Waymo Blog

The technology for autonomous cars does exist. Latest data from Waymo is that they can drive 5.000 miles on average before disengagement (https://medium.com/waymo/accelerating-the-pace-of-learning-36f6bc2ee1d… They are not ready to be widely deployed but are close, which is why we're talking about them. It's an exciting technology with great potential impact on the future and a lot of that impact is positive. As far as bikes go: no one is complaining about them. It's all in your mind. As far as public transit: autonomous cars will improve it. By my calculations, autonomous car will be cheaper, unsubsidized, than a $2.50 bus ride subsidized by the city from our taxes (SF has ~$1 billion budget to fund money-loosing bart, buses etc.). And that's cars. Things will be even cheaper if we get buses to be autonomous. At which point it's likely bus service will be cheaper and provided by a commercial company (the only reason public transport is government owned is because it looses money, so it wouldn't exist as private company).

Retired. Explained here: https://medium.com/waymo/from-post-it-note-to-prototype-the-journey-of…

I have no clue how thoroughly implemented this is, especially for pedestrians other than police, but Waymo does have support for hand signals and body language: https://www.cnet.com/roadshow/news/waymo-self-driving-cars-police-offi… https://medium.com/waymo/safely-sharing-the-road-with-cyclists-9fe6ad3…

Why would you be surprised? Google did that with no safety drivers over 7 years ago [1], before Tesla even released Autopilot, after 6 years of development. The gap between that and a proper autonomous vehicle with no geofencing that is safer than even the bottom 10% of human drivers is immense and has not been achieved yet. That Tesla has achieved less in 6 years than what Waymo did in 6 years when they were trailblazing the field over a decade ago is disappointing. That Tesla executives believe their Full Self Driving product is acceptable to sell and ship to untrained customers, when systems that are nearly a decade more advanced are unacceptable, is criminal. [1] https://medium.com/waymo/scenes-from-the-street-5bb77046d7ce

Waymo uses sound to detect emergency vehicles: https://medium.com/waymo/recognizing-the-sights-and-sounds-of-emergenc…

https://medium.com/waymo/a-note-on-our-lawsuit-against-otto-and-uber-8… - 14,000 highly confidential and proprietary design files for Waymo’s various hardware systems, including designs of Waymo’s LiDAR and circuit board - 9.7 GB of Waymo’s highly confidential files and trade secrets, including blueprints, design files and testing documentation. - supplier lists, manufacturing details and statements of work with highly technical information

https://medium.com/waymo/partnering-with-lyft-to-serve-more-riders-in-… looks to be the Waymo post on the subject.

Original Medium post: https://medium.com/waymo/learning-to-drive-beyond-pure-imitation-46549… ArXiv link: https://arxiv.org/abs/1812.03079

The link at the bottom of that article is pointing to another Medium post with details of the launch: https://medium.com/waymo/riding-with-waymo-one-today-9ac8164c5c0e Notably, "At the start, Waymo-trained drivers will be riding along to supervise our vehicles for riders’ comfort and convenience." Edit: Re-reading my comment, it sounds negative, so I want to acknowledge that I think this is a big deal. No matter how "soft" this launch, it's still a historic moment.

Google does the hardware well too. They built their own lidar to reduce cost compared to velodyne by 90%. https://arstechnica.com/cars/2017/01/googles-waymo-invests-in-lidar-te… They also built a second narrowly focused longer range lidar that can be automatically pointed at the ROI of objects visuslly detected beyond the range of velodyne's ~200m. https://medium.com/waymo/introducing-waymos-suite-of-custom-built-self… Both are used on their vehicles. If you have better hardware it makes the software problems higher up the stack easier.

Here's Waymo's official blog post on the subject: https://medium.com/waymo/meet-our-newest-self-driving-vehicle-the-all-…

I think Waymo is claiming 5 million miles in total, and Uber 2 million miles. [1] https://medium.com/waymo/waymo-reaches-5-million-self-driven-miles-61f… [2] https://www.forbes.com/sites/bizcarson/2017/12/22/ubers-self-driving-c…

Per this old article from 2016, yes: https://medium.com/waymo/sounds-of-the-self-driving-car-c26f30fcf76c

https://medium.com/waymo/waymos-fleet-reaches-4-million-self-driven-mi… https://www.forbes.com/sites/bizcarson/2017/12/22/ubers-self-driving-c… so, 6 million miles driven and one fatality is significantly worse record than human drivers. So far.

Can't speak for Uber, but Waymo/Google apparently has billions of miles tested on closed track, vs just 4+ million miles on the open road: https://medium.com/waymo/waymos-fleet-reaches-4-million-self-driven-mi…

I think any news story out there is just a rehash of Waymo's medium post[0]. I believe this post was entirely in response to Uber's press coverage 3 days ago around running trucks in Arizona[1]. [0] https://medium.com/waymo/same-driver-different-vehicle-bringing-waymo-… [1] https://www.theverge.com/2018/3/6/17081626/uber-self-driving-trucks-de…

This article from Dec 2016 seems to suggest that's still the case [0]. However, it also looks like those maps can be built by the cars themselves, which should simplify expansion. [0]: https://medium.com/waymo/building-maps-for-a-self-driving-car-723b4d9c…

From April: https://medium.com/waymo/apply-to-be-part-of-waymos-early-rider-progra…

Waymo says they have proof of #1 and #2. We found that six weeks before his resignation this former employee, Anthony Levandowski, downloaded over 14,000 highly confidential and proprietary design files for Waymo’s various hardware systems, including designs of Waymo’s LiDAR and circuit board. To gain access to Waymo’s design server, Mr. Levandowski searched for and installed specialized software onto his company-issued laptop. Once inside, he downloaded 9.7 GB of Waymo’s highly confidential files and trade secrets, including blueprints, design files and testing documentation. Then he connected an external drive to the laptop. Mr. Levandowski then wiped and reformatted the laptop in an attempt to erase forensic fingerprints. Ref: https://medium.com/waymo/a-note-on-our-lawsuit-against-otto-and-uber-8…

"Having our hardware and software development under one roof is incredibly valuable. Our sensors are developed in close collaboration with our software experts who specialize in AI techniques like machine learning. All of our sensors — including LiDARs, vision system, and radars — are deeply integrated with the brain of our self-driving cars and specially designed for our software. A single integrated system means that all the different parts of our self-driving technology work together seamlessly. Like a person’s own five senses, our sensors are more useful and more powerful when we put them all together." https://medium.com/waymo/introducing-waymos-suite-of-custom-built-self…

If you're on the fence as to whether Uber demonstrates hubris, we're probably too far apart to have any meaningful debate. On the "knew about these downloaded files", that's not the story Waymo presented[1]. They said an email from a supplier had attached files of a Uber lidar board that looked a lot like a Waymo proprietary board. That is what prompted a look into the logs. [1]https://medium.com/waymo/a-note-on-our-lawsuit-against-otto-and-uber-8…

Nowhere in the article does the author prove his request triggered Waymo’s lawsuit. Google's own explanation for their lawsuit is at odds author's claim. For a refresher, Google said https://medium.com/waymo/a-note-on-our-lawsuit-against-otto-and-uber-8… Recently, we [Google] received an unexpected email. One of our suppliers specializing in LiDAR components sent us an attachment (apparently inadvertently) of machine drawings of what was purported to be Uber’s LiDAR circuit board — except its design bore a striking resemblance to Waymo’s unique LiDAR design. It's clear Google's statement contradicts the author's premise. The author can claim whatever he wants but to me this reads like a baseless puff piece.

Misappropriating trade secrets and infringing on patents, as per the Waymo blogpost: https://medium.com/waymo/a-note-on-our-lawsuit-against-otto-and-uber-8…

Premapping is still required as of today, but they do collect data to try and correct those maps: https://medium.com/waymo/building-maps-for-a-self-driving-car-723b4d9c…

They have a number of blog posts that just launched on Medium: https://medium.com/waymo

Will they be the current cars, or cars with the new next-gen hardware that are substantially safer? The cars that end up driving could signal a lot to the industry. New lidar was spotted a few months ago and more recently on the Jaguar cars and the CEO said it’s an order of magnitude better: https://thelastdriverlicenseholder.com/2019/04/21/new-waymo-lidar-spot… https://medium.com/waymo/waymo-iaa-frankfurt-2019-b3cca36d8479 One would imagine this early announcement comes in reaction to their recent “valuation” cut: https://www.cnbc.com/2019/09/27/waymo-valuation-cut-40percent-by-morga… If Waymo starts driving without safety drivers en-masse, even on small fixed routes, it will signal certain takeover metrics have been hit. It will be interesting to see if Waymo uses existing cars (the ML and planners just got better) or if they use new hardware and signal a certain lidar improvement is necessary for achieving a viable takeover rate. The signal won’t be clear but should be there. And then it’s up to the rest of the industry to show how fast they can react to the change.

Rodney Brooks is misleading. He says things like, "It was actually done in Germany in 1987." but neglects to mention that the road had no other cars on it.[1] He also claims that the first autonomous coast to coast drive happened in 1995, but actually the project was autonomously controlling steering, not gas or brakes, and 150 miles of the trip were driven by humans.[2] Modern autonomous vehicles are much more impressive. They were successfully navigating urban environments 12 years ago.[3] Waymo's cars have driven over 10 million miles and disengagement rate is once every 11,000 miles.[4] We're at the point where no major breakthroughs are needed, just incremental improvements. That's what's different from earlier eras of autonomous vehicles. 1. https://en.wikipedia.org/wiki/History_of_self-driving_cars#1980s has this quote: > In the 1980s, a vision-guided Mercedes-Benz robotic van, designed by Ernst Dickmanns and his team at the Bundeswehr University Munich in Munich, Germany, achieved a speed of 39 miles per hour (63 km/h) on streets without traffic. 2. http://www.cs.cmu.edu/afs/cs/usr/tjochem/www/nhaa/nhaa_home_page.html 3. https://en.wikipedia.org/wiki/DARPA_Grand_Challenge_(2007) 4. https://medium.com/waymo/an-update-on-waymo-disengagements-in-californ…

1) Tesla does not report their numbers, though one person who went for a ridealong in the autonomy day demo reported one takeover in 20-minutes [1], so at least once every 10 miles. 2) Waymo does testing on a lot of types of roads. They reported 1.26 million miles in CA last year [2]. It's not possible to apples-to-apples compare this to Tesla's numbers because Tesla does not share their data. Musk even turned down an analyst's request the other day for details backing up his claim of autopilot safety [3]. Tesla/Musk are being unreasonable when they claim stats show their system is 40% safer or 2x safer than normal driving because they are comparing to NHTSA stats which include all classes of cars (including motorcycles), all road types (whereas AP is mainly used on divided highways), and all weather conditions (nobody activates AP in the snow, I hope, and I doubt many do in rain). [1] https://youtu.be/2BZHXh1nbWc?t=450 [2] https://medium.com/waymo/an-update-on-waymo-disengagements-in-californ… [3] https://www.youtube.com/watch?v=HqvatzjHGyk&t=47m17s

Depending upon your statistical sources, US traffic fatalities are around 1.25-1.50 per 100 million miles. [1] All forms of real-world autonomous driving across all manufacturers across the world are still somewhere below 200 million miles, conservatively estimated. [2] [3] Between the Tesla and Uber fatalities, by these rough back-of-the-envelope numbers, autonomous of various grades is still roughly 2X higher than human drivers. Maybe 1X if you squint at the numbers hard enough, but likely not orders of magnitude lower. I don't anticipate rapid legislative and insurance liability protections for autonomous systems until we see orders of magnitude differences on a per 100 million miles driven basis, and that will take time. Waymo racks up about 10,000 miles per day across about 600 vehicles spread in about 25 cities. [4] Roughly 3.6 million miles per year if they stay level, but they're anticipated to rapidly add more vehicles to their fleet. In the US alone, about 3.22 trillion miles were driven in 2016. [5] Don't know what a statistically valid sample size is based upon that (I get nonsensical results below 2000 miles, so I'm doing something stupid), though. If Waymo puts two orders of magnitude more cars out there, they'll still "only" rack up about 365 million miles per year, and not all the miles on the same version of software. [1] https://en.wikipedia.org/wiki/Transportation_safety_in_the_United_Stat… [2]…