Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

The ultimate Engineering flex is making almost any shape fly.😁 AUREOLE - PVRA TriDisc is our experimental drone concept that replaces spinning propellers with Perimetric Vectoring Ring Arrays (PVRA). We place micro-nozzle belts around tri-lobed ring. These tiny jets push air to generate lift, lateral motion, and rotational control... show more

Mathelirium

30,399 subscribers

44,691 views • 4 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

SHAPE-SHIFTING WING COULD REWRITE FLIGHT EFFICIENCY This prototype wing isn’t fixed in place, it’s alive in the air. Its surface can twist, stretch, and adjust camber on the fly, reacting instantly to shifting aerodynamic conditions. Each micro-adjustment trims drag and boosts lift, squeezing every drop of efficiency from takeoff to landing. The payoff is sharper stability, smoother maneuverability, and fuel savings that could ground old designs for good. It’s the kind of tech that makes the sky feel like a smarter place to fly. Source: kaizen.engineered

SHAPE-SHIFTING WING COULD REWRITE FLIGHT EFFICIENCY This prototype wing isn’t fixed in place, it’s alive in the air. Its surface can twist, stretch, and adjust camber on the fly, reacting instantly to shifting aerodynamic conditions. Each micro-adjustment trims drag and boosts lift, squeezing every drop of efficiency from takeoff to landing. The payoff is sharper stability, smoother maneuverability, and fuel savings that could ground old designs for good. It’s the kind of tech that makes the sky feel like a smarter place to fly. Source: kaizen.engineered

Mario Nawfal

200,283 views • 11 months ago

Wolfram Stephen Wolfram might be onto something here😁 WOLFRAM PHYSICS in motion: Two competing feeders and and a predator. Everything here is a hypergraph...including the environment. We visualize a synthetic micro-ecosystem built on computational irreducibility, hypergraph rule-flow & emergent geometry. Inspired by the Wolfram Physics Project's quest for a "Theory of Everything". The full 1750 line python code is available to Gold members on YouTube upon request. Wolfram #WolframPhysics #TheoryOfEverything #ComputationalUniverse

Wolfram Stephen Wolfram might be onto something here😁 WOLFRAM PHYSICS in motion: Two competing feeders and and a predator. Everything here is a hypergraph...including the environment. We visualize a synthetic micro-ecosystem built on computational irreducibility, hypergraph rule-flow & emergent geometry. Inspired by the Wolfram Physics Project's quest for a "Theory of Everything". The full 1750 line python code is available to Gold members on YouTube upon request. Wolfram #WolframPhysics #TheoryOfEverything #ComputationalUniverse

Mathelirium

99,485 views • 9 months ago

The Most Powerful Formula in All of Mathematics. This beast can cover almost any shape you can think of 💪

The Most Powerful Formula in All of Mathematics. This beast can cover almost any shape you can think of 💪

Mathelirium

53,079 views • 4 months ago

A Million-Dollar Storm Mathematics Still Cannot Tame. Turbulence matters because it is the default behavior of real fluids once motion becomes strong enough, e.g. air over wings, blood through vessels, weather in the atmosphere, water in oceans, fuel in engines, and flow in pipes and turbines. We can write down the Navier-Stokes equations for all of this, but in 3D one of the deepest open questions is still whether smooth solutions always stay smooth, or can break down in finite time. That is crucial because it asks whether the basic equations of fluid motion remain mathematically under control forever, or can form a true singularity where the theory itself breaks. Solve that and you got yourself a million dollars

A Million-Dollar Storm Mathematics Still Cannot Tame. Turbulence matters because it is the default behavior of real fluids once motion becomes strong enough, e.g. air over wings, blood through vessels, weather in the atmosphere, water in oceans, fuel in engines, and flow in pipes and turbines. We can write down the Navier-Stokes equations for all of this, but in 3D one of the deepest open questions is still whether smooth solutions always stay smooth, or can break down in finite time. That is crucial because it asks whether the basic equations of fluid motion remain mathematically under control forever, or can form a true singularity where the theory itself breaks. Solve that and you got yourself a million dollars

Mathelirium

30,039 views • 3 months ago

Do you know how we simulate electromagnetic radiation around real systems like antennas, aircraft, and waveguides? We break the geometry into a mesh, a collection of small elements that lets the solver compute Maxwell’s equations locally instead of attacking the whole shape at once. This makes the simulations practical, fast, and accurate enough to use in real engineering.

Do you know how we simulate electromagnetic radiation around real systems like antennas, aircraft, and waveguides? We break the geometry into a mesh, a collection of small elements that lets the solver compute Maxwell’s equations locally instead of attacking the whole shape at once. This makes the simulations practical, fast, and accurate enough to use in real engineering.

Mathelirium

73,166 views • 3 months ago

#WATCH | Delhi: At the Synergia Conclave, Lieutenant General Vipul Shinghal, AVSM, SM, Deputy Chief of Integrated Defence Staff (Doctrine, Organisation, and Training), says, "...Even when I operate an AI system, I understand how to use it, but I don’t know what manipulation of data is happening... Where we have control and where we are also focusing is that our commanders, who earlier were only dealing with troops and making decisions based on that, are now dealing with algorithms and systems... they must have the ability to question machine outputs... These aspects are being debated worldwide... India itself has recently lost any regulation after the AI summit, and we are part of these discussions. The consensus is hard, but it is building..." He adds, "Meaningful human control is another aspect that is taking shape. Meaningful human control means that commanders must be able to access control meaningfully, and for that, they require 4 inputs or rather 4 levers: sufficient situational awareness... adequate time and information... And the ability to override or intervene... if they understand its limitations, we will be able to, at least in systems of the armed forces and weapons systems, ensure that we use AI for user responsibility. The moral responsibility must remain with the commander, and our conscience must keep that in place... In the Indian context, we have always believed that Shakti must go hand in hand with Dharma, that this force must go hand in hand with righteousness..." (11.03)

#WATCH | Delhi: At the Synergia Conclave, Lieutenant General Vipul Shinghal, AVSM, SM, Deputy Chief of Integrated Defence Staff (Doctrine, Organisation, and Training), says, "...Even when I operate an AI system, I understand how to use it, but I don’t know what manipulation of data is happening... Where we have control and where we are also focusing is that our commanders, who earlier were only dealing with troops and making decisions based on that, are now dealing with algorithms and systems... they must have the ability to question machine outputs... These aspects are being debated worldwide... India itself has recently lost any regulation after the AI summit, and we are part of these discussions. The consensus is hard, but it is building..." He adds, "Meaningful human control is another aspect that is taking shape. Meaningful human control means that commanders must be able to access control meaningfully, and for that, they require 4 inputs or rather 4 levers: sufficient situational awareness... adequate time and information... And the ability to override or intervene... if they understand its limitations, we will be able to, at least in systems of the armed forces and weapons systems, ensure that we use AI for user responsibility. The moral responsibility must remain with the commander, and our conscience must keep that in place... In the Indian context, we have always believed that Shakti must go hand in hand with Dharma, that this force must go hand in hand with righteousness..." (11.03)

ANI

104,382 views • 4 months ago

Erwin Schrödinger’s 1926 equation changed the game by turning Quantum Mechanics into wave dynamics. That move gave Physics a new way to think. Instead of forcing a particle onto one sharp path, it lets a complex wavefunction evolve in time, with its shape and phase holding the structure of the phenomenon. What makes this so striking is that Schrödinger’s equation does not start from vague mystery. It starts from a precise and daring idea The state of a particle is a complex field ψ(x,t), and the dynamics must push ψ forward in a way that preserves total probability.

Erwin Schrödinger’s 1926 equation changed the game by turning Quantum Mechanics into wave dynamics. That move gave Physics a new way to think. Instead of forcing a particle onto one sharp path, it lets a complex wavefunction evolve in time, with its shape and phase holding the structure of the phenomenon. What makes this so striking is that Schrödinger’s equation does not start from vague mystery. It starts from a precise and daring idea The state of a particle is a complex field ψ(x,t), and the dynamics must push ψ forward in a way that preserves total probability.

Mathelirium

54,730 views • 3 months ago

In Calculus of Variations, we give up the idea of only optimizing values and start optimizing geometries instead. The unknown is not a single x. It is a whole curve/surface y(x). The object you are minimizing is usually not a simple formula that you can guess. It is an integral that judges the whole shape. In our first lecture, we discuss the famous Brachistochrone problem. You choose two points, turn on gravity and ask a question which almost sounds too simple...which track will allow a bead to move from A to B in the minimum time? At your first attempt, your instinct will lead you astray. It is not the straight line. It is not the drop hard then cruise sketch either. The winner turns out to be a cycloid...the curve a point on a rolling circle traces. The track is the moving character in the animation. We begin with a flawed curve, perform gradient descent in curve-space, and observe the geometry change frame by frame as T[y] collapses to the brachistochrone. Please see the comment below for the math breakdown. #CalculusOfVariations #Brachistochrone #Cycloid #Physics #Optimization #Mathematics

In Calculus of Variations, we give up the idea of only optimizing values and start optimizing geometries instead. The unknown is not a single x. It is a whole curve/surface y(x). The object you are minimizing is usually not a simple formula that you can guess. It is an integral that judges the whole shape. In our first lecture, we discuss the famous Brachistochrone problem. You choose two points, turn on gravity and ask a question which almost sounds too simple...which track will allow a bead to move from A to B in the minimum time? At your first attempt, your instinct will lead you astray. It is not the straight line. It is not the drop hard then cruise sketch either. The winner turns out to be a cycloid...the curve a point on a rolling circle traces. The track is the moving character in the animation. We begin with a flawed curve, perform gradient descent in curve-space, and observe the geometry change frame by frame as T[y] collapses to the brachistochrone. Please see the comment below for the math breakdown. #CalculusOfVariations #Brachistochrone #Cycloid #Physics #Optimization #Mathematics

Mathelirium

23,254 views • 1 month ago

Gravity makes things orbit...but what happens when the mass distribution itself is rotating and dragging phase space into resonances and chaos? In this scene we follow tens of thousands of stars in a toy barred galaxy: a flat disc with a central mass and a rotating bar of extra density that is not rigid, but wobbling, swaying, and breathing in strength over time. The stars start on almost circular orbits in a calm ring, but as the bar turns and its pattern speed and strength modulate, they feel a time-dependent gravitational shove that nudges some onto resonant tracks. 🤩😍 #Mathelirium #Astrophysics #GalacticDynamics #BarredGalaxy #PhaseSpace #HamiltonianChaos #OrbitalResonance

Gravity makes things orbit...but what happens when the mass distribution itself is rotating and dragging phase space into resonances and chaos? In this scene we follow tens of thousands of stars in a toy barred galaxy: a flat disc with a central mass and a rotating bar of extra density that is not rigid, but wobbling, swaying, and breathing in strength over time. The stars start on almost circular orbits in a calm ring, but as the bar turns and its pattern speed and strength modulate, they feel a time-dependent gravitational shove that nudges some onto resonant tracks. 🤩😍 #Mathelirium #Astrophysics #GalacticDynamics #BarredGalaxy #PhaseSpace #HamiltonianChaos #OrbitalResonance

Mathelirium

152,143 views • 7 months ago

Why Are Some People Still Taking String Theory Seriously? String theory is controversial, but it is still one of the few ideas that tries to describe Quantum Physics and Gravity in one picture. This animation points to one of its best-known ideas: Holography. What happens on the boundary helps determine what happens in the interior, so the edge seems to shape the bulk.

Why Are Some People Still Taking String Theory Seriously? String theory is controversial, but it is still one of the few ideas that tries to describe Quantum Physics and Gravity in one picture. This animation points to one of its best-known ideas: Holography. What happens on the boundary helps determine what happens in the interior, so the edge seems to shape the bulk.

Mathelirium

29,696 views • 2 months ago

FLIGHT STATS 🥩🚀 - 33G's max acceleration - Mach 2.6 - 8.5km - Meat internal temp reached 105C / 221F Yaw/pitch/roll control worked great! At low speed and low air pressure we get a little oscillation, starting on the roll axis and progressing to pitch/yaw. A little more detail in the modeling should fix that. Cross range at apogee was about 230m from the launch point with lateral velocity less than 2m/s! HUGE win for my goal with pitch/yaw control: reducing recovery dispersion. The rocket is in awesome shape, I think it should fly again! Maybe as a second stage to a much higher altitude so we can nail down attitude control in the upper atmosphere.

FLIGHT STATS 🥩🚀 - 33G's max acceleration - Mach 2.6 - 8.5km - Meat internal temp reached 105C / 221F Yaw/pitch/roll control worked great! At low speed and low air pressure we get a little oscillation, starting on the roll axis and progressing to pitch/yaw. A little more detail in the modeling should fix that. Cross range at apogee was about 230m from the launch point with lateral velocity less than 2m/s! HUGE win for my goal with pitch/yaw control: reducing recovery dispersion. The rocket is in awesome shape, I think it should fly again! Maybe as a second stage to a much higher altitude so we can nail down attitude control in the upper atmosphere.

Joe Barnard 🚀

163,390 views • 1 year ago

Not only does our company believe in the Second Amendment, but we also believe in freedom of expression protected by the First Amendment. We love the United States. There is no other place in the world that shares the liberties that we cherish here on a daily basis; our products revolve around a concept that, in many other nations, is completely abolished for civilian ownership. A nation of freedom is what we have strived to be since conception, and a free nation should recognize that the burning of any flag is a protected form of free speech.

Not only does our company believe in the Second Amendment, but we also believe in freedom of expression protected by the First Amendment. We love the United States. There is no other place in the world that shares the liberties that we cherish here on a daily basis; our products revolve around a concept that, in many other nations, is completely abolished for civilian ownership. A nation of freedom is what we have strived to be since conception, and a free nation should recognize that the burning of any flag is a protected form of free speech.

Rattler Innovations

2,896,917 views • 10 months ago

Theoretical Physicist Dr. Lara Anderson: "Our 3 dimensional universe is expanding in to a 4th dimension" "Early 20th-century physics revealed our universe has more dimensions than we can see, and string theory suggests they shape everything from particles to reality itself." "The universe is not only stranger than we suppose, but stranger than we can suppose." This insight from physicist Arthur Eddington captures how extra dimensions, compactified in complex shapes like Calabi-Yau manifolds, remain hidden yet influence the fundamental laws we observe. These dimensions aren't sci-fi portals. They're tiny, folded geometries woven into the fabric of spacetime, enabling string theory to unify quantum mechanics and gravity while explaining unseen aspects like dark matter. Consciousness may even connect to these deeper structures in ways physics is only beginning to explore. Mind bending science that challenges everything we think we know about existence. What if the reality we perceive is just a slice of something far richer?

Theoretical Physicist Dr. Lara Anderson: "Our 3 dimensional universe is expanding in to a 4th dimension" "Early 20th-century physics revealed our universe has more dimensions than we can see, and string theory suggests they shape everything from particles to reality itself." "The universe is not only stranger than we suppose, but stranger than we can suppose." This insight from physicist Arthur Eddington captures how extra dimensions, compactified in complex shapes like Calabi-Yau manifolds, remain hidden yet influence the fundamental laws we observe. These dimensions aren't sci-fi portals. They're tiny, folded geometries woven into the fabric of spacetime, enabling string theory to unify quantum mechanics and gravity while explaining unseen aspects like dark matter. Consciousness may even connect to these deeper structures in ways physics is only beginning to explore. Mind bending science that challenges everything we think we know about existence. What if the reality we perceive is just a slice of something far richer?

Interstellar

25,281 views • 11 days ago

Reminder that if every Armenian left Artsakh and Azerbaijan had full control, there still wouldn't be peace with AZ. Aliyev on "Western AZ" (the parts of Armenia AZ regularly attacks): "Present-day Armenia is our land; we need to develop a concept of returning to Western AZ."

Reminder that if every Armenian left Artsakh and Azerbaijan had full control, there still wouldn't be peace with AZ. Aliyev on "Western AZ" (the parts of Armenia AZ regularly attacks): "Present-day Armenia is our land; we need to develop a concept of returning to Western AZ."

Lindsey Snell

271,883 views • 3 years ago

We just completed a successful flight for our tech demonstrator, Lat One v0.2. Lat Aerospace is building ultra-short takeoff and landing aircraft using blown wing technology. Think fixed-wing performance with near-helicopter access. A couple of months ago, v0.1 achieved uSTOL but crashed shortly after. That was expected. v0.2 was about completing the full mission, and it did. The blown wing concept worked in reality. Closed-loop control got validated. We'd predicted a cruise speed of 30-32 m/s and cruised comfortably at 33. No thermal issues despite a burning afternoon. The quick-detach wings held through aggressive turns. Was in the air for over 6 minutes. Smooth touchdown, and ready to fly again. But the thing that makes me the happiest isn't any of that. It's that our CFD studies, aerodynamic models, SIL simulations, and flight logs all match, almost perfectly. That's what real engineering looks like. I am so proud of our team. A long way to go, and we are getting there. LAT Aerospace Surobhi

We just completed a successful flight for our tech demonstrator, Lat One v0.2. Lat Aerospace is building ultra-short takeoff and landing aircraft using blown wing technology. Think fixed-wing performance with near-helicopter access. A couple of months ago, v0.1 achieved uSTOL but crashed shortly after. That was expected. v0.2 was about completing the full mission, and it did. The blown wing concept worked in reality. Closed-loop control got validated. We'd predicted a cruise speed of 30-32 m/s and cruised comfortably at 33. No thermal issues despite a burning afternoon. The quick-detach wings held through aggressive turns. Was in the air for over 6 minutes. Smooth touchdown, and ready to fly again. But the thing that makes me the happiest isn't any of that. It's that our CFD studies, aerodynamic models, SIL simulations, and flight logs all match, almost perfectly. That's what real engineering looks like. I am so proud of our team. A long way to go, and we are getting there. LAT Aerospace Surobhi

Deepinder Goyal

580,682 views • 3 months ago

Dropping the CapCut Video Studio Behind the Scene Series: Episode 1 - Getting Started. When people first start creating with AI, it often begins with a blank screen. A loose idea, a fleeting visual, something you can almost see but not fully shape yet. In this episode, we will follow how creators getting start to shape their story with Video Studio. How an idea is framed, how direction is set, and how the first decisions shape everything that follows. If you’ve ever wondered how to start strong and turn a rough idea into something real, this is something you don’t want to miss.

Dropping the CapCut Video Studio Behind the Scene Series: Episode 1 - Getting Started. When people first start creating with AI, it often begins with a blank screen. A loose idea, a fleeting visual, something you can almost see but not fully shape yet. In this episode, we will follow how creators getting start to shape their story with Video Studio. How an idea is framed, how direction is set, and how the first decisions shape everything that follows. If you’ve ever wondered how to start strong and turn a rough idea into something real, this is something you don’t want to miss.

CapCut

27,131,782 views • 3 months ago

In just a few months, we've closed the gap from 21 points to 5 points in the polls. We can end political corruption. We can control AI so it works for humanity, not the oligarchs. We can have Medicare-for-all and lower the cost of living. But to do any of that, we have to change the leadership and direction of the Democratic Party, and our campaign is the only one willing to speak that truth. San Franciscans agree, and that's why we're surging. Sign up to volunteer at This is our chance.

In just a few months, we've closed the gap from 21 points to 5 points in the polls. We can end political corruption. We can control AI so it works for humanity, not the oligarchs. We can have Medicare-for-all and lower the cost of living. But to do any of that, we have to change the leadership and direction of the Democratic Party, and our campaign is the only one willing to speak that truth. San Franciscans agree, and that's why we're surging. Sign up to volunteer at This is our chance.

Saikat Chakrabarti for Congress

45,719 views • 3 months ago

We often hear that Machine Learning models learn patterns in data. But what does that actually look like in Geometry? If you dropped a little elastic mesh into a cloud of points and let it learn, how would it fold itself to match the shape of the data? In this scene we watch a Self-Organizing Map (SOM), a simple unsupervised neural model, learn the shape of a 3D datasets l, one static and the other dynamic. On top of this, we lay down a square grid of neurons whose weights live in the same plane. At the start, this grid is just a flat net floating across the cloud. It knows nothing about the structure underneath. Learning is a repeated game: Pick a random data point, find the neuron whose weight is closest, and then nudge that neuron and its neighbours toward the point. Do this again and again, while slowly shrinking how far the neighbourhood influence spreads. Python code is available for Subscribers. #MachineLearning #ManifoldLearning #UnsupervisedLearning #NeuralMaps #GeometricML

We often hear that Machine Learning models learn patterns in data. But what does that actually look like in Geometry? If you dropped a little elastic mesh into a cloud of points and let it learn, how would it fold itself to match the shape of the data? In this scene we watch a Self-Organizing Map (SOM), a simple unsupervised neural model, learn the shape of a 3D datasets l, one static and the other dynamic. On top of this, we lay down a square grid of neurons whose weights live in the same plane. At the start, this grid is just a flat net floating across the cloud. It knows nothing about the structure underneath. Learning is a repeated game: Pick a random data point, find the neuron whose weight is closest, and then nudge that neuron and its neighbours toward the point. Do this again and again, while slowly shrinking how far the neighbourhood influence spreads. Python code is available for Subscribers. #MachineLearning #ManifoldLearning #UnsupervisedLearning #NeuralMaps #GeometricML

Mathelirium

76,194 views • 4 months ago

Mr Zelenskyy, If China had provided military supplies to Russia, the situation on the battleground would not have been where it is now. If your goal is to gain Trump's favor, smearing China won't help. In this video, we see a Chinese drone that can soar through the air with the grace of a bird and a size comparable to a classic hardwood-handled grenade. Its payload coefficient is the highest of any UAV currently in existence. It is also China's micro combat drone which weighs less than one kilogram and is intended for use by all infantry squads. 🔵 During surveillance operations, it can fly stealthily to the area around enemy positions and relay real-time intelligence, including the opponent's troop deployment, weaponry, and equipment, to its headquarters through high-definition cameras. 🔵 During combat, it can carry weapons and up to three grenades. 🔵 This drone's propeller blades are foldable, making it easier to transport and deploy for use in combat. 🔵 This little military drone has a payload capacity that is double its weight. Its ability to harness aerodynamics and produce more lift thanks to its coaxial double-rotor design allows it to transport bigger loads or pieces of equipment. 🔵 The drone has built-in NPU computer capacity, which is powered by AI technology. Allow the drone to learn in advance, and it will be able to perform duties autonomously on the battlefield. 🔵 A 35mm gun-mounted grenade launcher can be used to launch this drone, allowing the soldier to strike at a much greater distance. 🔵 In some situations, this tiny combat drone can be converted into a multi-rotor. In other words, the power mechanism may be easily transformed into a 4-rotor or 6-rotor aircraft, allowing it to carry out a variety of duties and increase its total pulling force.

Mr Zelenskyy, If China had provided military supplies to Russia, the situation on the battleground would not have been where it is now. If your goal is to gain Trump's favor, smearing China won't help. In this video, we see a Chinese drone that can soar through the air with the grace of a bird and a size comparable to a classic hardwood-handled grenade. Its payload coefficient is the highest of any UAV currently in existence. It is also China's micro combat drone which weighs less than one kilogram and is intended for use by all infantry squads. 🔵 During surveillance operations, it can fly stealthily to the area around enemy positions and relay real-time intelligence, including the opponent's troop deployment, weaponry, and equipment, to its headquarters through high-definition cameras. 🔵 During combat, it can carry weapons and up to three grenades. 🔵 This drone's propeller blades are foldable, making it easier to transport and deploy for use in combat. 🔵 This little military drone has a payload capacity that is double its weight. Its ability to harness aerodynamics and produce more lift thanks to its coaxial double-rotor design allows it to transport bigger loads or pieces of equipment. 🔵 The drone has built-in NPU computer capacity, which is powered by AI technology. Allow the drone to learn in advance, and it will be able to perform duties autonomously on the battlefield. 🔵 A 35mm gun-mounted grenade launcher can be used to launch this drone, allowing the soldier to strike at a much greater distance. 🔵 In some situations, this tiny combat drone can be converted into a multi-rotor. In other words, the power mechanism may be easily transformed into a 4-rotor or 6-rotor aircraft, allowing it to carry out a variety of duties and increase its total pulling force.

Eivor

1,382,457 views • 1 year ago

How do you give a humanoid the general motion capability? Not just single motions, but all motion? Introducing SONIC, our new work on supersizing motion tracking for natural humanoid control. We argue that motion tracking is the scalable foundation task for humanoids. So we "supersized" it: 9k+ GPU hours and 100M+ motion frames. But tracking alone is not enough; we show how to make a useful control system out of it: - Universal Kinematic Planner: Enables game-like gamepad control and high-level teleoperation, just like controlling a character in a game. - VR Full-Body Teleop: Direct, real-time whole-body control by a human wearing a VR headset. - VR Keypoint Teleop: Control the upper body (hands/head) while our planner handles robust locomotion automatically. - VLA Integration: We connect this motion tracker to autonomous Visual-Language-Action (VLA) models for autonomous task execution! We use a Universal Token Space to UNIFY this command space, turning our robust tracker into a general-purpose, programmable humanoid brain. This is the generalist "System 1" for humanoids. 🚀 Project: #Humanoids #Robotics #AI #FoundationModels #NVIDIAResearch 🧠🔥

How do you give a humanoid the general motion capability? Not just single motions, but all motion? Introducing SONIC, our new work on supersizing motion tracking for natural humanoid control. We argue that motion tracking is the scalable foundation task for humanoids. So we "supersized" it: 9k+ GPU hours and 100M+ motion frames. But tracking alone is not enough; we show how to make a useful control system out of it: - Universal Kinematic Planner: Enables game-like gamepad control and high-level teleoperation, just like controlling a character in a game. - VR Full-Body Teleop: Direct, real-time whole-body control by a human wearing a VR headset. - VR Keypoint Teleop: Control the upper body (hands/head) while our planner handles robust locomotion automatically. - VLA Integration: We connect this motion tracker to autonomous Visual-Language-Action (VLA) models for autonomous task execution! We use a Universal Token Space to UNIFY this command space, turning our robust tracker into a general-purpose, programmable humanoid brain. This is the generalist "System 1" for humanoids. 🚀 Project: #Humanoids #Robotics #AI #FoundationModels #NVIDIAResearch 🧠🔥

Zhengyi “Zen” Luo

62,040 views • 8 months ago