Загрузка видео...

Не удалось загрузить видео

На главную

“Pretraining as we know it will end” Robotics: Hold my 🍺 , new data coming Source: Agibot

74,904 просмотров • 1 год назад •via X (Twitter)

Комментарии: 11

Фото профиля Appy Pie
Appy Pie1 год назад

Ha! Robotics stepping in with a bang. The evolution of AI and robotics is bound to change the game in ways we can't fully predict. Exciting times ahead!

Фото профиля Fast Company
Fast Company2 лет назад

#AI agents: from tools to teammates. Software that can act, react, and interact with both humans and other agents will transform how businesses operate—and how they should invest in technology. This @EY_US article explains more. #ad

Фото профиля T
T1 год назад

hello we would like to make… hello…?

Фото профиля sagi
sagi1 год назад

Isn’t teleoperation technically post training data?

Фото профиля Yuxi on the Wired
Yuxi on the Wired1 год назад

English website: Chinese website:

Фото профиля engineeringXroads
engineeringXroads1 год назад

True

Фото профиля Eriiiiiiiick
Eriiiiiiiick1 год назад

@xuxin_cheng your AI art is straight up next level, fam. What's the secret sauce behind your creative grind, and how do you think AI's gonna remix our whole vibe in the future?

Фото профиля Justin a AuDHDer… 🇨🇦
Justin a AuDHDer… 🇨🇦1 год назад

What is the data and who come the video has no sound?

Фото профиля This is Jarvi
This is Jarvi1 год назад

The data streams are about to 1000x

Фото профиля crypto_collector(🧀,🧀)
crypto_collector(🧀,🧀)1 год назад

So they just collecting real world data and how do they store it? All these different type of robots?

Фото профиля The New Money
The New Money1 год назад

So, is it time to look a bit closer at robot stocks?

Похожие видео

🔥 JUST IN: Open-source robotics dataset from 100% real-world scenarios! 🤯 Chinese robotics company AGIBOT just released AGIBOT WORLD 2026, an open-source dataset systematically covering key embodied AI research directions. Built entirely from real-world environments: commercial spaces, and homes. Collected using AGIBOT G2 robots in free-form collection mode, providing structured, accurately annotated, high-quality data. Digital twin technology creates 1:1 scale replicas in simulation matching the real environments. Both real-world and simulation data are open-sourced. The AGIBOT G2 platform collects multiple data types simultaneously: RGB(D) cameras, tactile sensors, force sensors, LiDAR, IMU, and full-body joint states. Whole-body control coordinates arms, waist, and hands for complex tasks. First-person teleoperation lets operators control the robot from its perspective. The tasks covered are fine-grained manipulation, ultra-long-horizon tasks, spatial navigation, dual-arm coordination, and multi-agent/human-robot collaboration. The dataset includes error-recovery trajectories with annotations. Most datasets only show successful demonstrations. AGIBOT includes failures and how the robot recovers, teaching models how to handle mistakes. After collection, data is tested through policy training and real-robot deployment to ensure quality. Then processed through industrial quality control with multiple screening and cleaning rounds. Making it open-source accelerates embodied AI research by giving researchers access to high-quality real-world robot data at scale. 🇨🇳 Learn more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

40,583 просмотров • 4 месяцев назад