| 684 |
@InProceedings{Zhang:FM24,
AUTHOR = {Zhang, Changjian and Kapoor, Parv and Meira Goes, Romulo and Garlan, David and Kang, Eunsuk and Ganlath, Akila and Mishra, Shatadal and Ammar, Nejib},
TITLE = {Tolerance of Reinforcement Learning Controllers against Deviations in Cyber Physical Systems},
YEAR = {2024},
MONTH = {11-13 September},
BOOKTITLE = {26th International Symposium on Formal Methods (FM24)},
PDF = {http://acme.able.cs.cmu.edu/pubs/uploads/pdf/FM 2024.pdf},
ABSTRACT = {Cyber-physical systems (CPS) with reinforcement learning (RL)-based controllers are increasingly being deployed in complex phys- ical environments such as autonomous vehicles, the Internet-of-Things (IoT), and smart cities. An important property of a CPS is tolerance; i.e., its ability to function safely under possible disturbances and un- certainties in the actual operation. In this paper, we introduce a new, expressive notion of tolerance that describes how well a controller is ca- pable of satisfying a desired system requirement, specified using Signal Temporal Logic (STL), under possible deviations in the system. Based on this definition, we propose a novel analysis problem, called the tol- erance falsification problem, which involves finding small deviations that result in a violation of the given requirement. We present a novel, two- layer simulation-based analysis framework and a novel search heuristic for finding small tolerance violations. To evaluate our approach, we con- struct a set of benchmark problems where system parameters can be configured to represent different types of uncertainties and disturbances in the system. Our evaluation shows that our falsification approach and heuristic can effectively find small tolerance violations.
},
NOTE = {To appear},
KEYWORDS = {Cyberphysical Systems, Formal Methods, Machine Learning}
}
|
|
