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.
Interesting graph that shows that lidar is coming to more cheaper EVs. The y axis is the price of the car, not the price of the lidar.

GFqxqVKWIAASOQj
 
It's still to be determined whether or not LIDAR is superior to vision.

That's a false argument. Lidar has some advantages over vision and some disadvantages over vision too. Lidar is used as a compliment to vision, not as a replacement to vision. All self-driving systems rely on vision. But some systems will add a front lidar as a back-up, primarily for collision avoidance. The idea is that if your vision fails to detect an object, you have lidar as a back-up that will detect the object and therefore, it will greatly increase the reliability of your collision avoidance.
 
Wonder how Hesai being added to the U.S. "Chinese Military Companies" list will impact this for the US. IIRC they are one of the cheapest LiDAR suppliers and in both Cruise and Waymo vehicles.
Double post, but wanted to follow up on this after learning a bit more.

It seems like Hesai is mostly in L4 platforms, with L2 having other suppliers. So this may not impact consumer vehicles much, if at all. Highlighted the L4 companies and removed speculation from the quote. Also of note that I was wrong about Waymo using their LiDAR arrays as well.

Hesai is the dominant LiDAR provider for the L4 robotaxi market today, serving major global players like Zoox, Aurora, Nuro, Baidu, Cruise, Aurora, Apollo, DiDi, Pony.ai, and AutoX.

The L2/L3 market is different and accelerating, with many dominant players like Innovusion, Valeo, Innoviz and Cepton.


They have also stated they will challenge the placement on the U.S. "Chinese Military Companies" list (who wouldn't).

 
  • Like
Reactions: SidetrackedSue
Shashua interview on autonomous vehicles:

Shashua talked with The Associated Press about the next steps toward autonomous vehicles. The interview has been edited for length and clarity.

Q: With problems at Cruise and recalls of Tesla’s partially automated driving systems, what do you see as the future of autonomous vehicles?

A: When you talk about autonomous vehicles, what immediately comes to mind is Waymo, Cruise, robotaxis. But the story is much more nuanced. It really opens up how the future of the car industry is going to look. It’s not just robotaxis. I would frame it as three stories.

The first one is about safety. Today you have a front-facing camera, sometimes the front-facing radar. There are functions that enable accident avoidance. You can take safety to a much higher degree by having multiple cameras around the car and provide a much higher level of safety. An accident would be very rare.

The second story is to add more redundant sensors like a front-facing lidar (laser), like imaging radars, and start enabling an eyes-off (the road) system so it’s hands-free, eyes-off (the road). You are allowed legally not to pay attention and not to be responsible for driving on certain roads. It could start from highways and then add secondary roads. This is a value proposition of productivity, of buying back time. If you are driving from San Francisco to Los Angeles, 90% of the time you are on interstate highways. You kind of relax and legally do something else, like work on your smartphone.

Then comes this third story. This is the robotaxi where there’s no driver, and we are utilizing the car to a much higher level and enable moving people like Uber and Lyft at a much more efficient, economical state because you don’t have a driver.

Q: When do you see a lot of fully autonomous vehicles on the roads?

A: Mobileye’s SuperVision, which is now on about 200,000 vehicles in China and will start to expand to Europe and the US this year, has 11 cameras around the car and provides a hands-free but eyes-on system. The second story of an eyes-off system on highways is already in the works. Mobileye announced that we have a global Western OEM (original equipment manufacturer). We call the system Chauffeur. Add a front-facing lidar and imaging radars and nine car models to be launched in 2026.

The third story: if you look at the success of Waymo, its challenge is not technological. It’s more about how to scale and build a business. Deployment of these kinds of robotaxis is slower than originally expected five years ago. But it is something that is really, really happening. Mobileye is working with Volkswagen on the ID. Buzz (van) to start deploying thousands of such vehicles in 2026.

Q: Will Mobileye be responsible legally for the eyes-off system, or is the automaker?

A: If a driver works on a smartphone and there is an accident, you cannot come to the driver and say, “You are responsible, because I allowed you to do something else.” So this means that the bar in terms of the performance of the system, we call this mean time between failure, should be very high, much higher than human statistics. It’s a system of liabilities that is handled between the supplier and the automaker.

Q: What do you think of Tesla’s Autopilot and “Full Self-Driving” now, and what impact are those systems having on public perception of automated driving?

A: Tesla’s technical capabilities are very high. The question of whether this kind of system powered by only cameras can eventually be an eyes-off. This is where we part ways. We believe that we need additional sensors for redundancy. It’s not just a matter of improving the algorithms, adding more computing. You need to create redundancies, from a sensor point of view and from the computing point of view.

 
From the current GM Super Cruise page. Presented only as an FYI. Their latest announcement will apparently change the list a bit, though I wonder how much of the list is ultimately legal disclaimer stuff. For example, "During difficult or uncertain driving conditions". Who defines that?

When not to use Super Cruise
These are some of the situations when Super Cruise should not be activated:
  • When you're not on a compatible road
  • During difficult or uncertain driving conditions
  • When lane markings are poor or visibility is limited
  • In a tunnel or construction zone
  • In slippery or other adverse conditions, including rain, sleet, fog, ice or snow
  • On a road shoulder or service drive
  • When towing a trailer, unless equipped with Super Cruise trailering capability
  • On a freeway or highway exit lane
 
There’s a map of supported roads. Site Maintenanc
Looks like a few rural two lane paved roads are supported here in San Diego county.
I see some high speed two lane roads that I am familiar with in Texas. Obviously, the system is not available where those roads go through towns, but there are some curious gaps along stretches tha have no traffic control devices and would seem like they would be acceptable.

It is hit or miss though with most rural highways not included.
 
Wayve adding language as an input to their E2E model:

Language is a powerful tool to interact with machines.Adding language can create more efficient training and support the explainability of end-to-end AI driving systems. That's why at Wayve we are integrating language as a new data modality in building AI models for automated driving. Read more
@AVImagazine https://autonomousvehicleinternational.com/features/feature-how-large-language-models-llms-are-coming-for-self-driving-cars.html


Here is a chart that shows the input to the LLM. I wonder if "language instructions" means that you could give a voice command to tell the self-driving car what to do, like "engage autonomous mode" to activate the self-driving or "turn left at next traffic light" of you want the self-driving to take a different route?

DPb9TPS.png
 
  • Like
Reactions: WyoDude