RobotCar - an inexpensive alternative to Google's self-driving cars (w/video)
(Nanowerk News) Taking a different approach to Google's self-driving cars, Oxford University has come up with a new autonomous car, which can drive itself, interact safely with other road users and can use roads efficiently.
RobotCar is a modified Nissan LEAF. Unlike Google's system that uses GPS, RobotCar uses lasers and cameras which are subtly mounted around the vehicle. It also takes up some of the boot space is a computer which performs all the calculations necessary to plan, control speed and avoid obstacles. Externally it's hard to tell this car apart from any other on the road.
The base vehicle is a Nissan LEAF - an all-electric car. The car has an off-the-shelf computer in the boot connected to various cameras and lasers hidden around the car’s body.
The company has not used GPS. It believes, even when GPS is available, it does not offer the accuracy required for robots to make decisions about how and when to move safely. Even if it did, it would say nothing about what is around the robot, and that has a massive impact on autonomous decision-making.
RobotCar, which uses lasers and cameras, constantly monitors the road ahead to look for pedestrians, cars or anything that could pose a danger.
"Currently, the system leverages an array of low-profile stereo cameras and lasers that rings up at about £5,000 (approximately $7,750), but the next goal is to knock the price down to £500, and eventually to a cool £100 (roughly $150)," reports Engadget.
RobotCar constantly monitors the road ahead to look for pedestrians, cars or anything that could pose a danger. If an obstacle is detected the vehicle comes to a controlled stop and waits until the obstacle has moved out of the way. Once clear the car simply accelerates and continues its journey.
There are three computers onboard. The iPad, the LLC (Low Level Controller) and the MVC (Main Vehicle Computer). The iPad runs the user interface and demands constant attention from the LLC. If any of these computers disagree the driver will not be able to start autonomous driving. If at any point there is a problem when the car is in control the human driver is prompted to take control, if they fail to do so the car is automatically brought to a stop.
The whole user experience is provided by an iPad which quickly guides the user through the few checks that are needed to induce autonomy. At any time the driver can take back control of the car by touching the brake - it's exactly like cruise control in an existing vehicle - only this time the car sees obstacles, controls speed and steering.
The company has modified the base Nissan LEAF systems to allow complete fly-by-wire control. Everything from the steering to the indicators can be manipulated by the main vehicle computer in the boot.
RobotCar senses the world in two main ways. The first uses a pair of stereo cameras to assess the road and navigate, much like a human driver's eyes. The second is a little different and uses several lasers mounted around the vehicle. These sensors assess the 3D structure of world and also improve performance at night. The vehicle is all electric. This means no carbon emissions.