Ryan Wolcott, a doctoral candidate in computer science and engineering at the University of Michigan, used video game technology to develop the low-cost self-driving car navigation system.

The technology will enable cars while navigating, using a single video camera and also is believed to deliver accuracy as laser scanners do but at a lower cost.

"The laser scanners used by most self-driving cars in development today cost tens of thousands of dollars, and I thought there must be a cheaper sensor that could do the same job," Wolcott said.

"Cameras only cost a few dollars each and they're already in a lot of cars. So they were an obvious choice," he said.

Wolcott's system converts the data in the map into a three-dimensional picture, similar like a video game. The navigation system in the car them compares these synthetic pictures with real-world pictures.

Ryan Eustice, a U-M associate professor of naval architecture and marine engineering who is working with Wolcott on the technology, said one of the key challenges was designing a system that could process a massive amount of video data in real time.

The team tried and built a system by processing the graphics of the technology that is well-known to the gamers. They resumed to video game search, the system will be available for a lower-cost and will be equally efficient at the same time.

The system has successfully been tested on the streets of downtown Ann Arbor by the team. The navigation system was successfully able to provide accurate location information.

The system won't completely replace laser scanners, at least for now as they're still needed for other functions like long-range obstacle detection. But the researchers said it's an important step toward building lower-cost navigation systems.

The new system will not replace the laser scanners completely because for functions like long-range obstacle detection, they will still be needed. But this technology is an effective and an important step towards evolution in lower-cost navigation technology.