Загрузка видео...

Не удалось загрузить видео

На главную

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.

BotJunkie's profile picture

Evan Ackerman

15,416 subscribers

2,318,625 просмотров • 3 лет назад •via X (Twitter)

Наука и технологииНовости и политикаОбразование
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 10

Фото профиля Evan Ackerman
Evan Ackerman3 лет назад

Featuring @anybotics of course!

Фото профиля Hígado Reptante
Hígado Reptante3 лет назад

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

Фото профиля Divisi Humas PoIisi Bikini Bottom
Divisi Humas PoIisi Bikini Bottom3 лет назад

@leggedrobotics @NVIDIAEmbedded

Фото профиля Freyr Aloysius
Freyr Aloysius3 лет назад

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

Фото профиля Just a sad little Rogue
Just a sad little Rogue3 лет назад

@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.

Фото профиля Bike Mayor of the Lumpenproletariat كاحسخ
Bike Mayor of the Lumpenproletariat كاحسخ3 лет назад

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

Фото профиля commander
commander3 лет назад

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

Фото профиля Melody the Vax'ilfan
Melody the Vax'ilfan3 лет назад

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

Фото профиля Ishmael, Stay-Behind Wife Gal
Ishmael, Stay-Behind Wife Gal3 лет назад

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

Фото профиля Cyber Aughts
Cyber Aughts3 лет назад

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

Похожие видео

Researchers trained humanoid robots to climb and vault obstacles, testing AI systems designed to improve how quickly robots understand and react to their environment.
0:35

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 просмотров • 7 месяцев назад

Robots Using Their Feet to Manipulate Objects ETH Zurich researchers have advanced "pedipulation," where legged robots use their feet for manipulation instead of robotic arms. Their new approach trains robots to navigate and manipulate objects while avoiding static and dynamic obstacles. Tested on the ANYmal quadruped, the method enables precise foot control in complex, unseen environments after minimal training in simulation. Will this research open up new possibilities for efficient, obstacle-aware robot manipulation?
1:04

Robots Using Their Feet to Manipulate Objects ETH Zurich researchers have advanced "pedipulation," where legged robots use their feet for manipulation instead of robotic arms. Their new approach trains robots to navigate and manipulate objects while avoiding static and dynamic obstacles. Tested on the ANYmal quadruped, the method enables precise foot control in complex, unseen environments after minimal training in simulation. Will this research open up new possibilities for efficient, obstacle-aware robot manipulation?

Circuit

11,802 просмотров • 1 год назад

China sends robots racing up the stone steps of Mount Tai The robots competed in four events: legged racing, cargo carrying, terrain reconnaissance and races involving humanoid machines. The participants had to navigate steep climbs, winding sections and long stone staircases. The fastest robots completed the course in less than an hour — faster than the humans accompanying them. Developers hope these trials will help adapt robots for cargo delivery and inspections in difficult terrain.
1:00

China sends robots racing up the stone steps of Mount Tai The robots competed in four events: legged racing, cargo carrying, terrain reconnaissance and races involving humanoid machines. The participants had to navigate steep climbs, winding sections and long stone staircases. The fastest robots completed the course in less than an hour — faster than the humans accompanying them. Developers hope these trials will help adapt robots for cargo delivery and inspections in difficult terrain.

NEXTA

19,923 просмотров • 8 дней назад

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
1:39

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 просмотров • 9 месяцев назад

From Nvidia drumming up cash to four legged robots keeping homes safe, these are the most important tech stories of the week
2:04

From Nvidia drumming up cash to four legged robots keeping homes safe, these are the most important tech stories of the week

Reuters

59,079 просмотров • 2 месяцев назад

🤖ROBOTS ARE GETTING SMARTER AT TOUCHING THE REAL WORLD Researchers from UC Berkeley, NVIDIA and Stanford introduced T-Rex, a framework that combines vision, language and tactile sensing. Instead of relying on cameras alone, robots can now respond to physical contact in real time. Robots are no longer just seeing objects. They’re learning how to FEEL them.
2:22

🤖ROBOTS ARE GETTING SMARTER AT TOUCHING THE REAL WORLD Researchers from UC Berkeley, NVIDIA and Stanford introduced T-Rex, a framework that combines vision, language and tactile sensing. Instead of relying on cameras alone, robots can now respond to physical contact in real time. Robots are no longer just seeing objects. They’re learning how to FEEL them.

Coin Bureau

28,275 просмотров • 4 месяцев назад

Humans are recording themselves so that the robots can replace them.
1:29

Humans are recording themselves so that the robots can replace them.

Crooked Media

50,486 просмотров • 3 месяцев назад

The CEO of NVIDIA asked them once and for all to these little robots and so responded. Thanks to artificial intelligence, Hugging Face Microducks have been trained in a simulation to practice their movements in the real world.
1:07

The CEO of NVIDIA asked them once and for all to these little robots and so responded. Thanks to artificial intelligence, Hugging Face Microducks have been trained in a simulation to practice their movements in the real world.

Massimo

75,963 просмотров • 10 дней назад

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.
0:37

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 просмотров • 6 месяцев назад

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
0:59

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 просмотров • 9 месяцев назад

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.
50:15

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

44,826 просмотров • 11 месяцев назад

Before robots can take over our jobs, they first need to learn how humans move. With cameras strapped to their foreheads, blue-collar workers in India are training humanoid robots by filming how they use their hands in what might be AI's latest gold rush
1:38

Before robots can take over our jobs, they first need to learn how humans move. With cameras strapped to their foreheads, blue-collar workers in India are training humanoid robots by filming how they use their hands in what might be AI's latest gold rush

Bloomberg

78,945 просмотров • 2 месяцев назад

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.
1:21

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 просмотров • 9 месяцев назад

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.”
0:59

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 просмотров • 9 месяцев назад

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.
3:30

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 просмотров • 1 год назад

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.
0:52

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

17,895 просмотров • 2 лет назад

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:
1:36

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

901,241 просмотров • 3 лет назад

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
0:25

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 просмотров • 10 месяцев назад