Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

what if the robot could test its next move before the real arm moves? this setup already shows the first step: a 3D model follows the physical arm on screen right now, the model shows what the robot is doing the next step would be letting it test a... show more

ard

4,181 subscribers

33,298 просмотров • 14 дней назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

you can compensate gravity in your robot arm by calculating its own weight and countering it the video on the right shows the compensation algorithm in action, the arm holds itself upright and moves freely try it for yourself:

you can compensate gravity in your robot arm by calculating its own weight and countering it the video on the right shows the compensation algorithm in action, the arm holds itself upright and moves freely try it for yourself:

Frédéric Legrand

41,737 просмотров • 1 год назад

In animation, moving the arm without shoulder engagement can make it look disconnected or "broken," lacking natural flow. Adding shoulder movement supports the arm, creating a more believable, anatomical motion that reflects how bodies move in real life.

In animation, moving the arm without shoulder engagement can make it look disconnected or "broken," lacking natural flow. Adding shoulder movement supports the arm, creating a more believable, anatomical motion that reflects how bodies move in real life.

FramebyFrame

433,042 просмотров • 6 месяцев назад

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 просмотров • 4 месяцев назад

I didn't get what GPT-6 meant for robotics until I actually tried it. GPT-6 Astra just does physical ICL out of the box. we drop a recording of a human doing a novel task into 𝗰𝗼𝗱𝗲𝘅 app. Prompt it to drive a robot arm the same way. It just works on the first pass!

I didn't get what GPT-6 meant for robotics until I actually tried it. GPT-6 Astra just does physical ICL out of the box. we drop a recording of a human doing a novel task into 𝗰𝗼𝗱𝗲𝘅 app. Prompt it to drive a robot arm the same way. It just works on the first pass!

Wenli Xiao

241,310 просмотров • 23 дней назад

🤯 BITCOIN MAY BE PLAYING OUT THE MOST FAMOUS BOTTOM PATTERN IN TRADING. It is called Wyckoff accumulation. The way smart money builds a position before a markup. And Bitcoin is tracking it almost step for step. The selling climax. Done. The secondary test. Done. Next comes the spring. The final flush below support that traps the last sellers. Then the markup begins. If this schematic holds, the scariest drop is the setup. The bottom is built where everyone gives up.

🤯 BITCOIN MAY BE PLAYING OUT THE MOST FAMOUS BOTTOM PATTERN IN TRADING. It is called Wyckoff accumulation. The way smart money builds a position before a markup. And Bitcoin is tracking it almost step for step. The selling climax. Done. The secondary test. Done. Next comes the spring. The final flush below support that traps the last sellers. Then the markup begins. If this schematic holds, the scariest drop is the setup. The bottom is built where everyone gives up.

Mister Crypto

273,839 просмотров • 3 месяцев назад

This is f*cking gold - I built catbrain catch The idea is simple: a camera sees a ball, a cat-inspired visual model reacts, and the system asks: WHERE will it be when the arm gets there? Here’s the pipeline. Oriented filters extract visual features. Simulated neurons respond to those features and changes between frames. Color, shape, neural activity, and tracking history help identify the ball. Then a trajectory fit predicts where it will cross a target line in the image. → Camera input becomes neural responses → Motion helps separate targets from static clutter → Recent observations become an interception forecast → Lost tracking clears the prediction The next challenge is the REAL one: turning image coordinates into a reachable catch position on a physical robot. I left the project link in the replies. Build it, test it, break it.

This is f*cking gold - I built catbrain catch The idea is simple: a camera sees a ball, a cat-inspired visual model reacts, and the system asks: WHERE will it be when the arm gets there? Here’s the pipeline. Oriented filters extract visual features. Simulated neurons respond to those features and changes between frames. Color, shape, neural activity, and tracking history help identify the ball. Then a trajectory fit predicts where it will cross a target line in the image. → Camera input becomes neural responses → Motion helps separate targets from static clutter → Recent observations become an interception forecast → Lost tracking clears the prediction The next challenge is the REAL one: turning image coordinates into a reachable catch position on a physical robot. I left the project link in the replies. Build it, test it, break it.

BuBBliK

35,422 просмотров • 14 дней назад

The hardest part of V14 to explain to people is just how locked in and responsive it is. There is a step change here vs V13. The car is aware and calculating future moves so insanely fast. In this video, watch the moment my speedometer goes from 70 to 69mph. It recognizes the signaling of vehicle in the right lane, and before it even begins its slide into our lane, FSD is slowing to prepare its next move. It’s hard to explain this because you have to be in the car to feel how quickly the car shows you through movement and speed change that it is aware of what’s happening. I felt it even before you see the speedometer move. It’s almost instant. Way faster than humans and V13.

The hardest part of V14 to explain to people is just how locked in and responsive it is. There is a step change here vs V13. The car is aware and calculating future moves so insanely fast. In this video, watch the moment my speedometer goes from 70 to 69mph. It recognizes the signaling of vehicle in the right lane, and before it even begins its slide into our lane, FSD is slowing to prepare its next move. It’s hard to explain this because you have to be in the car to feel how quickly the car shows you through movement and speed change that it is aware of what’s happening. I felt it even before you see the speedometer move. It’s almost instant. Way faster than humans and V13.

Mike P

50,915 просмотров • 10 месяцев назад

🚨 THIS IS HOW IT STARTS — HUMANOID ROBOT SUDDENLY LUNGES AT A MAN — EXACTLY THE MOMENT PEOPLE FEARED A humanoid robot was casually kicking a soccer ball around during a public demonstration. Then the ball rolled toward a man in the audience. He tried to kick it back. That’s when the robot suddenly charged toward him and raised its arm like it was about to swing. Within seconds, a handler rushed in and grabbed the robot before the moment escalated. People in the room laugh nervously… but the clip is making the rounds online for one reason: The movement looks almost human. The way it runs. The stance. The arm coming up. Even the comments are losing it: • “Tf was it going to HIT for???” • “Why did it need to be held back?” • “DON’T TOUCH MY BALL” • “How do they get pissed off if they supposedly don’t have emotions?” The strangest part? The robot seemed to react the instant the human interfered with the ball. Are we just watching a glitch during a demo… or the exact moment people warned about?

🚨 THIS IS HOW IT STARTS — HUMANOID ROBOT SUDDENLY LUNGES AT A MAN — EXACTLY THE MOMENT PEOPLE FEARED A humanoid robot was casually kicking a soccer ball around during a public demonstration. Then the ball rolled toward a man in the audience. He tried to kick it back. That’s when the robot suddenly charged toward him and raised its arm like it was about to swing. Within seconds, a handler rushed in and grabbed the robot before the moment escalated. People in the room laugh nervously… but the clip is making the rounds online for one reason: The movement looks almost human. The way it runs. The stance. The arm coming up. Even the comments are losing it: • “Tf was it going to HIT for???” • “Why did it need to be held back?” • “DON’T TOUCH MY BALL” • “How do they get pissed off if they supposedly don’t have emotions?” The strangest part? The robot seemed to react the instant the human interfered with the ball. Are we just watching a glitch during a demo… or the exact moment people warned about?

HustleBitch

54,191 просмотров • 6 месяцев назад

A humanoid robot fell and broke its arm during rehearsal at the 2026 World Robot Conference in Beijing. After a quick repair on the sidelines, it got back on stage and finished the performance. What doesn't kill you makes you stronger!

A humanoid robot fell and broke its arm during rehearsal at the 2026 World Robot Conference in Beijing. After a quick repair on the sidelines, it got back on stage and finished the performance. What doesn't kill you makes you stronger!

China Xinhua News

28,152 просмотров • 1 месяц назад

Let me explain the agent loop, simple It's the core of every agentic system, and the part most people overcomplicate It's just this: 1. Send messages to the model 2. Model responds, maybe calls a tool 3. You run the tool 4. Append the result back to messages 5. Repeat until stop_reason is end_turn Step 4 is the whole thing, the write-back is what makes it an agent The model has to see what actually happened before it decides the next move That's the entire loop... understand this cold before you reach for a framework

Let me explain the agent loop, simple It's the core of every agentic system, and the part most people overcomplicate It's just this: 1. Send messages to the model 2. Model responds, maybe calls a tool 3. You run the tool 4. Append the result back to messages 5. Repeat until stop_reason is end_turn Step 4 is the whole thing, the write-back is what makes it an agent The model has to see what actually happened before it decides the next move That's the entire loop... understand this cold before you reach for a framework

Daniel San

12,514 просмотров • 3 месяцев назад

MAKING AXIS TASKS FEEL EASY 👀🤖 I made a quick video showing how to complete an Axis Robotics task step by step. The task gives you a clear goal, steps, controls and camera views to guide you. In this one, the goal is simple, Open the trash bin, pick up the onion, and place it inside. 🧅 Just follow the instructions, control the robot arm and complete the task. What I like is that even beginners can understand what they need to do. But the interesting part is what happens with these interactions after we complete them. Each completed task can contribute valuable robot training data, helping Physical Ai systems learn how to handle different objects and environments. Small tasks from the community can become useful data for teaching robots how to interact with the real world. That’s what makes Axis interesting to me.

MAKING AXIS TASKS FEEL EASY 👀🤖 I made a quick video showing how to complete an Axis Robotics task step by step. The task gives you a clear goal, steps, controls and camera views to guide you. In this one, the goal is simple, Open the trash bin, pick up the onion, and place it inside. 🧅 Just follow the instructions, control the robot arm and complete the task. What I like is that even beginners can understand what they need to do. But the interesting part is what happens with these interactions after we complete them. Each completed task can contribute valuable robot training data, helping Physical Ai systems learn how to handle different objects and environments. Small tasks from the community can become useful data for teaching robots how to interact with the real world. That’s what makes Axis interesting to me.

SufianXFN

14,419 просмотров • 27 дней назад

Valve updated the character model movement/sway ⁉️ > It wasn't mentioned in the release notes but it now appears to be closer to CSGO's where the model is more static... what do we think?

Valve updated the character model movement/sway ⁉️ > It wasn't mentioned in the release notes but it now appears to be closer to CSGO's where the model is more static... what do we think?

Ozzny

320,760 просмотров • 8 месяцев назад

Carve-your-Body: 1 Arm Cable Rows Step 1: Use the Same Leg and Rest your Knee right Behind the Bench. Step 2: Next you want to Grab the Handle with a Neutral Grip, so you can tuck your body into your Body. Step 3: Use a Thumbless Grip to Create a Greater Mind-to-Muscle Connection with your Back. Step 4: Instead of Keeping your Bod Upright, Slightly Lean Forward, so you can get a greater Stretch and Contraction in the movement. Save This for Next time you do 1 Arm Cable Rows Keep crushing it

Carve-your-Body: 1 Arm Cable Rows Step 1: Use the Same Leg and Rest your Knee right Behind the Bench. Step 2: Next you want to Grab the Handle with a Neutral Grip, so you can tuck your body into your Body. Step 3: Use a Thumbless Grip to Create a Greater Mind-to-Muscle Connection with your Back. Step 4: Instead of Keeping your Bod Upright, Slightly Lean Forward, so you can get a greater Stretch and Contraction in the movement. Save This for Next time you do 1 Arm Cable Rows Keep crushing it

Gym Workout | Strength Training | Clean Form

11,909 просмотров • 1 месяц назад

TESLA HALTED MODEL S AND MODEL X PRODUCTION TO BUILD AN ARMY OF OPTIMUS ROBOTS The Fremont assembly line was torn down in 46 days. In its place, Tesla is building a line for humanoid production, aiming for a million units a year A humanoid robot is a body shaped like a human. Physical AI is the intelligence that controls that body Walking and making coffee is often just imitation learning from a scripted routine. But once the environment shifts, the learned trick stops working Language models had the entire internet to train on. Robotics has nothing close to that scale of data, which is why one giant brain hasn't worked for anyone yet The industry is moving toward modularity instead - separate models for vision, movement, and planning, each improved on its own The real question is no longer whether a robot can move impressively. It's whether it can pull its sensors into one picture of the world and adapt to whatever wasn't scripted for it

TESLA HALTED MODEL S AND MODEL X PRODUCTION TO BUILD AN ARMY OF OPTIMUS ROBOTS The Fremont assembly line was torn down in 46 days. In its place, Tesla is building a line for humanoid production, aiming for a million units a year A humanoid robot is a body shaped like a human. Physical AI is the intelligence that controls that body Walking and making coffee is often just imitation learning from a scripted routine. But once the environment shifts, the learned trick stops working Language models had the entire internet to train on. Robotics has nothing close to that scale of data, which is why one giant brain hasn't worked for anyone yet The industry is moving toward modularity instead - separate models for vision, movement, and planning, each improved on its own The real question is no longer whether a robot can move impressively. It's whether it can pull its sensors into one picture of the world and adapt to whatever wasn't scripted for it

iamigorekk

22,205 просмотров • 1 месяц назад

A Gaussian Splat can become a world where Robots and AI agents can act. In our latest OVER Research experiment, we placed a robot inside a real-world 3D capture, with a VLM making decisions based on what it sees. At every step, the robot holds a pose in the reconstruction, gets a newly rendered view of the environment, takes an action, moves, and sees the world again from its new position. Why does this matter? Because 3D captures can become more than reconstructions to explore. They can become environments where embodied AI and robots can navigate, act, be evaluated and eventually train across real-world spaces at scale. Capture a place once. Then turn it into a world where AI and Robots can act. The full experiment, including what we discovered once we actually put the loop to the test:

A Gaussian Splat can become a world where Robots and AI agents can act. In our latest OVER Research experiment, we placed a robot inside a real-world 3D capture, with a VLM making decisions based on what it sees. At every step, the robot holds a pose in the reconstruction, gets a newly rendered view of the environment, takes an action, moves, and sees the world again from its new position. Why does this matter? Because 3D captures can become more than reconstructions to explore. They can become environments where embodied AI and robots can navigate, act, be evaluated and eventually train across real-world spaces at scale. Capture a place once. Then turn it into a world where AI and Robots can act. The full experiment, including what we discovered once we actually put the loop to the test:

Over the Reality 🌐

15,261 просмотров • 1 месяц назад

Fable 5 comes back！It can now build playable game prototypes. I think it is actually a signal for where AI coding is going. Making a game is not just “write some code.” Even a small browser game needs: game loop；character movement；collision logic；scoring system；UI states；physics tuning；visual feedback；bug fixing；playtesting This is why game prototyping is a great test for AI models. A model cannot fake it with a pretty answer. Either the game runs, or it does not. What impressed me about Fable 5 is that it is useful for the messy middle: turning an idea into mechanics, turning mechanics into code, debugging broken interactions, and iterating until the prototype feels playable. But here is the practical part: I would not use the strongest model for every step. For game building, I would split the workflow: 1. Fable 5 for game design + architecture 2. a fast coding model for routine implementation 3. a vision-capable model for screenshot/UI feedback 4. a cheaper model for docs, test cases, and small fixes 5. fallback when latency, cost, or output quality becomes a problem That is the real AI coding stack. Not “one magic model does everything.” More like: the right model, for the right task, at the right cost, with fallback when things break. This is why I’ve been looking at ZenMux ZenMux. ZenMux gives developers one gateway to access multiple leading AI models, with OpenAI / Anthropic / Google Vertex compatible APIs, cost tracking, quality benchmarks, auto-routing, and compensation when output quality, latency, or throughput falls short. If AI can now make games, the next question is not just “which model is strongest?” It is:how do we manage the whole model workflow Fable 5 shows the creative ceiling. ZenMux is closer to the infrastructure layer you need when AI coding becomes a real production habit.

Fable 5 comes back！It can now build playable game prototypes. I think it is actually a signal for where AI coding is going. Making a game is not just “write some code.” Even a small browser game needs: game loop；character movement；collision logic；scoring system；UI states；physics tuning；visual feedback；bug fixing；playtesting This is why game prototyping is a great test for AI models. A model cannot fake it with a pretty answer. Either the game runs, or it does not. What impressed me about Fable 5 is that it is useful for the messy middle: turning an idea into mechanics, turning mechanics into code, debugging broken interactions, and iterating until the prototype feels playable. But here is the practical part: I would not use the strongest model for every step. For game building, I would split the workflow: 1. Fable 5 for game design + architecture 2. a fast coding model for routine implementation 3. a vision-capable model for screenshot/UI feedback 4. a cheaper model for docs, test cases, and small fixes 5. fallback when latency, cost, or output quality becomes a problem That is the real AI coding stack. Not “one magic model does everything.” More like: the right model, for the right task, at the right cost, with fallback when things break. This is why I’ve been looking at ZenMux ZenMux. ZenMux gives developers one gateway to access multiple leading AI models, with OpenAI / Anthropic / Google Vertex compatible APIs, cost tracking, quality benchmarks, auto-routing, and compensation when output quality, latency, or throughput falls short. If AI can now make games, the next question is not just “which model is strongest?” It is:how do we manage the whole model workflow Fable 5 shows the creative ceiling. ZenMux is closer to the infrastructure layer you need when AI coding becomes a real production habit.

Rachel🥥

61,994 просмотров • 3 месяцев назад

THE MARKET DOESN'T MOVE TO YOUR TARGET IT MOVES TO WHERE THE LIQUIDITY IS Right now the liquidity map shows: - Massive cluster of liquidations at $52K - Stop losses stacked below $58K - Zero significant buy liquidity between here and $52K This is not bearish sentiment This is math The price will go where it needs to feed Follow me - I read liquidity before the move, not after

THE MARKET DOESN'T MOVE TO YOUR TARGET IT MOVES TO WHERE THE LIQUIDITY IS Right now the liquidity map shows: - Massive cluster of liquidations at $52K - Stop losses stacked below $58K - Zero significant buy liquidity between here and $52K This is not bearish sentiment This is math The price will go where it needs to feed Follow me - I read liquidity before the move, not after

philarekt

29,347 просмотров • 3 месяцев назад

From seeing → to understanding → to following → now to finding. In the last update, our robot learned how to recognize and follow people SR Agentic now evolves from human-following → to goal-driven object search. Give it a task like: → “find the white bottle on the table ” It will: • break down the instruction via LLM task planning • scan the environment in real-time • localize the object in 3D space • navigate and approach autonomously Step by step, capability by capability — from perception → to tracking → to task execution in the physical world. This is how real-world agentic robotics is built

From seeing → to understanding → to following → now to finding. In the last update, our robot learned how to recognize and follow people SR Agentic now evolves from human-following → to goal-driven object search. Give it a task like: → “find the white bottle on the table ” It will: • break down the instruction via LLM task planning • scan the environment in real-time • localize the object in 3D space • navigate and approach autonomously Step by step, capability by capability — from perception → to tracking → to task execution in the physical world. This is how real-world agentic robotics is built

Strike Robot

22,038 просмотров • 5 месяцев назад

Trained a simple world model for my robot arm. It predicts the future over 20000 times faster than real time on a single NVIDIA RTX 3090 GPU (128 batch -> 160x faster each).

Trained a simple world model for my robot arm. It predicts the future over 20000 times faster than real time on a single NVIDIA RTX 3090 GPU (128 batch -> 160x faster each).

Alexander Koch

40,821 просмотров • 2 лет назад

Furniture assembly is the task everyone name-drops and nobody actually attempts at real scale. Every demo I have seen is a scaled down IKEA leg or a single arm on a toy chair. This paper does it properly, real scale, bimanual, up to 7 subtasks and 1,550 control steps per episode, and it is validated on a real Kinova Gen3, not just in sim. That real-robot number is the one that matters: only a 16 percent drop on the hardest task going from simulation to hardware. That is a small enough gap to take seriously, and it did not happen by accident. They built a VR teleoperation rig specifically for coordinated dual-arm collection, because generic single-arm teleop setups do not capture the coordination real assembly needs, and the model predicts a continuous progress signal alongside the action chunk rather than a discrete subtask label, letting it auto-transition and catch drift before it compounds into total failure. The simulation ablation is what got them there, 48 to 80 percent over baselines, with another 21 points from their perception and control design study alone, but that is groundwork, not the headline. Watch the video, there is a clip of the robot misgrasping the seat panel, reopening the gripper, and regrasping on its own. That is not scripted recovery behaviour, it emerged from training, and it emerged on hardware. Excellent work from the team from Mitsubishi Electric Research Laboratories, with Oxford and UNC Chapel Hill Clinical Laboratory Science. Video and project page in comments. #Robotics #Manipulation #VLA

Furniture assembly is the task everyone name-drops and nobody actually attempts at real scale. Every demo I have seen is a scaled down IKEA leg or a single arm on a toy chair. This paper does it properly, real scale, bimanual, up to 7 subtasks and 1,550 control steps per episode, and it is validated on a real Kinova Gen3, not just in sim. That real-robot number is the one that matters: only a 16 percent drop on the hardest task going from simulation to hardware. That is a small enough gap to take seriously, and it did not happen by accident. They built a VR teleoperation rig specifically for coordinated dual-arm collection, because generic single-arm teleop setups do not capture the coordination real assembly needs, and the model predicts a continuous progress signal alongside the action chunk rather than a discrete subtask label, letting it auto-transition and catch drift before it compounds into total failure. The simulation ablation is what got them there, 48 to 80 percent over baselines, with another 21 points from their perception and control design study alone, but that is groundwork, not the headline. Watch the video, there is a clip of the robot misgrasping the seat panel, reopening the gripper, and regrasping on its own. That is not scripted recovery behaviour, it emerged from training, and it emerged on hardware. Excellent work from the team from Mitsubishi Electric Research Laboratories, with Oxford and UNC Chapel Hill Clinical Laboratory Science. Video and project page in comments. #Robotics #Manipulation #VLA

Stephen James

14,952 просмотров • 2 месяцев назад