I came across an interesting article today about a driverless car competition that was recently held, and spurred talk about how far away a commercially viable driverless car actually is.
According to the report 11 driverless cars took part in the race, where entrants had to navigate around a 60 mile urban environment avoiding other cars and safely navigating single and duel cartridge ways, junctions, buildings and car parks within a simulated town.
Of the 11 vehicles that started the race six completed the course with the winner BOSS completing the course in less than 6 hours, collecting a $2 million prize in the process. The race was held in the state of California on a disused US Air Force base in Victorville.
The race had been organised by the US military’s Defence Advanced Research Projects Agency (Darpa), with the objective of developing unmanned vehicle for possible implementation in the battlefield. The technology could also be used in commercial driverless cars, and with General Motors partnering the winning Tartan Racing team, there are clear signs that large commercial companies plan to develop the technology for the commercial sector in the future.
Although most remained in look and appearance much like conventional cars, the participating vehicles were mounted with an array of sensors on the roof and each bumper corner. The winning model featured a unique revolving laser that rotated ten times a second building up a virtual representation of the environment around it, enabling the vehicle to effectively navigate the course.
“It has 64 individual lasers in it, and it spins about 10 times a second to generate about a million measurements of the world. That gives us a kind of point cloud which we can use to help understand where features are - cars, walls, the sidewalk and so on.” explained Chris Urmson.
Although a great day for robotics with so many vehicles completing the simulated urban environment, I don’t think it will be any time soon that we see driverless cars on public roads. A nice concept, and nice to see the developments in a technology that could have wide ranging applications in many fields, however the proposed 2015 deadline I think is a bit premature.
Recent Comments