Projects per year
Abstract
We present a technique for learning explainable timed automata from passive observations of a black-box function, such as an artificial intelligence system. Our method accepts a single, long, timed word with mixed input and output actions and learns a Mealy machine with one timer. The primary advantage of our approach is that it constructs a symbolic observation tree from a concrete timed word. This symbolic tree is then transformed into a human comprehensible automaton. We provide a prototype implementation and evaluate it by learning the controllers of two systems: a brick-sorter conveyor belt trained with reinforcement learning and a real-world derived smart traffic light controller. We compare different model generators using our symbolic observation tree as their input and achieve the best results using k-tails. In our experiments, we learn smaller and simpler automata than existing passive timed learners while maintaining accuracy.
Original language | English |
---|---|
Title of host publication | NASA Formal Methods : 15th International Symposium, NFM 2023, Houston, TX, USA, May 16–18, 2023, Proceedings |
Editors | Kristin Yvonne Rozier, Swarat Chaudhuri |
Number of pages | 18 |
Publisher | Springer Science+Business Media |
Publication date | 16 May 2023 |
Pages | 104-121 |
ISBN (Print) | 978-3-031-33169-5 |
ISBN (Electronic) | 978-3-031-33170-1 |
DOIs | |
Publication status | Published - 16 May 2023 |
Event | 15th International Symposium on NASA Formal Methods, NFM 2023 - Houston, United States Duration: 16 May 2023 → 18 May 2023 |
Conference
Conference | 15th International Symposium on NASA Formal Methods, NFM 2023 |
---|---|
Country/Territory | United States |
City | Houston |
Period | 16/05/2023 → 18/05/2023 |
Series | Lecture Notes in Computer Science (LNCS) |
---|---|
Volume | 13903 LNCS |
ISSN | 0302-9743 |
Bibliographical note
Publisher Copyright:© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
Fingerprint
Dive into the research topics of 'Learning Symbolic Timed Models from Concrete Timed Data'. Together they form a unique fingerprint.Projects
- 1 Active
-
S4OS: SCALABLE ANALYSIS OF SAFE, SMALL AND SECURE STRATEGIES FOR CYBER-PHYSICAL SYSTEMS
Larsen, K. G. (PI)
01/01/2021 → 31/12/2027
Project: Research