Resilient Control of Cyber-Physical Systems with Distributed Learning - January 2023
PI(s) and Co-PI(s): Sayan Mitra and Geir Dullerud and Sanjay Shakkotai (U. Texas at Austin)
Researchers: Dawei Sun and Negin Musavi
HARD PROBLEM(S) ADDRESSED
This refers to Hard Problems, released November 2012.
Resiliency: Effective verification of safety and security properties of autonomous and cyber-physical systems
Metrics: How much data is necessary to achieve a certain level of confidence regarding a safety/security claim
PUBLICATIONS
Papers written as a result of your research from the current quarter only.
Learning Certifiably Robust Controllers Using Fragile Perception, Dawei Sun, Negin Musavi, Geir Dullerud, Sanjay Shakkottai, Sayan Mitra, NeurIPS 2022 5th Robot Learning Workshop: Trustworthy Robotics, 2022
Verifying Controllers with Vision-based PerceptionUsing Safe Approximate Abstractions. Chiao Hsieh, Keyur Joshi, Dawei Sun, Yangge Li, Sasa Misailovic, and Sayan Mitra. Proceedings of EMSoft, 2022 and IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.
Using Probabilistic Programming in Anonymous Communication Networks, Hussein Darir, Geir Dullerud, Nikita Borisov, to appear at Network and Distributed System Security Symposium (NDSS), 2023.
Revisiting PGD Attack for Stability Analysis of Large-Scale Nonlinear Systems and Perception-Based Control, by Aaron Havens, Darioush Keivan, Peter Seiler, Geir E. Dullerud, Bin Hu, Proceedings of IEEE Control and Decision Conference (CDC), 2022.
KEY HIGHLIGHTS
Each effort should submit one or two specific highlights. Each item should include a paragraph or two along with a citation if available. Write as if for the general reader of IEEE S&P.
The purpose of the highlights is to give our immediate sponsors a body of evidence that the funding they are providing (in the framework of the SoS lablet model) is delivering results that "more than justify" the investment they are making.
We are developing safety and security analysis approaches for real-life of autonomous and cyber-physical systems using statistical and machine learning techniques. Our approaches rely on distributed and sample-efficient optimization techniques that have been developed in the context of the Multi-armed bandit problem. We have shown how these optimization algorithms can be used effectively for statistical model checking of markov decision processes and autonomous systems that use complex machine learning models. We have built a suite of benchmarks related to online safety analysis of autonomous and semi-autonomous vehicles. Our initial results are very promising as the data usage and the running time of our algorithms can be several orders of magnitude better than existing model checking approaches such as Storm and Prism. Two PhD students are dedicating their research time to the project and the prototype tool has been made available online.
COMMUNITY ENGAGEMENTS
We developed and organized the GRAIC Autonomous Racing Competition which was co-located with CPSWeek 2021. The live event had more than 80 registered members and 30+ attendees. The software framework has been made available to the community for research.
We have been presenting monthly project updates to our project's champions Stephanie Polczynski and Jason Hogue.
- Mitra created and successfully organized a Code a Car summer camp for high school students. Link Media
- Paper presentation on "Revisiting PGD Attack for Stability Analysis of Large-Scale Nonlinear Systems and Perception-Based Control" at IEEE Conference on Decision and Control (CDC); student presentation (Dullerud)
EDUCATIONAL ADVANCES
We have created content for a Summer School for highschool students, supported by the SoS program and Illinois WYSE (Worldwide Youth in Science and Engineering). All the educational material, code, and presentations have been made publicly available.