CS 690-003
Connected and Automated Vehicles
Meets
Friday 10:00 am - 12:40 pm Arlington: Van Metre Hall 113
Professor
Zoran Duric.
About the Class
This course addresses the research and
engineering challenges encountered in designing, implementing, and
deploying connected automated vehicles. They include sensing,
recognition, planning, control and communication aspects for vehicles
and roadside infrastructure. The connected automated vehicles are
expected to improve the safety and comfort of all traffic participants
including the vehicle occupants, bicyclists and pedestrians while
minimizing the environmental impact of traffic. In addition, providing
the right of way for emergency vehicles and traffic arrangements
around special events and parking in congested cities need to be
addressed in a comprehensive framework for connected automated
vehicles. The course will be taught by Dr. Zoran Duric and occasionally
by guest lecturers. A part of the course will include reading and
presenting recent research paper by the students.
A significant part of the course will include experimenting in the lab
and the field.
The lab is equipped with driving simulators, traffic signaling
equipment and
multiple sensors including video and thermal cameras, radars, lidars a
nd high-precision GPS. The available equipment includes three cars that can be mounted with sensor packages.
Prerequisites
CS580 or CS584.
Reading Materials and in Class Presentations
A part of the grade (20%) will be based on reading and presenting
research papers on connected and automated vehicles.
Software
We will use Python and Matlab for homework assignments and
projects. We will also use Sumo and Carla traffic simulation
software.
Main Topics of the Course
- Introduction: A broad overview of all traffic-related
problems. Levels of automation. the role of various parts including
infrastructure, network, and traffic participants. Smart vehicles,
infrastructure, connectivity. Maps and planning. Low-level planning
and driving, parking. Security, privacy, and comfort levels. Human
driving vs. fully automated vs. mixed traffic on roads.
- Traffic Simulation: Traffic simulation using Sumo and
Carla.
- Sensing and smart vehicles: Knowledge extraction from multiple
sensors. Computer vision for smart vehicles.
- Planning and route computation: Planning
algorithms for smart vehicles.
Course Web Page
We will communicate through
Canvas. Slides,
handouts, and assignments will be posted on the Canvas course
page. We will answer questions on the Canvas discussion board.
Grading
Grading will be based on a combination of the following factors:
- Programming assignments: 50%
- Final Group Project : 30%
- Class participation: 20%
Honor Code
The class enforces the GMU Academic
Standards Code, and the more specific honor code policy special to the Department of Computer Science. You will be expected to adhere to this code and policy.
Disabilities
If you have a documented learning disability or other condition which may affect academic performance, make sure this documentation is on file with the Office of Disability Services and come talk to me about accommodations.
Course Outcomes
- An understanding of important topics in
Connected and Automated Vehicles
- A knowledge of traffic simulation sofware
including Carla and Sumo.
- A knowledge of planning and route
computation techniques.
- A knowledge of sensing and data
processing methods for Advanced Driver-assistance systems.