Researchers from Oxford University are testing a self-driving version of the Nissan Leaf, built using robotic technology developed in-house. The iPad’s 9.7 inch screen acts as an interface to the car’s self-driving system, allowing the driver to hand over control to the car or take back control into his or her own hands.
Unlike Google’s self-driving car, which is completely driverless, Oxford’s technology is developed keeping in mind a driver who’d want to switch between ‘auto drive’ and ‘manual drive’ from time to time. A key selling point of Oxford’s technology is that instead of GPS, it relies on a low-cost navigation system, consisting of small cameras and lasers, to sense surroundings, making it much more likely to be included in regular cars in the future.
The iPad features a user interface that the driver can use to switch between ‘auto drive’ and ‘manual drive’. The robotic system takes control of the car when one taps a button on the iPad. At any time when you hit the brakes, the robotic system returns the control back to the human driver.
Here’s how the team behind the self-driving car describes the working of their project:
We use the mathematics of probability and estimation to allow computers in robots to interpret data from sensors like cameras, radars and lasers, aerial photos and on-the-fly internet queries. We use machine learning techniques to build and calibrate mathematical models which can explain the robot’s view of the world in terms of prior experience (training), prior knowledge (aerial images, road plans and semantics) and automatically generated web queries. We wish to produce technology which allows robots always to know precisely where they are and what is around them.
While the current sensors required to equip the Nissan Leaf with self-awareness cost around $7,600, the team intends to produce a system with an estimated cost of $150.