Wayne State conducting NSF-funded research on real-time computing system for connected autonomous driving
A critical aspect to the development of autonomous driving will be achieving safe and reliable connected vehicle technology. A system in which cars, personal communication devices, roadside units and other elements of infrastructure have stable wireless communication with each other is central to the perception tasks and timing correctness necessary to bring this technology to life.
Zheng Dong, assistant professor of computer science at Wayne State University, is working to develop predictable real-time computing to connected autonomous driving (CAD). His latest project received a two-year, $174,944 grant from the National Science Foundation's Computer and Information Science and Engineering (CISE) Research Initiation Initiative (CRII).
"Building a CAD system will constitute a major technological breakthrough towards realizing fully autonomous vehicles," said Dong. "In particular, this project emphasizes both scheduling algorithm design and system implementation."
The framework of the project is a practical real-time task model to integrate exterior devices into the on-vehicle perception system, as well as an algorithm that ensures perception tasks - collecting and processing data to understand the world around the vehicle, much like the vision of a human driver - are completed at the proper time. The prototype system will be evaluated using HydraOne, an indoor experimental research and education platform developed in the CAR Lab at Wayne State, and its roadside counterpart, Equinox.
"The creation of new real-time resource allocation methods, together with the associated analysis for validating timing constraints, will drive the scheduling theory towards real applications in future cyber-physical systems," said Dong.
This project will also further the development of HydraOne for undergraduate education and research, and can aid in the design of hands-on learning opportunities for Wayne State and K-12 students.
The project number for this NSF award is 2103604.