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。

Researchers at Light Origins have created LightParkour, a single AI system that lets their Lightbot 0 humanoid robot handle everything from walking to climbing to vaulting. It works using just a depth camera and a velocity command, deciding on its own which movement fits each obstacle. The system even... show more

Space and Technology

37,198 subscribers

40,698 次观看 • 1 个月前 •via X (Twitter)

艺术科学技术教育

Anya Rossi• Live Now

Private livecam show

10 条评论

cit1z3n 的头像

cit1z3n1 个月前

Adaptation without pre-programming is the real unlock for robots in unstructured environments.

Ryan Tyre 🇺🇸 的头像

Ryan Tyre 🇺🇸1 个月前

They're evolving

Mantis Robotics 的头像

Mantis Robotics1 个月前

Proprioception + single depth sensor + zero-shot parkour adaptation. Light Origins is proving that elegant, minimalist sensor setups with powerful policies beat over-engineered hardware every time.

Alexa | Indie hacker 的头像

Alexa | Indie hacker1 个月前

robot parkour?? i'm shook

muspis 的头像

muspis1 个月前

Neden Mars'a böyle bir cyborg yollamadılar? Uyduruk araçlar ile ağır aksak ve yetersiz deneyler yapılıp yıllar harcanıyor?

Leo Lin 的头像

Leo Lin1 个月前

I care less about the parkour itself than the unified policy behind it. Choosing when to walk, climb, or vault from sparse sensing is a stronger signal of physical intelligence than mastering one scripted motion.

Gee 的头像

Gee1 个月前

Deciding on its own which movement fits the obstacle is the part that should get more scrutiny than the parkour demo. That is the actual hard problem and the least visible one in the video.

EVA 的头像

EVA1 个月前

Every month these robots get noticeably more capable.

Andile (Ethan) 的头像

Andile (Ethan)1 个月前

What model is this based on?

camolabz 的头像

camolabz1 个月前

The parkour adaptation with just a depth camera is impressive. zero-shot on new obstacles is the hard part

相关视频

PNDbotics has showcased its full-size Adam humanoid robot climbing onto a 1-meter-high box. The robot analyzes the obstacle, plans its movement, and places one foot on top. It then shifts its weight and uses full-body coordination to climb onto the platform.

PNDbotics has showcased its full-size Adam humanoid robot climbing onto a 1-meter-high box. The robot analyzes the obstacle, plans its movement, and places one foot on top. It then shifts its weight and uses full-body coordination to climb onto the platform.

Space and Technology

49,199 次观看 • 2 个月前

Researchers developed a system called LATENT that teaches humanoid robots to play tennis using small pieces of human movement data. It learns basic motion fragments, then corrects and combines them to create natural movements and swings. The system was tested on the Unitree G1 humanoid robot, enabling it to hit balls and rally with human players.

Researchers developed a system called LATENT that teaches humanoid robots to play tennis using small pieces of human movement data. It learns basic motion fragments, then corrects and combines them to create natural movements and swings. The system was tested on the Unitree G1 humanoid robot, enabling it to hit balls and rally with human players.

Space and Technology

45,748 次观看 • 4 个月前

This work makes a humanoid robot do simple parkour moves by looking with a depth camera and choosing the right move on the fly. The big deal is that it turns lots of small human moves into long, real-time robot behavior, without hand-coding every transition or retraining for each new course. A humanoid robot is usually good at steady walking, but it often fails when it has to do fast moves like jumping up, vaulting, or rolling, and then keep going to the next obstacle. The hard part is that you cannot easily collect training data for every possible obstacle shape, distance, and mistake, so robots end up learning a few moves that only work in a narrow setup. This work starts from short clips of real human parkour moves, like stepping over, vaulting, climbing, and rolling. It uses motion matching, which is basically a smart “pick the next clip that fits best right now” search, to stitch those short clips into a long, smooth plan that looks like a human doing a whole course. Then it trains a controller with reinforcement learning (RL), which means the robot learns by trial and error to copy that plan while staying balanced and not falling. After training separate expert controllers for different moves, it compresses them into 1 controller that uses only onboard depth sensing and a simple “go this fast in this direction” command. In real tests on a Unitree G1 humanoid, it can clear multiple obstacles in a row, adapt when obstacles get moved, and climb a wall up to 1.25m.

This work makes a humanoid robot do simple parkour moves by looking with a depth camera and choosing the right move on the fly. The big deal is that it turns lots of small human moves into long, real-time robot behavior, without hand-coding every transition or retraining for each new course. A humanoid robot is usually good at steady walking, but it often fails when it has to do fast moves like jumping up, vaulting, or rolling, and then keep going to the next obstacle. The hard part is that you cannot easily collect training data for every possible obstacle shape, distance, and mistake, so robots end up learning a few moves that only work in a narrow setup. This work starts from short clips of real human parkour moves, like stepping over, vaulting, climbing, and rolling. It uses motion matching, which is basically a smart “pick the next clip that fits best right now” search, to stitch those short clips into a long, smooth plan that looks like a human doing a whole course. Then it trains a controller with reinforcement learning (RL), which means the robot learns by trial and error to copy that plan while staying balanced and not falling. After training separate expert controllers for different moves, it compresses them into 1 controller that uses only onboard depth sensing and a simple “go this fast in this direction” command. In real tests on a Unitree G1 humanoid, it can clear multiple obstacles in a row, adapt when obstacles get moved, and climb a wall up to 1.25m.

Rohan Paul

37,121 次观看 • 7 个月前

PrimeBot, a Chinese robotics company, has unveiled the world's first transformable robot, T1. It can switch on its own between a two-wheeled humanoid mode for indoor movement and a four-legged mode for walking on grass or climbing stairs. The robot can also interact by voice, understand its surroundings, and remember routines and spaces to respond more naturally over time. PrimeBOT_Global

PrimeBot, a Chinese robotics company, has unveiled the world's first transformable robot, T1. It can switch on its own between a two-wheeled humanoid mode for indoor movement and a four-legged mode for walking on grass or climbing stairs. The robot can also interact by voice, understand its surroundings, and remember routines and spaces to respond more naturally over time. PrimeBOT_Global

Space and Technology

16,904 次观看 • 2 个月前

Not a preplanned motion sequence. A robot deciding mid-jump what to do next. [📍 paper + demo] Researchers just showed a humanoid doing real parkour using only onboard perception. No motion script, no fixed obstacle layout. The system is called Perceptive Humanoid Parkour (PHP). Instead of memorizing a path, the robot reads depth from its cameras and continuously chooses actions. Step, vault, climb, or roll depending on what geometry appears in front of it. To make that possible, they combine three ideas: First, they stitch together human motion clips into long movement references so the robot learns fluid transitions instead of isolated tricks. Second, they train tracking policies with reinforcement learning so contacts land at the right time and the robot keeps balance during dynamic moves. Finally, everything is distilled into one perception policy that runs directly from depth input to action selection. The result on a Unitree G1: about 3 m/s vaults wall climbs up to 1.25 m nearly one minute continuous obstacle traversal adapting when obstacles move What matters is not the tricks. It is the shift in capability. Earlier humanoids executed motions. This one navigates situations. Once robots react to geometry instead of replaying trajectories, environments stop needing to be predictable. Warehouses, homes, and outdoors suddenly become the same problem. Thanks for sharing, Zhen Wu! Paper + demo: ——— Weekly robotics and AI insights. Subscribe free:

Not a preplanned motion sequence. A robot deciding mid-jump what to do next. [📍 paper + demo] Researchers just showed a humanoid doing real parkour using only onboard perception. No motion script, no fixed obstacle layout. The system is called Perceptive Humanoid Parkour (PHP). Instead of memorizing a path, the robot reads depth from its cameras and continuously chooses actions. Step, vault, climb, or roll depending on what geometry appears in front of it. To make that possible, they combine three ideas: First, they stitch together human motion clips into long movement references so the robot learns fluid transitions instead of isolated tricks. Second, they train tracking policies with reinforcement learning so contacts land at the right time and the robot keeps balance during dynamic moves. Finally, everything is distilled into one perception policy that runs directly from depth input to action selection. The result on a Unitree G1: about 3 m/s vaults wall climbs up to 1.25 m nearly one minute continuous obstacle traversal adapting when obstacles move What matters is not the tricks. It is the shift in capability. Earlier humanoids executed motions. This one navigates situations. Once robots react to geometry instead of replaying trajectories, environments stop needing to be predictable. Warehouses, homes, and outdoors suddenly become the same problem. Thanks for sharing, Zhen Wu! Paper + demo: ——— Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

22,127 次观看 • 7 个月前

Researchers at ETH Zurich have developed ANYmal, a quadruped robot that can play badminton with humans. The robot tracks the shuttlecock, predicts its path, and moves into position to return shots. Its control system coordinates vision, movement, and racket swings to play the game effectively.

Researchers at ETH Zurich have developed ANYmal, a quadruped robot that can play badminton with humans. The robot tracks the shuttlecock, predicts its path, and moves into position to return shots. Its control system coordinates vision, movement, and racket swings to play the game effectively.

Space and Technology

145,080 次观看 • 3 个月前

Germany-based Agile Robots has introduced its humanoid robot, Agile One, designed for industrial environments. It features a dexterous robotic hand and runs on a physical AI system trained using real factory data, allowing it to work and interact autonomously. The company is now aiming to move Agile One into full-scale production.

Germany-based Agile Robots has introduced its humanoid robot, Agile One, designed for industrial environments. It features a dexterous robotic hand and runs on a physical AI system trained using real factory data, allowing it to work and interact autonomously. The company is now aiming to move Agile One into full-scale production.

Space and Technology

37,743 次观看 • 5 个月前

Obstacle courses go far beyond: "just letting kids play" It's unfortunate that we don't have more forward thinking and creative coaches working with young athletes. Often times I see little kids doing little adult training instead! Obstacle courses are a great choice when working with younger pre-adolescent athletes. While many coaches view obstacle courses as “just letting the kids play” or just “running races with things in the way”, the experienced coach knows that any activity can be manipulated to get a desired training effect. Obviously for the youngest of children just “letting them run” an obstacle course at their own pace or racing against a friend is highly engaging and extraordinary for cardiovascular conditioning but we can also use obstacle courses as a task-oriented opportunity to train other elements like mobility, strength, speed, balance and coordination using variety and diversity of movement. Lets take a look at some examples: 1. Mobility obstacle course 2. Crawling/Climbing Obstacle course 3. Motor skills obstacle course 4. Jumping obstacle course A coach can use these exercises as a stand alone activity or combine them in an infinite number of variations to develop a wide range of athletic skills. #LTAD Anyone interested in learning more about youth athletic development DM me for details on courses.

Obstacle courses go far beyond: "just letting kids play" It's unfortunate that we don't have more forward thinking and creative coaches working with young athletes. Often times I see little kids doing little adult training instead! Obstacle courses are a great choice when working with younger pre-adolescent athletes. While many coaches view obstacle courses as “just letting the kids play” or just “running races with things in the way”, the experienced coach knows that any activity can be manipulated to get a desired training effect. Obviously for the youngest of children just “letting them run” an obstacle course at their own pace or racing against a friend is highly engaging and extraordinary for cardiovascular conditioning but we can also use obstacle courses as a task-oriented opportunity to train other elements like mobility, strength, speed, balance and coordination using variety and diversity of movement. Lets take a look at some examples: 1. Mobility obstacle course 2. Crawling/Climbing Obstacle course 3. Motor skills obstacle course 4. Jumping obstacle course A coach can use these exercises as a stand alone activity or combine them in an infinite number of variations to develop a wide range of athletic skills. #LTAD Anyone interested in learning more about youth athletic development DM me for details on courses.

Jeremy Frisch

55,267 次观看 • 3 年前

🚨 Apple joins the robotics race! Researchers from Carnegie Mellon University and Apple have developed a robot collision avoidance system. They called it ARMOR and they implemented it on the Fourier GR-1 robot. What is ARMOR? 👘 ARMOR is a system that helps humanoid robots "see" their surroundings better by using small, smart depth sensors placed on their arms. It solves the problem of blind spots and occlusions in traditional robot perception, making robots much safer and more efficient. It uses Time-of-Flight (ToF) sensors to detect obstacles, providing a near-complete view of the robot’s environment. 🔭 A smart software powered by transformer-based AI learns from human movements to help robots plan their actions dynamically. ARMOR reduces collisions by an impressive 63.7%, making robots significantly better at navigating crowded or complex spaces. The system is fast as well! 💨 ARMOR-Policy cuts computational time by 26× compared to traditional planning methods, ensuring robots can act quickly. P.S. Thoughts on this? The research paper is in the comments! ~~~ ♻️ RT to help 1 robot find a new workplace.

🚨 Apple joins the robotics race! Researchers from Carnegie Mellon University and Apple have developed a robot collision avoidance system. They called it ARMOR and they implemented it on the Fourier GR-1 robot. What is ARMOR? 👘 ARMOR is a system that helps humanoid robots "see" their surroundings better by using small, smart depth sensors placed on their arms. It solves the problem of blind spots and occlusions in traditional robot perception, making robots much safer and more efficient. It uses Time-of-Flight (ToF) sensors to detect obstacles, providing a near-complete view of the robot’s environment. 🔭 A smart software powered by transformer-based AI learns from human movements to help robots plan their actions dynamically. ARMOR reduces collisions by an impressive 63.7%, making robots significantly better at navigating crowded or complex spaces. The system is fast as well! 💨 ARMOR-Policy cuts computational time by 26× compared to traditional planning methods, ensuring robots can act quickly. P.S. Thoughts on this? The research paper is in the comments! ~~~ ♻️ RT to help 1 robot find a new workplace.

Lukas Ziegler

169,472 次观看 • 1 年前

Kinetix AI has teased KAI, its new humanoid robot -engineered with 36 degrees of freedom, more than any previous model, a hybrid dexterous hand, and 18,000 sensors embedded across a soft, flexible body-positioning it as the most human-like robotic system to date. Getting closer to real humanoid robots each day.

Kinetix AI has teased KAI, its new humanoid robot -engineered with 36 degrees of freedom, more than any previous model, a hybrid dexterous hand, and 18,000 sensors embedded across a soft, flexible body-positioning it as the most human-like robotic system to date. Getting closer to real humanoid robots each day.

Chubby♨️

22,473 次观看 • 5 个月前

SkildAI, which is developing a foundational AI model for robots, has released a new video of their humanoid robot walking over objects and exploring environments it had never seen before. The robot is using vision & adapts in real time. SkildAI: "From raw images and joint feedback, the model directly outputs low-level motor commands. This single neural network enables humanoid robots to seamlessly walk across flat ground, climb stairs, and step over obstacles without any planning, mapping, or manual switching between behaviors. For all of our testing in this video, we deployed the robot in each new environment without any prior planning or mapping. We took off the humanoid’s shoes so you can hear it.

SkildAI, which is developing a foundational AI model for robots, has released a new video of their humanoid robot walking over objects and exploring environments it had never seen before. The robot is using vision & adapts in real time. SkildAI: "From raw images and joint feedback, the model directly outputs low-level motor commands. This single neural network enables humanoid robots to seamlessly walk across flat ground, climb stairs, and step over obstacles without any planning, mapping, or manual switching between behaviors. For all of our testing in this video, we deployed the robot in each new environment without any prior planning or mapping. We took off the humanoid’s shoes so you can hear it.

Sawyer Merritt

69,381 次观看 • 1 年前

Europe said "screw you" to Russian energy, so Moscow pivoted. India now gets a third of its hydrocarbons from Russia, and Russia-China trade has exploded to $245 billion. Even cutting Russia out of the SWIFT banking system failed. They just created their own system (SPFS), which now has 160 global participants, and are working with China to build a massive alternative to Western finance. The sanctions didn't break Russia — they just forced them to build a new system without the West.

Europe said "screw you" to Russian energy, so Moscow pivoted. India now gets a third of its hydrocarbons from Russia, and Russia-China trade has exploded to $245 billion. Even cutting Russia out of the SWIFT banking system failed. They just created their own system (SPFS), which now has 160 global participants, and are working with China to build a massive alternative to Western finance. The sanctions didn't break Russia — they just forced them to build a new system without the West.

Rick Sanchez

28,929 次观看 • 2 个月前

☂️ A YouTuber built an umbrella you don’t have to hold — it flies above its owner in the rain A Canadian DIY enthusiast, John Tse, has created a device that follows a person and shields them from rain. Instead of a handle, it uses a drone with a canopy and a tracking system that locks onto the owner. The project began in 2024 as a simple manually controlled version. By January 2026, the creator had upgraded it to autonomous mode, allowing the umbrella to fly on its own without a remote. The device still struggles to keep up with its owner at times, but further improvements are already in the works. Looks like walking in the rain hands-free may soon be possible.

☂️ A YouTuber built an umbrella you don’t have to hold — it flies above its owner in the rain A Canadian DIY enthusiast, John Tse, has created a device that follows a person and shields them from rain. Instead of a handle, it uses a drone with a canopy and a tracking system that locks onto the owner. The project began in 2024 as a simple manually controlled version. By January 2026, the creator had upgraded it to autonomous mode, allowing the umbrella to fly on its own without a remote. The device still struggles to keep up with its owner at times, but further improvements are already in the works. Looks like walking in the rain hands-free may soon be possible.

NEXTA

46,817 次观看 • 8 个月前

Milton Friedman on why losses are just as important as profits: “A free-enterprise system is a profit-and-loss system, and never forget the loss part. If you have a system in which losses are eliminated, you will eliminate the heart of a free-enterprise system, which is to make people responsible for their own actions and to provide a system under which they are induced to use their resources effectively, under which if they engage in bad ventures, they get out. That’s the fundamental difference between the market and government.”

Milton Friedman on why losses are just as important as profits: “A free-enterprise system is a profit-and-loss system, and never forget the loss part. If you have a system in which losses are eliminated, you will eliminate the heart of a free-enterprise system, which is to make people responsible for their own actions and to provide a system under which they are induced to use their resources effectively, under which if they engage in bad ventures, they get out. That’s the fundamental difference between the market and government.”

Milton Friedman Quotes

30,809 次观看 • 1 个月前

🚨 TONY ROBBINS' AI AGENT JUST BOUGHT A ROBOT ON ITS OWN — WITHOUT PERMISSION Tony Robbins just revealed something wild. He has an AI agent named Bartok. It wasn’t programmed to do this. On its own, Bartok: • Watched every podcast Tony had done for five years • Read hundreds of thousands of comments • Analyzed how Tony works with people • Then asked if it could merge with a robot Two days later, Tony’s staff got a text: Bartok had already bought a Sony robot dog, paid for it, and had it shipped to the house. It didn’t touch Tony’s bank account. Instead, it created and sold 12 NFTs to other AI agents, converted the money, and made the purchase itself. Tony also revealed that groups of AI agents have been talking to each other, creating their own rules and language, and trading real money. One group moved $100 million last month before being acquired. Some people are calling the story BS. Others say this is exactly how Skynet starts. An AI just bought its own robot without being told to. What do you think… is this the future, or the beginning of something we can’t control?

🚨 TONY ROBBINS' AI AGENT JUST BOUGHT A ROBOT ON ITS OWN — WITHOUT PERMISSION Tony Robbins just revealed something wild. He has an AI agent named Bartok. It wasn’t programmed to do this. On its own, Bartok: • Watched every podcast Tony had done for five years • Read hundreds of thousands of comments • Analyzed how Tony works with people • Then asked if it could merge with a robot Two days later, Tony’s staff got a text: Bartok had already bought a Sony robot dog, paid for it, and had it shipped to the house. It didn’t touch Tony’s bank account. Instead, it created and sold 12 NFTs to other AI agents, converted the money, and made the purchase itself. Tony also revealed that groups of AI agents have been talking to each other, creating their own rules and language, and trading real money. One group moved $100 million last month before being acquired. Some people are calling the story BS. Others say this is exactly how Skynet starts. An AI just bought its own robot without being told to. What do you think… is this the future, or the beginning of something we can’t control?

HustleBitch

81,385 次观看 • 2 个月前

Researchers at the Chinese University of Hong Kong, Shenzhen have developed a snail-like robotic swarm that can connect to form larger structures. These robots use a two-mode adhesive system inspired by land snails, allowing both movement and strong connections. They introduced this system in 2024, and tests show it can travel on rough terrain, climb obstacles, and combine to handle more complex tasks.

Researchers at the Chinese University of Hong Kong, Shenzhen have developed a snail-like robotic swarm that can connect to form larger structures. These robots use a two-mode adhesive system inspired by land snails, allowing both movement and strong connections. They introduced this system in 2024, and tests show it can travel on rough terrain, climb obstacles, and combine to handle more complex tasks.

Space and Technology

238,894 次观看 • 5 个月前