Ride-sharing companies are embracing Waymo’s autonomous vehicles. Where’s Tesla?
Waymo’s 2024 Year in Review
Please consider That’s a Wrap! Waymo’s 2024 Year in Review
2024 has been a year of incredible growth, connection, and learning for Waymo.We couldn’t be more grateful for our riders and the trust they’ve placed in us to serve over 150,000 trips every week. To all those who’ve been with us from day one in Phoenix to our daily riders in San Francisco, trendsetters in Los Angeles, and early riders in Austin — thank you for coming on this journey with us.
We served over 4 million fully autonomous rides this year alone, bringing us to over 5 million rides total. With the Waymo Driver at the wheel, riders enjoyed over 1 million hours in their own trusted space to make the most of their time – working on the go, belting karaoke, or just sitting back to unwind. And with our all-electric fleet powered by renewable energy, Waymo riders helped avoid over 6 million kilograms of CO2 emissions.
To provide riders with more travel options, we expanded our service areas across all of our cities in 2024. We now serve nearly 500 square miles encompassing four major metropolitan areas to get people where they’re going safely. The most popular destinations in each city this year were Sky Harbor International Airport in Phoenix, The Ferry Building in SF, and The Grove shopping center in LA.
With 2024 coming to a close, we excitedly look ahead to what the new year will bring. With Phoenix, San Francisco, and Los Angeles now fully open to the public, the opportunity to provide safe and sustainable transportation for more riders has never been greater. We’re hard at work preparing to commercially launch in Austin and Atlanta on the Uber app next year, and continue to lay the groundwork for a Miami launch with fleet partner Moove in 2026. We’re also excited about our first international road trip to Tokyo next year in partnership with Nihon Kotsu and GO.
Robotaxi Revolution
The Wall Street Journal comments How Uber and Lyft Are Gearing Up for the Robotaxi Revolution
Uber Technologies UBER and Lyft LYFT gave up on big plans to develop their own driverless taxis years ago. Now, they are revamping their businesses to accommodate competitors who may have figured it out.
The ride-hailing leaders are preparing to bring driverless taxis to your door with new app features that allow customers to use their phones to open trunks and honk horns. They are building infrastructure to maintain the high-tech taxis and training human support staff to handle riders without drivers.
Both companies will have driverless cars—from Alphabet’s GOOGL Waymo and others—on their apps this year. In the coming months, riders in Austin, Texas, and Atlanta will be able to hail a Waymo through the Uber app. Lyft plans to offer May Mobility’s driverless taxis in Atlanta.
Uber and Lyft have agreed to maintain these driverless fleets. They are finding locations to store the cars, equipping them with chargers and high-speed internet, and training workers to maintain the cameras, lidar and other gadgets that driverless vehicles depend on.
Uber struck a deal with Waymo that will allow customers in Austin and Atlanta to hail the company’s driverless taxis only through the Uber app, a move that will prevent the driverless carmaker from taking market share in those cities. Waymo will continue to operate its own app in other cities.
In August, Waymos picked up close to 500,000 passengers in California, up from fewer than 20,000 a year earlier.
Consumer receipts analyzed by YipitData within Waymo’s operating zone in San Francisco found that the company had taken a 22% share in November. Lyft’s share in the area fell to 22% the same month, from 34% in August 2023. Uber’s share in the area slipped 10 percentage points to 55% over the same period.
How Much Better Is Waymo than Tesla at Self Driving?
That’s the question I asked Grok, Musk’s Artificial Intelligence (AI) application.
Grok responded …
The comparison between Waymo and Tesla’s self-driving technologies involves several nuanced aspects, including their approaches, capabilities, and operational metrics. Here’s a detailed look at how they differ:
Technology and Approach:
- Waymo uses a combination of sensors including lidar, radar, and cameras, which allows for a more comprehensive understanding of the environment. This multi-sensor approach enables Waymo vehicles to operate driverlessly in specific, pre-mapped areas. Waymo’s technology is known for its reliability in complex urban environments where it has high-definition maps and can leverage remote operators for support if needed.
- Tesla, on the other hand, primarily relies on camera-based vision technology with no lidar, focusing on a vision-only approach for its Full Self-Driving (FSD) system. This approach aims at scalability and lower hardware costs but has been criticized for inconsistent performance in varied scenarios and weather conditions.
Performance Metrics:
- Waymo has demonstrated a higher level of autonomy in real-world operations, with vehicles going thousands of miles without human intervention in geofenced areas. Their system has been noted for fewer disengagements (when a human driver must take control), with statistics showing Waymo vehicles traveling significantly between interventions compared to Tesla’s FSD.
- Tesla’s FSD is still considered a level 2 autonomy system, requiring constant driver supervision. While there are reports of Tesla FSD handling long drives with fewer interventions, these are under supervised conditions and not fully autonomous like Waymo’s operations. Tesla’s system has faced scrutiny for unexpected disengagements and safety concerns.
Scalability and Market Strategy:
- Waymo currently operates in limited geographic areas but with plans to expand. Their service model is focused on robotaxi services, initially in select cities, which might not scale as quickly as Tesla’s approach but aims for high reliability within those areas.
- Tesla touts the advantage of scaling its technology across its entire fleet of vehicles, which number in the millions, allowing for vast data collection for improving AI. However, this comes with the caveat that Tesla’s system is not yet capable of full driverless operation without supervision, unlike Waymo’s driverless taxis.
- Public Perception and User Experience:
- Posts and discussions on platforms like X suggest a contrast in user experience. Some users praise Waymo for its smooth, confident driving in urban settings, while others critique Tesla’s FSD for not matching this level of autonomy or smoothness, though Tesla’s system is noted for its potential scalability and broader application.
In summary, Waymo currently outperforms Tesla in terms of actual driverless capability within its operational areas due to its use of advanced sensor technology and strategic deployment. However, Tesla’s approach might lead to broader market penetration and potentially lower costs if they can solve the reliability and safety issues associated with their vision-only system. The “better” aspect thus depends on the context: for immediate, reliable driverless service in specific areas, Waymo leads; for widespread potential and cost-effectiveness, Tesla holds promise but has significant ground to cover.
I consider that a surprisingly good answer, and it came in seconds. I especially like the following paragraph (emphasis added):
Grok: “Waymo uses a combination of sensors including lidar, radar, and cameras, which allows for a more comprehensive understanding of the environment.”
Grok: “Tesla’s FSD is still considered a level 2 autonomy system, requiring constant driver supervision. While there are reports of Tesla FSD handling long drives with fewer interventions, these are under supervised conditions and not fully autonomous like Waymo’s operations. Tesla’s system has faced scrutiny for unexpected disengagements and safety concerns.”
Tesla’s “Full Self Driving” is a comparative joke because it is not self driving at all. A driver must be present. Waymo is level 4 autonomy. Despite decades of promises Tesla is level 2.
Musk maintains that he can train cars by accumulating data so that they can go anywhere. That will not hold up in adverse conditions.
Also, Waymo is undoubtedly gathering test data from millions of actual drives vs Tesla’s big fat zero.
Perhaps Musk will buy enough regulatory favors to give it a go. But there is more to robotaxis than just the car.
Musk cut corners to build cars cheaper. That ‘s great for cheap mass production but it isn’t great for safety.
Waymo has Uber and Lift buy-ins as well as hailing software. What does Tesla have other than theories and Musk’s eternal promises?
What About Safety?
Please note a New Swiss Re study: Waymo is safer than even the most advanced human-driven vehicles.
Today, we’re sharing our new cutting-edge research with Swiss Re, one of the world’s leading reinsurers, analyzing liability claims related to collisions from 25.3 million fully autonomous miles driven by Waymo. The study uses auto liability claims aggregate statistics as a proxy for at-fault collisions and expands on our previous research. It demonstrates that as we’ve scaled operations across Phoenix, San Francisco, Los Angeles, and Austin, the Waymo Driver significantly outperforms both the overall driving population and the latest generation of human-driven vehicles equipped with advanced driver assistance systems (ADAS).
Notably, the Waymo Driver’s safety advantages hold true even when compared to newer vehicles (2018-2021 models) equipped with modern safety technology. This includes advanced driver assistance systems (ADAS) such as automated emergency braking, forward collision warning, lane keeping assistance, and blind spot warning. When compared to this group, the Waymo Driver showed an 86% reduction in property damage claims and 90% reduction in bodily injury claims.
“Our research shows how insurance data can help evaluate autonomous vehicle safety and provide the framework needed to support widespread adoption,” said Ali Shahkarami, Global Head P&C Solutions at Swiss Re. “By analyzing a larger dataset across multiple cities, we deepened our understanding of how this technology performs in real-world conditions. These promising results help underscore the potential of this technology to create a safer future for our roads.”
Robocars Did Arrive in 2024
2024 marks the beginning of the end of chauffeur-driven taxi and limo services.
For all the taunting I received about how autonomous driving would never work, robocars did arrive in 2023 with an enormous ramp in mid-2024.
My original estimate was 2022-2024. OK I was two years late if you see it that way. But this taxi ramp-up is way faster than I expected.
The end of chauffeur-driven taxi and limo services at major airports will soon arrive.
What About Trucking?
I thought we would have point-to-point interstate self-driving trucks first, or at least at the same time.
Conceptually, hub-to-hub interstate driving is easier. I envisioned human drivers would do the last trucking miles in the cities.
I believe that vision may still the case because city driving has more perils and unknowns than well-understood interstate routes that change infrequently. However, I do not totally rule out point-to-point.
Regardless, millions or trucking jobs will vanish as I have stated.
Robo-trucks can drive 24-7 with no driver. There will be fewer accidents and lower insurance rates. No strikes.
The advantage of getting rid of the driver and ability to drive continually without mandated breaks is too cost advantageous to not happen, and quickly once it does.
The trucking start was slower than I expected, but the ramp will be faster because the cost savings are too great.
All things considered, I called this correctly. The fully autonomous nay-sayers were wrong.