正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

🌍 Physical AI, Large Geospatial Models, and OVRMaps LLMs understand language. But the next evolution of AI is about machines that can move, see, and operate in the physical world. This is Physical AI, and it’s already happening. 🧵👇🏼

Over the Reality 🌐

91,932 subscribers

100,941 次观看 • 1 年前 •via X (Twitter)

科学技术新闻政治教育

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Physical AI is taking on tougher industrial work. 🦾 From development to deployment, Noble Machines is building general-purpose robots with NVIDIA Isaac GR00T, Jetson, and ADLINK Technology edge AI platforms to help bring physical AI into demanding industrial environments. Read the story 📖

Physical AI is taking on tougher industrial work. 🦾 From development to deployment, Noble Machines is building general-purpose robots with NVIDIA Isaac GR00T, Jetson, and ADLINK Technology edge AI platforms to help bring physical AI into demanding industrial environments. Read the story 📖

NVIDIA Robotics

17,011 次观看 • 1 个月前

Physical AI is taking on tougher industrial work. 🦾 From development to deployment, Noble Machines is building general-purpose robots with NVIDIA Isaac GR00T, Jetson, and ADLINK Technology edge AI platforms to help bring physical AI into demanding industrial environments. Read the story 📖

Physical AI is taking on tougher industrial work. 🦾 From development to deployment, Noble Machines is building general-purpose robots with NVIDIA Isaac GR00T, Jetson, and ADLINK Technology edge AI platforms to help bring physical AI into demanding industrial environments. Read the story 📖

NVIDIA Robotics

24,088 次观看 • 24 天前

This is how AI is eliminating physical jobs. This autonomous cleaner already eliminated at least 1. It will be so fast, so brutal and so wide sweep of physical labor replacement with humanoid robots.

This is how AI is eliminating physical jobs. This autonomous cleaner already eliminated at least 1. It will be so fast, so brutal and so wide sweep of physical labor replacement with humanoid robots.

Furkan Gözükara

11,655 次观看 • 2 个月前

Europe's industries are building towards an autonomous future. 🌍 Join Rev Lebaredian, VP of Physical AI Simulation, at #NVIDIAGTC Berlin for a special address exploring how open models and simulation are advancing physical AI, from robotics to autonomous vehicles. Add the session to your calendar 👉

Europe's industries are building towards an autonomous future. 🌍 Join Rev Lebaredian, VP of Physical AI Simulation, at #NVIDIAGTC Berlin for a special address exploring how open models and simulation are advancing physical AI, from robotics to autonomous vehicles. Add the session to your calendar 👉

NVIDIA Omniverse

12,609 次观看 • 10 天前

AI IS NO LONGER JUST WRITING CODE IT iS STARTING TO MOVE THINGS IN THE REAL WORLD. Someone just built a pizza delivery system where the drone does the driving No delivery car No traffic No driver sitting behind the wheel Just: -> Order comes in -> Drone picks up the pizza -> Flies directly to the destination -> Delivers it -> Returns And this is where the AI story gets interesting For years, the AI boom was mostly digital: > Chatbots > Coding agents > Image generation > AI music > AI video But the next phase is different AI is getting a body The same technology stack that started with models and GPUs is now moving into the physical world NVIDIA built the compute layer Researchers built the models Companies like Zoox are building autonomous vehicles And now we're seeing AI powered machines actually move through the real world The crazy part? We designed entire cities around the assumption that humans have to physically drive everything AI doesn't have that limitation Why send a pizza through 5 km of traffic when a machine can simply fly over it? The AI boom isn't just about replacing human work It's about removing constraints humans had to design around The next big AI companies might not live inside your browser They might be flying above your house Bookmark this so you wont miss the next delivery

AI IS NO LONGER JUST WRITING CODE IT iS STARTING TO MOVE THINGS IN THE REAL WORLD. Someone just built a pizza delivery system where the drone does the driving No delivery car No traffic No driver sitting behind the wheel Just: -> Order comes in -> Drone picks up the pizza -> Flies directly to the destination -> Delivers it -> Returns And this is where the AI story gets interesting For years, the AI boom was mostly digital: > Chatbots > Coding agents > Image generation > AI music > AI video But the next phase is different AI is getting a body The same technology stack that started with models and GPUs is now moving into the physical world NVIDIA built the compute layer Researchers built the models Companies like Zoox are building autonomous vehicles And now we're seeing AI powered machines actually move through the real world The crazy part? We designed entire cities around the assumption that humans have to physically drive everything AI doesn't have that limitation Why send a pizza through 5 km of traffic when a machine can simply fly over it? The AI boom isn't just about replacing human work It's about removing constraints humans had to design around The next big AI companies might not live inside your browser They might be flying above your house Bookmark this so you wont miss the next delivery

0xSlyth

14,149 次观看 • 1 个月前

The future of #AI is physical. 🦾 Read how #NVIDIACosmos and #OpenUSD are progressing #PhysicalAI for robotics and autonomous vehicles. ➡️

The future of #AI is physical. 🦾 Read how #NVIDIACosmos and #OpenUSD are progressing #PhysicalAI for robotics and autonomous vehicles. ➡️

NVIDIA Omniverse

17,093 次观看 • 1 年前

How can we responsibly deploy agentic AI robots in real-world environments? As we close the gap between AI reasoning and physical action, developing a new safety framework is key to advancing helpful robots. 🤖

How can we responsibly deploy agentic AI robots in real-world environments? As we close the gap between AI reasoning and physical action, developing a new safety framework is key to advancing helpful robots. 🤖

Google DeepMind

47,887 次观看 • 1 年前

Industrial digital twins are helping shape the future of physical AI in manufacturing.🏭 At #NVIDIAGTC Berlin, hear from the leaders bringing simulation, agentic AI, robotics, and autonomous systems from concept to the factory floor. Don't miss: 👉 Building Europe’s Industrial Future with NVIDIA’s Open Physical AI Platform 👉 Automation Meets Autonomy: Europe’s Next Era of Robotics - Agile Robots, Dexory, Wandelbots 👉 Building the Automotive Physical AI Playbook: Factory Robotics and Autonomous Vehicles - Mercedes-Benz 🔗

Industrial digital twins are helping shape the future of physical AI in manufacturing.🏭 At #NVIDIAGTC Berlin, hear from the leaders bringing simulation, agentic AI, robotics, and autonomous systems from concept to the factory floor. Don't miss: 👉 Building Europe’s Industrial Future with NVIDIA’s Open Physical AI Platform 👉 Automation Meets Autonomy: Europe’s Next Era of Robotics - Agile Robots, Dexory, Wandelbots 👉 Building the Automotive Physical AI Playbook: Factory Robotics and Autonomous Vehicles - Mercedes-Benz 🔗

NVIDIA Omniverse

10,361 次观看 • 24 天前

NVIDIA is advancing graphics and simulation with agentic and physical AI at #SIGGRAPH2026. From open models to real-time simulation, AI and graphics breakthroughs are transforming media, content creation, and robotics. Read the latest announcements. 👇

NVIDIA is advancing graphics and simulation with agentic and physical AI at #SIGGRAPH2026. From open models to real-time simulation, AI and graphics breakthroughs are transforming media, content creation, and robotics. Read the latest announcements. 👇

NVIDIA

111,135 次观看 • 2 个月前

Most of the data needed to scale Physical AI models is private. At Lightwheel, we think that's worth changing. So this week we released the first 10,000 hours of EgoSuite-Open100K — an open egocentric human dataset for Physical AI. 100,000 hours coming in total. Learn more here:

Most of the data needed to scale Physical AI models is private. At Lightwheel, we think that's worth changing. So this week we released the first 10,000 hours of EgoSuite-Open100K — an open egocentric human dataset for Physical AI. 100,000 hours coming in total. Learn more here:

Jonathan Stephens

10,578 次观看 • 1 个月前

MY PROPOSAL: The Library Of Galactica ALL LARGE AI COMPANIES FORM: A PHYSICAL BOOK AND MEDIA NATIONAL PUBLIC LIBRARY. Testing a logo.

Brian Roemmele

78,097 次观看 • 1 个月前

🌱 AI-powered farming, without chemicals. @Aigenio’s solar-powered robots use vision AI to identify and remove weeds at the plant level—helping farmers reduce herbicides and adopt more sustainable practices. Powered by simulation, real-world data and edge AI, this is what physical AI looks like in agriculture. 📖

🌱 AI-powered farming, without chemicals. @Aigenio’s solar-powered robots use vision AI to identify and remove weeds at the plant level—helping farmers reduce herbicides and adopt more sustainable practices. Powered by simulation, real-world data and edge AI, this is what physical AI looks like in agriculture. 📖

NVIDIA Robotics

114,986 次观看 • 5 个月前

Word's out: @StoryProtocol uses Automata's DCAP Attestation to anchor the age of AI with hardware trust Story's work on Confidential Data Rails and its AI-native stack, now secured by the physical integrity of the hardware. Verifiable machines for AI:

Word's out: @StoryProtocol uses Automata's DCAP Attestation to anchor the age of AI with hardware trust Story's work on Confidential Data Rails and its AI-native stack, now secured by the physical integrity of the hardware. Verifiable machines for AI:

Automata Network

12,290 次观看 • 6 个月前

🚨 MACHINES MAY SOON SEE THE WORLD LIKE HUMANS A US company has unveiled what it calls the world’s first “native color lidar” system giving machines the ability to perceive depth, distance, and color simultaneously. Unlike traditional lidar systems that need separate cameras, this new technology captures full 3D color information directly at the point of detection. In simple terms: Machines may soon understand the world more like human vision instead of just measuring shapes and distance. Why this matters: This could dramatically improve: • self-driving cars • robotics • drones • factory automation • AI navigation • autonomous machines The system can reportedly process over 10 million points every second and detect objects nearly 1,640 feet away. Researchers say this could become one of the key technologies powering the next generation of “Physical AI” where machines don’t just calculate the world… They visually understand it. We may be watching the birth of machine perception in real time. Follow for more future technology and AI discoveries.

🚨 MACHINES MAY SOON SEE THE WORLD LIKE HUMANS A US company has unveiled what it calls the world’s first “native color lidar” system giving machines the ability to perceive depth, distance, and color simultaneously. Unlike traditional lidar systems that need separate cameras, this new technology captures full 3D color information directly at the point of detection. In simple terms: Machines may soon understand the world more like human vision instead of just measuring shapes and distance. Why this matters: This could dramatically improve: • self-driving cars • robotics • drones • factory automation • AI navigation • autonomous machines The system can reportedly process over 10 million points every second and detect objects nearly 1,640 feet away. Researchers say this could become one of the key technologies powering the next generation of “Physical AI” where machines don’t just calculate the world… They visually understand it. We may be watching the birth of machine perception in real time. Follow for more future technology and AI discoveries.

TheNewPhysics

26,128 次观看 • 4 个月前

doodles AI beta. next week. we're building the tools for a new era of dynamic world-building. it starts with an image model that reimagines anything and everything through the doodles lens. this is the first iteration of many. as the product evolves, we'll introduce the ability to turn your generations into physical objects. video with sound and dialogue, realtime AR, and gaming are all on the roadmap. doodles AI aligns us with the speed and scale of the AI industry at large. our colourful world can now be plugged into new tech as it unfolds. create with us.

doodles AI beta. next week. we're building the tools for a new era of dynamic world-building. it starts with an image model that reimagines anything and everything through the doodles lens. this is the first iteration of many. as the product evolves, we'll introduce the ability to turn your generations into physical objects. video with sound and dialogue, realtime AR, and gaming are all on the roadmap. doodles AI aligns us with the speed and scale of the AI industry at large. our colourful world can now be plugged into new tech as it unfolds. create with us.

burnt toast

61,243 次观看 • 6 个月前

Video understanding is the next frontier, but not all videos are alike. Models now reason over youtube clips and feature films, but what about the everyday spaces we—and our future AI assistants—navigate and experience? Introducing Thinking in Space, our latest study exploring how multimodal LLMs see, remember and recall spaces. 🧵[1/n]

Video understanding is the next frontier, but not all videos are alike. Models now reason over youtube clips and feature films, but what about the everyday spaces we—and our future AI assistants—navigate and experience? Introducing Thinking in Space, our latest study exploring how multimodal LLMs see, remember and recall spaces. 🧵[1/n]

Saining Xie

211,236 次观看 • 1 年前

1/ NVIDIA just open-sourced Cosmos 3 at GTC Taipei! It's the first fully open "omnimodel" for physical AI - one model that understands the real world, predicts what happens next, and generates the actions a robot should take. Weights, code, datasets. All open. And this is really big. Lets dig into everything: 🧵

1/ NVIDIA just open-sourced Cosmos 3 at GTC Taipei! It's the first fully open "omnimodel" for physical AI - one model that understands the real world, predicts what happens next, and generates the actions a robot should take. Weights, code, datasets. All open. And this is really big. Lets dig into everything: 🧵

Chubby♨️

18,088 次观看 • 3 个月前

We just filed a Patent for a private Visual Positioning System (VPS) that runs inside Trusted Execution Environments (TEEs) As we step into the era of Physical AI, this could redefine how smart glasses, robots, and AR apps understand space, without sacrificing your privacy. Here’s why that matters 🧵👇🏼

We just filed a Patent for a private Visual Positioning System (VPS) that runs inside Trusted Execution Environments (TEEs) As we step into the era of Physical AI, this could redefine how smart glasses, robots, and AR apps understand space, without sacrificing your privacy. Here’s why that matters 🧵👇🏼

Over the Reality 🌐

108,524 次观看 • 1 年前

Vangrid × Teneo Protocol Teneo grids the internet. Vangrid grids the physical world. Teneo turns civilian devices into nodes feeding the agent economy: public, social, live data. Vangrid turns civilian pockets into nodes capturing the physical world: 3D spatial ground truth for embodied AI. Digital + Physical. Two decentralized networks. One backbone for autonomous agents. First move: joint expeditions. We point the swarm at the physical world. The grid is inevitable.

Vangrid × Teneo Protocol Teneo grids the internet. Vangrid grids the physical world. Teneo turns civilian devices into nodes feeding the agent economy: public, social, live data. Vangrid turns civilian pockets into nodes capturing the physical world: 3D spatial ground truth for embodied AI. Digital + Physical. Two decentralized networks. One backbone for autonomous agents. First move: joint expeditions. We point the swarm at the physical world. The grid is inevitable.

Vangrid

47,572 次观看 • 2 个月前

Robots are getting smarter, but how can their hardware match that growth? New Microsoft Research findings show that moving AI inference beyond the robot can improve task success, boost efficiency, and support more advanced physical AI workloads.

Robots are getting smarter, but how can their hardware match that growth? New Microsoft Research findings show that moving AI inference beyond the robot can improve task success, boost efficiency, and support more advanced physical AI workloads.

Microsoft Research

19,605 次观看 • 3 天前