Visible to the public Resilient Control of Cyber-Physical Systems with Distributed Learning - January 2021Conflict Detection Enabled

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.

Working paper:

Randomized reachability: A statistical learning perspective, Dawei Sun and Sayan Mitra, in preparation, October 2020.

Verification and Parameter Synthesis for Stochastic Systems using Optimistic Optimization, Negin Musavi, Dawei Sun, Sayan Mitra, Sanjay Shakkottai, and Geir Dullerud, submitted for review, September 2020.

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 have formulated a new direction of scientific enquiry into safety and security analysis of autonomous and cyber-physical systems. The approach relies 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 hybrid systems. 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

None this quarter.

EDUCATIONAL ADVANCES

The third edition of PI Mitra's new course Principles of Safe Autonomy at University of Illinois came to a successful conclusion this semester with a larger class size (38 students) despite the setbacks from the COVID19 outbreak. The course takes a deep dive into the seminal topics in object recognition, localization, decision making, path planning, and safety verification. Graduate and undergraduate students from ECE and CS are completing the course. The course team has designed 6 New programming assignments involving topics such as lane detection, road-sign recognition, localization with particle filters, decision making with reinforcement learning, path planning with rapidly expanding random trees, and safety verification using simulation-driven proofs. With support from the Illinois Center for Autonomy, we have setup a laboratory with 7 workstations with GPUs for performing simulation-based experiments. The students are using ROS, Gazebo, for testing their programming assignments. Find out more about the safe autonomy course and the student projects at https://publish.illinois.edu/safe-autonomy/