Загрузка видео...

Не удалось загрузить видео

На главную

Most robotics AI models suffer from the "stop-and-think" problem. They take a static picture, pause to reason, execute an action, and repeat. In the real world, that latency causes spills, collisions, and failed tasks. Google DeepMind just launched Gemini Robotics ER 2: an embodied reasoning model that thinks and...

kweinmeister's profile picture

Karl Weinmeister

2,156 subscribers

28,365 просмотров • 1 месяц назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 1

Фото профиля Karl Weinmeister
Karl Weinmeister1 месяц назад

Read the technical announcement and safety report on the Google DeepMind Blog 👉 P.S. All starter code, tool-orchestration examples, and interactive Jupyter notebooks are available open-source on GitHub:

Похожие видео

Gemini Robotics ER 2 is our most capable embodied reasoning model designed for physical AI 🤖 Built as a high-level brain for robotics, the model connects directly to the Gemini Live API. It processes continuous video streams to track progress, call tools, search the web, and command an action model in real time. Upgrades for developers include: + Enhanced progress tracking + Real-time mid-execution failure detection + Multi-robot collaboration + Advanced safety instruction following
2:31

Gemini Robotics ER 2 is our most capable embodied reasoning model designed for physical AI 🤖 Built as a high-level brain for robotics, the model connects directly to the Gemini Live API. It processes continuous video streams to track progress, call tools, search the web, and command an action model in real time. Upgrades for developers include: + Enhanced progress tracking + Real-time mid-execution failure detection + Multi-robot collaboration + Advanced safety instruction following

Google AI Developers

21,498 просмотров • 1 месяц назад

For decades, we’ve dreamed of robots that can seamlessly step into our world and lend a hand. Today, we take a major stride toward making that dream a reality: Introducing Gemini Robotics 2 from Google DeepMind, the intelligence layer powering the next generation of truly adaptable robots. This major advance unlocks intelligent whole-body control, advanced dexterity, and even multi-robot collaboration 🤯. Ok but... how does a robot actually "think"? Real-world tasks take time and planning. To manage that complexity, our new embodied reasoning model, Gemini Robotics ER 2, acts as the robot’s high-level brain, enhancing the robot’s capabilities to: — Observe the environment — Reason about the actions needed to complete the task — Coordinate with the vision-language-action model to carry out actions — Track progress until the job is done This setup allows robots to execute complex multi-step workflows, self-correct if a step fails, and adapt to completely novel situations. Learn more about Gemini Robotics ER 2 (and our two other brand new models) here:
2:16

For decades, we’ve dreamed of robots that can seamlessly step into our world and lend a hand. Today, we take a major stride toward making that dream a reality: Introducing Gemini Robotics 2 from Google DeepMind, the intelligence layer powering the next generation of truly adaptable robots. This major advance unlocks intelligent whole-body control, advanced dexterity, and even multi-robot collaboration 🤯. Ok but... how does a robot actually "think"? Real-world tasks take time and planning. To manage that complexity, our new embodied reasoning model, Gemini Robotics ER 2, acts as the robot’s high-level brain, enhancing the robot’s capabilities to: — Observe the environment — Reason about the actions needed to complete the task — Coordinate with the vision-language-action model to carry out actions — Track progress until the job is done This setup allows robots to execute complex multi-step workflows, self-correct if a step fails, and adapt to completely novel situations. Learn more about Gemini Robotics ER 2 (and our two other brand new models) here:

Google AI

784,050 просмотров • 1 месяц назад

Sundar Pichai on the robotics opportunity: ⦿ He's impressed by recent humanoid progress - so much so that he sometimes has to look closely to tell if a robot video is real or fake. ⦿ Google initially moved too early into the application layer, but now sees the combination of AI and robotics as the “sweet spot.” ⦿ He believes we’re 2–3 years away from a “magical moment” in robotics. ⦿ Google is working on playing a role similar to Android in robotics - one of its internal bets is already focused on supporting robotics manufacturers. ⦿ Gemini robotics models will work very well - how to productize them is still an open question at the company.
2:43

Sundar Pichai on the robotics opportunity: ⦿ He's impressed by recent humanoid progress - so much so that he sometimes has to look closely to tell if a robot video is real or fake. ⦿ Google initially moved too early into the application layer, but now sees the combination of AI and robotics as the “sweet spot.” ⦿ He believes we’re 2–3 years away from a “magical moment” in robotics. ⦿ Google is working on playing a role similar to Android in robotics - one of its internal bets is already focused on supporting robotics manufacturers. ⦿ Gemini robotics models will work very well - how to productize them is still an open question at the company.

The Humanoid Hub

87,088 просмотров • 1 год назад

My conversation with Kanishka Rao, who went from working on particle physics at CERN to driving robotics at Google DeepMind. We get into the Gemini Robotics 2 release, trending training recipes in the industry, physical AGI, world models, and more. 1:00 Intro 1:47 Does AI's pace feel crazy? 4:04 From particle physics PHD to robotics 6:03 Speech recognition's deep learning moment 8:43 Whole-body humanoid control 10:47 The trash-bag tying demo 13:07 The robotics data pyramid 14:13 Transferring skills across robots 16:30 How does Motion Transfer work 16:56 Why a separate reasoning model 19:02 Can distillation work in robotics? 20:02 The ASIMOV safety benchmark 22:47 VLAs vs world models 25:10 The missing tactile sensing piece 27:48 How far to physical AGI? 30:07 Fundamental breakthrough needed? 31:53 World models for evaluation 33:45 Will the model layer commoditize? 35:11 Humanoid as a form factor
38:27

My conversation with Kanishka Rao, who went from working on particle physics at CERN to driving robotics at Google DeepMind. We get into the Gemini Robotics 2 release, trending training recipes in the industry, physical AGI, world models, and more. 1:00 Intro 1:47 Does AI's pace feel crazy? 4:04 From particle physics PHD to robotics 6:03 Speech recognition's deep learning moment 8:43 Whole-body humanoid control 10:47 The trash-bag tying demo 13:07 The robotics data pyramid 14:13 Transferring skills across robots 16:30 How does Motion Transfer work 16:56 Why a separate reasoning model 19:02 Can distillation work in robotics? 20:02 The ASIMOV safety benchmark 22:47 VLAs vs world models 25:10 The missing tactile sensing piece 27:48 How far to physical AGI? 30:07 Fundamental breakthrough needed? 31:53 World models for evaluation 33:45 Will the model layer commoditize? 35:11 Humanoid as a form factor

The Humanoid Hub

22,037 просмотров • 1 месяц назад

Not the flashiest demos, but what’s under the hood represents a foundational shift for general-purpose robotics. World models are the next-gen foundation of Physical AI, not the VLM backbones found in typical VLAs. DreamZero is a 14B-parameter World Action Model (WAM) by NVIDIA that treats robotics as a joint video-and-action prediction task. Unlike traditional Vision-Language-Action (VLA) models that map images directly to motor commands, DreamZero leverages a pretrained video diffusion backbone to predict future world states and actions simultaneously. - achieves 2× better zero-shot generalization to unseen tasks and environments compared to state-of-the-art VLAs. - learns effectively from heterogeneous, non-repetitive data (500 hours), breaking the need for thousands of repeated demonstrations. - adapts to new robot embodiments with just 30 minutes of play data. - enables 7Hz closed-loop control via system optimizations and "DreamZero-Flash," making high-capacity diffusion models viable for real-time use.
1:01

Not the flashiest demos, but what’s under the hood represents a foundational shift for general-purpose robotics. World models are the next-gen foundation of Physical AI, not the VLM backbones found in typical VLAs. DreamZero is a 14B-parameter World Action Model (WAM) by NVIDIA that treats robotics as a joint video-and-action prediction task. Unlike traditional Vision-Language-Action (VLA) models that map images directly to motor commands, DreamZero leverages a pretrained video diffusion backbone to predict future world states and actions simultaneously. - achieves 2× better zero-shot generalization to unseen tasks and environments compared to state-of-the-art VLAs. - learns effectively from heterogeneous, non-repetitive data (500 hours), breaking the need for thousands of repeated demonstrations. - adapts to new robot embodiments with just 30 minutes of play data. - enables 7Hz closed-loop control via system optimizations and "DreamZero-Flash," making high-capacity diffusion models viable for real-time use.

The Humanoid Hub

35,204 просмотров • 7 месяцев назад

China-based TARS Robotics demonstrated a humanoid robot performing two-handed hand embroidery during a public showcase on December 22, marking a notable step in fine motor control for humanoid systems. The robot threaded a needle and stitched a logo using both hands with sub-millimeter accuracy, working with soft, flexible materials that are difficult for traditional industrial robots to handle due to deformation and variability. According to the company, this capability is enabled by a closed-loop "Data-Al-Physics" system that connects real-world data collection, embodied Al models, and physical execution, reducing the gap between simulation and real deployment. The models are said to be open source when released. Founded in February 2025, TARS Robotics has moved quickly from research to live demonstrations and has raised over $240 million in early funding from the Chinese government, reflecting growing interest in general-purpose humanoid robots for precision and dexterous tasks.
0:58

China-based TARS Robotics demonstrated a humanoid robot performing two-handed hand embroidery during a public showcase on December 22, marking a notable step in fine motor control for humanoid systems. The robot threaded a needle and stitched a logo using both hands with sub-millimeter accuracy, working with soft, flexible materials that are difficult for traditional industrial robots to handle due to deformation and variability. According to the company, this capability is enabled by a closed-loop "Data-Al-Physics" system that connects real-world data collection, embodied Al models, and physical execution, reducing the gap between simulation and real deployment. The models are said to be open source when released. Founded in February 2025, TARS Robotics has moved quickly from research to live demonstrations and has raised over $240 million in early funding from the Chinese government, reflecting growing interest in general-purpose humanoid robots for precision and dexterous tasks.

Brian Roemmele

82,611 просмотров • 8 месяцев назад

My conversation with Sergey Levine (Sergey Levine). Sergey is the co-founder of Physical Intelligence -- a company building foundation models that can control any robot to do any task in any environment. The company's thesis is that generality is more scalable than specialization, meaning that a model trained across many different robots and tasks will ultimately outperform any system built to do one thing well (eg, just wash dishes). Sergey is a researcher by background, but I think you will appreciate how practical and commercially grounded this conversation is. We discuss: - Why changing a diaper will be the last task a robot masters - The simulation v. real-world data debate - How multimodal LLMs give robots common sense - Moravec's Paradox + Robot Olympics - Why robots can do long-horizon tasks now - A realistic timeline for robots in our homes I should note that I am an investor in Physical Intelligence -- I made the investment because I believe it is one of the most important companies tackling the problem of robotics. Enjoy! Timestamps: 0:00 Intro 2:39 Defining Physical Intelligence 5:19 The Challenge of Building General Models 6:34 The Stakes and Future of General Purpose Robotics 8:15 Pros and Cons of Humanoid Robots 10:12 Historical Milestones in Robotics Research 15:31 Combining Generative AI and Deep RL 21:24 Moravec's Paradox 25:33 Kitchen Robots 29:30 Simulation vs. Real-World Data 30:48 The Robot Olympics 36:31 The Physiological Reality of Embodiment 38:56 Controversies in the Robotics Community 44:18 What Makes a Great Researcher 48:27 How Businesses Should Prepare for Robotics 54:09 Tracking Progress Through Research Papers 57:02 The Next Step: Mid-Level Reasoning 1:02:00 The Kindest Thing
1:15:15

My conversation with Sergey Levine (Sergey Levine). Sergey is the co-founder of Physical Intelligence -- a company building foundation models that can control any robot to do any task in any environment. The company's thesis is that generality is more scalable than specialization, meaning that a model trained across many different robots and tasks will ultimately outperform any system built to do one thing well (eg, just wash dishes). Sergey is a researcher by background, but I think you will appreciate how practical and commercially grounded this conversation is. We discuss: - Why changing a diaper will be the last task a robot masters - The simulation v. real-world data debate - How multimodal LLMs give robots common sense - Moravec's Paradox + Robot Olympics - Why robots can do long-horizon tasks now - A realistic timeline for robots in our homes I should note that I am an investor in Physical Intelligence -- I made the investment because I believe it is one of the most important companies tackling the problem of robotics. Enjoy! Timestamps: 0:00 Intro 2:39 Defining Physical Intelligence 5:19 The Challenge of Building General Models 6:34 The Stakes and Future of General Purpose Robotics 8:15 Pros and Cons of Humanoid Robots 10:12 Historical Milestones in Robotics Research 15:31 Combining Generative AI and Deep RL 21:24 Moravec's Paradox 25:33 Kitchen Robots 29:30 Simulation vs. Real-World Data 30:48 The Robot Olympics 36:31 The Physiological Reality of Embodiment 38:56 Controversies in the Robotics Community 44:18 What Makes a Great Researcher 48:27 How Businesses Should Prepare for Robotics 54:09 Tracking Progress Through Research Papers 57:02 The Next Step: Mid-Level Reasoning 1:02:00 The Kindest Thing

Patrick OShaughnessy

134,397 просмотров • 5 месяцев назад

Physical Intelligence (Physical Intelligence) is building a foundation model that can control any robot to do any task — what the team describes as the GPT moment for robotics. The company's cross-embodiment approach trains across many different robot platforms, and recent results show tasks being performed zero-shot that last year required hundreds of hours of data collection. In this episode of the Lightcone Podcast , co-founder Quan Vuong (Quan Vuong) sat down with Garry Tan, Jared Friedman, Diana, and Harj Taggar to talk about why robotics is finally ready for its scaling moment, how PI runs its models in the cloud rather than on-device, and the playbook for what Quan sees as a Cambrian explosion of vertical robotics companies. 00:00 — Robotics just got cheaper 00:41 — The GPT moment for robotics 02:24 — Why robots didn’t work before 05:30 — The breakthrough that changed everything 09:12 — The data problem 13:33 — Robots learning without data 15:05 — Robots folding laundry (for real) 22:18 — From engineering problem → ops problem 29:12 — The startup playbook 38:46 — Thousands of robotics startups are coming
49:26

Physical Intelligence (Physical Intelligence) is building a foundation model that can control any robot to do any task — what the team describes as the GPT moment for robotics. The company's cross-embodiment approach trains across many different robot platforms, and recent results show tasks being performed zero-shot that last year required hundreds of hours of data collection. In this episode of the Lightcone Podcast , co-founder Quan Vuong (Quan Vuong) sat down with Garry Tan, Jared Friedman, Diana, and Harj Taggar to talk about why robotics is finally ready for its scaling moment, how PI runs its models in the cloud rather than on-device, and the playbook for what Quan sees as a Cambrian explosion of vertical robotics companies. 00:00 — Robotics just got cheaper 00:41 — The GPT moment for robotics 02:24 — Why robots didn’t work before 05:30 — The breakthrough that changed everything 09:12 — The data problem 13:33 — Robots learning without data 15:05 — Robots folding laundry (for real) 22:18 — From engineering problem → ops problem 29:12 — The startup playbook 38:46 — Thousands of robotics startups are coming

Y Combinator

117,681 просмотров • 5 месяцев назад

Excited to share what we've been cooking Google DeepMind to bring Gemini into the physical world! 🦾🧠 Here is an uncut interaction of the Gemini Robotics VLA helping me clean up my desk. 🔊 Interacting with a robot through voice is the most surreal experience, and parallels the giddy excitement I had playing with early LLMs that is hard to put in words. You've got to try it to believe it! Over the next few days, we'll be sharing more such interactions that go beyond shiny demos and expose raw capabilities of our models. Stay tuned for more raw videos! Tech Report: Blog: YouTube Playlist:
2:43

Excited to share what we've been cooking Google DeepMind to bring Gemini into the physical world! 🦾🧠 Here is an uncut interaction of the Gemini Robotics VLA helping me clean up my desk. 🔊 Interacting with a robot through voice is the most surreal experience, and parallels the giddy excitement I had playing with early LLMs that is hard to put in words. You've got to try it to believe it! Over the next few days, we'll be sharing more such interactions that go beyond shiny demos and expose raw capabilities of our models. Stay tuned for more raw videos! Tech Report: Blog: YouTube Playlist:

Dhruv Shah

68,795 просмотров • 1 год назад

SITUATION EXPLAINED: A new generation of AI labs are betting that world models are the path to general intelligence that can interact with the real world. We had General Intuition CEO Pim de Witte on MTS to explain what world models are, and why intuitively world models offer a clearer path towards general intelligence than LLMs. For humans, text is a technology for compressing information about the unfolding, three-dimensional world around us and communicating it to other people. When LLMs reason about the world, they do so by reconstructing the world through text. World models work by modeling the three-dimensional world at the architecture level and then allowing agents to interact with that world. Unlike an LLM, which understands space and time through text, world models perform spatial and temporal reasoning natively. General Intuition hopes to use world models to create embodied AI—machines that can reason and act in the real world. But other companies are also pushing the frontier in this space. Odyssey ML today announced a multi-agent world model, Agora-1. Their launch video shows four participants interacting with a real-time world model simulation of GoldenEye, a first-person shooter for the N64. A playable preview of the GoldenEye simulation is available on their site.
1:31

SITUATION EXPLAINED: A new generation of AI labs are betting that world models are the path to general intelligence that can interact with the real world. We had General Intuition CEO Pim de Witte on MTS to explain what world models are, and why intuitively world models offer a clearer path towards general intelligence than LLMs. For humans, text is a technology for compressing information about the unfolding, three-dimensional world around us and communicating it to other people. When LLMs reason about the world, they do so by reconstructing the world through text. World models work by modeling the three-dimensional world at the architecture level and then allowing agents to interact with that world. Unlike an LLM, which understands space and time through text, world models perform spatial and temporal reasoning natively. General Intuition hopes to use world models to create embodied AI—machines that can reason and act in the real world. But other companies are also pushing the frontier in this space. Odyssey ML today announced a multi-agent world model, Agora-1. Their launch video shows four participants interacting with a real-time world model simulation of GoldenEye, a first-person shooter for the N64. A playable preview of the GoldenEye simulation is available on their site.

MTS

11,676 просмотров • 4 месяцев назад

JUST IN: Dyna Robotics just published one of the most important research papers in robotics this year. It could fundamentally change how robot foundation models are trained. A scaling law that transfers from human video to robot performance. Dyna-2 is out and it's 🔥 Here's what that means in plain terms. Dyna-2 was pre-trained on ONE MILLION hours of egocentric human video, 170 years of continuous human experience, cooking, folding, assembling, cleaning. And as that human data scaled, robot performance improved. Predictably. Monotonically. Across 39 tasks on two different robot embodiments the model had never seen. → 1,000 hours pre-training → 20% normalised task performance → 10,000 hours → 28% → 100,000 hours → 45% → 1,000,000 hours → 53% Human video exists at effectively unlimited scale. Every cook, every factory worker, every craftsperson wearing a camera is generating training data for future robots. But the finding that stunned even the researchers, world modeling is what makes the transfer work. A model trained to predict future video AND actions massively outperforms one trained on actions alone. Video is the new scaling axis for robotics. One more jaw-dropping data point. 13 minutes of teleoperation data was enough to fine-tune Dyna-2 to open a bottle cap using two five-fingered robot hands. The robots are coming, and they're learning from us directly :D Read more here: Congrats Jason Ma and team! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
1:35

JUST IN: Dyna Robotics just published one of the most important research papers in robotics this year. It could fundamentally change how robot foundation models are trained. A scaling law that transfers from human video to robot performance. Dyna-2 is out and it's 🔥 Here's what that means in plain terms. Dyna-2 was pre-trained on ONE MILLION hours of egocentric human video, 170 years of continuous human experience, cooking, folding, assembling, cleaning. And as that human data scaled, robot performance improved. Predictably. Monotonically. Across 39 tasks on two different robot embodiments the model had never seen. → 1,000 hours pre-training → 20% normalised task performance → 10,000 hours → 28% → 100,000 hours → 45% → 1,000,000 hours → 53% Human video exists at effectively unlimited scale. Every cook, every factory worker, every craftsperson wearing a camera is generating training data for future robots. But the finding that stunned even the researchers, world modeling is what makes the transfer work. A model trained to predict future video AND actions massively outperforms one trained on actions alone. Video is the new scaling axis for robotics. One more jaw-dropping data point. 13 minutes of teleoperation data was enough to fine-tune Dyna-2 to open a bottle cap using two five-fingered robot hands. The robots are coming, and they're learning from us directly :D Read more here: Congrats Jason Ma and team! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

23,576 просмотров • 1 месяц назад

Introducing our most advanced Gemini Audio models yet 🗣 Gemini 3.8 Live and 3.8 Live Extended Thinking let you speak, collaborate, and execute tasks seamlessly, meaning conversing with AI just got a lot more natural. So, what’s the difference between these two models? Let’s break it down: — Gemini 3.8 Live is built for scale, speed, and cost efficiency. It can handle mid-sentence interruptions, transitions across 97 languages on the fly, and understands visual context. Figure out how to fix a broken bike chain, or deal with a leaky pipe just by pointing your camera at the problem area in Search Live for step-by-step audio instructions. — Gemini 3.8 Live Extended Thinking goes one step further to bring increased intelligence to your most complex tasks. It reasons and speaks in parallel, even narrating its progress as it works. This lets it handle multi-step, behind-the-scenes projects, like planning an event, without ever losing the conversational flow. Watch how Gemini 3.8 Live combines real-time video and voice inputs in Search Live to tackle hands-on DIY plumbing tasks step by step 👇
1:17

Introducing our most advanced Gemini Audio models yet 🗣 Gemini 3.8 Live and 3.8 Live Extended Thinking let you speak, collaborate, and execute tasks seamlessly, meaning conversing with AI just got a lot more natural. So, what’s the difference between these two models? Let’s break it down: — Gemini 3.8 Live is built for scale, speed, and cost efficiency. It can handle mid-sentence interruptions, transitions across 97 languages on the fly, and understands visual context. Figure out how to fix a broken bike chain, or deal with a leaky pipe just by pointing your camera at the problem area in Search Live for step-by-step audio instructions. — Gemini 3.8 Live Extended Thinking goes one step further to bring increased intelligence to your most complex tasks. It reasons and speaks in parallel, even narrating its progress as it works. This lets it handle multi-step, behind-the-scenes projects, like planning an event, without ever losing the conversational flow. Watch how Gemini 3.8 Live combines real-time video and voice inputs in Search Live to tackle hands-on DIY plumbing tasks step by step 👇

Google AI

228,607 просмотров • 2 дней назад

Better data for robot hands! 🤲🏼 Embodied reasoning is the bottleneck now. It’s the data we are missing. Specifically, understanding what the robot's hands are doing throughout a task. Perceptron AI new Egocentric offering tracks both hands through an entire video instead of guessing from sampled frames. That matters because a lot happens between frames. Hand positions shift. Contacts change. The robot adjusts grip. You miss all that if you're sampling. 0.280 semantic end-to-end F1 score on WGO-Bench vs 0.158 from the best pipelines built on Gemini Robotics-ER 1.6. Training a robot to manipulate objects requires understanding every moment of hand-object interaction. If your training data has gaps: missing frames, missed contacts, unclear hand positions, the policy learns from incomplete information. You end up with robots that work in demos but fail in real tasks. Continuous hand tracking gives you the full picture. The policy learns from cleaner, more complete data. That compounds into better real-world performance. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:25

Better data for robot hands! 🤲🏼 Embodied reasoning is the bottleneck now. It’s the data we are missing. Specifically, understanding what the robot's hands are doing throughout a task. Perceptron AI new Egocentric offering tracks both hands through an entire video instead of guessing from sampled frames. That matters because a lot happens between frames. Hand positions shift. Contacts change. The robot adjusts grip. You miss all that if you're sampling. 0.280 semantic end-to-end F1 score on WGO-Bench vs 0.158 from the best pipelines built on Gemini Robotics-ER 1.6. Training a robot to manipulate objects requires understanding every moment of hand-object interaction. If your training data has gaps: missing frames, missed contacts, unclear hand positions, the policy learns from incomplete information. You end up with robots that work in demos but fail in real tasks. Continuous hand tracking gives you the full picture. The policy learns from cleaner, more complete data. That compounds into better real-world performance. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

18,434 просмотров • 2 месяцев назад

Boston Dynamics just gave its robot dog a brain that reasons about the physical world. Google DeepMind's Gemini Robotics model is now running inside Spot, the four-legged robot already deployed at thousands of facilities worldwide. The upgrade centers on something called embodied reasoning. Basically, instead of following rigid instructions, Spot now interprets what it sees and makes decisions on its own. One standout example: Spot can now look at a pressure gauge, zoom in on the needle, calculate the intervals between tick marks, and deliver an accurate reading. All autonomously. The model also introduces: > Multi-view reasoning, combining feeds from multiple cameras to understand its environment even when objects are blocked from one angle > Built-in success detection, so Spot knows when it's failed and decides whether to retry or move on That last part is a key requirement for true autonomy. Most companies building AI-powered robots are still stuck in the demo phase. Boston Dynamics is one of the few with actual paying customers... which means thousands of Spots collecting real-world data that feeds back into making the AI smarter. That flywheel is hard to compete with.
1:39

Boston Dynamics just gave its robot dog a brain that reasons about the physical world. Google DeepMind's Gemini Robotics model is now running inside Spot, the four-legged robot already deployed at thousands of facilities worldwide. The upgrade centers on something called embodied reasoning. Basically, instead of following rigid instructions, Spot now interprets what it sees and makes decisions on its own. One standout example: Spot can now look at a pressure gauge, zoom in on the needle, calculate the intervals between tick marks, and deliver an accurate reading. All autonomously. The model also introduces: > Multi-view reasoning, combining feeds from multiple cameras to understand its environment even when objects are blocked from one angle > Built-in success detection, so Spot knows when it's failed and decides whether to retry or move on That last part is a key requirement for true autonomy. Most companies building AI-powered robots are still stuck in the demo phase. Boston Dynamics is one of the few with actual paying customers... which means thousands of Spots collecting real-world data that feeds back into making the AI smarter. That flywheel is hard to compete with.

Rowan Cheung

54,376 просмотров • 5 месяцев назад

The next evolution: VLA+ models Just yesterday Microsoft Research released Rho-alpha (ρα) – their first robotics model, built on the Phi family. While most Vision-Language-Action (VLA) models stop at vision and language, Rho-alpha adds: ▪️ Tactile sensing to feel objects during manipulation ▪️ Online learning that lets it improve from human corrections (via teleoperation, 3D mouse or other tools) in real-time even after deployment. Both these sides make adaptability central rather than incidental. Microsoft calls it a VLA+ model, positioning it as an extension beyond what current VLA systems support. ➡️ Today Rho-alpha can control dual-arm robot setups to perform tasks such as: • Manipulating the BusyBox following natural-language instructions • Plug insertion • Toolbox packing and object arrangement with bimanual coordination But to understand why this "plus" matters, we need to understand what came before. Here, we'll take you through the entire landscape of VLA models – Gemini Robotics, π0, SmolVLA, Helix, ACoT-VLA and others:
0:24

The next evolution: VLA+ models Just yesterday Microsoft Research released Rho-alpha (ρα) – their first robotics model, built on the Phi family. While most Vision-Language-Action (VLA) models stop at vision and language, Rho-alpha adds: ▪️ Tactile sensing to feel objects during manipulation ▪️ Online learning that lets it improve from human corrections (via teleoperation, 3D mouse or other tools) in real-time even after deployment. Both these sides make adaptability central rather than incidental. Microsoft calls it a VLA+ model, positioning it as an extension beyond what current VLA systems support. ➡️ Today Rho-alpha can control dual-arm robot setups to perform tasks such as: • Manipulating the BusyBox following natural-language instructions • Plug insertion • Toolbox packing and object arrangement with bimanual coordination But to understand why this "plus" matters, we need to understand what came before. Here, we'll take you through the entire landscape of VLA models – Gemini Robotics, π0, SmolVLA, Helix, ACoT-VLA and others:

Turing Post

62,494 просмотров • 7 месяцев назад

I usually skip benchmark comparisons. They're almost always picked to flatter. But EgoSchema is different. It measures first-person, egocentric video understanding. The AI equivalent of “look through the robot's eyes and tell me what happened.” I spent some time testing Perceptron Mk1 (“Mark One”) on the robotics workflows Perceptron walked me through, and the EgoSchema result suddenly made a lot more sense. Perceptron Mk1 scored 80.60% on it. Gemini 3.1 Flash Lite scored 62.4%. That's a completely different level of understanding. Most frontier models were trained on the internet through text, images, and static content. The physical world works differently. Context lives across time. The critical moment rarely exists in a single frame. And that's exactly where production deployments start mattering. Manufacturing QC. Robotics data pipelines. Security footage. Everything is temporal. Native video reasoning. Temporal grounding. Structured output. Perceptron calls it “Mk1” because it marks the beginning of their closed-model series for physical-world intelligence, and honestly, the name fits. It feels engineered for deployment, not just demos. Feels like one of the first video AI systems being built around how the physical world actually behaves instead of adapting static-image intelligence into video later.
0:21

I usually skip benchmark comparisons. They're almost always picked to flatter. But EgoSchema is different. It measures first-person, egocentric video understanding. The AI equivalent of “look through the robot's eyes and tell me what happened.” I spent some time testing Perceptron Mk1 (“Mark One”) on the robotics workflows Perceptron walked me through, and the EgoSchema result suddenly made a lot more sense. Perceptron Mk1 scored 80.60% on it. Gemini 3.1 Flash Lite scored 62.4%. That's a completely different level of understanding. Most frontier models were trained on the internet through text, images, and static content. The physical world works differently. Context lives across time. The critical moment rarely exists in a single frame. And that's exactly where production deployments start mattering. Manufacturing QC. Robotics data pipelines. Security footage. Everything is temporal. Native video reasoning. Temporal grounding. Structured output. Perceptron calls it “Mk1” because it marks the beginning of their closed-model series for physical-world intelligence, and honestly, the name fits. It feels engineered for deployment, not just demos. Feels like one of the first video AI systems being built around how the physical world actually behaves instead of adapting static-image intelligence into video later.

Jaymin Shah

116,573 просмотров • 4 месяцев назад

Robotics has a massive, silent bottleneck. It isn’t just data collection—it’s the brutal 1x speed of the physical world. Genesis AI Genesis AI just unveiled Genesis World 1.0, and they are attempting to turn the notorious Sim2Real gap into a pure compute problem. Evaluating a robotics foundation model across edge cases usually means hundreds of hours of physical lab testing. With Genesis World 1.0, what traditionally takes nearly a week of continuous, real-world operation is being compressed into 30 minutes in simulation. What makes this different from just dropping a robot model into an off-the-shelf game engine? 1️⃣ Nyx Renderer: A custom, real-time path-traced engine rendering noise-free 1080p frames in under 4ms. Game engines use rasterization tricks that confuse AI; Nyx uses physically accurate multi-bounce lighting so the model's "eyes" see exactly what real sensors see. 2️⃣ Quadrants Compiler: A custom Python-to-GPU compiler to run heavily parallelized multi-physics simulations (rigid bodies, fluids, deformables) natively across architectures. 3️⃣ Evaluation First: They aren't rushing to train on synthetic data. They are using this purely for closed-loop evaluation to perfect the physics first, currently claiming an impressive 89% correlation with real-world hardware tests. If the industry can accurately evaluate models in simulation without the physical world bottleneck, humanoid development stops moving at wall-clock time and starts scaling with compute.
1:36

Robotics has a massive, silent bottleneck. It isn’t just data collection—it’s the brutal 1x speed of the physical world. Genesis AI Genesis AI just unveiled Genesis World 1.0, and they are attempting to turn the notorious Sim2Real gap into a pure compute problem. Evaluating a robotics foundation model across edge cases usually means hundreds of hours of physical lab testing. With Genesis World 1.0, what traditionally takes nearly a week of continuous, real-world operation is being compressed into 30 minutes in simulation. What makes this different from just dropping a robot model into an off-the-shelf game engine? 1️⃣ Nyx Renderer: A custom, real-time path-traced engine rendering noise-free 1080p frames in under 4ms. Game engines use rasterization tricks that confuse AI; Nyx uses physically accurate multi-bounce lighting so the model's "eyes" see exactly what real sensors see. 2️⃣ Quadrants Compiler: A custom Python-to-GPU compiler to run heavily parallelized multi-physics simulations (rigid bodies, fluids, deformables) natively across architectures. 3️⃣ Evaluation First: They aren't rushing to train on synthetic data. They are using this purely for closed-loop evaluation to perfect the physics first, currently claiming an impressive 89% correlation with real-world hardware tests. If the industry can accurately evaluate models in simulation without the physical world bottleneck, humanoid development stops moving at wall-clock time and starts scaling with compute.

Humanoids daily

17,302 просмотров • 3 месяцев назад

Robots might learn better from video than from language! 📼 Most Vision-Language-Action (VLA) models learn what to do from text, but still struggle with how things move in the real world. That makes them data-hungry and slow to train. mimic video takes a different route. Instead of grounding robot control in text, it grounds it in video, using large pre-trained video models that already capture physical motion and dynamics. The idea is straightforward: let the video model handle “what will happen next,” and let a smaller control model focus only on turning that visual plan into robot actions. The result is big gains in practice. Robots trained this way need 10× less data, converge twice as fast, and perform better on both simulated benchmarks and real bimanual manipulation tasks. If robots can “imagine” motion using video, control becomes a much simpler problem. Shoutout to Jonas Pai, Liam Achenbach, Oier Mees, Elvis Nava and the rest of the team! Here's the project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:47

Robots might learn better from video than from language! 📼 Most Vision-Language-Action (VLA) models learn what to do from text, but still struggle with how things move in the real world. That makes them data-hungry and slow to train. mimic video takes a different route. Instead of grounding robot control in text, it grounds it in video, using large pre-trained video models that already capture physical motion and dynamics. The idea is straightforward: let the video model handle “what will happen next,” and let a smaller control model focus only on turning that visual plan into robot actions. The result is big gains in practice. Robots trained this way need 10× less data, converge twice as fast, and perform better on both simulated benchmarks and real bimanual manipulation tasks. If robots can “imagine” motion using video, control becomes a much simpler problem. Shoutout to Jonas Pai, Liam Achenbach, Oier Mees, Elvis Nava and the rest of the team! Here's the project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

50,090 просмотров • 8 месяцев назад

We’re introducing Gemini 3.8 Flash ⚡️ built to tackle complex agentic and multi-step tasks with even greater diligence. Our most intelligent workhorse model yet delivers significant improvements in reasoning, evolving to an AI partner that doesn’t just write code, but can also navigate complex projects. While solving ambiguous and high-friction tasks is immensely helpful, it can also be expensive. Fortunately, 3.8 Flash features the usual effort controls, ensuring that the amount of thinking required to accomplish the task at hand is proportional to the tokens spent. Watch Gemini 3.8 Flash combine native video understanding with advanced coding to autonomously build this 3D game, play it to find errors, and execute code changes in a seamless agentic loop in Google Antigravity.
1:06

We’re introducing Gemini 3.8 Flash ⚡️ built to tackle complex agentic and multi-step tasks with even greater diligence. Our most intelligent workhorse model yet delivers significant improvements in reasoning, evolving to an AI partner that doesn’t just write code, but can also navigate complex projects. While solving ambiguous and high-friction tasks is immensely helpful, it can also be expensive. Fortunately, 3.8 Flash features the usual effort controls, ensuring that the amount of thinking required to accomplish the task at hand is proportional to the tokens spent. Watch Gemini 3.8 Flash combine native video understanding with advanced coding to autonomously build this 3D game, play it to find errors, and execute code changes in a seamless agentic loop in Google Antigravity.

Google AI

433,928 просмотров • 15 дней назад

Sergey Levine (Sergey Levine) is one of the world's top robotics researchers and co-founder of Physical Intelligence. We talked about where humanoid robotics is today, thoughts on the Chinese robotics ecosystem, and his predictions for future timelines. In this episode: • Current state of robotics and surprising capabilities so far • Chinese robotics compared to US ecosystem • If OpenAI and Anthropic got into robotics • His top robotics research paper recommendation • Predictions for when humanoid robotics will land Where to watch: • YouTube - • Spotify - • Apple Podcasts - • Transcript - Thank you to the sponsor of this episode for supporting my work: • WorkOS: makes your app Enterprise Ready with easy to use APIs to add SSO, SCIM, RBAC, and more in just a few lines of code, check them out at Chapters: 00:00 Intro 00:37 Where are we today 04:20 Most surprising capabilities so far 07:03 The most inspiring real world robotics 08:36 If OpenAI or Anthropic got into robotics 10:22 Chinese robotics 13:15 Will one lab breakout from the rest 16:59 Thoughts on a concrete roadmap 21:03 Generalization and demonstrating it 26:04 Types of data and which is best for robotics 34:34 Why humanoid robotics differs from Waymo 37:10 If humanoid robotics failed here is why 39:55 Are there hot take modeling architectures in robotics 42:05 Thoughts on AI safety in robotics 46:44 Top robotics research paper recommendation 49:35 Why is Boston Dynamics less top of mind 53:47 Advice for his younger self 56:42 Outro
57:38

Sergey Levine (Sergey Levine) is one of the world's top robotics researchers and co-founder of Physical Intelligence. We talked about where humanoid robotics is today, thoughts on the Chinese robotics ecosystem, and his predictions for future timelines. In this episode: • Current state of robotics and surprising capabilities so far • Chinese robotics compared to US ecosystem • If OpenAI and Anthropic got into robotics • His top robotics research paper recommendation • Predictions for when humanoid robotics will land Where to watch: • YouTube - • Spotify - • Apple Podcasts - • Transcript - Thank you to the sponsor of this episode for supporting my work: • WorkOS: makes your app Enterprise Ready with easy to use APIs to add SSO, SCIM, RBAC, and more in just a few lines of code, check them out at Chapters: 00:00 Intro 00:37 Where are we today 04:20 Most surprising capabilities so far 07:03 The most inspiring real world robotics 08:36 If OpenAI or Anthropic got into robotics 10:22 Chinese robotics 13:15 Will one lab breakout from the rest 16:59 Thoughts on a concrete roadmap 21:03 Generalization and demonstrating it 26:04 Types of data and which is best for robotics 34:34 Why humanoid robotics differs from Waymo 37:10 If humanoid robotics failed here is why 39:55 Are there hot take modeling architectures in robotics 42:05 Thoughts on AI safety in robotics 46:44 Top robotics research paper recommendation 49:35 Why is Boston Dynamics less top of mind 53:47 Advice for his younger self 56:42 Outro

Ryan Peterman

70,513 просмотров • 24 дней назад