Skip to content
0:00 / 0:00

#self-drivingcars#waymo#google

Google Self-Driving Car Project | SXSW Interactive 2016

SXSW

374K subscribers • 2 videos on Hallway

YouTube
  • Recommended by 2 people: 2 on Hacker News.
  • Presented by Chris Urmson, Director of Google's Self-Driving Car Project
  • May be out of date. The tools, versions or practices it shows have likely moved on.

Intermediate. Assumes working knowledge.

144K views10 years ago2 recommendations

AI and machine learningSystems programmingComputer visionTraining and serving models

Chris Urmson shares progress, sensor visualizations, and real-world challenges from Google's autonomous vehicle project.

Everyone's talking about self-driving cars these days, but how can you differentiate between hype and reality? In the six years of Google’s project, its vehicles have self-driven over 1.3 million miles, racking up the equivalent of 90 years of human driving experience. Google says its cars can now handle the vast majority of everyday situations it finds on the roads, but what does the path to a driverless future look like? How could it be that self-driving cars be both three and 30 years away? Urmson shares his stories from the front lines of building the world's first fully self-driving cars. Subscribe: youtube.com/user/sxsw?sub_confirmation=1 About SXSW: Started in 1987, South by Southwest (SXSW) is a set of film, interactive, and music festivals and conferences that take place early each year in mid-March in Austin, Texas. SXSW’s original goal was to create an event that would act as a tool for creative people and the companies they work with to develop their careers, to bring together people from a wide area to meet and share ideas. That continues to be the goal today whether it is music, film or interactive technologies. Connect with SXSW Online: Visit the SXSW WEBSITE: sxsw.com Like SXSW on FACEBOOK: facebook.com/SXSWFestival Follow SXSW on TWITTER: twitter.com/SXSW youtube.com/user/SXSW

Why it's here

2 people recommend this

What people say. Recommended as one of the best and most realistic presentations on the engineering challenges of self-driving cars.

Animatson Hacker News • Recommends

On “Tesla Model S Autopilot Reliability – Why Americans Should Love Tesla”

…d. What they did to prevent this from happening again is mentioned. Most of the talk is about the hard cases. In the beginning, Google developed a highway driving system, but that was years ago. Now they're working hard on dealing with everything that can happen on a road, including someone in an electric wheelchair chasing ducks with a broom. 1 link to this video…

Animatson Hacker News • Recommends

On “Former Apple Employee Charged with Theft of Autonomous Car Project Trade Secrets”

That's Chris Urmson's talk at SXSW in 2016 1, which has been widely viewed. It's one of the best talks on the subject. He said "How quickly can we get this into people's hands? If you read the papers, you see maybe it's three years, maybe it's thirty years. And I am here to tell you that honestly, it's a bit of both." Then he showed video of Google cars dealing with various challenging conditions. This included the famous scene where a Google self driving car encountered a woman in a powered wheelchair using a broom to chase a turkey. The software recognized this as something to avoid, even though it didn't classify it further. 1 link to this video

kyrraon Hacker News • Recommends

On “Four hundred miles with Tesla’s autopilot forced me to trust the machine”

This was a good presentation by the Google team: link to this video I believe they say in there that they got highway driving down really early on. They have been focusing on urban driving for the last few years.

Animatson Hacker News • Recommends

On “How Self-Driving Cars Work”

This article seems to be a summary of Chris Urmson's talk at SXSW.1 That's worth a watch. It gives a good overview of how Google does it. 1 link to this video

Animatson Hacker News • Recommends

On “Let’s Talk About Self-Driving Cars”

…mph when it was entering an intersection with poor visibility, detected cross-traffic, and stopped. I'm looking forward to the 2016 self-driving disengagement reports appearing on on the California DMV site.3 Those were due January 1, covering the year ending 1 December 2016. Then we'll have comparative info on how all the players are doing. 1 link to this video 2 link 3 link…

Animatson Hacker News • Recommends

On “Tesla Autopilot”

Compare Chris Urmson's SXSW talk from 2016 about Google's system.1 Look carefully at the graphics which show what the sensors are detecting, and compare with Tesla's. Watch Urmson discuss hard cases, problems, and failures. Not seeing that with Tesla. Or Uber. Or Cruise. Or Otto. 1 link to this video

Animatson Hacker News • Recommends

On “Comma.ai launches an $88 universal car interface called Panda”

Watch Chris Urmson's self-driving car talk at SXSW 2016.1 Especially the part where the Google car encounters someone in a powered wheelchair chasing a duck with a broom. Google can handle that. 1 link to this video

agildehauson Hacker News • Mentions

On “Uber seeking to buy self-driving cars: source”

They do well in rain but snow remains a problem, not due to icy roads (at SXSW Chris Urmson said they do well on slick roads) but that the "better than GPS" LIDAR-based location tracking stops working when snow is on the ground. The car simply cannot figure out where it is when there's a significant layer of snow on the ground because the reference maps stop looking like what the car is seeing. link to this video

EmployedRussianon Hacker News • Mentions

On “Post-Mortem for Google Compute Engine’s Global Outage on April 11”

When you are barreling down a highway at 65 miles per hour and are not paying attention (and you wouldn't, because the car drives itself just fine), giving you controls is much more dangerous (for you and others around you) then not. Urmson talks about it here: link to this video

studentrobon Hacker News • Mentions

On “Tesla Model S Autopilot Reliability – Why Americans Should Love Tesla”

Cool! Thank you for sharing this. Here's the part where he starts talking about the 2mph bus accident 1. He says the self-driving car should not have moved. He does not say why. He says they ran a lot of tests to make sure it will not happen again. In plain English, I'd say, when the SDC is stopped on the side of the road, give sufficient time for traffic coming from behind to clear out before the SDC moves forward. Also, if an accident is imminent, being in a non-moving position is probably safer and less likely to cause liability for the SDC than moving. Plus, rolling over some sandbags is probably preferable to being hit by a bus. 1 link to this video

Animatson Hacker News • Mentions

On “Misfortune”

…n the simulator using the live data, and work on the software until that won't happen again. Analyzing problems which didn't rise to the level of an accident provides far more situations to analyze. They're not limited to just accidents. See Chris Urmson's talk at SXSW, which has lots of playbacks of situations Google cars have encountered.1 1 link to this video…

Animatson Hacker News • Mentions

On “Nvidia on new self-driving system: “basically 5 years ahead and coming in 2017””

…ing much with road edge clutter. They're not marking every post, fireplug, and low-hanging branch. Train a deep learning system on cars, trucks, pedestrians, and bicycles, and your system sees only cars, trucks, pedestrians, and bicycles. These vision systems do a lot less than many people think they do. Watch the videos. 1 link 2 link 3 link to this video…

Animatson Hacker News • Mentions

On “Trump administration re-evaluating self-driving car guidance”

It's in his SXSW talk.1 It's the Google/Waymo and Volvo position, those being the two companies closest to a product. 1 link to this video

Animatson Hacker News • Mentions

On “Tesla hires Andrej Karpathy”

What this really reflects is that Tesla has painted itself into a corner. They've shipped vehicles with a weak sensor suite that's claimed to be sufficient to support self-driving, leaving the software for later. Tesla, unlike everybody else who's serious, doesn't have a LIDAR. Now, it's "later", their software demos are about where Google was in 2010, and Tesla has a big problem. This is a really hard problem to do with cameras alone. Deep learning is useful, but it's not magic, and it's not strong AI. No wonder their head of automatic driving quit. Karpathy may bail in a few months, once he realizes he's joined a death march. If anything, Tesla should have learned by now that you don't wan…

Retricon Hacker News • Mentions

On “Inside Waymo's Secret World for Training Self-Driving Cars”

Can you give an actual example? Because, not being able to identify something is not necessarily an issue as long as the car notices something is there and it should not hit it. EX: I am sure the car had no idea what this was: link to this video but as long as it can tell it's bigger than a bread box and so it should not to hit it that's enough.

Animatson Hacker News • Mentions

On “Waymo's big self-drive car report”

…The new material covers mainly the limitations Waymo is imposing on their system. It works only where they have very detailed maps of the road system, with more information than even StreetView. This is conservative, but not a bad decision for initial release. They have a button to call customer service. (That's so unlike Google.) 1 link 2 h link to this video…