��������Ƶ

Majid Zamani, an assistant professor in the Department of Computer Science at ��������Ƶ Boulder, wants to use real-life data, rather than mathematical models, to study and control autonomous systems with both software and physical components, bridging the gap between academia and industry and ensuring safety for all users. 

He has just been presented with a prestigious CAREER award from the National Science Foundation (NSF) for his proposal entitled “A Data-Driven Approach for Verification and Control of Cyber-Physical Systems.” 

CAREER awards provide funding over five years to support the research and educational activities of early career faculty members who have the potential to become leaders in their field. Six faculty members within the College of Engineering and Applied Science received CAREER Awards from the National Science Foundation in 2022.

Zamani said his CAREER award unifies three different fields: formal methods in computer science, optimization in operation research and control theory. The research brings insight from each to understand how to verify the safety of autonomous systems purely through data analysis.

"If I have enough data collected, I can work directly with the data to systematically generate the software code in charge of controlling a system," Zamani said.

Currently, rigid mathematical models that describe the behaviors of a system are the main ingredients of most academic research in ensuring safety in cyber-physical systems–- systems where software interacts tightly with physical systems—such as self-driving cars, pacemakers and power networks. 

To have these mathematical models, someone must rigorously model every part of the system. When you have thousands of different components in a machine and possibly hundreds of computer program interactions, the layers of complexity stack exponentially and it is very hard to build the models accurately. Even if the models are computed, Zamani said, they are too complex to be dealt with.

With his CAREER award, Zamani will be working to entirely bypass the need for such a model of the system. This means that systems that are too complex for us to know their internal workings, known as "black boxes," can still be formally guaranteed as safe. 

Safety is a constant concern when computer programs can impact the physical world. A single catastrophic safety failure in a cyber-physical system could cause trust in the autonomous system to be lost and lead to loss of life or infrastructure. 

Despite the need for safety, many self-driving car industries do not have the time or interest to mathematically model their systems, Zamani said.

"You approach a company and they say, 'no, we don't have a model. We have the actual car or its simulator, but we don't know the precise mathematical model for it,'" Zamani said.  

Zamani's award centers around the recent advances in inexpensive sensor technologies that can gather large amounts of data from a system's behaviors as it is run without autonomy, like when a person drives a car destined for autopilot.

Zamani said that, while they may not have models, industry partners do have large amounts of data available, making it possible to rigorously analyze realistic systems and build a "controller," the software code that autonomously controls the system, such as an auto-pilot in a self-driving car.

The framework that Zamani is crafting is also not system-dependent. Rather than needing a separate way of understanding self-driving cars, drones or medical devices, his work is abstracting the logic needed to create algorithms for controlling all these types of systems. 

In addition, safety can mean different things to different people. Zamani's work allows companies to decide how conservative their safety confidence levels should be. The more data collected, the higher the confidence levels Zamani's framework is able to guarantee.

And, as well as determining what level of safety is necessary, the research supports a variety of "properties of interest." For example, if a car is safe only if it doesn't crash, it might speed past the speed-limit regularly, but by adding a property that requires the car to also follow the speed-limit, you craft a controller that accommodates both properties of interest. 

This system-agnostic, flexible and data-driven framework provides an alternative to the severe computational complexity of rigid mathematical models and strong assumptions made about them that have caused a divide between academia and industry.  

"The main goal of my CAREER award is closing the gap between what happens in reality and the theoretical, rigorous analyses which happen in academia. People in industry are not using the techniques we've been developing in academia. There is a gap between their assumptions and ours, and this work is trying to help close it." Zamani said.