As self-driving cars gain the technical and legal ability to autonomously operate in more places, they will face new obstacles and more significant consequences while navigating them. Engineers tasked with ensuring vehicles’ safety will need to guarantee that their sensors correctly assess their surroundings, that their software makes the right decisions based on that sensor data and that the relevant hardware executes those decisions in time.
These interrelated challenges are the essence of cyber-physical systems (CPS), which also include smart power grids, implantable medical devices and environmental monitoring stations.
As an expert in CPS, Linh Thi Xuan Phan, Associate Professor in Penn Engineering’s Department of Computer and Information Science, is collaborating with an international team of researchers that will work to unify the design of software and hardware components in cyber-physical transportation systems.
By tightly integrating these elements and having them adapt to real-time conditions, self-driving cars and other autonomous transportation systems will benefit from increased efficiency and performance, as well as better safety guarantees.
“Adaptivity is really critical to making self-driving cars safe,” says Phan. “If the environment changes, obstacles show up, or components malfunction, the car has to switch between doing different things in response, but it also has to stay responsive during those transitions. Imagine what would happen if a self-driving car on an icy road stopped getting data from its collision avoidance systems while switching to a new handling mode. Even if that switch only takes a tiny fraction of a second, the car might crash by the time the transition finishes.”
Adaptive co-design would also have less obvious benefits for transportation systems, such as optimizing acceleration and braking speeds to maximize fuel efficiency.
The five-year, $5.7 million project, funded by the National Science Foundation (NSF), is being led by researchers at the University of California, Santa Cruz, and will feature collaborators from the University of California, Berkeley; Vanderbilt University; the University of Colorado, Boulder; the Norwegian University of Science Technology and Italy’s IMT School for Advanced Studies, Lucca.
The researchers will also collaborate with industry and academic partners to advance CPS 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,” says Ricardo Sanfelice, lead principal investigator 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 CPS science.”
Read more about the project at UC Santa Cruz Newscenter.