Waymo, the driverless ride-hailing arm of Google parent company Alphabet, has now launched a new AI research model for its self-driving operations.
In a pair of press releases on its approach to AI and its new end-to-end multimodal model for autonomous driving, dubbed EMMA, Waymo has shared details about its plans for the AI research model going forward. The company says it is still using the EMMA model in research stages, rather than in operational vehicles, and the approach comes as an alternative that looks a lot like Tesla’s Full Self-Driving (FSD) and other end-to-end model approaches.
“EMMA is research that demonstrates the power and relevance of multimodal models for autonomous driving,” said Drago Anguelov, VP and Head of Research at Waymo. “We are excited to continue exploring how multimodal methods and components can contribute towards building an even more generalizable and adaptable driving stack.”
Waymo says the EMMA model uses real-world knowledge based on its Gemini language model, while the end-to-end approach is expected to eventually let autonomous vehicles operate directly from sensor data and real-time driving scenarios. The company has also highlighted its use of Large Language Models (LLMs) and Vision-Language Models (VLMs), calling its architecture the Waymo Foundation Model.
Hear the company’s executive detail the Waymo research and AI program more below.
EMMA research and criticisms
In the announcement press release about EMMA, Waymo lays out the following as key aspects of the research program:
- End-to-End Learning: EMMA processes raw camera inputs and textual data to generate various driving outputs including planner trajectories, perception objects, and road graph elements.
- Unified Language Space: EMMA maximizes Gemini’s world knowledge by representing non-sensor inputs and outputs as natural language text.
- Chain-of-Thought Reasoning: EMMA uses chain-of-thought reasoning to enhance its decision-making process, improving end-to-end planning performance by 6.7% and providing interpretable rationale for its driving decisions.
“The problem we’re trying to solve is how to build autonomous agents that navigate in the real world,” says Srikanth Thirumalai, Waymo VP of Engineering. “This goes far beyond what many AI companies out there are trying to do.”
Still, some have cast doubt on the large-scale end-to-end model, saying that it may be too risky to utilize generative AI models without including significant safeguards.
“It’s bandwagoning around something that sounds impressive but is not a solution,” said Sterling Anderson, Aurora Innovation’s Chief Product Officer, in a statement to Automotive News.
Mobileye CTO Shai Shalev-Shwartz called end-to-end approaches “a huge risk,” especially regarding the verification of decision-making process for vehicles operating on the model. It’s also worth noting that Waymo is currently only researching the approach, and it doesn’t currently have any plans to make it commercially available.
The news comes after Waymo recently closed on a $5.6 billion funding round, effectively bringing the company’s valuation up past $45 billion. The company is also working on its next generation of self-driving vehicles based on the Hyundai Ioniq 5, built at a new factory in Georgia.
What are your thoughts? Let me know at zach@teslarati.com, find me on X at @zacharyvisconti, or send us tips at tips@teslarati.com.
Need accessories for your Tesla? Check out the Teslarati Marketplace:
News
Tesla Robotaxi rollout proves that Elon Musk still delivers, even if it’s late
Tesla is also still the company that makes the impossible feel late.

It took a long time, but Tesla has finally successfully rolled out its dedicated Robotaxi service in Austin this weekend. The initial rollout only involved a small fleet of cars operating in a small geofenced area in Texas, but it is still significant.
It does, if any, prove that Elon Musk is still capable of delivering on his promises, even if they are late. Tesla is also still the company that makes the impossible feel late.
Finally, a Rollout
Elon Musk has been predicting a Robotaxi rollout for years, so much so that even avid Tesla supporters have grown quite wary of his constant predictions. After a while, Elon Musk himself admitted that he has become the boy who cried FSD, though he still maintained that self-driving was really just around the corner.
This past weekend, Musk’s predictions finally came true. Actual paying customers used Tesla’s dedicated Robotaxi service for a small flat fee of $4.20 per ride. Elon Musk seemed quite happy with the Robotaxi’s initial launch, as evidenced by his congratulatory message to the Tesla AI team on X.
No More Tesla Vision Debates
One thing that is evident in Tesla’s initial Robotaxi rollout in Austin was the fact that the debate surrounding Tesla’s vision-only approach is completely gone now. With actual Robotaxis operating around Austin, there are no more questions about whether cars can navigate city streets on their own using only AI and cameras. They can, and safely too, at least based on Tesla’s initial fleet of Robotaxis.
The Beauty of Normalcy
The Robotaxi rides from Tesla owners who were fortunate enough to experience the first driverless rides from the EV maker’s fleet were quite uneventful. Comments on social media platforms such as X observed that the Robotaxis operated safely and cautiously, and their driving was actually smoother than some human drivers.
That may not sound very exciting at all, but that’s the beauty of it. Tesla’s Robotaxi service is designed to look and feel natural to people. And so far, it appears that Tesla is accomplishing this with its Robotaxi rollout.
Elon Musk
Tesla officially launches Robotaxi service with no driver
Tesla launches its driverless Robotaxi in Austin, marking the first time the company has offered its ride-hailing service anywhere in the world.

Tesla has officially launched its Robotaxi service platform with no driver in Austin, Texas. This is the first time Tesla has allowed driverless Robotaxis to pick up members of the public and take them around via the ride-sharing service the company has been developing for several years.
Teslarati had a first-hand look at the launch of the Robotaxi service in Austin, as we are part of the Early Access group, which is a limited group of people that will be able to hail a driverless Model Y in the geofenced area in Texas.
The Robotaxi platform is currently geofenced in a small portion of South Austin. It is roughly thirty minutes from end to end, and Tesla’s strategy is prioritizing safety through a number of safeguards that are implemented in this early program.
There is a fixed price of just $4.20 for any ride, regardless of duration, at this time. This will not always be the case, however. When a wider customer base is allowed to hail Robotaxis, ride fares will vary on things like travel distance, length of trip, and potentially time of day.
Here’s one of the first videos of Tesla Robotaxi ride
🎥: @BLKMDL3 https://t.co/LbVLoLtFGQ pic.twitter.com/PUQIqCRLQo
— TESLARATI (@Teslarati) June 22, 2025
The first rides kicked off at around 2 p.m. local time in Austin. They are confined to the back row of the Model Y, while a Tesla safety monitor sits in the passenger seat. Passengers will have their personal media and streaming settings available to them as the car will sync with their driver profiles.
Rides are requested through a Robotaxi addition on the regular Tesla iOS app:
🚨 Here’s our FIRST LOOK at the Tesla Robotaxi app! pic.twitter.com/kuEqP4n1SS
— TESLARATI (@Teslarati) June 22, 2025
The safety monitor is only there to ensure things go smoothly with each ride. They do not have pedals or a steering wheel on their side. The car is doing everything during these Robotaxi rides.
The big takeaway from Robotaxi’s launch is that Tesla will begin generating additional revenue through this new stream. As concerns over demand and annual growth rate continue to take focus from doubters, Tesla’s continuous rollout of the Robotaxi fleet will expand potential revenue opportunities, potentially creating billions upon trillions of dollars in value.
This is something Tesla permabulls like Cathie Wood of ARK Invest and Dan Ives of Wedbush have talked about for years: the launch of a driverless Robotaxi fleet that generates new income streams for Tesla.
Elon Musk
First Look at Tesla’s Robotaxi App: features, design, and more
Tesla is using a Robotaxi section of its normal smartphone application to enable access to driverless vehicles roaming around Austin.

Tesla has officially launched the Robotaxi platform to a limited number of people, giving them the ability to ask for a ride from a driverless Model Y in Austin, Texas. But how do you hail a ride?
Through the Tesla Robotaxi app, which officially launched on June 22 as the company initiated the first rides for non-employees, people can request rides from driverless cars that are traveling around Austin. Teslarati gained access to the app as we are members of the Early Access Rider program.
There are only a very limited number of vehicles operating within the fleet currently, as Tesla has said the number is between 10 and 20 vehicles.
Tesla is using a Robotaxi section of its iOS smartphone app for the launch, confirming what the company said prior to the program’s maiden voyage: there would not be a separate app for the Robotaxi.
First Look at the Robotaxi App
The Tesla Robotaxi app, similar to the official Tesla App, features a simple interface that should be familiar to anyone who has used a ride-sharing app in the past. Downloading the app brings users to a sign-in page, which features a Tesla Model Y Robotaxi as a header image. Users can then log in or create an account to access the service.

A Clean, Simple UI
Upon logging in, users are presented with a clean user interface that allows them to select a destination and pickup point. Upon booking, users are provided with a real-time update on when their Robotaxi will arrive. Users could also select some settings for their upcoming ride, such as their preferred temperature in the cabin.
Smart Suggestions
If there is one evident thing about Tesla’s Robotaxi App, it is the fact that it is smart and designed to make driverless ride sharing services feel as normal as possible. While waiting for their ride, customers are presented with a number of tips that should help them understand their robotaxi better.
These include tips on how to use the Model Y’s door handles, as well as information about the vehicle’s light signals. The app also includes smart suggestions on destinations that riders can visit using their Robotaxi. These include cafes, restaurants, parks, shopping centers, and other pertinent locations.
Cybercab Theme
Another thing that is evident with the Robotaxi App is its Cybercab-inspired color theme. This is evident from the login page, which already features the golden hues of the dedicated two-seater autonomous car. The golden Cybercab color theme is used to great effect inside the app itself as well.
No Tips, at Least for Now
As observed by Tesla owner-enthusiast @BLKMDL3, Tesla is not accepting anything more than the service’s flat $4.20 rate per ride for now. If customers wish to leave a tip for the service, they would be presented with a page featuring Tesla’s hedgehog mascot saying “Just Kidding.”
Tips will likely be an option in the future, but for this stage of the Robotaxi rollout, it appears that the service really will follow a flat rate system.
-
News2 weeks ago
I took a Tesla Cybertruck weekend Demo Drive – Here’s what I learned
-
Elon Musk2 weeks ago
Tesla tops Cathie Wood’s stock picks, predicts $2,600 surge
-
News2 weeks ago
First Tesla driverless robotaxi spotted in the wild in Austin, TX
-
Elon Musk2 weeks ago
X account with 184 followers inadvertently saves US space program amid Musk-Trump row
-
Elon Musk2 weeks ago
Tesla sues former Optimus engineer for stealing trade secrets
-
Elon Musk2 weeks ago
Tesla CEO Elon Musk reveals new details about Robotaxi rollout
-
News1 week ago
SpaceX produces its 10 millionth Starlink kit
-
News1 week ago
Tesla Robotaxi just got a big benefit from the U.S. government