Please note that this is not an asynchronous on-line track. Everyone is expected to log in every day all day according to the Winter Working Connections schedule. This is a synchronous track.

This on-line Working Connections event is intended solely for the person who registers. Link sharing is only permitted with the prior approval of the National Convergence Technology Center.

Description

A fully autonomous vehicle (AV) is a vehicle that can guide itself without human interaction which is commonly referred to as driverless car, robot car, or self-driving car. Connected vehicle (CV) technologies, on the other hand, allow vehicles to communicate with each other and the world around them. AV and CV are two key enabling techniques for future transportation system, aiming at reducing traffic accidents, enhancing quality of life, and improving efficiency. In this class, participants will learn the basics of AV and CV techniques and how they will benefit from each other. CV allows autonomous vehicles to exchange real-time sensor information to each other, achieving so-called cooperative perception. The extended field of view on autonomous vehicles is beneficial at times where there are occlusions preventing a complete perception of the environment. On the other hand, AV is a better platform to manifest the benefits of CV technology as the massive amount of information exchanged among vehicles can only be processed in real time by computers (not human).

Prerequisites

Basic knowledge in robotics is helpful.

Textbook

None

Instructors


Photo above courtesy of the article found here: https://engineering.unt.edu/news/experts-autonomous-vehicles-land-two-more-grants

Qing Yang, Ph.D., and Song Fu, Ph.D.

Qing Yang, Ph.D., is an Assistant Professor in the Department of Computer Science and Engineering at University of North Texas, TX. He received his Ph.D. degree in Computer Science and Software Engineering from Auburn University, AL, USA in 2011. His current research interests include connected and autonomous vehicles, Internet of Things, network security and privacy. His research is funded by the U.S. National Science Foundation, U.S. Federal Highway Administration, Office of Naval Research, Toyota InfoTech Inc., Fujitsu Laboratories of America Inc., and the University of North Texas Office of the Vice President for Research and Innovation.

Song Fu, Ph.D., is an Associate Professor in the Department of Computer Science and Engineering at the University of North Texas. He is the Director of the Dependable Computing Systems Lab (DCS). He was an Assistant Professor in the Department of Computer Science and Engineering at New Mexico Institute of Mining and Technology from 2008 to 2010. He obtained the Ph.D. degree in Computer Engineering from Wayne State University, Detroit Michigan, in 2008. His research interest is primarily in cyberinfrastructures, parallel, distributed and IoT-edge-cloud systems, including architecture, performance, dependability, security, and machine learning. His research has been supported in part by funding from the National Science Foundation, Department of Energy, Amazon, Cisco, Nvidia, Xilinx and University of North Texas.

Course Objectives

Upon successful completion of this course, participants should be able to:
1. Understand the fundamentals of autonomous vehicle technology.
2. Understand the wireless networking standard for connected vehicles.
3. Understand the difference and connection between AV and CV technologies.
4. Demonstrate ability to access, display and process sensor data generated by autonomous vehicles
5. Understand how to achieve cooperative perceptions on connected and autonomous vehicles (CAV).

Agenda

Topics to be Covered:

• Connected and Autonomous Vehicles
• Lane detection
• Localization
• Mapping
• Path planning
• Convolutional neural network (CNN)
• Object detection via CNN
• Cooperative object detection
• Wireless vehicular networks
• Vehicular edge/cloud computing

Tentative Daily Agenda:

Day 1 December 14, 2020
Module 1: Course Introduction
Module 2: Overview of autonomous vehicles
Module 3: Sensors on autonomous vehicles
Module 4: Connected and autonomous vehicles
Module 5: Lane detection
Module 6: Localization
Lab 1

Day 2 December 15, 2020
Module 7: Mapping
Module 8: Path planning
Module 9: Convolutional neural networks (CNN)
Module 10: Object detection via CNN
Module 11: Multi-vehicle cooperative object detection
Lab 2

Day 3 (half day) December 16, 2020
Module 12: Wireless vehicular networks
Module 13: Vehicular edge/cloud computing
Module 14: Software for autonomous vehicles

Please note that content is subject to change or modification based on the unique needs of the track participants in attendance.