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

Autonomous Car Progress

This site may earn commission on affiliate links.
Pennsylvania joins other States in allowing testing and deployment of driverless vehicles:

Pennsylvania is the latest state to allow driverless cars and trucks on the road, as the autonomous vehicle industry takes another step in its effort to prove commercial viability.

The Keystone State this month joined at least 20 other states that now explicitly allow either the testing or deployment of autonomous vehicles without a human operator. West Virginia and Oklahoma also approved laws this year.

 
  • Informative
Reactions: VanFriscia
Waymo got their CPUC driverless permit. The permit allows driverless rides to the public 24/7 throughout San Francisco and portions of Daly City, as well as in portions of the cities of Los Altos, Los Altos Hills, Mountain View, Palo Alto, and Sunnyvale. The permit does not allow Waymo to charge a fee yet. Waymo will need to apply for a separate permit before they can charge a fee.

With this authorization, Waymo may offer driverless passenger service throughout San Francisco and portions of Daly City, as well as in portions of the cities of Los Altos, Los Altos Hills, Mountain View, Palo Alto, and Sunnyvale. Waymo’s driverless test AVs may operate on public roadways with posted speed limits up to 65 miles per hour, at all times of day or night.

 
  • Informative
Reactions: Dewg
With Cruise expanding to daytime driverless for employees (for now), Waymo getting their driverless permit to offer driverless rides to the public in SF and revealing their Zeekr robotaxi, Motional announcing they are expanding driverless to LA soon, AV progress seems to be really speeding up recently.
 
Good video on Zoox perception that explains how each sensor works how they arrange the sensors to have overlap and redundancy and how they can perceive the intent of pedestrians and other vehicles etc...

 
Last edited:
  • Informative
Reactions: Jeff N
~1 hour driverless ride in Cruise AV with lots of situations.


0:00 Introduction
0:55 Swerve to avoid debris
1:18 Windy neighborhood road
2:16 Four-way stop with oncoming vehicle
2:36 Slowing to 7 mph for speed bump
3:10 A few traffic signal intersections
5:18 Right turn with pedestrian crossing
6:33 Oncoming bus
7:08 Unprotected left onto Divisadero with oncoming traffic
8:15 Window opening warning
9:22 Right lane change
11:33 Unknown slowing near on-street dining
13:42 Very steep grade
15:23 Stop sign with ambiguous precedence
19:41 Turning onto Polk Street
21:16 Destination update fails; car UI in bad state
24:52 Double stop
25:26 Driving up a few steep hills
26:52 Nudging for pedestrian
28:05 Unprotected left
28:32 Yielding to jaywalking pedestrian
31:54 Nudging for poorly parked vehicle
33:41 Turn signal for unknown reason
35:28 Chevy Bolt power meter
36:07 More turn signal confusion
37:04 Right lane change
38:46 Right lane change with traffic
39:48 Open door
44:23 Passing two double-parked vehicles
45:30 Nudging for double-parked vehicle
46:26 Conversation with another driver
47:31 Flashing red light
48:51 End of ride
 
Last edited:
  • Like
Reactions: Jeff N
Blog on Mobileye enhanced computer vision.

Some highlights:

- higher resolution cameras (8 MP instead of 1.7 MP) allow computer vision to see traffic lights, stop signs, car doors etc at greater distances.
- 120-degree field of view (instead of 52 degrees), covering a full third of the vehicle’s horizontal surroundings with a single camera.
- OCR allows computer vision to read text on signs and understand context like school zones.
- Neural Network Semantic Segmentation (NSS) – a highly advanced type of artificial intelligence that automatically labels objects in an image. NSS works on an individual-pixel level, so with more pixels comes ever-higher precision. This enables the system to better identify an array of features – including environmental elements (such as snow, rain, and mud) – to inform the driver and vehicle about the condition of the road surface
- The system can also identify emergency vehicles by their flashing lights. It can recognize gestures and postures to discern whether a person standing by the road is hailing a taxi, for example, or just talking on the phone. It can find the way through intersections without lane markings, determine if a road’s shoulder is safe to use in case of emergency, identify obstacles (such as oversized cargo and collapsible cranes) protruding from commercial vehicles, and even “remember” how you park in your driveway, enabling the vehicle to repeat the procedure automatically.
- the new EyeQ6 raises the bar even higher: our latest one-box, windshield-mountable SoC, EyeQ6 Lite boasts 450% more processing power than EyeQ4 Mid – with similar power consumption and in a 45% smaller package.

 
Moving to autonomous driving progress thread so as not to derail the other thread off-topic.

Definitely looking likely - for everyone, including even all the other self-driving companies with much more sophisticated vehicles!

We’ll see. Very hard to predict but in a very grim valley for everyone right now.

I disagree. I don't think it is a grim valley for everyone. Quite the contrary, the robotaxi era is already starting. Waymo and Cruise have real robotaxis now and are making good progress in scaling. Now, if you mean when robotaxis are everywhere, sure it will take many more years for that. But Waymo and Cruise already have real robotaxis now. I am very optimistic about robotaxis in general.
 
  • Like
Reactions: Dewg