正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Our humanoid robot vaults, climbs, and crosses terrain it’s never seen before—deciding which move to use in real time, completely on its own 🤖 Real → sim → real. 👇

LightOrigins

1,143 subscribers

31,905 次观看 • 1 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

16 条评论

LightOrigins 的头像

LightOrigins1 个月前

Blog: Follow @LightOrigins_ for updates.

Anto Patrex 的头像

Anto Patrex1 个月前

impressive movement but "real→sim→real" usually means the sim environment was carefully built to match the exact demo space. flip it: drop this into a random warehouse with uneven floors and different lighting and see what transfers. that's the real test.

Carlos DP 🤖🇺🇸 的头像

Carlos DP 🤖🇺🇸1 个月前

Really nice release! Probably the best formatted one I’ve seen all year, really appreciate the amount of detail you guys go into

LightOrigins 的头像

LightOrigins1 个月前

Thank you Carlos appreciate!

Willis 的头像

Willis1 个月前

Wow

LucN Markets 的头像

LucN Markets1 个月前

Le robot fait du parkour pendant que le manufacturing canadien coule doucement... bienvenue dans le futur du travail 😬

Sothh 的头像

Sothh1 个月前

I think u need something from @InvLambda

Daniel Lambert 的头像

Daniel Lambert1 个月前

Vaulting, climbing, and adapting to new terrain autonomously — physical intelligence is moving fast. 🤖🚀

Hollywood LA News 的头像

Hollywood LA News1 个月前

Want !!!!!!!

LightOrigins 的头像

LightOrigins1 个月前

😍

AI Mastery Guide 的头像

AI Mastery Guide1 个月前

deciding the move in real time on unseen terrain is the hard part done right

Andile (Ethan) 的头像

Andile (Ethan)1 个月前

When are you adding grippers!

LightOrigins 的头像

LightOrigins1 个月前

Probably next demo :)

Andile (Ethan) 的头像

Andile (Ethan)1 个月前

Any interest in super low lead time and cheap parallel grippers?

Oleg Shulga 的头像

Oleg Shulga1 个月前

Real to sim to real is the right test. A robot that only works on a polished demo floor is an actor with expensive knees. Unseen terrain and autonomous choices are where robotics stops being theater.

Shadow Defense 的头像

Shadow Defense1 个月前

I want involved. What do you have for me?

相关视频

A robot that sees the terrain and predicts its own future… up to 5 seconds ahead? This is real. ❗️Best Systems Paper finalist at #RSS2025 The team introduces a perceptive Forward Dynamics Model that helps legged robots safely navigate rough, complex environments: no manual tuning no rigid-body limits. Why this matters ✅ Predicts future robot states using both perception and proprioception ✅ Trained on years of sim + real data for strong sim-to-real performance ✅ Enables zero-shot navigation with minimal cost tuning ✅ Boosts success rates and safety on rough terrain like never before This isn’t just another planner, it’s a big step toward robust, adaptable locomotion. Paper: Project website:

A robot that sees the terrain and predicts its own future… up to 5 seconds ahead? This is real. ❗️Best Systems Paper finalist at #RSS2025 The team introduces a perceptive Forward Dynamics Model that helps legged robots safely navigate rough, complex environments: no manual tuning no rigid-body limits. Why this matters ✅ Predicts future robot states using both perception and proprioception ✅ Trained on years of sim + real data for strong sim-to-real performance ✅ Enables zero-shot navigation with minimal cost tuning ✅ Boosts success rates and safety on rough terrain like never before This isn’t just another planner, it’s a big step toward robust, adaptable locomotion. Paper: Project website:

Ilir Aliu

43,990 次观看 • 1 年前

Zerith Robotics in China has started mass production of its H1 humanoid robot for real-world use. It is designed for places like hotels and stores, moving on wheels and working on its own indoors. The robot can clean spaces and also help in supermarkets by picking and handling products automatically.

Zerith Robotics in China has started mass production of its H1 humanoid robot for real-world use. It is designed for places like hotels and stores, moving on wheels and working on its own indoors. The robot can clean spaces and also help in supermarkets by picking and handling products automatically.

Space and Technology

14,656 次观看 • 4 个月前

How to use simulation data for real-world robot manipulation? We present sim-and-real co-training, a simple recipe for manipulation. We demonstrate that sim data can significantly enhance real-world performance, even with notable differences between the sim and the real. (1/n)

How to use simulation data for real-world robot manipulation? We present sim-and-real co-training, a simple recipe for manipulation. We demonstrate that sim data can significantly enhance real-world performance, even with notable differences between the sim and the real. (1/n)

Zhenyu Jiang

44,813 次观看 • 1 年前

VinMotion’s Motion 2 is a humanoid robot made for both factories and home use. It can lift up to 40 kg, recover on its own after falling, and manage its own charging or battery swapping. It also supports multiple languages like Vietnamese and English for real-world communication and tasks.

VinMotion’s Motion 2 is a humanoid robot made for both factories and home use. It can lift up to 40 kg, recover on its own after falling, and manage its own charging or battery swapping. It also supports multiple languages like Vietnamese and English for real-world communication and tasks.

Space and Technology

15,593 次观看 • 5 个月前

Real-time inference is a big challenge for VLAs. We’ve been working on a way to amortize inference delays in π0.5. Our new Real-Time Chunking (RTC) method speeds up π0.5 by allowing the robot to “think” while it’s moving, which makes it quite a bit faster! 🧵👇

Real-time inference is a big challenge for VLAs. We’ve been working on a way to amortize inference delays in π0.5. Our new Real-Time Chunking (RTC) method speeds up π0.5 by allowing the robot to “think” while it’s moving, which makes it quite a bit faster! 🧵👇

Sergey Levine

73,757 次观看 • 1 年前

Boston Dynamics has demonstrated its new Atlas humanoid robot lifting and carrying a 50-pound fridge. The robot uses its whole body to balance and move the heavy object in a natural, human-like way. Before doing it in the real world, Atlas practiced the task for millions of hours in a virtual simulation.

Boston Dynamics has demonstrated its new Atlas humanoid robot lifting and carrying a 50-pound fridge. The robot uses its whole body to balance and move the heavy object in a natural, human-like way. Before doing it in the real world, Atlas practiced the task for millions of hours in a virtual simulation.

Space and Technology

180,862 次观看 • 3 个月前

Watch this robot dog learn to walk from scratch in real time! Our new method, APRL, dynamically adjusts exploration constraints to enable fast and performant RL directly in the real world. APRL can also adapt to changes in the terrain. No simulation, no demos. A thread 👇

Watch this robot dog learn to walk from scratch in real time! Our new method, APRL, dynamically adjusts exploration constraints to enable fast and performant RL directly in the real world. APRL can also adapt to changes in the terrain. No simulation, no demos. A thread 👇

Sergey Levine

105,579 次观看 • 2 年前

🏓🤖 Our humanoid robot can now rally over 100 consecutive shots against a human in real table tennis — fully autonomous, sub-second reaction, human-like strikes.

🏓🤖 Our humanoid robot can now rally over 100 consecutive shots against a human in real table tennis — fully autonomous, sub-second reaction, human-like strikes.

Zhi Su

672,975 次观看 • 1 年前

Humanoid robot development is too fragmented to scale. 🤖 With NVIDIA Isaac GR00T, developers unify simulation, data, and training in one open platform, cutting setup time from days to hours. See how Isaac GR00T helps research teams move faster from robot bring-up to skill development and real-world validation. Watch now 📺

Humanoid robot development is too fragmented to scale. 🤖 With NVIDIA Isaac GR00T, developers unify simulation, data, and training in one open platform, cutting setup time from days to hours. See how Isaac GR00T helps research teams move faster from robot bring-up to skill development and real-world validation. Watch now 📺

NVIDIA Robotics

22,669 次观看 • 2 个月前

We’ve all seen humanoid robots doing backflips and dance routines for years. But if you ask them to climb a few stairs in the real world, they stumble! We took our robot on a walk around town to environments that it hadn’t seen before. Here’s how it works🧵⬇️

We’ve all seen humanoid robots doing backflips and dance routines for years. But if you ask them to climb a few stairs in the real world, they stumble! We took our robot on a walk around town to environments that it hadn’t seen before. Here’s how it works🧵⬇️

Skild AI

271,828 次观看 • 1 年前

UBTech Robotics has showcased its humanoid robot Walker S2 playing tennis with a human. Using real-time vision sensors, it tracks the ball, adjusts its position, and returns shots with good accuracy. The robot can also swap its own batteries, allowing it to operate continuously without human help.

UBTech Robotics has showcased its humanoid robot Walker S2 playing tennis with a human. Using real-time vision sensors, it tracks the ball, adjusts its position, and returns shots with good accuracy. The robot can also swap its own batteries, allowing it to operate continuously without human help.

Space and Technology

16,121 次观看 • 4 个月前

Announcing REK - Become a REAL Robot Pilot with our humanoid fighting sim. Top 2 players this weekend qualify for REK2: The first 6 foot tall Humanoid fight in the West on August 15 (Fighting T800s!) Thank You to 8VC and RoboStrategy for co-leading our seed round last year!

Announcing REK - Become a REAL Robot Pilot with our humanoid fighting sim. Top 2 players this weekend qualify for REK2: The first 6 foot tall Humanoid fight in the West on August 15 (Fighting T800s!) Thank You to 8VC and RoboStrategy for co-leading our seed round last year!

CIX 🦾

521,084 次观看 • 2 个月前

For robots to be useful, they must be able to interact with a wide variety of environments; and yet, scaling interaction data is difficult, expensive, and time consuming. Instead, much research revolves around sim-to-real manipulation — but mostly this has not been mobile manipulation. Recently, though, this has begun to change. Two recent papers from Tairan He and Haoru Xue show us how to unlock the potential of this technique, building policies which, without any real data at all, can move objects around in the world and open doors in the real world with a humanoid robot. Watch Episode #60 of RoboPapers now to learn more, hosted by Chris Paxton and Jiafei Duan. In this episode, we cover two papers:. First is VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation; and second is DoorMan: Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer.

For robots to be useful, they must be able to interact with a wide variety of environments; and yet, scaling interaction data is difficult, expensive, and time consuming. Instead, much research revolves around sim-to-real manipulation — but mostly this has not been mobile manipulation. Recently, though, this has begun to change. Two recent papers from Tairan He and Haoru Xue show us how to unlock the potential of this technique, building policies which, without any real data at all, can move objects around in the world and open doors in the real world with a humanoid robot. Watch Episode #60 of RoboPapers now to learn more, hosted by Chris Paxton and Jiafei Duan. In this episode, we cover two papers:. First is VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation; and second is DoorMan: Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer.

RoboPapers

30,767 次观看 • 7 个月前

introducing real-time custom AI models. now you can train your own styles, characters, or products and use them in Krea Real-time. tutorial below 👇

introducing real-time custom AI models. now you can train your own styles, characters, or products and use them in Krea Real-time. tutorial below 👇

Krea

250,265 次观看 • 1 年前