Загрузка видео...

Не удалось загрузить видео

На главную

NEWS: Waymo has introduced the Waymo World Model, "a frontier generative model built on Google DeepMind’s Genie 3 that sets a new bar for large-scale, hyper-realistic autonomous driving simulation." "By simulating the “impossible”, we proactively prepare the Waymo Driver for some of the most rare and complex scenarios—from tornadoes...

SawyerMerritt's profile picture

Sawyer Merritt

1,096,087 subscribers

133,168 просмотров • 4 месяцев назад •via X (Twitter)

Новости и политикаНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

NEWS: Waymo has released a new blog post detailing their AI strategy and how it’s allowing them to bring service to more riders faster. "Achieving demonstrably safe AI — where safety is proven, not just promised — requires a holistic approach. Beyond a smart and capable Driver, you also need a closed-loop, realistic Simulator to train and rigorously test the Driver in a myriad of challenging situations, and a sharp Critic to evaluate the Driver's performance and identify areas for improvement." Waymo says that autonomous driving isn’t just a matter of building a “smart driver,” but rather creating a full AI ecosystem centered on safety from the ground up. At the core is the Waymo Foundation Model, a unified world-model that powers all major components of Waymo’s autonomous stack (Driver, Simulator, Critic). "By using a “Think Fast/Think Slow” architecture (combining rapid sensor-fusion with deep semantic reasoning), this system enables the car to detect complex and rare road scenarios (e.g. a burning vehicle ahead), reason about them, and choose safe behavior. Waymo trains large “Teacher” AI-models for driving, simulation, and evaluation, then distills them into smaller, efficient “Student” models suitable for real-world deployment, while keeping safety validation tightly integrated. The result is a continuous “flywheel” of learning: driving data (real and simulated) generate feedback, which leads to refinements, more simulation, more data, and only when safety checks pass is new code deployed. Having already exceeded 100 million fully autonomous miles, Waymo reports a more than ten-fold reduction in severe-injury crashes compared to human drivers." Full blog post:
1:33

NEWS: Waymo has released a new blog post detailing their AI strategy and how it’s allowing them to bring service to more riders faster. "Achieving demonstrably safe AI — where safety is proven, not just promised — requires a holistic approach. Beyond a smart and capable Driver, you also need a closed-loop, realistic Simulator to train and rigorously test the Driver in a myriad of challenging situations, and a sharp Critic to evaluate the Driver's performance and identify areas for improvement." Waymo says that autonomous driving isn’t just a matter of building a “smart driver,” but rather creating a full AI ecosystem centered on safety from the ground up. At the core is the Waymo Foundation Model, a unified world-model that powers all major components of Waymo’s autonomous stack (Driver, Simulator, Critic). "By using a “Think Fast/Think Slow” architecture (combining rapid sensor-fusion with deep semantic reasoning), this system enables the car to detect complex and rare road scenarios (e.g. a burning vehicle ahead), reason about them, and choose safe behavior. Waymo trains large “Teacher” AI-models for driving, simulation, and evaluation, then distills them into smaller, efficient “Student” models suitable for real-world deployment, while keeping safety validation tightly integrated. The result is a continuous “flywheel” of learning: driving data (real and simulated) generate feedback, which leads to refinements, more simulation, more data, and only when safety checks pass is new code deployed. Having already exceeded 100 million fully autonomous miles, Waymo reports a more than ten-fold reduction in severe-injury crashes compared to human drivers." Full blog post:

Sawyer Merritt

83,618 просмотров • 6 месяцев назад

Now beginning to offer fully autonomous freeways rides in SF, LA, and PHX! Express interest in the Waymo app to be one of the first in the world to relax on freeways with no one behind the wheel. More about this and our SF Bay Area expansion at
0:46

Now beginning to offer fully autonomous freeways rides in SF, LA, and PHX! Express interest in the Waymo app to be one of the first in the world to relax on freeways with no one behind the wheel. More about this and our SF Bay Area expansion at

Waymo

433,265 просмотров • 7 месяцев назад

Earlier this year, we began testing the Waymo Driver on Phoenix freeways in rider-only mode with our employees. Here’s a glimpse of freeway driving as we keep pushing forward to safely and responsibly scale our operations.
1:01

Earlier this year, we began testing the Waymo Driver on Phoenix freeways in rider-only mode with our employees. Here’s a glimpse of freeway driving as we keep pushing forward to safely and responsibly scale our operations.

Dmitri Dolgov

190,873 просмотров • 2 лет назад

We’ve built the Waymo Driver to operate without the need for human intervention, and in order to do that sometimes, it requires additional context from our fleet response team. See their role in helping us safely scale:
0:29

We’ve built the Waymo Driver to operate without the need for human intervention, and in order to do that sometimes, it requires additional context from our fleet response team. See their role in helping us safely scale:

Waymo

54,130 просмотров • 2 лет назад

Introducing GAIA-2 🌎Generative world modeling just stepped up a gear. GAIA-2 is the latest development of Wayve’s video-generative world model tailored for driving. GAIA-2 offers richer, more realistic, and highly controllable synthetic driving scenarios, accelerating Wayve’s path to safe driver assistance and automated driving at scale. Learn more about GAIA-2 in our Blog: #GAIA2 #GAIA #EmbodiedAI
0:30

Introducing GAIA-2 🌎Generative world modeling just stepped up a gear. GAIA-2 is the latest development of Wayve’s video-generative world model tailored for driving. GAIA-2 offers richer, more realistic, and highly controllable synthetic driving scenarios, accelerating Wayve’s path to safe driver assistance and automated driving at scale. Learn more about GAIA-2 in our Blog: #GAIA2 #GAIA #EmbodiedAI

Wayve

41,626 просмотров • 1 год назад

We're bringing Waymo to more places, faster than ever. This reflects years of building foundational AI tech behind the Waymo Driver and operations that enable us to scale safely and efficiently to major U.S. and global cities.
2:03

We're bringing Waymo to more places, faster than ever. This reflects years of building foundational AI tech behind the Waymo Driver and operations that enable us to scale safely and efficiently to major U.S. and global cities.

Dmitri Dolgov

46,305 просмотров • 10 месяцев назад

I took my wife on some Tesla Robotaxi and Waymo rides. She thought the Tesla Robotaxi was smoother and more comfortable than Waymo. I think it's a combination of several things (Tesla's end-to-end neural net, orders of magnitude more human driving data than Waymo, Model Y more comfortable than Jaguar I-Pace , etc). Here's a 56-minute edited video of the rides with my wife.
56:52

I took my wife on some Tesla Robotaxi and Waymo rides. She thought the Tesla Robotaxi was smoother and more comfortable than Waymo. I think it's a combination of several things (Tesla's end-to-end neural net, orders of magnitude more human driving data than Waymo, Model Y more comfortable than Jaguar I-Pace , etc). Here's a 56-minute edited video of the rides with my wife.

Dave Lee

108,864 просмотров • 1 год назад

Ride to more places in the Bay and LA. ✨ Starting today in SF, with new areas coming to LA later this week. Download the Waymo One app to see our new service areas.
0:20

Ride to more places in the Bay and LA. ✨ Starting today in SF, with new areas coming to LA later this week. Download the Waymo One app to see our new service areas.

Waymo

142,936 просмотров • 1 год назад

One big differentiator between Waymo and Tesla? The ride model. Waymo requires partnerships and fleet control. Tesla can crowdsource its fleet, allowing owners to “opt in” like Airbnb hosts for autonomous rides. Sam Korus highlights more distinctions in "The Brainstorm."
1:07

One big differentiator between Waymo and Tesla? The ride model. Waymo requires partnerships and fleet control. Tesla can crowdsource its fleet, allowing owners to “opt in” like Airbnb hosts for autonomous rides. Sam Korus highlights more distinctions in "The Brainstorm."

ARK Invest

2,738,094 просмотров • 1 год назад

Meet some of the brilliant minds that have worked for the European Commission and the European Parliament Riding a Waymo in San Francisco and THIS is what they talk about How will Waymo comply with the AI act in 2 years from now? One actually feels sick to her stomach from driving in a Waymo and believes it poses a safety risk 🤦‍♂️ Europe is doomed
5:10

Meet some of the brilliant minds that have worked for the European Commission and the European Parliament Riding a Waymo in San Francisco and THIS is what they talk about How will Waymo comply with the AI act in 2 years from now? One actually feels sick to her stomach from driving in a Waymo and believes it poses a safety risk 🤦‍♂️ Europe is doomed

Kees Roelandschap

65,497 просмотров • 10 месяцев назад

Revving up production! ⚡ Partnering with Magna International, we've opened our new Waymo Driver integration plant in Mesa, AZ, to scale the future of autonomous mobility. See how we're building thousands of all-electric vehicles:
0:20

Revving up production! ⚡ Partnering with Magna International, we've opened our new Waymo Driver integration plant in Mesa, AZ, to scale the future of autonomous mobility. See how we're building thousands of all-electric vehicles:

Waymo

331,785 просмотров • 1 год назад

Today we are announcing Genie 3, a general purpose world model by Google DeepMind that can generate dynamic, interactive environments with a single text prompt. World models are AI that understand facets of the world (like Veo's knowledge of intuitive physics or Genie's mastery of new environments), and serve as a key stepping stone on the path to AGI. Genie 3 is our first world model to allow interaction in real-time, while also improving consistency and realism compared to Genie 2. Learn more ➡️
0:33

Today we are announcing Genie 3, a general purpose world model by Google DeepMind that can generate dynamic, interactive environments with a single text prompt. World models are AI that understand facets of the world (like Veo's knowledge of intuitive physics or Genie's mastery of new environments), and serve as a key stepping stone on the path to AGI. Genie 3 is our first world model to allow interaction in real-time, while also improving consistency and realism compared to Genie 2. Learn more ➡️

Google AI

102,524 просмотров • 10 месяцев назад

Waymo testing vehicle in LA this past Sunday. Fortunately the Waymo driver is ok, and there were no people in the vehicles it hit. But a close call with a family having just walked from the street in the path of the Waymo.
0:25

Waymo testing vehicle in LA this past Sunday. Fortunately the Waymo driver is ok, and there were no people in the vehicles it hit. But a close call with a family having just walked from the street in the path of the Waymo.

JC Christopher

150,786 просмотров • 5 месяцев назад

Prime Minister Rutte Rob Jetten took a ride in a Waymo self-driving car on the streets of Phoenix, making him the first world leader to do so. During the ride learn more about the development and safety of autonomous vehicles in the Unites States.
0:20

Prime Minister Rutte Rob Jetten took a ride in a Waymo self-driving car on the streets of Phoenix, making him the first world leader to do so. During the ride learn more about the development and safety of autonomous vehicles in the Unites States.

Theo Peters

75,187 просмотров • 2 лет назад

Our latest research findings in collaboration with Swiss Re, one of the largest reinsurers in the world, are clear: In 3.8M rider-only miles, the Waymo Driver significantly reduced bodily injury & property damage claims in comparison to the human baseline.
0:34

Our latest research findings in collaboration with Swiss Re, one of the largest reinsurers in the world, are clear: In 3.8M rider-only miles, the Waymo Driver significantly reduced bodily injury & property damage claims in comparison to the human baseline.

Waymo

15,783 просмотров • 2 лет назад

XPENG is thrilled to introduce X-World, our controllable multi-view generative world model powered by video diffusion technology. Pushing the boundaries of smart mobility, X-World delivers real-time response and continuous multi-view generation to simulate complex driving environments. Xianming Liu, Head of XPENG’s General AI Center, emphasizes: "Beyond generation, X-World serves as the scalable infrastructure critical for training and validating the next leap in autonomous driving." $XPEV
1:36

XPENG is thrilled to introduce X-World, our controllable multi-view generative world model powered by video diffusion technology. Pushing the boundaries of smart mobility, X-World delivers real-time response and continuous multi-view generation to simulate complex driving environments. Xianming Liu, Head of XPENG’s General AI Center, emphasizes: "Beyond generation, X-World serves as the scalable infrastructure critical for training and validating the next leap in autonomous driving." $XPEV

XPENG

4,070,681 просмотров • 2 месяцев назад

Today we're announcing #GAIA1: a 9B parameter world model, trained on 4,700 hours of driving data, able to simulate complex and diverse driving scenes from video, text and action inputs. This model is 480x larger than the preview we shared earlier this year and the results are incredible. These videos are entirely synthetically generated by Wayve's generative AI, GAIA-1. But there is more here than just generating videos, GAIA is an entire world model. A world model allows us to simulate the future, conditioned on video, text and action inputs, which can be leveraged for making informed decisions when driving. Why is this game-changing for autonomous driving? 1. Safety. One limitation with AI systems like today's Large Language Models is that they are autoregressive, next-word prediction algorithms, but aren't necessarily aware of the implications of their decisions. A world model allows us to give our AI the capability to be aware of its decisions, by simulating the future, which is important for self-driving safety. 2. Synthetic training data. I believe synthetic training data is the future for AI, because it is safer, cheaper, and infinitely scalable. GAIA-1 unlocks unprecedented realism and diversity of synthetic data for self-driving. 3. Long-tail robustness. One of the biggest challenges for self-driving is long-tail robustness: dealing with the enormous magnitude of edge cases we see on the road. An advantage of generative AI is its incredible ability to recombine experiences in new ways. This is exciting for self-driving as it means we can learn from two edge case scenarios, and combine them to become a corner case. For example, we can experience driving in fog, and experience of jay-walking pedestrians, and GAIA can learn from these experiences to understand how to generate a fog+jay walking scenario. Check out many more videos in our blog or further technical details in our paper: Or come chat with our team who are at the International Conference on Computer Vision (#ICCV2023) this week in Paris in Booth 32 Jamie Shotton
0:41

Today we're announcing #GAIA1: a 9B parameter world model, trained on 4,700 hours of driving data, able to simulate complex and diverse driving scenes from video, text and action inputs. This model is 480x larger than the preview we shared earlier this year and the results are incredible. These videos are entirely synthetically generated by Wayve's generative AI, GAIA-1. But there is more here than just generating videos, GAIA is an entire world model. A world model allows us to simulate the future, conditioned on video, text and action inputs, which can be leveraged for making informed decisions when driving. Why is this game-changing for autonomous driving? 1. Safety. One limitation with AI systems like today's Large Language Models is that they are autoregressive, next-word prediction algorithms, but aren't necessarily aware of the implications of their decisions. A world model allows us to give our AI the capability to be aware of its decisions, by simulating the future, which is important for self-driving safety. 2. Synthetic training data. I believe synthetic training data is the future for AI, because it is safer, cheaper, and infinitely scalable. GAIA-1 unlocks unprecedented realism and diversity of synthetic data for self-driving. 3. Long-tail robustness. One of the biggest challenges for self-driving is long-tail robustness: dealing with the enormous magnitude of edge cases we see on the road. An advantage of generative AI is its incredible ability to recombine experiences in new ways. This is exciting for self-driving as it means we can learn from two edge case scenarios, and combine them to become a corner case. For example, we can experience driving in fog, and experience of jay-walking pedestrians, and GAIA can learn from these experiences to understand how to generate a fog+jay walking scenario. Check out many more videos in our blog or further technical details in our paper: Or come chat with our team who are at the International Conference on Computer Vision (#ICCV2023) this week in Paris in Booth 32 Jamie Shotton

Alex Kendall

631,844 просмотров • 2 лет назад

Our first episode of AI in Motion just dropped. 🚙 In this episode, Google DeepMind’s Carolina Parada discusses the future of robots and how they interact with the physical world. Watch the full episode:
0:54

Our first episode of AI in Motion just dropped. 🚙 In this episode, Google DeepMind’s Carolina Parada discusses the future of robots and how they interact with the physical world. Watch the full episode:

Waymo

55,548 просмотров • 7 месяцев назад

Day 3. Finished 5 Tesla Robotaxi rides, 4 Waymo rides, and 1 Uber ride. (See 39-minute edited video below.) Uber is in a tough situation. Classic innovators dilemma. Autonomous ride-hailing clearly is the future, but if Uber invites Waymo then that's working against their human drivers which will hurt Uber's recruiting ability (which they need to keep density especially in suburban areas). But if they don't welcome Waymo, then Uber is toast because people want cheaper/autonomous ride-hailing. Also, if Uber welcomes Waymo and Waymo cars increase then Waymo can just bypass Uber with their own Waymo app. Uber's only "hope" would be if multiple autonomous driving companies come online soon and Uber becomes the ride-hailing marketplace for them. But I think this is unlikely. Autonomous driving is just a really hard problem to solve, and with data and network effects. I think it's a winner-takes-most market. We'll see. But the more I take Tesla's Robotaxi, the more I think it's smoother and better than Waymo. And the more I take Waymo, the more I get pessimistic about Uber's long-term future.
39:29

Day 3. Finished 5 Tesla Robotaxi rides, 4 Waymo rides, and 1 Uber ride. (See 39-minute edited video below.) Uber is in a tough situation. Classic innovators dilemma. Autonomous ride-hailing clearly is the future, but if Uber invites Waymo then that's working against their human drivers which will hurt Uber's recruiting ability (which they need to keep density especially in suburban areas). But if they don't welcome Waymo, then Uber is toast because people want cheaper/autonomous ride-hailing. Also, if Uber welcomes Waymo and Waymo cars increase then Waymo can just bypass Uber with their own Waymo app. Uber's only "hope" would be if multiple autonomous driving companies come online soon and Uber becomes the ride-hailing marketplace for them. But I think this is unlikely. Autonomous driving is just a really hard problem to solve, and with data and network effects. I think it's a winner-takes-most market. We'll see. But the more I take Tesla's Robotaxi, the more I think it's smoother and better than Waymo. And the more I take Waymo, the more I get pessimistic about Uber's long-term future.

Dave Lee

593,309 просмотров • 1 год назад

Our friends Waymo have simulated billions of miles of driving, across countless types of scenarios and weather conditions – from harsh sun to intense snow. ❄️ By learning from those experiences, in addition to real-world driving, Waymo’s AI is ready for any rare, complex events. Hear the deep dive with Hannah Fry and Waymo's Distinguished Engineer Vincent Vanhoucke, on our podcast ↓ Timecodes 00:00 Intro 01:02 Ride around town 03:48 The driverless car problem 08:43 Sensors 13:00 3D model of the world 16:42 Closed loop problem 22:51 Multimodal models 29:31 Tokenizing 34:39 Human drivers 43:51 Safety 48:41 London and the future 52:44 Outro
53:44

Our friends Waymo have simulated billions of miles of driving, across countless types of scenarios and weather conditions – from harsh sun to intense snow. ❄️ By learning from those experiences, in addition to real-world driving, Waymo’s AI is ready for any rare, complex events. Hear the deep dive with Hannah Fry and Waymo's Distinguished Engineer Vincent Vanhoucke, on our podcast ↓ Timecodes 00:00 Intro 01:02 Ride around town 03:48 The driverless car problem 08:43 Sensors 13:00 3D model of the world 16:42 Closed loop problem 22:51 Multimodal models 29:31 Tokenizing 34:39 Human drivers 43:51 Safety 48:41 London and the future 52:44 Outro

Google DeepMind

54,916 просмотров • 7 месяцев назад