When it comes to the development of autonomous, or self-driving, vehicles, there’s a lot more to it than meets the eye. It takes a warehouse full of technology – cameras, radars and other sensors, security and recognition technology, not to mention a trunkful of computers – to make it happen.
At Michigan State University, researchers are involved in the work that will someday make self-driving vehicles not just a reality, but commonplace.
Working as part of a project known as CANVAS – Connected and Autonomous Networked Vehicles for Active Safety – the scientists are focusing much of their energy on key areas, including recognition and tracking objects such as pedestrians or other vehicles; fusion of data captured by radars and cameras; localization, mapping and advanced artificial intelligence algorithms that allow an autonomous vehicle to maneuver in its environment; and computer software to control the vehicle.
“Much of our work focuses on technology that integrates the vehicle with its environment,” said Hayder Radha, a professor of electrical and computer engineering and director of CANVAS. “In particular, MSU is a recognized leader in computer vision, radars and antenna design, high-assurance computing and related technologies, all areas that are at the core of self-driving vehicles.”
CANVAS is part of the larger MSU Mobility Studio initiative, consisting of CANVAS, smart infrastructure and mobility management of autonomous and conventional vehicles, pedestrians and cyclists.
Another important aspect of a future connected-and-autonomous vehicle is its ability to communicate with other vehicles and the infrastructure surrounding it. Such communications enable a car to detect other vehicles that are approaching an intersection and recognize whether the other vehicle is going to stop in time.
A connected vehicle, said John Verboncoeur, associate dean for research in MSU’s College of Engineering, also can be used to synchronize traffic lights, so traffic can move more efficiently and reduce backups.
“If the sensors in the car and in traffic lights are communicating,” he said, “much information can be gathered – information that can save lives and fuel and reduce greenhouse gas emissions.”
Biometrics and recognition technology research at MSU will also be an invaluable part of an autonomous vehicle. Specifically, said Verboncoeur, the technology will monitor not only the identity but also the health and well-being of a vehicle’s occupants.
“In the event of a problem, a human has to be ready to take over,” Verboncoeur said. “This technology will help understand a person’s status. Are they sleeping? Or perhaps visually impaired?”
If a vehicle occupant is unable to drive, the technology can detect that and pull the car over to the side of the road.
MSU recently acquired a car that is equipped with a series of radars and LIDARs (laser radar), cameras and accompanying software that will be tested on the MSU campus.
For example, the LIDAR technology has the ability to develop a 3-D map of the area in which the car is driving for maneuverability improvement, as well as develop advanced algorithms that will assist in navigating a particular environment.
“We are testing and conducting performance analysis of state-of-the-art sensors,” Radha said. “We’re examining which ones perform the best. How good are they at detecting objects? And what are the best algorithms for recognizing these objects and for maneuvering a vehicle around them?”