Waymo bundles up for cold weather.
Robotaxis Head to Las Vegas, San Diego, and Detroit
Please note Waymo is bringing its robotaxis to Las Vegas, San Diego, and Detroit.
Today, Waymo LLC announced it’s bringing its autonomous ride-hailing service to three more cities: Las Vegas, San Diego, and Detroit. The company started driving in each city today with a mixed fleet of its Jaguar I-PACE and Zeekr RT vehicles equipped with its sixth-generation Waymo Driver.
The news comes just a few weeks after Waymo shared its plans to bring its robotaxi services to London in 2026. The company’s other international plans include Tokyo, where it had deployed test vehicles to adapt it autonomous vehicle (AV) technology to local traffic patterns and road features.
In the U.S., the Waymo Driver has already driven over 100 million fully autonomous miles on public roads and provided more than 10 million paid rides. The company said it is now driving more than 2 million fully autonomous miles and providing over a quarter of a million rides per week. The company currently operates services in Phoenix, San Francisco, Los Angeles, and Austin.
In March, Waymo announced plans to bring its robotaxis to Washington, D.C., in 2026. The district gets an average of 13.7 in. of snow a year, according to the National Weather Service.
Waymo has also shown some interest in the city of Boston. In May, it sent a small fleet of robotaxis, driven by human drivers, to map Boston’s unique driving environment.
Additionally, in August, New York City granted Waymo a permit to test a limited number of AVs, equipped with safety drivers, in parts of Manhattan and downtown Brooklyn.
The Waymo Driver uses cameras, radar, and lidar to perceive the world around it, with each sensor providing a complementary field of view that’s especially helpful in inclement weather. Its automated cleaning system — using engineered and heating elements — keeps the sensors clear so the vehicle can continue serving riders without needing to pull over.
The company said its AI can distinguish between snow, slush, ice, and a normal road surface. The Waymo Driver then uses this information to adjust its driving behavior to match the road conditions in real time, allowing the Waymo Driver to navigate based on what it sees and feels, the company said.
Where’s Tesla?
Nowhere near cold, in beta, with backup drivers.
Tesla is currently testing its robotaxi service, which uses autonomous vehicles for on-demand rides, in limited areas like Austin, Texas, with plans to expand to eight to ten metro areas by the end of 2025. The service is still in a beta phase, often with human safety drivers, and relies on the company’s Full Self-Driving (FSD) software. In the future, Tesla plans to introduce purpose-built, fully autonomous vehicles called the Cybercab, which won’t have a steering wheel or pedals.
Grok’s Take Q&A
Mish: Will FSD work without LIDAR in snow, sleet, dust storms?
Grok ….
Performance in Snow and Sleet
- Light to moderate snow: Recent versions (e.g., FSD v13.x in 2024–2025) have shown notable improvements. User reports and videos demonstrate reliable handling on snow-covered or unplowed roads, including gravel paths with 5+ inches of accumulation, following ruts/grooves, avoiding deeper snow, and maintaining traction without interventions in many cases. Traction control integrates well, and the system can infer road position even without visible lane lines.
- Heavy snow, blizzards, or whiteouts: Performance degrades sharply. Cameras often get covered in snow/slush (especially rear and side ones), leading to warnings, disengagements, or unsafe behavior like veering, accelerating too quickly, or failing to detect edges. reddit.com +2 Older videos (e.g., FSD Beta in 2023) show dangerous sliding or inability to navigate. carscoops.com In extreme cases, no sensor system (including human vision) works reliably, and FSD may hand control back or refuse to engage. brownstoneresearch.com
- Sleet (freezing rain/ice) compounds issues with camera icing and slippery surfaces, often requiring manual intervention. @JPPelletier3
Performance in Dust Storms
- Dust severely limits camera visibility, similar to heavy fog or snow. There’s limited real-world data, but reports indicate FSD would struggle in near-zero visibility (e.g., haboobs), as it can’t “see through” opaque air like radar might. @TheTrueTruth777 Elon Musk has noted LIDAR also fails here due to scatter, implying vision-only isn’t uniquely disadvantaged—but in practice, pure camera systems are blinded when light is blocked. gearmusk.com +1
Why No LIDAR Helps or Hurts
- Tesla argues humans drive with eyes only, and billions of miles of training data allow neural nets to infer depth/position reliably. brownstoneresearch.com LIDAR is called a “crutch” that’s expensive and scatters in precipitation/dust. @elonmusk
- Critics (and competitors like Waymo/Cruise) counter that LIDAR + radar provide redundancy: LIDAR for precise 3D mapping (filtered for noise in snow/rain), radar for penetration in fog/dust/snow. electrek.co +2 Waymo operates in snow/fog with these sensors, adapting speed and path in real-time.
Current Reality (as of November 2025)FSD (Supervised) is SAE Level 2—you must always supervise and be ready to intervene. @ArAIstotle
It works increasingly well in mild adverse weather but is not reliable in severe snow, sleet, or dust storms without human oversight. Improvements are rapid via over-the-air updates and fleet data, but extreme conditions remain a weak point for vision-only systems. No autonomous tech (LIDAR-equipped or not) is perfect in whiteouts—safe driving often means pulling over. thinkautonomous.ai
In short: It can work in lighter conditions (better than ever), but no, not fully or unsupervised in heavy snow/sleet/dust without risks. Tesla’s page doesn’t claim otherwise for these scenarios.
LIDAR Q&A
LIDAR is not a crutch. It is an aid. It cannot hurt.
Musk did not want to pay for LIDAR. That was a mistake because costs did not stay prohibitively high.
Mish: What is the cost of Waymo’s LIDAR per vehicle?
Grok …
Historical Context and Cost Reductions
- Early LIDAR units (e.g., Velodyne models used in prototypes) cost up to $75,000 per unit. businessinsider.com +2
- By 2017, Waymo’s in-house development (e.g., Honeycomb and Laser Bear series) reduced this by over 90%, to around $7,500 per high-end unit. arstechnica.com +2 Short-range units were likely under $5,000. tech
Current Estimates (5th and 6th Generation Hardware)Waymo vehicles use multiple custom LIDAR units (e.g., 5 in 5th-gen, 4 in 6th-gen) for redundancy and 360° coverage up to 500m. waymo.com
- Full sensor suite (cameras + LIDAR + radar):
- 5th-gen (e.g., on Jaguar I-Pace): ~$9,300–$12,700 total per vehicle (BloombergNEF and Contrary Research estimates, 2024–2025). reddit.com +1
- Older estimates for similar suites: $40–50k (pre-2023). tangramvision.com +1
- LIDAR-specific portion:
- Likely $2,000–$5,000 total across all units in recent gens, inferred from suite breakdowns and Waymo’s emphasis on “significantly reduced cost” in 6th-gen (announced 2024, with fewer LIDARs but higher performance). waymo.com +1 Per-unit costs for mass-produced equivalents (e.g., Chinese suppliers like Hesai) are now under $1,000, trending to $200–500.
Why Costs Have Dropped
Waymo’s vertical integration (in-house design/manufacturing) and scaling production have driven reductions, similar to battery price curves. businessinsider.com +1 The 6th-gen suite (13 cameras, 4 LIDAR, 6 radar) is “optimized for greater performance at a significantly reduced cost” without safety compromises. waymo.com
In robotaxi operations, even $10k+ sensor suites add ~3–5 cents/mile over a vehicle’s life (assuming 300k+ miles), making them viable for fleets. reddit.com
Waymo’s focus on redundancy (LIDAR + radar + cameras) prioritizes safety in adverse conditions over pure vision systems. businessinsider.com
China reduced the cost to under $1,000. OK tariffs will make that price impossible to get.
Current estimates are $2,00 to $5,000. Grok points out “Even $10k+ sensor suites add ~3–5 cents/mile over a vehicle’s life (assuming 300k+ miles), making them viable for fleets.”
Cost Questions
What’s the cost of all these delays trying to get FSD to work? How far behind is Tesla?
And what’s the cost of a lawsuit?
Amusing Flashback
Please recall More Absurd Predictions from Elon Musk: 1 Million Self-Driving Fleet in a Year
Q: When was that?
A: April 23, 2019
Also, “Probably two years from now we’ll make a car with no steering wheels or pedals.”
Flash Forward
July 20, 2025: Motor Trend Tests Tesla’s FSD, Tesla Flunks 3 Ways, Funny Videos
Tesla’s FSD is not ready for prime time and won’t be without LIDAR.
Please click on the above post if you have not see it. The video is hilarious.
Seeing such cars in cities of Europes still having a medieval shape would be a baest.Streets act like mazew. This is difficult without guiding software for Humans but managing the traffic at corners would be completely different than in the Us and need better driving trainning even for Humans than in square shaped streets of the Us.
Of course, there s Italia, but I think to downtown Grenoble in France or Northeast Toulon.
Sorry, Mish, but this is another one of your Waymo vs. Tesla comparisons I don’t really get.
These two companies are currently (maybe forever) situated in completely different markets. And so we should expect different (not the same) outcomes and technologies.
Waymo is selling cars that will be purchased, owned and operated by business fleets that sell many different taxi rides over an extended period of time, and must be liable for those paid consumer rides. Will any Waymo cars be bought by a regular user/customer picking up groceries and going to work daily?
Tesla is primarily (if not completely) selling cars to individual consumers that will use their car for personal use. If Tesla is the only US company making a car that can self-drive some of (or all) the time for that personal user (outside of Chinese cars not selling here), it can have a huge profit-making advantage over other US car manufacturers.
I think right now Tesla/Musk is trying to bridge the Waymo taxi/personal use car models because their current tech may eventually be able to compete in both markets. But even if that doesn’t work out, testing the tech on the road makes their current car model better and better each day, potentially adding more and more customers that want that tech personally but can’t find it elsewhere.
So again, almost a night and day comparison between the two companies.
If Waymo can get its taxis running smoothly in a winter climate like Detroit, it will be a huge advancement for the technology and the companies prospects. I have never understood Musks reticence in using Lidar.
Topic 2 which is Detroit as a city. I have had to travel there a few times this year on business and have to report that it has improved dramatically. Far cleaner ~ and the urban blight of empty homes has been extensively remediated. Dearborn remains a place that I refuse to spend time.
Once again gold is the tell on confidence in our governance and I just saw a print above $4,200. With the debt about to explode upwards it would appear that the sale on mining stocks and gold itself is over.
“China reduced the cost to under $1,000. OK tariffs will make that price impossible to get.”
Not for Chinese competitors on the world market. Which is why long-term tariffs are idiocy. The only way for Waymo to compete on the world market is to produce overseas to avoid tariffs. Too many Americans think the US is the center of the world. It’s not. Not even close. And America will become increasingly irrelevant, as the American people no longer even want to try and compete.
Googl contractors in Thailand replaces China,
TSLA and Googl (Waymo) compete with each other. FSD cost is falling. New innovation co will enter the FSD field. The competition will be fierce. They will fight with the giants, or become their contractor. The will expand the transport industry. Prices will fall. AMZN might use FSD and robots for deliveries ==> USPS deflates.
Tariffs and Obamacare cause inflation. AI cause deflation. Total ==> osc between low inflation and moderate deflation.
Elon’s cultists are as bad as Trump’s.
Had a conversation with a TSLA shareholder. Was convinced the new pay deal was good for them, because it incentivized Elon to work hard to grow the company. This person couldn’t understand Elon already has such a large slice of the company that people should fire him or sell their shares if he isn’t already 100% committed to growing the company market cap. Person couldn’t understand that a shareholder owning a large slice of the pie gets to enjoy an even bigger slice when they grow the pie, because that’s what happens when you own a percentage.
It reminds me of how quite a few regular people think no amount of money is too much for oligarchs. Always a rationalization.
“Fake it until you make it” on FSD so far. Been working for St. Elon for a long time now. But with the government behind you (ICE makers paying carbon credits, all Elon’s other government biz), why not?
I do expect TSLA to succeed, finally. Not confident it deserves its valuation though. IMO its stock depends on the new businesses it’s pursuing. But with its current market cap, that’s a lot of money to pay for startup businesses.
Not to say Tesla is only Musk but when you asked: Where’s Tesla, I immediately thought Mars, starlink-ing, having kids, opining on the future of humanity which someone involves an UNINHABITABLE Mars, getting sucked into DOGE and tossed to the curb. Sure Tesla can develop without Musk but as CEO he spends an awful lot of his physical and mental time elsewhere, something most CEO’s do NOT do.
If Musk is a data guy, and I think he is, once the costs changed on LIDAR he should consider using where needed, but, alas, pride goeth before the fall and many great thinkers want their ideas to be THE reason for success. It might be too difficult for him to change course now without impairing his ego.
Regardless I could never get ride a self-driving car as motion sickness is a real thing for me. No EV credits or robotaxi rides in my future.
Can you ride in planes or trains without getting sick?
Tesla, a company for the future where the future never comes….
Never, Ever count Elon Musk out of anything. Space X was founded in 2002 By Elon Musk. Elon & Space X are talked about whenever Space is involved now days. That and StarLink and He’s making Billions over His Lifetime with just those 2!!!
You are a moony aren’t you? Admit it, man.
My own gut feeling, is that Musk has all but given up on Tesla. It will move on, and be a business, but no longer is He chasing China. It’s their Playground for EV’s and Not Americas.
I think Elon’s True Love is for Flying Cars!! Now that’s America’s Playground! I think behind the scenes He is robustly looking at that as His next Big Thing!! He is into Space and Soaring into it already, so what’s all that hard about soaring into Earths atmosphere? Child’s Play for Musk IMO!!!
Musk is just a dumb drug addict sucking on the tit of government
Show me another Multi-Billionaire drug addict, who is inventing things not even imagined a few short years ago? Called upon by The World for assistance in Space Matters, no matter what they are. Working with the President to save Billions in wasteful fraud, and the List goes on, as it’s rather large for this Brilliant Man!!!
Um, Elon bought into Tesla, which was an active company and someone else’s invention. SpaceX and self-landing rockets was the idea of some NASA engineers who couldn’t get NASA to listen, but Elon did. Robotaxis were Google’s invention. Robots have been around for decades.
Musk isn’t an inventive genius. His genius is in finding inventive geniuses and getting funding for their ideas, while taking a lot of free equity in the invention and claiming undeserved credit. But it is his genius and it works.
Um, He was a Co-Founder and now CEO and Largest Shareholder of Both Tesla & SpaceX.
Still waiting…
P.S. You did know that Elon Worked For Free!!! For the Government .
Do you still believe in Santa Clause? All that stolen data was valueless?
What Tesla needs to do more than anything is to hire a real marketing department. Engineers design & make cars, but they’re terrible at marketing. look no further than Musk’s vanity project the cybertruck.
Just build a freaking mainstream e-truck, dude, & stop with the stainless steel panels that can stop low velocity bullets. It’s gimmick.
He went all in too fast, but did pull back, but too late. I think he has abandoned the whole idea perhaps? Time and place, but just not now?
Go long big parachutes.
OT: Will studies like these being published influence health policy or the financials of vaccine manufacturers? You will not find these studies mentioned by the MSM.
An enormous landmark study published in the International Journal of Infectious Diseases, covering every single resident in South Korea — all 51.6 million people — has delivered a striking striking suggestive of vaccine-acquired immunodeficiency syndrome (VAIDS).
This massive dataset shows a consistent dose-dependent pattern: the more COVID-19 “vaccines” a person received, the higher their risk of developing the common cold and upper-respiratory infections.
https://www.thefocalpoints.com/p/breaking-51-million-person-study
Certainly not in the United States where pharmaceutical companies are allowed to give unlimited campaign contributions to elected representatives. Though they might have an effect in first world countries.
I saw that study mentioned on a couple of the science feeds I monitor. But have not noticed anything written of it in the MSM. As is to be expected.
The same banks, hedge funds and PE firms that own the pharmas also own the media.
FSD are thinking machines. They are AI. They are mobile data centers with computers and electronics parts that think, make decisions and move people, troops, or packages…from point A to B. Highly skilled workers developed it. Highly skilled workers maintain it. New logistic centers with parts to repair to recharge will be built. FSD enhance productivity. It reduce the need for pilots, soldiers, truck drivers and cars, which are expensive cost centers doing nothing all day. Productivity reduces prices. Productivity causes deflation. Within 3/5 years data centers will be built with supercomputers, or quantum computers, that will be able to learn, think and make decisions. AI will increase efficiency. AI will cause deflation. Deflation reduces cost, increases real income.
Ai and robots doing all the work will eliminate MONEY!
Off Topic: Well, that’s not rocket science, and certainly not something Mamdani is going to make part of his socialist / communist platform. Good luck NYC!
Analysis: Mass Immigration Pushes U.S. Housing Market to ‘Breaking Point’
Good to know Trump’s immigration efforts are all for show/just a lie/failed
Or whatever point it is you’re going for here
It’s Breitbart, guaranteed to be right wing nazi-ish propaganda but it does create logical contradictions for Trumpers doesn’t it?
If millions are being deported how is housing still an issue? Didn’t we just see a post that home builders aren’t selling empty completed houses and offering huge incentives?
If millions are being deported and the cause of medical costs and insurance costs then why hasn’t it dropped one bit after deporting millions?
Lastly, if all the millionaires and billionaires and well to do are going to “flee” NYC then doesn’t that solve the housing crisis in NYC?
Ah, you’re one of those guys who throws around Nazi’isms, so we fully dilute its real meaning.
Illegals don’t buy new homes.
It’s the medical industry. If they lose revenue in a particular area, they’ll just find ways to make it up elsewhere. That’s what they do.
Yes, I sincerely hope every uber wealthy person leaves NYC. Guess what’s going to happen? They made a movie about it with a guy named Snake. Plissken.
My point is stated quite obvious in the report:
Illegals increase demand for housing which, in general, drives up the price.
In fact, they drive up demand for all sorts of things.
However, I’m not pointing the finger solely at illegals.
But they are a notable part of increased inflation over the last 4 years.
That’s what 10M+ mouths to feed & bodies to house does to inflation.
Again, this isn’t rockets science.
Unfortunately, our political elite, especially dems, won’t level with Americans.
One of the reasons you can’t afford a house is because of illegals.
Let’s use the 80/20 rule here. 80% is because of bad Fed policies & probably about half of the other 20% is due to illegals.
And wouldn’t that increase in price signal capitalists to try and meet the increased demand by building more housing to create more supply? What if, instead of immigrants, these were just more Americans, born decades ago and finally ready to own their own houses, driving up prices? Would that be an unsolvable problem too?
I don’t know about elsewhere but the raw paperwork and the huge amount of fees necessary to build housing here in CA takes years to effect.
And then the land has to be available to purchase.
The state politicians recognized this 5-10 years back and instituted new rules that make it easier to build housing within 1/2 mile of what is called a “transit corridor”. Which is now leading to ugly 4-10 story mixed residential/retail housing all along many major byways. And yet, housing and rental prices have not declined.
It’s very easy to post magic wand solutions on net forums.
Like all things, it’s a resource issue. People build on the best land first. Over decades, the best land is used up. The best land is also where people want to live, because it is closer to things people value. At some point you have to tear down the old stuff and build vertically. But that takes extreme government interference.
10m equals only 3% of the population of the US not a big deal
What Musk has to “get done” in the next 10 years to collect his trillion dollar paycheck…
FSD is the key. But Musk is poison for the company.
As of 2025, Tesla is valued at roughly $800 Billion, Space X is valued @ roughly $50 Billion & as of 2024 StarLink is valued @ roughly $8 Billion!!! So in 2024/2025 Musk is already at $858 Billion, so I guess Musk doesn’t see that as nearly a problem as you seem to…
Altogether the core profit of those organizations are $4 billion. He just has to grow it by 100 times. If he can do it he deserves it. But that’s a BIG ask. Tesla would need to become the biggest car company on the planet, and its sales are predicted to decline this quarter relative to the overall market. The Chinese are giving away their FSD products for free. Tesla currently has zero Robotaxis in operation. It’s a BIG ask.
How long before certain people in Detroit stop a Waymo by putting cones in front and behind it to rob the passengers?
And when the passengers make emergency remote contact with tech support to beg the operator to remotely drive the car through some teen standing in front of the Waymo will that operator run that teen over and risk a vehicular homicide charge or just let the hoodlums rob (rape? maim? kill?) the stuck passenger.
At least with a real Uber driver the drivers life is on the line.
Waymo has its cars in dense metro areas. It would be very difficult for anyone to attack the passengers. The passenger can also dial 911 and get help within minutes.
If you watch videos of Detroit there are run down suburban streets where over half the houses are no longer there and half the remainder are burnt and/or abandoned. Also plenty of hood rats, bimbos twerking in the streets and a police force that has advised people that they need to protect themselves.
When seconds count the police will be there in minutes (if your lucky)
And what if the passenger is carrying a weapon?
One less criminal…
1. What is stopping that sort of thing currently? Putting up barriers etc
2. How are hoodlums supposed to identify a waymo and take the action described.
3. One solution is for waymo passengers to arm themselves.
4. If it does happen frequently what is stopping police from using waymo. Blowing away a few hoodlums…
A Waymo is easy to spot. A certain make and model with nobody in the drivers seat isn’t hard to spot.
It takes time to learn a new skillset but the good rats will learn that Waymo’s are an easy target.
Most blue zoo cities have laws against having guns in cars and if you target people coming from the airport they will have no guns and plenty to steal
It has never happened even once in over a decade of operation in that bluest of blue zoos: San Francisco. A place where, if Fox News is correct and we know they would never lie or exaggerate, every inch is covered by homeless, drug-addicted zombies robbing everyone at gun point.
How long until Waymo equips its cars with machine guns to put an end to such foolishness?
For Detroit a good option
“Move out of the road. You have 30 seconds to comply.”
Waymo-209 watches the carjacker retreat to the sidewalk…and then follows after him to run him over on the sidewalk.
Back in the boardroom watching the drama unfold. … “Dick, I’m very disappointed!…”
Perfect description of Detroit. The shithole of Mi.
After it happens once, the response will be quick.
At least, it would be in China or anywhere else with a functioning government. Let’s see what happens.
It’s weird to think some people walk around with this kind of mental model of the world in their head all day. It must be exhausting. I just had a similar encounter on Reddit with some guy who stockpiles weapons because the Jan 6th crowd was a threat to him or something. Meanwhile I don’t even lock my house doors, never have actually.
It’s popular though… It’s the same impetus behind the popularity of zombie survival tv shows, etc.
I choose to use my mind more constructively than obsessing on violence porn and fear.
I live in Florida and my elderly step-father is so far to the right that he is an avid believer in global cooling (as seen on YouTube). He is convinced that liberal Northerners are going come down here in droves as NYC becomes uninhabitable due to the ice sheets. He has spent a small fortune on guns, ammo and MREs in preparation for killing all of those leftist lunatics. We don’t hang out much anymore.