Oxford’s Self-Driving Car (on the Left Side of the Road)
Self-driving cars aren’t just the realm of corporate giants like Google. Academia plays a big role in this space too, as the BBC points out. Oxford University’s department of engineering science is behind something called the Oxford RobotCar UK project.
The chaps at Oxford use a Nissan LEAF as their base vehicle (they’ve teamed up with Nissan since September 2012, in fact). The Oxford team uses reflective beacons and guide wires to help the car self-navigate. GPS, the team reports, “does not offer the accuracy required for robots to make decisions about how and when to move safely.” (Bear that in mind, next time you turn a robot loose with your iPhone maps app.)
What’s some of the other hardware involved here? The team puts two scanning lasers beneath the front and rear bumpers of the LEAF, lasers which “allow us to sense the 3D structure of the car’s environment,” they report. Stereo cameras, coupled with a laser, help the robot determine the trajectory of the car “relative [to] routes it has been driven on before.” (The laser scanner simply comes off the shelf, offering an 85-degree field of view, and scanning 13 times a second.)
The team isn’t putting the car on the roads just yet. It’s testing it out in a “specially-made environment at Begbroke Science Park in Oxfordshire,” per the BBC. Professor Paul Newman, a lead on the project, says that the car is gaining “experiences,” of a sort. “The car is driven by a human, and it builds a 3D model of its environment. Using an iPad on the dashboard, a driver can determine when it wants to cede control to the robot, or seize the controls back for himself.
The whole system costs £5,000, but Newman told the BBC costs could be drastically reduced, potentially to as low as £100. Newman seems to think his team’s device will inevitably be cheaper than Google’s more-renowned experiments: “if you look at it, we don’t need a 3D laser spinning on the roof that’s really expensive–so that’s one thing straight away. I think our car has a lower profile,” he said. He added that he thought technology such as this would be commonplace in 15 years.
In the race towards robot-driven roads, who do you think is more likely to win, business or the academy?
Keep Reading
Most Popular
Large language models can do jaw-dropping things. But nobody knows exactly why.
And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.
How scientists traced a mysterious covid case back to six toilets
When wastewater surveillance turns into a hunt for a single infected individual, the ethics get tricky.
The problem with plug-in hybrids? Their drivers.
Plug-in hybrids are often sold as a transition to EVs, but new data from Europe shows we’re still underestimating the emissions they produce.
Google DeepMind’s new generative model makes Super Mario–like games from scratch
Genie learns how to control games by watching hours and hours of video. It could help train next-gen robots too.
Stay connected
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.