See London Through the Eyes of a Self-Driving Car

To see how driverless cars might perceive the world, ScanLAB Projects drove a 3D laser scanner through the streets of London.


It’s always cool to see the world through the perspective of a self-driving car. But this video below might be the most incredible example yet.

ScanLAB Projects strapped one of its 3D laser scanners to a Honda CR-V and drove around the streets of their hometown of London. Driven by a human, the car used LIDAR to create a real-time map of its environment.

The video, produced by The New York Times Magazine, shows how far this technology has come, but it also shows it has some way to go. “Their work reveals is a landscape of aging monuments and ornate buildings, but also one haunted by duplications and digital ghosts. The city’s double-­decker buses, scanned over and over again, become time-­stretched into featureless mega-­structures blocking whole streets at a time. Other buildings seem to repeat and stutter, a riot of Houses of Parliament jostling shoulder to shoulder with themselves in the distance. Workers setting out for a lunchtime stroll become spectral silhouettes popping up as aberrations on the edge of the image. Glass towers unravel into the sky like smoke.”

The article also reiterates a hypothetical scenario posed by Illah Nourbakhsh, a robotics professor at Carnegie Mellon University, that would throw a self-driving car for a loop.

Imagine someone wearing a T-­shirt with a stop sign printed on it, he told me. “If they’re outside walking, and the sun is at just the right glare level, and there’s a mirrored truck stopped next to you, and the sun bounces off that truck and hits the guy so that you can’t see his face anymore - well, now your car just sees a stop sign. The chances of all that happening are diminishingly small - it’s very, very unlikely - but the problem is we will have millions of these cars. The very unlikely will happen all the time.

Sight Lines from ScanLAB on Vimeo.

[Source:] The New York Times Magazine




About the Author

Steve Crowe · Steve Crowe is managing editor of Robotics Trends. Steve has been writing about technology since 2008. He lives in Belchertown, MA with his wife and daughter.
Contact Steve Crowe: scrowe@ehpub.com  ·  View More by Steve Crowe.




Comments

Totally_Lost · November 23, 2015 · 11:34 am

No, my only direct experience with that was Grand Challenge, plus personal interest in the technology.

Much more interested in other AI and Robotics projects these days.

Steve Crowe · November 23, 2015 · 11:28 am

Are you working in the self-driving car industry?

Totally_Lost · November 23, 2015 · 11:21 am

yeah, caught that a few months ago, laughed for half a day smile

Steve Crowe · November 23, 2015 · 10:48 am

@Totally_Lost, not sure if you caught this story, but it was also interesting. A bicyclist confused a Google SDC while doing a track-stand on his bike. Had a 2-minute standoff at a four-way stop sign.

http://www.roboticstrends.com/article/a_cyclists_encounter_with_an_indecisive_google_self_driving_car

Totally_Lost · November 22, 2015 · 12:24 pm

Other scary things are wide bike lanes being mistaken for an acceptable travel lane for the self driving car, or sections of road under construction or re-pavement without lane markers at all, if not just a featureless dirt road or parking lot. Add to that construction detours.

One can minimize a lot of this with detailed high-res maps with approved traffic lanes, but the problem never goes completely away. Especially those that the car can easily learn with driver assist on regularly travel routes ... but none of this is fool proof (like construction detours, and temporary barriers for events). None of it’s easier than the Grand Challenge after a decade.


Totally_Lost · November 22, 2015 at 12:24 pm

Other scary things are wide bike lanes being mistaken for an acceptable travel lane for the self driving car, or sections of road under construction or re-pavement without lane markers at all, if not just a featureless dirt road or parking lot. Add to that construction detours.

One can minimize a lot of this with detailed high-res maps with approved traffic lanes, but the problem never goes completely away. Especially those that the car can easily learn with driver assist on regularly travel routes ... but none of this is fool proof (like construction detours, and temporary barriers for events). None of it’s easier than the Grand Challenge after a decade.

Steve Crowe · November 23, 2015 at 10:48 am

@Totally_Lost, not sure if you caught this story, but it was also interesting. A bicyclist confused a Google SDC while doing a track-stand on his bike. Had a 2-minute standoff at a four-way stop sign.

http://www.roboticstrends.com/article/a_cyclists_encounter_with_an_indecisive_google_self_driving_car

Totally_Lost · November 23, 2015 at 11:21 am

yeah, caught that a few months ago, laughed for half a day smile

Steve Crowe · November 23, 2015 at 11:28 am

Are you working in the self-driving car industry?

Totally_Lost · November 23, 2015 at 11:34 am

No, my only direct experience with that was Grand Challenge, plus personal interest in the technology.

Much more interested in other AI and Robotics projects these days.


Log in to leave a Comment



Editors’ Picks

How Many Robots Does it Take to Screw in a Light Bulb?
Watch a Fetch robot with a custom soft robotic gripper use a...

Disney: Focus on the Robot Experience
The robot experience included in a business strategy is important not only...

Flirtey Wants Drones to Deliver Defibrillators in Nevada
Flirtey and REMSA have partnered to use drones to delivery automated external...

NVIDIA: Drive PX Pegasus AI Computer Powers Level 5 Autonomous Vehicles
NVIDIA introduced its Drive PX Pegasus AI computer that it claims can...