Edge Intelligence and Its Application in Connected and Autonomous Vehicles

The proliferation of IoT and the success of rich cloud services have enabled a new computing paradigm, edge computing, which calls for processing data at the edge of the network. Edge computing has the potential to address the concerns of response-time requirement, battery-life constraint, bandwidth cost savings, and data safety and privacy. In this talk, Weisong Shi discusses the state-of-the-art of edge computing, the emergence of edge intelligence, and how it applies to connected and autonomous vehicles (CAVs).

Yongtao Yao introduces solutions for scheduling multiple collaborative deep neural networks (DNN) on a group of heterogeneous edge devices with the goal of reducing overall latency. Real-world applications usually call for the collaboration of multiple DNN models on heterogeneous edge platforms to complete complicated tasks with outstanding performance. However, due to the explosive growth in computational requirements, model size, number of involved models, and participating devices, the ability to concurrently and efficiently deploy and implement these collaborative models with different deployment constraints is an urgent issue.   

Dr. Weisong Shi is the associate dean for research and graduate studies at the College of Engineering, Wayne State University. He is a Charles H. Gershenson distinguished faculty fellow and a professor of computer science. He leads the Wayne Mobility Initiative and directs the Mobile and Internet Systems Laboratory and Connected and Autonomous Driving Laboratory, investigating performance, reliability, power- and energy-efficiency, and trust and privacy issues of networked computer systems and applications. He serves as the director of the National Science Foundation's Industry-University Cooperative Research Centers (IUCRC) on electric, connected, and autonomous technologies (eCAT) for mobility. One of the world leaders in the edge-computing research community, he wrote the pioneer paper, Edge Computing: Vision and Challenges, that has been cited more than 3,700 times. He has been involved in the activities of the Institute of Electrical and Electronics Engineers (IEEE) Computer Society and served as the chair of the Technical Committee on the Internet (TCI) 2012–2016. He is the founding steering-committee chair of the Association for Computing Machinery (ACM)/IEEE Symposium on Edge Computing (SEC), and the International Conference on Connected and Autonomous Driving. He is an IEEE fellow and an ACM distinguished scientist. 

Yongtao Yao is a PhD student at Wayne State University under the supervision of Weisong Shi. His research direction is edge computing. His specific research interests include model scheduling and video processing.

 

Product and Performance Information

1

Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.