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。

Beijing-based KingKong Robotics has open-sourced the software toolkit for Jumper, the six-legged red crab robot that drew crowds at China's big AI and robot expos this summer. Open the GitHub repo in an AI coding assistant, and a one-line prompt can train new moves in simulation, design new shells... show more

Interesting Engineering

318,440 subscribers

29,050 次观看 • 10 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

3 条评论

Logical Solutions Group 的头像

Logical Solutions Group9 天前

Open-sourcing the toolkit for a six-legged platform is useful, since legs handle uneven ground that wheels can't. For inspection work, is the extra mechanical complexity worth it versus a tracked platform?

ˈdʒoʊ.nʌt 🏳️‍⚧️ 的头像

ˈdʒoʊ.nʌt 🏳️‍⚧️9 天前

@zhiyishou if you wanna see more of the crab and the guy that made it

HeavyDLite 的头像

HeavyDLite9 天前

Aww look it's a Bubba crab!! ❤️

相关视频

GitHub + Cursor is just INSANE GitHub has 28 million open-source projects that anyone can fork and build a new product So I built a new product: Repo to Docs The Agent will scan entire GitHub repo, analyze all files and create a knowledge base (docs) for AI coding tools: ↓

GitHub + Cursor is just INSANE GitHub has 28 million open-source projects that anyone can fork and build a new product So I built a new product: Repo to Docs The Agent will scan entire GitHub repo, analyze all files and create a knowledge base (docs) for AI coding tools: ↓

CJ Zafir

123,805 次观看 • 1 年前

This little crab robot went viral. Now its training toolkit is open source. 🦀 It’s Jumper, a six-legged robot from China’s KingKong with 22 degrees of freedom. It walks, dances and grabs objects, and KingKong lists a jump height of at least 40 cm, roughly 16 inches. The release includes the robot model, MuJoCo simulation, reinforcement-learning training and deployment tools. Parts of the public deployment code still need validation on the real robot. I like that you don’t need to own one to get started. You can train a walking gait, tweak the rewards and replay the result to see how Jumper’s movement changes. Someone’s already used the model to build a browser game where you can assemble the robot and get a whole crowd of crabs dancing.

This little crab robot went viral. Now its training toolkit is open source. 🦀 It’s Jumper, a six-legged robot from China’s KingKong with 22 degrees of freedom. It walks, dances and grabs objects, and KingKong lists a jump height of at least 40 cm, roughly 16 inches. The release includes the robot model, MuJoCo simulation, reinforcement-learning training and deployment tools. Parts of the public deployment code still need validation on the real robot. I like that you don’t need to own one to get started. You can train a walking gait, tweak the rewards and replay the result to see how Jumper’s movement changes. Someone’s already used the model to build a browser game where you can assemble the robot and get a whole crowd of crabs dancing.

RoboHub🤖

22,454 次观看 • 5 天前

Tired of teleoperation? One human video → 1,000s of robot demos. (📍GitHub ) Scaling Robot Data Without Dynamics Simulation or Robot Hardware Real2Render2Real (R2R2R) is a new way to scale robot data without physics simulation or hardware. You take a phone scan + a single monocular human demo. It tracks the motion, renders photorealistic scenes, and generates diverse, robot-agnostic trajectories ready for training. > No teleop, no sim, no robot, just a phone and a video > Train VLA models and diffusion policies directly on the output > Supports multiple robot embodiments with kinematic consistency > 1000s of demos in 1/27 the time of real-world collection Thank you, Max Fu, for sharing!! Project: Paper: Code coming soon: It shows that with the right pipeline, you can scale robot learning data without touching a robot. One of the most interesting directions in scalable robotics today. —— Weekly robotics and AI insights. Subscribe free:

Tired of teleoperation? One human video → 1,000s of robot demos. (📍GitHub ) Scaling Robot Data Without Dynamics Simulation or Robot Hardware Real2Render2Real (R2R2R) is a new way to scale robot data without physics simulation or hardware. You take a phone scan + a single monocular human demo. It tracks the motion, renders photorealistic scenes, and generates diverse, robot-agnostic trajectories ready for training. > No teleop, no sim, no robot, just a phone and a video > Train VLA models and diffusion policies directly on the output > Supports multiple robot embodiments with kinematic consistency > 1000s of demos in 1/27 the time of real-world collection Thank you, Max Fu, for sharing!! Project: Paper: Code coming soon: It shows that with the right pipeline, you can scale robot learning data without touching a robot. One of the most interesting directions in scalable robotics today. —— Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

42,864 次观看 • 8 个月前

NEW: Gay robot spotted walking around in Los Angeles, California. "The Rizzbot" was seen crossing traffic and confronting people in LA. The AI-powered robot stands at 4 feet tall, weighs 77 pounds, and is manufactured by China-based Unitree Robotics. The "humanoid" agent develops "based on deep reinforcement learning and simulation training."

NEW: Gay robot spotted walking around in Los Angeles, California. "The Rizzbot" was seen crossing traffic and confronting people in LA. The AI-powered robot stands at 4 feet tall, weighs 77 pounds, and is manufactured by China-based Unitree Robotics. The "humanoid" agent develops "based on deep reinforcement learning and simulation training."

Collin Rugg

1,333,858 次观看 • 1 年前

This New AI Just Nuked the Competition Genesis AI is here to wipe out every outdated simulation and totally dominate AI world. - Open sourced - Create data from prompt - 430,000x faster than real-time - Create 4D physical worlds in seconds with text prompt Let's dive in:

This New AI Just Nuked the Competition Genesis AI is here to wipe out every outdated simulation and totally dominate AI world. - Open sourced - Create data from prompt - 430,000x faster than real-time - Create 4D physical worlds in seconds with text prompt Let's dive in:

el.cine

358,440 次观看 • 1 年前

btw this robot runs on a fully open source AI framework called Xiaozhi it turns a $8 ESP32 chip into a fully autonomous voice assistant NO expensive cloud servers or high latency wake-word detection and audio streaming happen locally on the chip: > requires only an ESP32-S3, a microphone, and a basic speaker > supports real-time conversational voice interaction > completely open-source and customizable for any DIY robotics project anyone can now build a personal AI companion for the price of a cup of coffee. (github link in the replies)

btw this robot runs on a fully open source AI framework called Xiaozhi it turns a $8 ESP32 chip into a fully autonomous voice assistant NO expensive cloud servers or high latency wake-word detection and audio streaming happen locally on the chip: > requires only an ESP32-S3, a microphone, and a basic speaker > supports real-time conversational voice interaction > completely open-source and customizable for any DIY robotics project anyone can now build a personal AI companion for the price of a cup of coffee. (github link in the replies)

ard

42,210 次观看 • 2 个月前

Robotics is the next frontier for AI, surpassing $150B in the next 2 years. OpenMind works alongside major players like Circle, NVIDIA, and Unitree to build important software that powers the AI brains in robots. Therefore, Fabric Foundation was established to build a path for open robotics across the world and to hasten the development of onchain payments, identity, and governance infrastructure. The decentralized robot economy begins today, powered by $ROBO.

Robotics is the next frontier for AI, surpassing $150B in the next 2 years. OpenMind works alongside major players like Circle, NVIDIA, and Unitree to build important software that powers the AI brains in robots. Therefore, Fabric Foundation was established to build a path for open robotics across the world and to hasten the development of onchain payments, identity, and governance infrastructure. The decentralized robot economy begins today, powered by $ROBO.

Fabric Foundation

107,019 次观看 • 7 个月前

One prompt built and deployed a visual AI agent for a manufacturing line in under 30 minutes, with alerts, video search, and incident reports. Check out our new tutorial that shows you how to build one with the new Build Vision AI skill in the NVIDIA VSS Blueprint 3.3. Tutorial:

One prompt built and deployed a visual AI agent for a manufacturing line in under 30 minutes, with alerts, video search, and incident reports. Check out our new tutorial that shows you how to build one with the new Build Vision AI skill in the NVIDIA VSS Blueprint 3.3. Tutorial:

NVIDIA AI

27,790 次观看 • 17 天前

Build an assistant that can store and search what it sees, hears, and is told, all without leaving the device. In Building AI Assistants with On-Device Memory, you'll build a local memory system that recalls text, voice, and images, and teach it to recognize something new from a few photos. Built in partnership with Qdrant and taught by Dylan Couzon, Developer Experience Engineer at Qdrant. This course also includes our new AI coding lab, so you can practice building with an AI coding agent from the mobile app. Enroll for free:

Build an assistant that can store and search what it sees, hears, and is told, all without leaving the device. In Building AI Assistants with On-Device Memory, you'll build a local memory system that recalls text, voice, and images, and teach it to recognize something new from a few photos. Built in partnership with Qdrant and taught by Dylan Couzon, Developer Experience Engineer at Qdrant. This course also includes our new AI coding lab, so you can practice building with an AI coding agent from the mobile app. Enroll for free:

DeepLearning.AI

15,444 次观看 • 24 天前

Path Robotics has developed a legged robot called Rove for large-scale industrial welding. It moves to the worksite and scans welding seams to understand their shape. Then, its AI performs welding and adjusts the process in real time.

Path Robotics has developed a legged robot called Rove for large-scale industrial welding. It moves to the worksite and scans welding seams to understand their shape. Then, its AI performs welding and adjusts the process in real time.

Space and Technology

57,456 次观看 • 4 个月前

Chinese robotics company Unitree has unveiled a new "Superman" robot that can reportedly outrun Usain Bolt and jump over 6.5 feet vertically. David Muir, who interviewed the company in May, reports on the race to lead in AI.

Chinese robotics company Unitree has unveiled a new "Superman" robot that can reportedly outrun Usain Bolt and jump over 6.5 feet vertically. David Muir, who interviewed the company in May, reports on the race to lead in AI.

World News Tonight

14,504 次观看 • 1 个月前

On May 11, elementary students in Xiaoshan performed a song for Chinese and international guests attending the 2026 World Digital Education Conference, with an AI teaching assistant robot swaying along in the middle. This school has been using digital technology to build a future-oriented new ecosystem for education.

On May 11, elementary students in Xiaoshan performed a song for Chinese and international guests attending the 2026 World Digital Education Conference, with an AI teaching assistant robot swaying along in the middle. This school has been using digital technology to build a future-oriented new ecosystem for education.

iXiaoshan

200,372 次观看 • 5 个月前

The coolest part of Microduck might not be the robot. It's how it learns to move. This repo shows the full reinforcement learning pipeline behind Microduck. The robot learns in simulation using MuJoCo, PPO and GPU-based training, then the trained policy is exported to ONNX and deployed on the real robot. But the real challenge is sim-to-real. The simulation models things like actuator behavior, battery voltage, command delays, friction and even gear backlash. That helps make the learned policy work when it moves from simulation to the physical robot. The repo includes policies for walking, fall recovery, sitting, standing, kicking, ground picking and even roller skating. Train in simulation. Test the behavior. Export the policy. Run it on a real robot.

The coolest part of Microduck might not be the robot. It's how it learns to move. This repo shows the full reinforcement learning pipeline behind Microduck. The robot learns in simulation using MuJoCo, PPO and GPU-based training, then the trained policy is exported to ONNX and deployed on the real robot. But the real challenge is sim-to-real. The simulation models things like actuator behavior, battery voltage, command delays, friction and even gear backlash. That helps make the learned policy work when it moves from simulation to the physical robot. The repo includes policies for walking, fall recovery, sitting, standing, kicking, ground picking and even roller skating. Train in simulation. Test the behavior. Export the policy. Run it on a real robot.

Praveen Kumar Verma

138,017 次观看 • 1 个月前

What If Your Desk Robot Could Learn Your Moves? Meet Quaddle, a tiny open-source quadruped built for tinkering. It has just 4 servos, but can run, glide sideways and spin in place. You can program it with Block coding, Python or C++. You can physically guide it through a movement, tap to record, and it can learn and replay the trick. There is also AI conversation, touch interaction, sensors and 3D-printable parts. A fun way to get hands-on with robotics, coding, AI and mechanical design.

What If Your Desk Robot Could Learn Your Moves? Meet Quaddle, a tiny open-source quadruped built for tinkering. It has just 4 servos, but can run, glide sideways and spin in place. You can program it with Block coding, Python or C++. You can physically guide it through a movement, tap to record, and it can learn and replay the trick. There is also AI conversation, touch interaction, sensors and 3D-printable parts. A fun way to get hands-on with robotics, coding, AI and mechanical design.

Praveen Kumar Verma

15,079 次观看 • 2 个月前

🤖Verne Robotics builds AI software for robot arms to learn new skills in hours (their AI model is SOTA), making it easy for any company to adopt automation. Congrats on the launch, Neil Nie and Aditya Jha!

🤖Verne Robotics builds AI software for robot arms to learn new skills in hours (their AI model is SOTA), making it easy for any company to adopt automation. Congrats on the launch, Neil Nie and Aditya Jha!

Y Combinator

74,550 次观看 • 1 年前

Shanghai-based Matrix Robotics has introduced a new humanoid robot called MATRIX-3. The robot features soft skin with built-in touch sensors for safer interaction. Its advanced hands can use tools and handle delicate objects with impressive precision.

Shanghai-based Matrix Robotics has introduced a new humanoid robot called MATRIX-3. The robot features soft skin with built-in touch sensors for safer interaction. Its advanced hands can use tools and handle delicate objects with impressive precision.

Space and Technology

13,385 次观看 • 4 个月前