Verification of Low-Dimensional Neural Network Control
(2023) 62nd IEEE Conference on Decision and Control, CDC 2023 p.4566-4571- Abstract
We verify safety of a nonlinear continuous-time system controlled by a neural network controller. The system is decomposed into low-dimensional subsystems connected in a feedback loop. Our application is a rocket landing, and open-loop properties of the two-dimensional altitude subsystem are verified using worst-case simulations. Closed-loop safety properties (crash-avoidance) of the full system are obtained from composition of contracts for open-loop safety properties of subsystems in a fashion analogous to the small-gain theorem.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/029ebcfc-55ac-404d-bfdc-b9c63885de23
- author
- Grönqvist, Johan LU and Rantzer, Anders LU
- organization
- publishing date
- 2023
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Proceedings of the IEEE Conference on Decision and Control
- pages
- 6 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 62nd IEEE Conference on Decision and Control, CDC 2023
- conference location
- Singapore, Singapore
- conference dates
- 2023-12-13 - 2023-12-15
- external identifiers
-
- scopus:85184832418
- ISBN
- 9798350301243
- DOI
- 10.1109/CDC49753.2023.10384149
- project
- Stability and Robustness with Neural Networks in Control
- Artificial intelligence techniques for guidance, navigation, and control
- language
- English
- LU publication?
- yes
- id
- 029ebcfc-55ac-404d-bfdc-b9c63885de23
- date added to LUP
- 2024-02-27 10:36:18
- date last changed
- 2024-02-29 09:03:05
@inproceedings{029ebcfc-55ac-404d-bfdc-b9c63885de23, abstract = {{<p>We verify safety of a nonlinear continuous-time system controlled by a neural network controller. The system is decomposed into low-dimensional subsystems connected in a feedback loop. Our application is a rocket landing, and open-loop properties of the two-dimensional altitude subsystem are verified using worst-case simulations. Closed-loop safety properties (crash-avoidance) of the full system are obtained from composition of contracts for open-loop safety properties of subsystems in a fashion analogous to the small-gain theorem.</p>}}, author = {{Grönqvist, Johan and Rantzer, Anders}}, booktitle = {{Proceedings of the IEEE Conference on Decision and Control}}, isbn = {{9798350301243}}, language = {{eng}}, pages = {{4566--4571}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{Verification of Low-Dimensional Neural Network Control}}, url = {{http://dx.doi.org/10.1109/CDC49753.2023.10384149}}, doi = {{10.1109/CDC49753.2023.10384149}}, year = {{2023}}, }