LONDON – Technology developed at Oxford University has been used enable a Nissan Leaf electric car to drive itself over a route that it has previously trained to recognize. As well as recognizing where it is and controlling the car the technology includes safety systems for collision avoidance.
The car was given a run out at Begbroke Science Park, near Oxford, England.The technology does not rely on any additional infrastructure or even satellite navigation thereby reducing cost and easing introduction.
The Nissan Leaf has small cameras and lasers built into the body of the car and linked to a computer in the boot while the user interface and control is performed from an iPad added to the dashboard. At any time a tap on the brake pedal returns control to the human driver.
Nissan Leaf with extensive cameras and computer systems driving itself.
"Our approach is made possible because of advances in 3-D laser mapping that enable an affordable car-based robotic system to rapidly build up a detailed picture of its surroundings," said Professor Paul Newman of Oxford University's Department of Engineering Science, who is leading the research alongside Oxford's Ingmar Posner.
"Because our cities don't change very quickly robotic vehicles will know and look out for familiar structures as they pass by so that they can ask a human driver 'I know this route, do you want me to drive?' and the driver can choose to let the technology take over."
The prototype navigation system costs around £5,000 (about $7,700) but the long-term goal is to produce a system costing about £100 (about $155), said Professor Newman.
The next stage of the research will involve enabling the robotic system to understand complex traffic flows, such as might be found at traffic lights, and make decisions as to which routes to take.
'Whilst our technology won't be in a car showroom near you any time soon, and there’s lots more work to do, it shows the potential for this kind of affordable robotic system that could make our car journeys safer, more efficient, and more pleasant for drivers,' said Professor Newman.
I think it will move faster because self-drive will become compelling when coupled to other transitions and the current vehicle manufacturers may be displaced.
The game changing package will be self drive + electric vehicle + radical new layout (e.g. no steering wheel) + new business model. Instead of owning cars we will pay a fee to be able to summon a car on demand.
Remember, the automakers move a bit more slowly than CE companies. I think in 10 years we will start to see this in production cars, but it's probably 20 years before cars that can drive autonomously are more common than those that cannot.
Ten years. That's my prediction. In another ten years after that, self-driving cars will be more common than cars without the capability.
I think that the technology will start with the assisted parking, lane holding and adaptive cruise control systems that we're seeing now in high end card. It will filter down and little by little work toward full autonomous driving. In half a decade, most new cars will have a pretty aggressive adaptive cruise control as well as emergency accident avoidance assist.
A lot of people seem to think that the computer assist would be best in normal driving activities, with a human driver being superior in an emergency. That may be the case for a skilled and well trained rally driver, but not for most of us.
Well we already have assisted parking!
I think in the case of impending accidents...fail-safe braking etc. kicks in and control is given back to the "driver"
So the driver is probably responsible.
But what is interesting is how a "smart" car that is familiar with a route could interact with a driver given "permission" not to concentrate.
Join our online Radio Show on Friday 11th July starting at 2:00pm Eastern, when EETimes editor of all things fun and interesting, Max Maxfield, and embedded systems expert, Jack Ganssle, will debate as to just what is, and is not, and embedded system.