Trendaavat aiheet
#
Bonk Eco continues to show strength amid $USELESS rally
#
Pump.fun to raise $1B token sale, traders speculating on airdrop
#
Boop.Fun leading the way with a new launchpad on Solana.
Reborn
Full episode’s out.
@YuhengQiu discussed how to bridge SLAM with modern embodied AI, and shared an interesting story behind his best paper award in ICRA-25, hosted by @Jianfei.
One of the sharpest minds in VO and SLAM today. Tune in: 🎧👇
21.7. klo 06.12
🎙️ New Robot Mind teaser is here!
We sit down with @QiuYuhengQiu (PhD @ CMU AirLab, Intern @ Amazon Robotics) to explore his ICRA 2025 Best Paper, MAC-VO — a breakthrough in learning-based visual odometry with metrics-aware uncertainty modeling.
From real-time demo at ICRA to robot deployment, we dive deep into:
✅ What VO really is and why it still matters
✅ How to bridge classical robotics with modern embodied AI
✅ How "firing himself" and "opening minds" shaped his journey as a SLAM researcher
✅ The differences between academia and industry
Whether you're into robotics or vision, this one’s for you.
9,03K
🎙️ New Robot Mind teaser is here!
We sit down with @QiuYuhengQiu (PhD @ CMU AirLab, Intern @ Amazon Robotics) to explore his ICRA 2025 Best Paper, MAC-VO — a breakthrough in learning-based visual odometry with metrics-aware uncertainty modeling.
From real-time demo at ICRA to robot deployment, we dive deep into:
✅ What VO really is and why it still matters
✅ How to bridge classical robotics with modern embodied AI
✅ How "firing himself" and "opening minds" shaped his journey as a SLAM researcher
✅ The differences between academia and industry
Whether you're into robotics or vision, this one’s for you.
9,05K
Let the robot make a hamburger from scratch!
Incredible progress on long-horizon dexterous manipulation. Vision alone often falls short—this work smartly integrates high-res tactile sensing via cross-modal learning. ViTacFormer not only anticipates contact, but also enables robust imitation learning with anthropomorphic hands. A milestone for multi-modal robotic control.
8.7. klo 23.15
🤖 What if a humanoid robot could make a hamburger from raw ingredients—all the way to your plate?
🔥 Excited to announce ViTacFormer: our new pipeline for next-level dexterous manipulation with active vision + high-resolution touch.
🎯 For the first time ever, we demonstrate ~2.5 minutes of continuous, autonomous control—combining active vision, high-res touch, and high-DoF robot hands SharpaWave — to complete complex, real-world tasks.
Code is fully released; check out our:
Homepage:
Paper link:
Github:
3,75K
How do we teach robots to handle the world?
Step 2: Let them feel the flow.
In this second demo, we show our humanoid learns a pick-and-place task — picking up fruits with natural, human-like precision. Using VR mocap, we capture the coordinated motion of the entire arm and fingers, used to train the robot for delicate grasping and smooth placement.
1,75K
🎙️Full episode with Booster Robotics (@boosterobotics) is out now.
We dive into how they built the world-famous T1 humanoid robot — super robust, affordable, and open-source. From winning @robocup_org, to being featured at @nvidia GTC, to supporting humanoid locomotion research at @berkeley_ai.
Hosted by @Jianfei_AI.
19.6.2025
🎙️ Teaser from our upcoming Robot Mind podcast with Chaoyi, the head of Globalization at @boosterobotics .
"If you want robots to move like humans, you have to build like humans — open, agile, and fearless."
Booster Robotics is one of our key partners, providing the robust and affordable T1 humanoid. In this episode, we dive into the story of Booster T1 — the open-source robot that caught the attention of NVIDIA’s CEO Jensen Huang — and explore how data and models will shape Booster’s future.
Full episode coming soon. Stay tuned.
7,45K
Johtavat
Rankkaus
Suosikit