With the support of a nearly $6 million grant from the National Science Foundation (NSF) through their Cyber-Physical Systems program, researchers at UC Santa Cruz will lead a five year, multi-institutional project to explore a new vision of engineering cyber-physical systems (CPSs).
CPSs are highly complex systems that involve algorithms, networks, and physical components. Examples of CPSs include smart power 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, analyzing, and designing of a new generation of intelligent transportation systems so the algorithms running them are adapted to computational constraints and the systems can run efficiently and reliably. The researchers will collaborate with industry and academic partners to advance CPSs both in research and education through strong 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 direct impact in the rapidly growing, multi-billion dollar autonomous systems market,” said Ricardo Sanfelice, lead principal investigator (PI) on the project, professor of electrical and computer engineering, and director of the UCSC Baskin School of Engineering’s Cyber-Physical Systems Research Center (CPSRC). “We envision that our results will have a broad impact by improving the safety and reliability of transportation systems, such as aviation systems and self-driving vehicles, in particular, by reducing the carbon footprint of these systems, and training the workforce of the future in key CPSs science.”
Designing for adaptability
CPSs face major engineering challenges from the computational limitations of traditional processors as well as the scale and diversity of physical components, which can be human-made structures and/or the natural landscape. In traditional systems, the computers are updated with information from the physical systems only periodically, meaning the system at certain points runs on old information which could jeopardize its safety and performance.
To solve these problems, this project will focus on codesigning the algorithms and hardware of CPSs so that the physics, hardware, and software are unified. The researchers will use results from verification, implementation, and testing of their new systems to redesign their algorithms, a process which will also happen in an automated fashion as the systems are running.
“Unlike the current state-of-the-art, this is one of the first proposals in which algorithms and hardware are jointly co-designed, enabling CPS with higher performance, and better safety, at lower cost,” said Assistant Professor of Computer Science and Engineering Heiner Litz, a co-PI on the project who works in the field of computer architecture and hardware.
This new model of providing feedback to CPSs will allow researchers to create systems that are more adaptive. The new control algorithms will adjust to the specification and the environment they are deployed on and will be tailored to best provide feedback for use by the algorithms.
“We are excited to explore the possibility of leveraging advances in machine learning for the purpose of learning the hardware by an algorithm,” said Abhishek Halder, assistant professor of applied mathematics and a co-PI on the project. “By learning the hardware features such as the available power and memory during runtime, a control software may be able to adapt itself to maximize the overall performance of the transportation CPS.”
These new tools will reduce overall development cost and time for CPSs, and the new software will be open-source to enable broad reuse.
“To meet the stringent requirements that intelligent transportation applications demand, such as performance and safety, the algorithms implemented in the control stack require advanced algorithms that exploit data to learn the environment, the physics, and the cyber,” Sanfelice said. “We believe this is the best way to enable CPSs to make close-to-optimal decisions.”
Collaboration and education
This project will involve vast collaboration across academia and industry, leveraging expertise in fields such as hardware architecture, real-time systems, and hybrid control systems.
There are seven principal investigators on the project: UCSC Professor of Electrical and Computer Engineering Ricardo Sanfelice; UCSC Assistant Professor of Applied Mathematics Abhishek Halder; UCSC Assistant Professor of Computer Science and Engineering Heiner Litz; UC Berkeley Professor of Electrical Engineering and Computer Sciences Murat Arcak; University of Pennsylvania Associate Professor of Computer and Information Science Linh Thi Xuan Phan; Vanderbilt University Professor of Computer Science Jonathan Sprinkle; and University of Colorado Boulder Assistant Professor of Computer Science Majid Zamani. They will also collaborate with researchers at the Norwegian University of Science Technology and Italy’s IMT School for Advanced Studies Lucca. Professor and Department Chair of Astronomy and Astronomy and Astrophysics Raja GuhaThakurta and Associate Director of Development for Baskin Engineering Alexandria Leckliter will facilitate key outreach.
The researchers will work with industry partners such as Toyota Motor Engineering & Manufacturing, Toyota Research Institute, Joby Aviation, and Summer Robotics to gather strategic advice about existing hardware and to validate the autonomous transportation systems created by this project. Through this focused collaboration, they aim to bring their work from research to practice.
In recruiting researchers for this project, the PIs will focus on involving and mentoring women and historically marginalized communities, spanning all levels of education from K-12 to post-docs via UCSC's world-renowned Science Internship Program, the brand-new Shadow the Scientists initiative, and the MESA College Prep program. Activities will include a CPSs industry seminar series, competitions to create tools and datasets, and integration of research advances into engineering curriculum at several of the participating universities.
In addition to addressing the effectiveness of CPSs, this project presents a vision for reducing the growing global carbon footprint by promoting an increased use of autonomous systems in transportation.
“Transcending the computational challenges of traditional methods, Sanfelice and his team are innovating intelligent transportation systems of the future,” said Alexander Wolf, dean of the Baskin School of Engineering. “This grant places our researchers at the forefront of a field critically important in our rapidly changing world, while centering the contributions of our students.”
This project is funded through the NSF’s Cyber-Physical Systems program, under the Frontier category. The proposal was prepared with assistance by the UCSC Cyber-Physical Systems Research Center and the UCSC Office of Research (OR), and through seed funds provided by the OR and the Baskin School of Engineering to research intelligent transportation.
"Frontier projects at the NSF must address clearly identified critical CPS challenges that cannot be achieved by a set of smaller projects,” Sanfelice said. “Back in 2017, we founded the UCSC CPSRC with the intention of providing a platform for leading a winning Frontier proposal. I'm thrilled that NSF has selected our proposal for an award and feel privileged to lead this innovative project."
