Welcome to Tesla Motors Club
Discuss Tesla's Model S, Model 3, Model X, Model Y, Cybertruck, Roadster and More.
Register

Blog Waymo Testing Vehicles Without Human Drivers

This site may earn commission on affiliate links.
[vc_row][vc_column][vc_column_text]Waymo, the autonomous vehicle division of Alphabet, Google’s parent company, says it has been operating a fleet of autonomous vehicles in Arizona without a human behind the wheel since mid-October.

Soon, the company plans to invite regular people for rides in these fully self-driving vehicles.

The cars will be geofenced within a 100-square-mile area of the town of Chandler, a suburb of Phoenix. But, Waymo plans to expand the number of cars in the fleet and the range to an area larger than Greater London over time. The company is asking people to apply to be part of an “early rider program.”

Arizona has no restrictions against operating an autonomous vehicle without a person in the driver’s seat. California, however, requires self-driving cars to have a safety driver in the front seat.

Waymo shared the milestone in a Medium post and video, posted below.[/vc_column_text][/vc_column][/vc_row][vc_row][vc_column][vc_video link=”https://www.youtube.com/watch?v=aaOB-ErYq6Y” video_title=”1″][/vc_column][/vc_row]

 
Last edited by a moderator:
I wonder when such compagnies will start to work together with the police, how great would it be for the police if a Tesla spots and locates a stolen vehicle by recognising their numberplate without the Tesla driver even realising? Sounds to me like relatively easy job for Tesla to do. But only to catch thiefs or/and criminals, not for wrong parking, driving to fast, or things like that.
 
Boo-yah!

Tesla just got lapped in the self-driving race.


... but you wouldn't catch me owning a car that looks like that. I guess the bigger point to be made though, is people won't own cars as much, so .. does it really matter?
 
The biscuit represents fully self driving cars.
The grey cat is tesla owners.
The ginger cat is google users.
stealing-cat.gif
 
So the Ghostbustermobile can drive in astoundingly clearly marked roads at speeds under 40 mph with very little traffic. Yawn.
Come take a drive in the real world where I live in Texas where 8 sets of previously marked lanes in different places all head in different directions with all but one leading into a concrete barrier which are 2 feet from your car at all times, while driving west with the glaring sun at 70 mph with cars surrounding you on all sides. That will be full self driving and would be impressive. This is an obviously extremely well mapped out area that also has virtually brand new road markings, wide lines, and no traffic to speak of.
 
So the Ghostbustermobile can drive in astoundingly clearly marked roads at speeds under 40 mph with very little traffic. Yawn.
Come take a drive in the real world where I live in Texas where 8 sets of previously marked lanes in different places all head in different directions with all but one leading into a concrete barrier which are 2 feet from your car at all times, while driving west with the glaring sun at 70 mph with cars surrounding you on all sides. That will be full self driving and would be impressive. This is an obviously extremely well mapped out area that also has virtually brand new road markings, wide lines, and no traffic to speak of.

Damn, if you are going to *sugar* all over someones work, at least be realistic. This car uses LIDAR, which cares less about the glaring sun than I do about this post.
 
  • Funny
Reactions: mblakele
Damn, if you are going to *sugar* all over someones work, at least be realistic. This car uses LIDAR, which cares less about the glaring sun than I do about this post.

It is true that these cars use about $150,000 worth of equipment to self drive, including $70k worth of a LIDAR system. I'd still like to see the vehicle perform in something other than Mayberry like conditions. I would also be curious about the economic modelling in which that expensive of equipment is viable for a fleet of vehicles. I guess if you are talking taxis and can kill off enough jobs, it could be worth it.
 
I have it on good authority from someone who actually knows the numbers that LIDAR units are much much less expensive than the number you are stating.

You could be right. I'm no expert on this in fact a novice...got the figure from this wiki: Waymo - Wikipedia

That said, it is apparent to the eye that Waymo is putting waymo electronic equipment in their cars than anyone else by a very large margin. I believe the costs of those products are substantially more than the human assist products Tesla and other car makers are utilizing.
 
Google and Tesla's solutions are very different. Google's is at least proven to work reliably now, and for what it's worth they are starting to test in poor weather including snow.

Google have a much bigger sensor suite, including lidar. Their car builds up a detailed picture of the world around it, which you can see on the car's displays. Their use of AI is somewhat limited, they concentrate on having good sensors and algorithms to decide what to do.

Tesla have fairly minimal sensors, mostly cameras. They rely heavily on AI to interpret the images from cameras to build up a picture of things near the car. They are hoping that their AI can get good enough to match human levels of perception using cameras that aren't as good as the human eye.

Google seems to be aiming for zero accidents and extremely safe operation. As we have seen with Autopilot, Tesla is willing to accept a lower safety standard. Musk has said "as good as humans" is the minimum.

I'd say that Google's system is much more likely to be able to handle unusual situations and bad behaviour by other road users, but the trade-off is that the sensors are quite large and expensive.
 
  • Like
Reactions: cybergates