Supported by a nearly $6 million grant from the National Science Foundation (NSF) through their Cyber-Physical Systems programresearchers from UC Santa Cruz will lead a five-year, multi-institutional project to explore a new vision of cyber-physical systems (CPS) engineering.
CPS are very complex systems that involve algorithms, networks and physical components. Examples of CPS include smart grids, implantable medical devices, and transportation such as self-driving cars, the latter being the focus of this project.
This project aims to rethink the modeling, analysis and design of a new generation of intelligent transport systems so that the algorithms running them are adapted to the computational constraints and that the systems can operate efficiently and reliably. Researchers will collaborate with industry and academic partners to advance CPS in both research and education through robust training programs for high school and undergraduate students, with a particular focus on creating research opportunities for students from underrepresented backgrounds.
“This research will have a direct impact on the rapidly growing, multi-billion dollar autonomous systems market,” said project principal investigator Ricardo Sanfelice, professor of electrical and computer engineering and director of UCSC Baskin School of Engineering. . Cyber-Physical Systems Research Center (CPSRC). “We expect our results to have a broad impact in improving the safety and reliability of transportation systems, such as aviation systems and autonomous vehicles, in particular by reducing the carbon footprint of these systems, and in forming the workforce of the future in the key science of CPS.
Design for adaptability
CPSs face major engineering challenges due to the computational limitations of traditional processors as well as the scale and diversity of physical components, which may be man-made structures and/or the natural landscape. In traditional systems, computers are only updated with information from physical systems periodically, which means that the system at certain times runs on old information that could compromise its security and performance.
To address these issues, this project will focus on the coded design of CPS algorithms and hardware so that physics, hardware, and software are unified. Researchers will use the results of verifying, implementing, and testing their new systems to redesign their algorithms, a process that will also take place in an automated fashion while the systems are running. This is different from today’s state-of-the-art systems, where algorithms and hardware are usually not co-designed, resulting in a time-consuming and expensive verification process.
This new model of feedback to CPS will allow researchers to create systems that are much more adaptive than the current state of the art. The new control algorithms will adapt to the specifications and the environment in which they are deployed, by learning and adapting to key factors such as power consumption and execution time. New hardware will be designed to best provide feedback that can be used by these algorithms.
“To meet the stringent requirements that intelligent transportation applications demand, such as performance and security, the algorithms implemented in the control stack require advanced algorithms that leverage data to learn the environment, physics, and traffic. cyber,” Sanfelice said. “We believe this is the best way to allow CPS to make near-optimal decisions.”
These new tools will reduce the cost and overall development time of CPS. The more accurate models will eliminate hardware overprovision and the new software will be open source to enable wider reuse.
Cooperation and education
This project will involve extensive collaboration between universities and industry. The group will leverage its expertise in areas such as hardware architecture, real-time systems and hybrid control systems.
Including Sanfelice, there are seven principal investigators on the project: UCSC Assistant Professor of Applied Mathematics Abhishek Halder; Assistant Professor of Computer Science and Engineering at UCSC, Heiner Litz; Murat Arcak, professor of electrical engineering and computer science at UC Berkeley; Linh Thi Xuan Phan, associate professor of computer and information science at the University of Pennsylvania; Jonathan Sprinkle, professor of computer science at Vanderbilt University; and Majid Zamani, assistant professor of computer science at the University of Colorado at Boulder. They will also collaborate with researchers from the Norwegian University of Science and Technology and the Italian school IMT for advanced studies in Lucca.
Researchers will work with industry partners such as Toyota Motor Engineering & Manufacturing, Toyota Research Institute, Joby Aviation and Summer Robotics to gather strategic advice on existing hardware and to test and validate the autonomous transport systems created by this project. Through this focused collaboration, they aim to move their work from research to practice.
In recruiting scholars to work on this project, PIs will focus on engaging and mentoring women and historically marginalized communities, spanning all levels of education, from K-12 to post-docs. . Activities will include a series of CPS industry seminars, competitions to create tools and datasets, and the integration of research advances into the engineering curriculum of several of the participating universities.
In addition to addressing the effectiveness of CPS, this project presents a vision for reducing the growing global carbon footprint by promoting increased use of autonomous systems in transportation.
“Transcending the computational challenges of traditional methods, Sanfelice and his team are innovating the intelligent transportation systems of the future,” said Alexander Wolf, Dean of the Baskin School of Engineering. “This grant places our scholars at the forefront of a field of critical importance in our rapidly changing world, while centering the contributions of our students.”
This project is funded by the NSF Cyber-Physical Systems Program, in the Border category. The proposal was prepared with the assistance of UCSC’s Cyber-Physical Systems Research Center and UCSC’s Office of Research (OR), and by seed fund provided by the OR and the Baskin School of Engineering for intelligent transportation research.
“Frontier projects at NSF must address clearly identified critical CPS challenges that cannot be achieved by a set of smaller projects,” Sanfelice said. “In 2017, we founded the UCSC CPSRC with the intention of providing a platform to lead a winning frontier. I am delighted that the NSF has selected our proposal for an award and I feel privileged to lead this innovative project. »