leveraging off-the-shelf automatic differentiation tools, we are able to efficiently backpropagate through STL robustness formulas and hence enable a natural and easy-to-use integration of STL specifications with many gradient-based approaches used in robotics. Through a number of examples stemming from various robotics applications, we demonstrate that STLCG is versatile, computationally efficient, and capable of incorporating human-domain knowledge into the problem formulation.
Förderung
- Office of Naval Research
- NASA University Leadership Initiative
- Toyota Research Institute
Zitieren
APA
Leung, K., Aréchiga, N., & Pavone, M. (2023). Backpropagation through signal temporal logic specifications: Infusing logical structure into gradient-based methods. The International Journal of Robotics Research, 42(6), 356-370. https://doi.org/10.1177/02783649221082115
Vancouver
Leung K, Aréchiga N, Pavone M. Backpropagation through signal temporal logic specifications: Infusing logical structure into gradient-based methods. The International Journal of Robotics Research. 2023;42(6):356-370. doi:10.1177/02783649221082115
BibTeX
@article{Leung2023,
author = {Leung, Karen and Aréchiga, Nikos and Pavone, Marco},
title = {Backpropagation through signal temporal logic specifications: Infusing logical structure into gradient-based methods},
journal = {The International Journal of Robotics Research},
year = {2023},
volume = {42},
number = {6},
pages = {356--370},
doi = {10.1177/02783649221082115}
}
EUVIMED