Hear the Show 28:25 min – 16.2 mb mp3
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,” Hayder Radha, a professor of electrical and computer engineering and director of CANVAS, tells Michigan State University President Lou Anna K. Simon and Spartans Athletic Director Mark Hollis on MSU Today. “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.”
Radha explains both the differences and the vital links between autonomous and connected vehicles. And he details how Michigan State University is among eight North American universities selected for the upcoming AutoDrive Challenge – a new autonomous vehicle design competition to develop and demonstrate a fully autonomous passenger vehicle.
“One of the really interesting problems we’re working on at MSU is trying to get the radars in these vehicles to the level of capability of recognition of objects such as vehicles and pedestrians of cameras.
“If you look at the potential benefits of autonomous driving, it’s really phenomenal. They’re safer than cars people drive, and we could literally save about a million lives a year worldwide.”
These issues have significant and, as of yet, not fully-determined implications for the insurance industry. And Radha adds that the technical challenges are profound.
“I frankly believe strongly that we haven’t yet even reached the level of competence of human driving because we humans are so good at recognizing our environment when we drive.”
Radha describes 2021 as “a magic year” for the industry, and he expects a very diverse reaction to and acceptance of this technology by the public. But once the technology is demonstrated in a very robust and safe way, he expects all of society to get used to the technology as it emerges over the next decade or two.
He defines the term platooning and says the mining and farming industries are early adopters in embracing and advancing these new technologies.