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.

Roboticists from Robotic Systems Lab and NVIDIA Embedded are teaching four-legged robots climb and jump. After training in simulation, the robots can autonomously decide how to scramble over and under obstacles, which will help them do dangerous jobs so that humans don't have to.

Evan Ackerman

15,346 subscribers

2,317,927 views • 2 years ago •via X (Twitter)

Science & Technology News & Politics Education

Anya Rossi• Live Now

Private livecam show

10 Comments

Evan Ackerman2 years ago

Featuring @anybotics of course!

Hígado Reptante2 years ago

@leggedrobotics @NVIDIAEmbedded They are for military applications, stop the f euphemisms.

Divisi Humas PoIisi Bikini Bottom2 years ago

@leggedrobotics @NVIDIAEmbedded

Freyr Aloysius2 years ago

@leggedrobotics @NVIDIAEmbedded "Dangerous jobs" yeah like delivering a bomb to somebody the cops don't like

Just a sad little Rogue2 years ago

@leggedrobotics @NVIDIAEmbedded "which will help them do dangerous jobs so that humans don't have to." Yeah, say that when the robot steals delivery jobs (or whatever), just because it'll be cheap. or when the robot is murdering your poor unemployed family. or both.

Bike Mayor of the Lumpenproletariat كاحسخ2 years ago

@leggedrobotics @NVIDIAEmbedded These are combat robot they're making and I'm tired of you all pretending otherwise.

commander2 years ago

@leggedrobotics @NVIDIAEmbedded These are soldiers in 2 years time. Fuck.

Melody the Vax'ilfan2 years ago

@leggedrobotics @NVIDIAEmbedded To everyone praising this, there's no chance that these are gonna follow Azimov's first law of robotics

Ishmael, Stay-Behind Wife Gal2 years ago

@leggedrobotics @NVIDIAEmbedded Cool! If I see one of these in the wild, I will destroy it with hammers 👍

Cyber Aughts2 years ago

@leggedrobotics @NVIDIAEmbedded I'm gonna be killed by an animatronic dog modeled after the little tikes car?

Related Videos

Researchers trained humanoid robots to climb and vault obstacles, testing AI systems designed to improve how quickly robots understand and react to their environment.

Researchers trained humanoid robots to climb and vault obstacles, testing AI systems designed to improve how quickly robots understand and react to their environment.

Interesting Engineering

17,519 views • 2 months ago

Everything that moves will be autonomous, and #physicalAI will embody robots of every kind. 🤖 Discover how NVIDIA Omniverse and #NVIDIACosmos are enabling robots to learn through simulation, training, and real-world experience. Watch the full video ▶️

Everything that moves will be autonomous, and #physicalAI will embody robots of every kind. 🤖 Discover how NVIDIA Omniverse and #NVIDIACosmos are enabling robots to learn through simulation, training, and real-world experience. Watch the full video ▶️

NVIDIA Robotics

56,496 views • 1 year ago

ELON: TESLA’S ROBOTS ARE MOVING FROM SIMULATIONS TO REALITY “For the robot, we’re going to need to build a lot of them and put them in an Optimus Academy so they can do self-play in reality and test different tasks. Tesla has quite a good, physics accurate, reality-generator, and we’re doing that for the robots. So you can do millions of robots in a simulated world, and then 10k in the real world to close the simulation to reality gap. Grok would orchestrate the behavior of the Optimus robots.” Source: Cheeky Pint Podcast, Elon Musk

ELON: TESLA’S ROBOTS ARE MOVING FROM SIMULATIONS TO REALITY “For the robot, we’re going to need to build a lot of them and put them in an Optimus Academy so they can do self-play in reality and test different tasks. Tesla has quite a good, physics accurate, reality-generator, and we’re doing that for the robots. So you can do millions of robots in a simulated world, and then 10k in the real world to close the simulation to reality gap. Grok would orchestrate the behavior of the Optimus robots.” Source: Cheeky Pint Podcast, Elon Musk

Mario Nawfal

19,289 views • 4 months ago

Chinese researchers have developed snail-inspired modular robots that can move individually across rough terrain and then connect together to form larger structures, allowing them to climb obstacles and carry out more complex coordinated tasks.

Chinese researchers have developed snail-inspired modular robots that can move individually across rough terrain and then connect together to form larger structures, allowing them to climb obstacles and carry out more complex coordinated tasks.

Science girl

83,424 views • 1 month ago

Simulating and training robots requires a physics-first approach. 🤖 With Newton, the open-source physics simulation engine co-developed by Disney Research, Walt Disney Imagineering, Google DeepMind and NVIDIA, Disney’s BDX Droid can move through shifting sand and gravel with exceptional precision. Watch to see how Newton is playing a key role in teaching robots how to move, behave, and interact with different objects and materials in the real world. #CES2026

Simulating and training robots requires a physics-first approach. 🤖 With Newton, the open-source physics simulation engine co-developed by Disney Research, Walt Disney Imagineering, Google DeepMind and NVIDIA, Disney’s BDX Droid can move through shifting sand and gravel with exceptional precision. Watch to see how Newton is playing a key role in teaching robots how to move, behave, and interact with different objects and materials in the real world. #CES2026

NVIDIA Robotics

45,717 views • 4 months ago

Robots need to be able to apply pressure and make contact with objects as needed in order to accomplish their tasks. From compliance to working safely around humans to whole-body manipulation of heavy objects, combining force and position control can dramatically expand the capabilities of robots. This is especially true for legged robots, which have so much ability to exert forces on the world around them. But how do we train robots which can do this? Baoxiong Jia tells us more in our discussion of his team’s recent, Best Paper Award winning work on learning a unified policy for position and force control, called UniFP. To learn more, watch Episode #49 of RoboPapers, hosted by Michael Cho - Rbt/Acc and Chris Paxton.

Robots need to be able to apply pressure and make contact with objects as needed in order to accomplish their tasks. From compliance to working safely around humans to whole-body manipulation of heavy objects, combining force and position control can dramatically expand the capabilities of robots. This is especially true for legged robots, which have so much ability to exert forces on the world around them. But how do we train robots which can do this? Baoxiong Jia tells us more in our discussion of his team’s recent, Best Paper Award winning work on learning a unified policy for position and force control, called UniFP. To learn more, watch Episode #49 of RoboPapers, hosted by Michael Cho - Rbt/Acc and Chris Paxton.

RoboPapers

44,774 views • 6 months ago

Elon : For Optimus, it’s difficult to match the flywheel of the existing vehicle fleet. The plan is to build a fleet of 10k–30k robots to perform self-play and testing. Millions of robotic agents will train in Tesla's "reality generator" (simulation), the real robots can then close the gap between simulation and reality.

Elon : For Optimus, it’s difficult to match the flywheel of the existing vehicle fleet. The plan is to build a fleet of 10k–30k robots to perform self-play and testing. Millions of robotic agents will train in Tesla's "reality generator" (simulation), the real robots can then close the gap between simulation and reality.

The Humanoid Hub

26,474 views • 4 months ago

Within the Robotic Systems Lab at ETH Zurich, we've dedicated the past six years to pioneering research in #ai for wheeled-legged #robots. Today, we are thrilled to announce that we are commercializing our embodied AI deployed on a Unitree hardware platform! #startup #hiring

Within the Robotic Systems Lab at ETH Zurich, we've dedicated the past six years to pioneering research in #ai for wheeled-legged #robots. Today, we are thrilled to announce that we are commercializing our embodied AI deployed on a Unitree hardware platform! #startup #hiring

RIVR

37,555 views • 2 years ago

Elon Musk in new interview on how Tesla’s Optimus robot will learn more quickly: "What we're going to need to do is build a lot of robots and put them in a kind of like a "Optimus Academy" so they can do self-play in reality. We're actually building that out. We're gonna have at least 10,000 Optimus robots, maybe 20,000 or 30,000, that are doing self-play and testing different tasks. Tesla has quite a good reality generator. A physics-accurate reality generator that we made for the cars. We'll do the same things for the robots, and actually have done that for the robots. You can do millions of simulated robots in a simulated world, and you use the tens of thousands in the real world to close the simulation to reality gap.”

Elon Musk in new interview on how Tesla’s Optimus robot will learn more quickly: "What we're going to need to do is build a lot of robots and put them in a kind of like a "Optimus Academy" so they can do self-play in reality. We're actually building that out. We're gonna have at least 10,000 Optimus robots, maybe 20,000 or 30,000, that are doing self-play and testing different tasks. Tesla has quite a good reality generator. A physics-accurate reality generator that we made for the cars. We'll do the same things for the robots, and actually have done that for the robots. You can do millions of simulated robots in a simulated world, and you use the tens of thousands in the real world to close the simulation to reality gap.”

Sawyer Merritt

250,956 views • 4 months ago

The Robots are Coming We are “2 to 3 years” from mass adoption of robots — Elon thinks it could happen even faster. How will it change our lives — and what will happen to jobs.

The Robots are Coming We are “2 to 3 years” from mass adoption of robots — Elon thinks it could happen even faster. How will it change our lives — and what will happen to jobs.

Peter St Onge, Ph.D.

202,398 views • 1 year ago

Running legged robots with AI. Today we met @swiss_mile, the team connecting AI with the physical world using autonomous machines. An ideal mobile robot needs to move quickly, overcoming obstacles while carrying heavy loads—something current robots still struggle with. Many robots haven't been widely adopted due to issues with real-world problem-solving. To address this, the Swiss-mile team have created a solution that combines robots with wheels and legs, powered by advanced AI. These robots can walk, drive, stand, open doors, and even handle packages. By integrating these features, the team are on a mission to push automation forward beyond stationary robotic arms and have raised $22m in Seed Funding from Jeff Bezos, HongShan, Amazon Industrial Innovation Fund and Armada Investment to do so.

Running legged robots with AI. Today we met @swiss_mile, the team connecting AI with the physical world using autonomous machines. An ideal mobile robot needs to move quickly, overcoming obstacles while carrying heavy loads—something current robots still struggle with. Many robots haven't been widely adopted due to issues with real-world problem-solving. To address this, the Swiss-mile team have created a solution that combines robots with wheels and legs, powered by advanced AI. These robots can walk, drive, stand, open doors, and even handle packages. By integrating these features, the team are on a mission to push automation forward beyond stationary robotic arms and have raised $22m in Seed Funding from Jeff Bezos, HongShan, Amazon Industrial Innovation Fund and Armada Investment to do so.

Circuit

17,829 views • 1 year ago

Trump understands what’s coming. The United States is going to lead the world in AI and robotics, especially humanoid robots, bc of Elon. Whoever leads humanoid robots and AI will define the next industrial era, and America has the pole position with Tesla. “Get somebody to start those robots and you’re going to have to improve the robots. But we’re going to have robotic factories plus manpower. So we’re going to have enough. We’re going to need the help of robots and other forms of, I guess you could say, employment. We’re going to be employing a lot of artificial things. But the beauty is we’re going to have more jobs than we’ve ever had.” - Donald Trump

Trump understands what’s coming. The United States is going to lead the world in AI and robotics, especially humanoid robots, bc of Elon. Whoever leads humanoid robots and AI will define the next industrial era, and America has the pole position with Tesla. “Get somebody to start those robots and you’re going to have to improve the robots. But we’re going to have robotic factories plus manpower. So we’re going to have enough. We’re going to need the help of robots and other forms of, I guess you could say, employment. We’re going to be employing a lot of artificial things. But the beauty is we’re going to have more jobs than we’ve ever had.” - Donald Trump

Teslaconomics

134,275 views • 5 months ago

Robots help us do tasks in space that are too dangerous or challenging for humans. We’re working on a new generation of robotic spacecraft that can work together without being controlled by astronauts or teams on Earth:

Robots help us do tasks in space that are too dangerous or challenging for humans. We’re working on a new generation of robotic spacecraft that can work together without being controlled by astronauts or teams on Earth:

NASA

901,062 views • 2 years ago

Elon just dropped a MAJOR nugget on how Tesla is going to be training Optimus to do real world tasks. They are building an Optimus Academy, which is a large scale, dedicated real-world training facility to accelerate the development of Optimus. The Academy will deploy thousands of Optimus units, potentially 10,000 to 30,000 robots, in a controlled realistic environment where they perform self-play, experiment with tasks, iterate on behaviors, and continuously generate training data through trial and error. The Tesla bots will also run millions of simulations in Tesla’s high-fidelity physics-accurate engine, allowing Optimus to close the “sim-to-real gap” by using these real-world observations to refine and validate the simulations! “You’re actually highlighting an important limitation and difference from cars. We’ll soon have 10 million cars on the road. It’s hard to duplicate that massive training flywheel. For the robot, what we’re going to need to do is build a lot of robots and put them in kind of an Optimus Academy so they can do self-play in reality. We’re actually building that out. We can have at least 10,000 Optimus robots, maybe 20-30,000, that are doing self-play and testing different tasks. Tesla has quite a good reality generator, a physics-accurate reality generator, that we made for the cars. We’ll do the same thing for the robots. We actually have done that for the robots. So you have a few tens of thousands of humanoid robots doing different tasks. You can do millions of simulated robots in the simulated world. You use the tens of thousands of robots in the real world to close the simulation to reality gap. Close the sim-to-real gap.”

Elon just dropped a MAJOR nugget on how Tesla is going to be training Optimus to do real world tasks. They are building an Optimus Academy, which is a large scale, dedicated real-world training facility to accelerate the development of Optimus. The Academy will deploy thousands of Optimus units, potentially 10,000 to 30,000 robots, in a controlled realistic environment where they perform self-play, experiment with tasks, iterate on behaviors, and continuously generate training data through trial and error. The Tesla bots will also run millions of simulations in Tesla’s high-fidelity physics-accurate engine, allowing Optimus to close the “sim-to-real gap” by using these real-world observations to refine and validate the simulations! “You’re actually highlighting an important limitation and difference from cars. We’ll soon have 10 million cars on the road. It’s hard to duplicate that massive training flywheel. For the robot, what we’re going to need to do is build a lot of robots and put them in kind of an Optimus Academy so they can do self-play in reality. We’re actually building that out. We can have at least 10,000 Optimus robots, maybe 20-30,000, that are doing self-play and testing different tasks. Tesla has quite a good reality generator, a physics-accurate reality generator, that we made for the cars. We’ll do the same thing for the robots. We actually have done that for the robots. So you have a few tens of thousands of humanoid robots doing different tasks. You can do millions of simulated robots in the simulated world. You use the tens of thousands of robots in the real world to close the simulation to reality gap. Close the sim-to-real gap.”

Teslaconomics

42,563 views • 4 months ago

🔥🚨BREAKING: Robotic food delivery services are under fire after this woman with cerebral palsy was brutally harassed by this robot that can also be controlled by humans in Los Angeles. Many viewers believe these companies need to review the access humans have with this robots since they have cameras and could hypothetically spread havoc.

🔥🚨BREAKING: Robotic food delivery services are under fire after this woman with cerebral palsy was brutally harassed by this robot that can also be controlled by humans in Los Angeles. Many viewers believe these companies need to review the access humans have with this robots since they have cameras and could hypothetically spread havoc.

Dom Lucre | Breaker of Narratives

138,281 views • 8 months ago

This research from ETH Zurich examines advancements in quadruped robots for industrial settings, specifically addressing their ability to climb ladders—a previously overlooked but essential capability. While legged robots excel over wheeled robots on rough terrain, their inability to scale ladders has limited their effectiveness in inspecting dangerous areas, impacting both safety and efficiency. Credit: ETH Zurich #engineering #technology #robotics #robots -------------------------------- Stay ahead of the curve! Follow us now on our WhatsApp ( and Telegram ( channels and stay updated about the cutting edge.

This research from ETH Zurich examines advancements in quadruped robots for industrial settings, specifically addressing their ability to climb ladders—a previously overlooked but essential capability. While legged robots excel over wheeled robots on rough terrain, their inability to scale ladders has limited their effectiveness in inspecting dangerous areas, impacting both safety and efficiency. Credit: ETH Zurich #engineering #technology #robotics #robots -------------------------------- Stay ahead of the curve! Follow us now on our WhatsApp ( and Telegram ( channels and stay updated about the cutting edge.

Wevolver

10,615 views • 11 months ago

Pale Kasarani the fans are arriving in style! Jirani alisema Kenyans are robots with robotic players playing for money and Kenyans have not disappointed, the robots too have arrived to support and cheer Harambee Stars.

Pale Kasarani the fans are arriving in style! Jirani alisema Kenyans are robots with robotic players playing for money and Kenyans have not disappointed, the robots too have arrived to support and cheer Harambee Stars.

Abdulahi Adan

111,726 views • 9 months ago

Elon Musk says Tesla is building an “Optimus Academy” so the robots can perform different tasks in the real world. “We’re going to need to build a lot of robots, and put them into a Optimus Academy, so they can do self-play in reality. We’re actually building that out, we’re going to have at least 10-30K Optimus robots that are testing different tasks.”

Elon Musk says Tesla is building an “Optimus Academy” so the robots can perform different tasks in the real world. “We’re going to need to build a lot of robots, and put them into a Optimus Academy, so they can do self-play in reality. We’re actually building that out, we’re going to have at least 10-30K Optimus robots that are testing different tasks.”

Nic Cruz Patane

20,052 views • 4 months ago

🤖WE HUMANS ARE TRAINING OUR AI REPLACEMENTS Humanoid robots are learning by watching humans work. Workers wear devices that capture egocentric data, showing robots exactly how tasks look from a human perspective. We are not just building robots. We are handing them our job's playbook.

🤖WE HUMANS ARE TRAINING OUR AI REPLACEMENTS Humanoid robots are learning by watching humans work. Workers wear devices that capture egocentric data, showing robots exactly how tasks look from a human perspective. We are not just building robots. We are handing them our job's playbook.

Coin Bureau

20,144 views • 16 days ago