What are the possibilities when artificial intelligence (AI) and wireless communication are used to improve the functionality of self-driving (autonomous) vehicles? Passengers can take comfort in knowing they will reach their destinations safely and securely.
Dr. Honggang Wang, associate professor of electrical and computer engineering, and Dr. Hua Fang, associate professor of computer and information science, are the recipients of a $153,299 award from the National Science Foundation for their collaborative research project “Enabling Machine Learning based Cooperative Perception with mmWave Communication for Autonomous Vehicle Safety.” Their project will use advanced sensor technology to ensure the safe driving of autonomous vehicles over a narrow scope and improved traffic flow efficiency over an extended scope.
“The main research objective of this project is to understand the sensing and communication challenges to achieving cooperative perception among autonomous vehicles, and to use the insights thus gained to guide the design of suitable data exchange format, data fusion algorithms, and efficient millimeter-wave vehicular communications,” says Wang.
Results will include a framework that will shed light on effectively combining feature maps, derived from machine learning models on autonomous vehicles. The use of feature maps will significantly reduce the amount of data exchanged among vehicles, enabling agile and the ability to monitor roadblocks and nearby vehicles. “Self-driving vehicles will become highly intelligent. Safety is the top priority in autonomous driving. Fewer accidents means reduced economic burdens,” says Fang.
The expected research outcomes will also enhance the current curricula related to machine learning, artificial intelligence, and wireless communications. Undergraduate and graduate assistants will be involved in research that uses components of engineering, mechanics, and computer science. “This project offers a wide variety of research activities from data collection, algorithm design, system development, and in-the-field evaluation, which will be attractive to students with various backgrounds and goals,” says Fang.