Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

We’ve been collaborating with Physical Intelligence to deploy their models on our robots to automate order packing in real warehouses. With a sufficiently scoped and repetitive task, we have achieved a high level of reliable autonomy. This is an uncut, 1 minute time-lapse of a full 8-hour shift during...

Ultraroboticsco's profile picture

Ultra

3,441 subscribers

56,053 Aufrufe • vor 3 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Introducing Dynamism v1 (DYNA-1) by Dyna Robotics – the first robot foundation model built for round-the-clock, high-throughput dexterous autonomy. Here is a time-lapse video of our model autonomously folding 850+ napkins in a span of 24 hours with • 99.4% success rate — zero human intervention • 60% human throughput speed • 4.3/5 quality ratings (set by the client) A thread on our motivation, insights and results:
2:33

Introducing Dynamism v1 (DYNA-1) by Dyna Robotics – the first robot foundation model built for round-the-clock, high-throughput dexterous autonomy. Here is a time-lapse video of our model autonomously folding 850+ napkins in a span of 24 hours with • 99.4% success rate — zero human intervention • 60% human throughput speed • 4.3/5 quality ratings (set by the client) A thread on our motivation, insights and results:

Jason Ma

517,351 Aufrufe • vor 1 Jahr

Our robots now run autonomously >80% of the time. We still have human teleoperators in-the-loop, who take control when the robot gets stuck or something goes wrong. As autonomy improves, we'll grow our robot-to-operator efficiency until we have one person overseeing 10+ robots. Useful, AI-powered robots are here. And it's only going to get better.
10:03

Our robots now run autonomously >80% of the time. We still have human teleoperators in-the-loop, who take control when the robot gets stuck or something goes wrong. As autonomy improves, we'll grow our robot-to-operator efficiency until we have one person overseeing 10+ robots. Useful, AI-powered robots are here. And it's only going to get better.

Ultra

26,315 Aufrufe • vor 8 Monaten

Wouldn't it be great if we could train robots without any teleoperation! In our latest paper, we train robots to mimic a human video of the task by simply matching the object features using RL. We only need one video and under an hour of robot training.
0:22

Wouldn't it be great if we could train robots without any teleoperation! In our latest paper, we train robots to mimic a human video of the task by simply matching the object features using RL. We only need one video and under an hour of robot training.

Lerrel Pinto

46,197 Aufrufe • vor 1 Jahr

In feature film VFX, our lighting teams spend a lot of time shaving off as much render time as possible. Even 1 minute saved per frame adds up. For a 5 second shot, 1 minute less per frame saves you 2 hours of rendering per shot. Our shots are usually a lot heavier than this and our teams usually get a lot more optimization for render times than 1 minute per frame. Some shots can be rendering for up to 30 hours per frame depending on complexity. Large studios have a plethora of optimization tools which shave off a lot of render time from our shots. Rendering technology is always improving, bringing render times down and increasing physical accuracy. Video is of Hyperion with interactive rendering with Pixar's RenderMan XPU renderer, which is up to 5x faster than their older RIS architecture.
1:21

In feature film VFX, our lighting teams spend a lot of time shaving off as much render time as possible. Even 1 minute saved per frame adds up. For a 5 second shot, 1 minute less per frame saves you 2 hours of rendering per shot. Our shots are usually a lot heavier than this and our teams usually get a lot more optimization for render times than 1 minute per frame. Some shots can be rendering for up to 30 hours per frame depending on complexity. Large studios have a plethora of optimization tools which shave off a lot of render time from our shots. Rendering technology is always improving, bringing render times down and increasing physical accuracy. Video is of Hyperion with interactive rendering with Pixar's RenderMan XPU renderer, which is up to 5x faster than their older RIS architecture.

Rassoul Edji

16,128 Aufrufe • vor 1 Jahr

We’d like to take some time to appreciate what the last 16 seasons have meant to us. 16 seasons, three Stanley Cups, and some of our favorite memories. On the anniversary of the day Talbot 🤫 the city of Philadelphia, we thought we'd share some of our top moments from Round 1.
1:56

We’d like to take some time to appreciate what the last 16 seasons have meant to us. 16 seasons, three Stanley Cups, and some of our favorite memories. On the anniversary of the day Talbot 🤫 the city of Philadelphia, we thought we'd share some of our top moments from Round 1.

Pittsburgh Penguins

177,089 Aufrufe • vor 3 Jahren

The lessons of faith we learn in our youth can have a lasting impact on the rest of our lives. Kathy and I are excited to share some of our personal experiences with you during Family Discovery Day at RootsTech. You can watch on March 8 on at 1:30 p.m. MST.
1:48

The lessons of faith we learn in our youth can have a lasting impact on the rest of our lives. Kathy and I are excited to share some of our personal experiences with you during Family Discovery Day at RootsTech. You can watch on March 8 on at 1:30 p.m. MST.

Neil L. Andersen

11,444 Aufrufe • vor 1 Jahr

Sharing a few more demos of our first #LargeBehaviorModel (LBM) at TRI. 1/🍎This model enables a robot to learned to core and cut an apple into multiple slices autonomously. We trained our diffusion-based LBM on almost 1,700 hours of robot data, conducted 1,800 real-world evaluation rollouts, and ran over 47,000 simulation rollouts to rigorously study its capabilities. Learn more here:
2:04

Sharing a few more demos of our first #LargeBehaviorModel (LBM) at TRI. 1/🍎This model enables a robot to learned to core and cut an apple into multiple slices autonomously. We trained our diffusion-based LBM on almost 1,700 hours of robot data, conducted 1,800 real-world evaluation rollouts, and ran over 47,000 simulation rollouts to rigorously study its capabilities. Learn more here:

Zubair Irshad

12,202 Aufrufe • vor 10 Monaten

1/ We had an amazing day 2 at @ETHDenver growing and building our dev community to unlock the full potential of #USDC to push the limits of #Web3. Here were some of our favorite moments 👇
1:08

1/ We had an amazing day 2 at @ETHDenver growing and building our dev community to unlock the full potential of #USDC to push the limits of #Web3. Here were some of our favorite moments 👇

Circle

17,992 Aufrufe • vor 3 Jahren

✨ Tap here to watch the full tutorials! As we close out yet another amazing year, we’re filled with gratitude for everyone who has been part of this community.⁠ ⁠ Seeing how much we’ve grown and connected together has been truly inspiring, and we want to thank you from the bottom of our hearts for being part of this journey. ⁠ ⁠ To celebrate, we’ve put together a special compilation of some of our favorite moments from this year’s classes. Comment below your favorite class, and what you'd like to see more of💕⁠ ⁠ Here’s to an even more incredible 2026 🌟
0:56

✨ Tap here to watch the full tutorials! As we close out yet another amazing year, we’re filled with gratitude for everyone who has been part of this community.⁠ ⁠ Seeing how much we’ve grown and connected together has been truly inspiring, and we want to thank you from the bottom of our hearts for being part of this journey. ⁠ ⁠ To celebrate, we’ve put together a special compilation of some of our favorite moments from this year’s classes. Comment below your favorite class, and what you'd like to see more of💕⁠ ⁠ Here’s to an even more incredible 2026 🌟

Shibari Study

10,638 Aufrufe • vor 5 Monaten

One of our absolute favorite Christmas movies. 🍿 Home Alone has been a tradition in our house for a very long time. Here are some behind the scenes video of some of their most famous moments. What’s your favorite Christmas movies? And yes, Die Hard is a Christmas movie 😁
0:21

One of our absolute favorite Christmas movies. 🍿 Home Alone has been a tradition in our house for a very long time. Here are some behind the scenes video of some of their most famous moments. What’s your favorite Christmas movies? And yes, Die Hard is a Christmas movie 😁

CeCe

1,019,051 Aufrufe • vor 1 Monat

A throwback to some of our all-time favorite TV commercials. Which Ghanaian advert has stuck with you the most
0:26

A throwback to some of our all-time favorite TV commercials. Which Ghanaian advert has stuck with you the most

KOBY BINEY🇬🇭

106,742 Aufrufe • vor 11 Monaten

Today, we’re introducing KinetIQ, our own AI framework for end-to-end orchestration of humanoid robot fleets. One system, multiple robot embodiments. Industrial, service and home environments coordinated in real time. The framework consists of 4 cognitive layers: from high-level task allocation and workflow optimisation down to VLA-based task execution and RL-trained whole-body control. Watch how KinetIQ runs both our wheeled and bipedal robots. Read more on our blog:
3:47

Today, we’re introducing KinetIQ, our own AI framework for end-to-end orchestration of humanoid robot fleets. One system, multiple robot embodiments. Industrial, service and home environments coordinated in real time. The framework consists of 4 cognitive layers: from high-level task allocation and workflow optimisation down to VLA-based task execution and RL-trained whole-body control. Watch how KinetIQ runs both our wheeled and bipedal robots. Read more on our blog:

Humanoid

23,887 Aufrufe • vor 4 Monaten

Demonstrating our latest localization system in action. At bootup, the robot has no prior position estimate, but within seconds it autonomously localizes itself using a fusion of three algorithms. Unlike our previous version, this updated system incorporates vision, allowing the robot to adapt to real-world changes (e.g., moved furniture) by recognizing previously seen environments. In this demo, we repeatedly reset navigation and reposition the robot to random locations, showing robust, repeatable localization. The robot then executes a full patrol, following a planned path (visualized in RViz) with real-time path tracking. Because our software is hardware-agnostic, it brings the same reliable performance to any robot it runs on.
1:52

Demonstrating our latest localization system in action. At bootup, the robot has no prior position estimate, but within seconds it autonomously localizes itself using a fusion of three algorithms. Unlike our previous version, this updated system incorporates vision, allowing the robot to adapt to real-world changes (e.g., moved furniture) by recognizing previously seen environments. In this demo, we repeatedly reset navigation and reposition the robot to random locations, showing robust, repeatable localization. The robot then executes a full patrol, following a planned path (visualized in RViz) with real-time path tracking. Because our software is hardware-agnostic, it brings the same reliable performance to any robot it runs on.

OpenMind

12,814 Aufrufe • vor 1 Monat

Our journey began with a bold idea: To amplify the voices of ordinary Africans. Over the past 25 years, that idea has flourished into a trusted source of reliable data on African experiences, democracy, governance, and quality of life. As we draw the curtain on our 25th anniversary celebrations, this 30-minute documentary explores the inspiration behind our mission, the challenges we’ve overcome, the milestones we’ve achieved, and the impact we’ve made across the continent. #AfrobarometerAt25 #WeAreAfrobarometer #VoicesAfrica
32:04

Our journey began with a bold idea: To amplify the voices of ordinary Africans. Over the past 25 years, that idea has flourished into a trusted source of reliable data on African experiences, democracy, governance, and quality of life. As we draw the curtain on our 25th anniversary celebrations, this 30-minute documentary explores the inspiration behind our mission, the challenges we’ve overcome, the milestones we’ve achieved, and the impact we’ve made across the continent. #AfrobarometerAt25 #WeAreAfrobarometer #VoicesAfrica

Afrobarometer

34,941 Aufrufe • vor 1 Jahr

A little snippet of our 45-minute high-pressing class. We detail the understanding and implementation of the high press in our first class, with many more to come.
3:43

A little snippet of our 45-minute high-pressing class. We detail the understanding and implementation of the high press in our first class, with many more to come.

Tactx

74,914 Aufrufe • vor 11 Monaten

Kling Omni Launch Week · 1-Minute High-Energy Recap From breakthrough features to next-level creativity—relive the biggest moments of our five-day innovation blast.
1:05

Kling Omni Launch Week · 1-Minute High-Energy Recap From breakthrough features to next-level creativity—relive the biggest moments of our five-day innovation blast.

Kling AI

262,129 Aufrufe • vor 6 Monaten

A breakthrough in real-time video generation. As a research preview developed with NVIDIA and shared at NVIDIAGTC this week, we trained a new real-time video model running on Vera Rubin. HD videos generate instantly, with time-to-first-frame under 100ms. Unlocking an entirely new creative paradigm and bolstering the foundations of our General World Model, GWM-1. Real-time generation opens a fundamentally different design space for video models and world simulation. We're investing in co-designing our models alongside advances in hardware to keep pushing this frontier.
0:54

A breakthrough in real-time video generation. As a research preview developed with NVIDIA and shared at NVIDIAGTC this week, we trained a new real-time video model running on Vera Rubin. HD videos generate instantly, with time-to-first-frame under 100ms. Unlocking an entirely new creative paradigm and bolstering the foundations of our General World Model, GWM-1. Real-time generation opens a fundamentally different design space for video models and world simulation. We're investing in co-designing our models alongside advances in hardware to keep pushing this frontier.

Runway

1,159,937 Aufrufe • vor 2 Monaten

1 in 15 people in our country - 7% of the population - have been present at the scene of a mass shooting. 1 in 15 people in our country have been subjected to the violence, loss, and grief that is unimaginable and yet all too real for too many people in our country and our state.
0:24

1 in 15 people in our country - 7% of the population - have been present at the scene of a mass shooting. 1 in 15 people in our country have been subjected to the violence, loss, and grief that is unimaginable and yet all too real for too many people in our country and our state.

Representative Andy Boesenecker

54,032 Aufrufe • vor 1 Jahr

Humanoid and Siemens successfully completed a POC testing humanoid robots in industrial logistics. HMND 01 robot autonomously performed a tote-to-conveyor destacking task during a two-week on-site deployment at the Siemens Electronics Factory in Erlangen. This is the first step in our broader partnership with Siemens as humanoid robots move closer to real-world deployment. Learn more here:
3:07

Humanoid and Siemens successfully completed a POC testing humanoid robots in industrial logistics. HMND 01 robot autonomously performed a tote-to-conveyor destacking task during a two-week on-site deployment at the Siemens Electronics Factory in Erlangen. This is the first step in our broader partnership with Siemens as humanoid robots move closer to real-world deployment. Learn more here:

Humanoid

22,813 Aufrufe • vor 4 Monaten