Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Teaching robots to work smoothly with humans! 👀 Soon enough, a robot will be standing in the garage holding a flashlight for your dad, and doing a better job of it than you ever did. 🔦 Carnegie Mellon University and The University of Texas at Arlington researchers introduced HALO,... a new method for robots to collaborate better with humans. When robots work with humans, they face unpredictable behavior. Every person moves differently, makes different decisions, and reacts differently to the robot. Traditional learning approaches struggle because the robot and human are fundamentally different, they think and move in completely different ways. This mismatch causes the robot's learning to become unstable, like trying to balance on a wobbly chair. Mentioned research solves this by mathematically guaranteeing the robot's learning stays stable. Pushing objects together in sync, transporting items through tight spaces, and handling super-long objects that require coordination. Real humanoid-robot experiments show HALO handles tricky collaborative situations much better. How it works? It basically has 3 layers. Vision layer understands what needs to happen by looking at the scene. Coordination layer figures out how the robot and human should work together tactically. Control layer executes the movements with fast, stable whole-body control. 📜 Paper website: Congrats Ding Zhao + all co-authors! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →show more

Lukas Ziegler

56,509 subscribers

28,192 Aufrufe • vor 2 Monaten •via X (Twitter)

Bildung Gesundheit & Wellness Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

🚨 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 Aufrufe • vor 1 Jahr

Brain-controlled exoskeletons to train humanoid robots! 🧠 Fourier just presented human tele-operators using brain control interfaces and exoskeletal arms to train humanoid robots on home tasks. The brain control interface is the interesting part. Instead of using a controller or joystick to teleoperate, the operator's movements and intentions are captured more naturally through the exoskeleton and BCI. This means the demonstrations are more fluid, more human-like, and better suited for training robots to perform delicate home tasks. Multiple tele-operators are simultaneously generating training data across multiple robots. This is how you build the dataset needed for eventual full autonomy, without waiting years for it to arrive. This might be the bridge between "robots that work in controlled environments" and "robots that work in homes." Not full autonomy right away, but trusted human intelligence operating through a robot body, getting better with every task completed. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Brain-controlled exoskeletons to train humanoid robots! 🧠 Fourier just presented human tele-operators using brain control interfaces and exoskeletal arms to train humanoid robots on home tasks. The brain control interface is the interesting part. Instead of using a controller or joystick to teleoperate, the operator's movements and intentions are captured more naturally through the exoskeleton and BCI. This means the demonstrations are more fluid, more human-like, and better suited for training robots to perform delicate home tasks. Multiple tele-operators are simultaneously generating training data across multiple robots. This is how you build the dataset needed for eventual full autonomy, without waiting years for it to arrive. This might be the bridge between "robots that work in controlled environments" and "robots that work in homes." Not full autonomy right away, but trusted human intelligence operating through a robot body, getting better with every task completed. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

20,898 Aufrufe • vor 5 Monaten

🇨🇦 ROBOT HANDS JUST LEVELED UP IN CANADA Sanctuary AI showed off a robotic hand that uses hydraulic power to grip, twist, and move like a real one. The hand can handle delicate objects, like dice, without crushing them, proving robots are getting scary precise. Hydraulic actuation gives the robot smoother, stronger control, making it better for heavy industrial work and tricky small tasks. This could change how robots work in factories, warehouses, or even in jobs too dangerous for humans. The future of robot hands? Less clunky claws, more human-like grip power with machine muscle. Source: Wevolver

🇨🇦 ROBOT HANDS JUST LEVELED UP IN CANADA Sanctuary AI showed off a robotic hand that uses hydraulic power to grip, twist, and move like a real one. The hand can handle delicate objects, like dice, without crushing them, proving robots are getting scary precise. Hydraulic actuation gives the robot smoother, stronger control, making it better for heavy industrial work and tricky small tasks. This could change how robots work in factories, warehouses, or even in jobs too dangerous for humans. The future of robot hands? Less clunky claws, more human-like grip power with machine muscle. Source: Wevolver

Mario Nawfal

50,661 Aufrufe • vor 10 Monaten

A pentagon robot! 🖐🏽 Compared to typical SCARA models, it delivers higher speed, improved stability, better space efficiency, and can operate smoothly in tight areas, even through singularity positions. These robots are a good fit for handling complex tasks in challenging environments where conventional robots often fall short. Have you ever seen a robot like this? 👀 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

A pentagon robot! 🖐🏽 Compared to typical SCARA models, it delivers higher speed, improved stability, better space efficiency, and can operate smoothly in tight areas, even through singularity positions. These robots are a good fit for handling complex tasks in challenging environments where conventional robots often fall short. Have you ever seen a robot like this? 👀 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

42,565 Aufrufe • vor 3 Monaten

A robot with wheels and legs! 🦿 Wheeled mobile robots are popular in many fields because they are stable, efficient, and simple to build. However, they often occupy more space than humans and struggle to navigate crowded hallways, ramps, or elevators. 🛗 To address this, a robot developed at the Korea University of Technology and Education combines legs for extra support and mecanum wheels for smooth, all-directional movement. It has a slim, human-like design with four wheel-leg mechanisms, each using a special 2-DOF leg and a mecanum wheel. A unique mechanism keeps the wheels steady while the legs move, helping the robot stay agile and absorb shocks. The design also reduces strain on the motors, making it more efficient. Tests showed that the robot could move quickly, climb steps, and navigate elevators with people. Research paper in the comments! 🗞️ ~~~ ♻️ R to help 1 robot find a new workplace.

A robot with wheels and legs! 🦿 Wheeled mobile robots are popular in many fields because they are stable, efficient, and simple to build. However, they often occupy more space than humans and struggle to navigate crowded hallways, ramps, or elevators. 🛗 To address this, a robot developed at the Korea University of Technology and Education combines legs for extra support and mecanum wheels for smooth, all-directional movement. It has a slim, human-like design with four wheel-leg mechanisms, each using a special 2-DOF leg and a mecanum wheel. A unique mechanism keeps the wheels steady while the legs move, helping the robot stay agile and absorb shocks. The design also reduces strain on the motors, making it more efficient. Tests showed that the robot could move quickly, climb steps, and navigate elevators with people. Research paper in the comments! 🗞️ ~~~ ♻️ R to help 1 robot find a new workplace.

Lukas Ziegler

35,663 Aufrufe • vor 1 Jahr

Six arms instead of two! 🤯 Midea Group humanoid robot has six arms instead of two. It handles heavy components with lower limbs and performs fine assembly work with upper limbs. Full 360-degree rotation, stable vertical lifting, rapid tool-swapping. The robot handles workstation transitions that would typically require multiple human workers or separate machines. So no idle-time between stations. Pretty cool. But I'm really curious about the cost, and how this 6-arms robot compares to a regular robot arm, and then to a regular humanoid What do yo think? Overcomplicated? ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Six arms instead of two! 🤯 Midea Group humanoid robot has six arms instead of two. It handles heavy components with lower limbs and performs fine assembly work with upper limbs. Full 360-degree rotation, stable vertical lifting, rapid tool-swapping. The robot handles workstation transitions that would typically require multiple human workers or separate machines. So no idle-time between stations. Pretty cool. But I'm really curious about the cost, and how this 6-arms robot compares to a regular robot arm, and then to a regular humanoid What do yo think? Overcomplicated? ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

12,841 Aufrufe • vor 1 Monat

NEO robot achieves “almost human-like” hand dexterity The Norwegian-American startup 1X has demonstrated new capabilities of its humanoid robot NEO — it has learned to perform fine motor tasks at a level close to humans. The robot can assemble Lego, eat chips, play video games, screw in a light bulb, pick a grape, and carefully hold a wine glass. Previously, one of the biggest challenges for robots was handling small objects — they struggled to understand how much force was needed to grip them. NEO solves this problem with cable-driven actuators and a force-control system: each joint moves the finger while simultaneously measuring pressure. The developers believe these technologies could become an important step toward the creation of universal home robots.

NEO robot achieves “almost human-like” hand dexterity The Norwegian-American startup 1X has demonstrated new capabilities of its humanoid robot NEO — it has learned to perform fine motor tasks at a level close to humans. The robot can assemble Lego, eat chips, play video games, screw in a light bulb, pick a grape, and carefully hold a wine glass. Previously, one of the biggest challenges for robots was handling small objects — they struggled to understand how much force was needed to grip them. NEO solves this problem with cable-driven actuators and a force-control system: each joint moves the finger while simultaneously measuring pressure. The developers believe these technologies could become an important step toward the creation of universal home robots.

NEXTA

45,406 Aufrufe • vor 1 Tag

China unveils humanoid robot with lifelike skin and blinking eyes built for daily life | Prabhat Ranjan Mishra, Interesting Engineering Large Language Models (LLMs) and Vision-Language Models (VLMs) help process and interpret complex data from human interactions. A Shanghai-based company has developed humanoid robots that appear as real as humans. The advanced bionic humanoid robot is integrated with self-supervised AI algorithms. Named Elf V1, the robot can perceive the world, communicate, learn, and interact intelligently with its surroundings. Developed by AheadForm Technology, the robot offers up to 30 degrees of freedom, powered by a precise control system and an advanced AI learning algorithm. Robot offers expressive facial features The robot offers expressive facial features, moving eyes, and synchronized speech. It can also convey emotions and understand human non-verbal cues, making interactions more natural and engaging. The robot has highly interactive capabilities and lifelike appearances. AheadForm expects that its robots could soon seamlessly integrate into daily life, providing assistance, companionship, and support across various industries. “We believe that by developing realistic and expressive robot heads, we can bridge the gap between humans and machines, fostering a new era of interactive and intelligent robotics,” said the company in a statement. Reports revealed that to avoid the “uncanny valley” effect and be able to interact with us, they are given lifelike skin and capabilities to read our emotions and respond appropriately using dynamic expression simulation and emotion generation tech. Bionic skin and high-precision control system The Elf V1 series of humanoids features 30 facial muscles animated by brushless micro-motors and managed by a high-precision control system. Paired with an ability to detect their users’ emotions with low latency and bionic skin, their facial expressions are nearly identical to those of humans, reported CGTN. The company claims it’s pioneering the development of realistic humanoid robots designed to revolutionize human-robot interaction. It’s enhancing sophisticated humanoid robot heads that can express emotions, perceive their environment, and interact seamlessly with humans. By combining cutting-edge AI and advanced robotics, AheadForm aims to bring life to machines and transform how humans engage with technology. AI models boost robots’ responsiveness Seamless integration of Large Language Models (LLMs) and Vision-Language Models (VLMs) into the humanoid robots can help them process and interpret complex data from human interactions, enabling the robot to learn and adapt in real-time, achieving human-level understanding and responsiveness. AheadForm uses Brushless Motors that deliver ultra-quiet operation and high responsiveness, specifically designed for precision facial movements in humanoid robots. With its compact size, lightweight design, and energy efficiency, this motor is the ideal choice for next-generation robots that require precise, subtle facial control to create a truly human-like experience. Previously, the company unveiled the Lan Series that features realistic humanoid robots with soft skin and 10 degrees of freedom, offering a lifelike appearance and intuitive movements. This series is designed for cost-efficiency, for applications prioritizing mobility and manipulation.

China unveils humanoid robot with lifelike skin and blinking eyes built for daily life | Prabhat Ranjan Mishra, Interesting Engineering Large Language Models (LLMs) and Vision-Language Models (VLMs) help process and interpret complex data from human interactions. A Shanghai-based company has developed humanoid robots that appear as real as humans. The advanced bionic humanoid robot is integrated with self-supervised AI algorithms. Named Elf V1, the robot can perceive the world, communicate, learn, and interact intelligently with its surroundings. Developed by AheadForm Technology, the robot offers up to 30 degrees of freedom, powered by a precise control system and an advanced AI learning algorithm. Robot offers expressive facial features The robot offers expressive facial features, moving eyes, and synchronized speech. It can also convey emotions and understand human non-verbal cues, making interactions more natural and engaging. The robot has highly interactive capabilities and lifelike appearances. AheadForm expects that its robots could soon seamlessly integrate into daily life, providing assistance, companionship, and support across various industries. “We believe that by developing realistic and expressive robot heads, we can bridge the gap between humans and machines, fostering a new era of interactive and intelligent robotics,” said the company in a statement. Reports revealed that to avoid the “uncanny valley” effect and be able to interact with us, they are given lifelike skin and capabilities to read our emotions and respond appropriately using dynamic expression simulation and emotion generation tech. Bionic skin and high-precision control system The Elf V1 series of humanoids features 30 facial muscles animated by brushless micro-motors and managed by a high-precision control system. Paired with an ability to detect their users’ emotions with low latency and bionic skin, their facial expressions are nearly identical to those of humans, reported CGTN. The company claims it’s pioneering the development of realistic humanoid robots designed to revolutionize human-robot interaction. It’s enhancing sophisticated humanoid robot heads that can express emotions, perceive their environment, and interact seamlessly with humans. By combining cutting-edge AI and advanced robotics, AheadForm aims to bring life to machines and transform how humans engage with technology. AI models boost robots’ responsiveness Seamless integration of Large Language Models (LLMs) and Vision-Language Models (VLMs) into the humanoid robots can help them process and interpret complex data from human interactions, enabling the robot to learn and adapt in real-time, achieving human-level understanding and responsiveness. AheadForm uses Brushless Motors that deliver ultra-quiet operation and high responsiveness, specifically designed for precision facial movements in humanoid robots. With its compact size, lightweight design, and energy efficiency, this motor is the ideal choice for next-generation robots that require precise, subtle facial control to create a truly human-like experience. Previously, the company unveiled the Lan Series that features realistic humanoid robots with soft skin and 10 degrees of freedom, offering a lifelike appearance and intuitive movements. This series is designed for cost-efficiency, for applications prioritizing mobility and manipulation.

Owen Gregorian

179,005 Aufrufe • vor 9 Monaten

Robot dog learned dexterity! 🤯 Robots usually struggle to move and handle objects at the same time, a challenge called loco-manipulation. Researchers at the RAI Institute have developed a new system called ReLIC that makes this easier. Instead of giving robots fixed roles for arms and legs, ReLIC lets them switch roles on the fly, for example, using a leg to help lift something while balancing on the others. This approach is more natural, similar to how humans use different body parts together without thinking about it. ReLIC was tested on a four-legged robot, which successfully performed tasks like moving boxes, opening drawers, and placing items into containers.

Robot dog learned dexterity! 🤯 Robots usually struggle to move and handle objects at the same time, a challenge called loco-manipulation. Researchers at the RAI Institute have developed a new system called ReLIC that makes this easier. Instead of giving robots fixed roles for arms and legs, ReLIC lets them switch roles on the fly, for example, using a leg to help lift something while balancing on the others. This approach is more natural, similar to how humans use different body parts together without thinking about it. ReLIC was tested on a four-legged robot, which successfully performed tasks like moving boxes, opening drawers, and placing items into containers.

Lukas Ziegler

19,743 Aufrufe • vor 9 Monaten

Elon Musk: Humanoid Robots Could Be The Biggest Opportunity Ever Elon expanded on the massive market size for Optimus at last year's All-In Summit: "I think the useful humanoid robot opportunity is the single biggest opportunity ever." "You could expect that in high volume, sort of the million unit-plus per year level ... basically think of it like Optimus will cost less than a small car." "It's probably like $20,000 for a humanoid robot that can be your buddy, like a combination of R2-D2 and C-3PO, but better." "I think the number of robots will vastly exceed the number of humans." "Who would not want their robot buddy? Everyone wants a robot buddy." "Especially if it can take your dog for a walk. It could mow the lawn. It could watch your kids. It could teach your kids." "I think the ratio of humanoid robots to humans is gonna be at least 2-to-1, maybe 3-to-1." "Everybody will want one, and then there'll be a bunch of robots that you don't see that are making goods and services." Recorded: Sept 9, 2024 Join us in 2025:

Elon Musk: Humanoid Robots Could Be The Biggest Opportunity Ever Elon expanded on the massive market size for Optimus at last year's All-In Summit: "I think the useful humanoid robot opportunity is the single biggest opportunity ever." "You could expect that in high volume, sort of the million unit-plus per year level ... basically think of it like Optimus will cost less than a small car." "It's probably like $20,000 for a humanoid robot that can be your buddy, like a combination of R2-D2 and C-3PO, but better." "I think the number of robots will vastly exceed the number of humans." "Who would not want their robot buddy? Everyone wants a robot buddy." "Especially if it can take your dog for a walk. It could mow the lawn. It could watch your kids. It could teach your kids." "I think the ratio of humanoid robots to humans is gonna be at least 2-to-1, maybe 3-to-1." "Everybody will want one, and then there'll be a bunch of robots that you don't see that are making goods and services." Recorded: Sept 9, 2024 Join us in 2025:

The All-In Podcast

27,525 Aufrufe • vor 1 Jahr

Robots might learn better from video than from language! 📼 Most Vision-Language-Action (VLA) models learn what to do from text, but still struggle with how things move in the real world. That makes them data-hungry and slow to train. mimic video takes a different route. Instead of grounding robot control in text, it grounds it in video, using large pre-trained video models that already capture physical motion and dynamics. The idea is straightforward: let the video model handle “what will happen next,” and let a smaller control model focus only on turning that visual plan into robot actions. The result is big gains in practice. Robots trained this way need 10× less data, converge twice as fast, and perform better on both simulated benchmarks and real bimanual manipulation tasks. If robots can “imagine” motion using video, control becomes a much simpler problem. Shoutout to Jonas Pai, Liam Achenbach, Oier Mees, Elvis Nava and the rest of the team! Here's the project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Robots might learn better from video than from language! 📼 Most Vision-Language-Action (VLA) models learn what to do from text, but still struggle with how things move in the real world. That makes them data-hungry and slow to train. mimic video takes a different route. Instead of grounding robot control in text, it grounds it in video, using large pre-trained video models that already capture physical motion and dynamics. The idea is straightforward: let the video model handle “what will happen next,” and let a smaller control model focus only on turning that visual plan into robot actions. The result is big gains in practice. Robots trained this way need 10× less data, converge twice as fast, and perform better on both simulated benchmarks and real bimanual manipulation tasks. If robots can “imagine” motion using video, control becomes a much simpler problem. Shoutout to Jonas Pai, Liam Achenbach, Oier Mees, Elvis Nava and the rest of the team! Here's the project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

49,920 Aufrufe • vor 6 Monaten

In order for robots to be deployed in the real world, performing tasks of real value, they must be reliable. Unfortunately, even more, most robotic demos work maybe 70-80% of the time at best. The way to get better reliability is to do real-world reinforcement learning: having the robot teach itself how to perform the task up to a high level of success. The key to doing this is to start with a core of expert human data, use that to train a policy then iteratively improve it, until finally finishing with on-policy reinforcement learning. Kun Lei talks through a unified framework for imitation and reinforcement learning based on PPO, which enables this improvement process. In this episode, Kun Lei explains the theory behind his reinforcement learning method and how it allowed his robot to run in a shopping mall juicing oranges for seven hours at a time, among experiments on a wide variety of tasks and embodiments. Watch episode 58 of RoboPapers now, hosted by Michael Cho - Rbt/Acc and Chris Paxton!

In order for robots to be deployed in the real world, performing tasks of real value, they must be reliable. Unfortunately, even more, most robotic demos work maybe 70-80% of the time at best. The way to get better reliability is to do real-world reinforcement learning: having the robot teach itself how to perform the task up to a high level of success. The key to doing this is to start with a core of expert human data, use that to train a policy then iteratively improve it, until finally finishing with on-policy reinforcement learning. Kun Lei talks through a unified framework for imitation and reinforcement learning based on PPO, which enables this improvement process. In this episode, Kun Lei explains the theory behind his reinforcement learning method and how it allowed his robot to run in a shopping mall juicing oranges for seven hours at a time, among experiments on a wide variety of tasks and embodiments. Watch episode 58 of RoboPapers now, hosted by Michael Cho - Rbt/Acc and Chris Paxton!

RoboPapers

18,813 Aufrufe • vor 6 Monaten

Humanoid robots are cool. But most of them aren’t ready for real-world work. X-Humanoid just launched Embodied Tien Kung 3.0 - a full-size humanoid robot built to actually operate in industrial and commercial environments. What makes it different? • Strong, high-torque joints for heavy tasks • Can move dynamically and stay stable • Handles complex motions (even over obstacles) • Millimeter-level precision for detailed work It runs on the Wise KaiWu AI platform, which allows the robot to see, think, and act in a continuous loop with less human control and support for multi-robot collaboration. It also supports ROS2, MQTT, and TCP/IP, and offers more open hardware + software interfaces to make development easier for teams. The goal is simple: make humanoid robots practical, easier to build on, and ready for real-world use. Visit: Check out the official launch video below to see what it can do! 👇 #Robotics #HumanoidRobot #AI

Humanoid robots are cool. But most of them aren’t ready for real-world work. X-Humanoid just launched Embodied Tien Kung 3.0 - a full-size humanoid robot built to actually operate in industrial and commercial environments. What makes it different? • Strong, high-torque joints for heavy tasks • Can move dynamically and stay stable • Handles complex motions (even over obstacles) • Millimeter-level precision for detailed work It runs on the Wise KaiWu AI platform, which allows the robot to see, think, and act in a continuous loop with less human control and support for multi-robot collaboration. It also supports ROS2, MQTT, and TCP/IP, and offers more open hardware + software interfaces to make development easier for teams. The goal is simple: make humanoid robots practical, easier to build on, and ready for real-world use. Visit: Check out the official launch video below to see what it can do! 👇 #Robotics #HumanoidRobot #AI

Chidanand Tripathi

69,604 Aufrufe • vor 4 Monaten

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 Aufrufe • vor 4 Monaten

Robotics is entering the mainstream! 👀 Let's accept this fact. Consumptionism – stonks. Possibilities (HW + SW) – stonks. Demographics - not stonks. Modern robots are often designed to interact with our legacy world, whether it's a household, a factory, or a shipyard. That means they often need to work with existing machines, tools, and spaces. In short: retrofitting. Improving old machines with new technologies without major interference in their operation. Modern way of integrating things. You don't have to change the entire environment to deploy a robot. The robot will adapt, just as human would when freshly hired. The promise is to have an army of robots to help with the world designed for us. I also believe that general purpose robots, are not a direct competition for single purpose machines (like a highly efficient specialized packaging machine, for example). It's like adding a robot to this carriage. Specialized machine could be a car ;) ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Robotics is entering the mainstream! 👀 Let's accept this fact. Consumptionism – stonks. Possibilities (HW + SW) – stonks. Demographics - not stonks. Modern robots are often designed to interact with our legacy world, whether it's a household, a factory, or a shipyard. That means they often need to work with existing machines, tools, and spaces. In short: retrofitting. Improving old machines with new technologies without major interference in their operation. Modern way of integrating things. You don't have to change the entire environment to deploy a robot. The robot will adapt, just as human would when freshly hired. The promise is to have an army of robots to help with the world designed for us. I also believe that general purpose robots, are not a direct competition for single purpose machines (like a highly efficient specialized packaging machine, for example). It's like adding a robot to this carriage. Specialized machine could be a car ;) ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

14,396 Aufrufe • vor 5 Monaten

All right, who wants a robot worm? 🪱 Researchers at Case Western Reserve University developed a robot inspired by earthworms. Worms move by using wave-like muscle contractions called peristalsis. This version of the worm-inspired robot has a flexible outer mesh that can continuously change shape. Using this mesh, the robot's fixed parts can move smoothly between each other, providing power and control. This project is referred to as a "soft hyper-redundant robot," due to its highly flexible nature and ability to adapt to various environments. This design could prove useful in scenarios where traditional rigid robots struggle, such as navigating tight spaces or uneven terrain. Please let me know what your thoughts are! 👀 🔔 Hit the bell on my profile to never miss a robot story!

Lukas Ziegler

24,755 Aufrufe • vor 1 Jahr

What if robots could learn real-world tasks from your perspective… without ever touching a robot? This is a system that trains robot policies using nothing but human-first, egocentric video data from smart glasses. No robots, no teleop, no sensors, just humans doing real tasks in the real world. Why it matters ✅ Learns robot policies from 20 minutes of human video; zero robot demos ✅ Generalizes to new objects, views, and even robot morphologies ✅ Uses 3D points for interpretable, spatially grounded learning ✅ Deploys directly to real-world robots with strong zero-shot success Thank you, Vincent Liu, for sharing!!! Learn more here: 🔗 Paper: 🌐 Website: 📍 BOOKMARK FOR LATER

What if robots could learn real-world tasks from your perspective… without ever touching a robot? This is a system that trains robot policies using nothing but human-first, egocentric video data from smart glasses. No robots, no teleop, no sensors, just humans doing real tasks in the real world. Why it matters ✅ Learns robot policies from 20 minutes of human video; zero robot demos ✅ Generalizes to new objects, views, and even robot morphologies ✅ Uses 3D points for interpretable, spatially grounded learning ✅ Deploys directly to real-world robots with strong zero-shot success Thank you, Vincent Liu, for sharing!!! Learn more here: 🔗 Paper: 🌐 Website: 📍 BOOKMARK FOR LATER

Ilir Aliu - eu/acc

10,509 Aufrufe • vor 1 Jahr

Robots with tentacles! 🐙 SpiRobs are soft robots inspired by nature, designed in the shape of a logarithmic spiral. They mimic the flexible movements of octopus arms and elephant trunks to grasp objects. 🐘 SpiRobs use simple cables to move, making them easy to control and operate. They can scale from small to large sizes, ranging from centimeters to meters. The robots can adapt to different object shapes, improving their grasping ability. A mini version can act as a tiny gripper, while a large version can be mounted on drones. Interestingly, multiple robots can work together to wrap around and hold large objects. That's just out of this world! 😮‍💨 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Robots with tentacles! 🐙 SpiRobs are soft robots inspired by nature, designed in the shape of a logarithmic spiral. They mimic the flexible movements of octopus arms and elephant trunks to grasp objects. 🐘 SpiRobs use simple cables to move, making them easy to control and operate. They can scale from small to large sizes, ranging from centimeters to meters. The robots can adapt to different object shapes, improving their grasping ability. A mini version can act as a tiny gripper, while a large version can be mounted on drones. Interestingly, multiple robots can work together to wrap around and hold large objects. That's just out of this world! 😮‍💨 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

121,234 Aufrufe • vor 6 Monaten

Experiments in progress. The one on the right has been learning for ~3 hours, the one in the middle for ~1 hour, and the one on the left just started a few minutes ago. The initial motivation for making the physical Atari was just to commit ourselves to a subset of algorithms that can make progress in this setup. This commitment rules out algorithms that require billions of samples to learn (or worse, require multiple environments running in parallel). Atari games are simple enough that we should be able to show learning on them in a short amount of time with no prior knowledge. Since then, I've realized that this setup is also a good way to compare different paradigms in robotics in a principled way. These paradigms are sim2real, learning from tele-operated data, and learning directly on the robots. So far, I have observed that getting sim2real to work reliably is hard. It requires tweaks that don't scale. Policies that can play perfectly in simulation fall apart because of latencies and the messiness of the real world. These aspects could be modeled to improve the simulation, but not without sinking significant human engineering hours. I have higher hopes for learning from tele-operated data, but that requires a human to learn the task first. These experiments are on my to-do list. I have to learn to play some of the games well through the robot. I’m half-decent at playing Pong and Ms Pacman now. Learning directly on robots is looking like the most promising approach. This approach takes away pesky distribution shifts and makes it possible to have algorithms that continually improve with more data and time without any human intervention. It feels great to let experiments run overnight and wake up to find improved policies. With learning on robots, I should, in principle, be able to go on a long vacation and come back to find better policies for complex tasks beyond Atari games. Whether that is possible with current learning algorithms is a different question.

Experiments in progress. The one on the right has been learning for ~3 hours, the one in the middle for ~1 hour, and the one on the left just started a few minutes ago. The initial motivation for making the physical Atari was just to commit ourselves to a subset of algorithms that can make progress in this setup. This commitment rules out algorithms that require billions of samples to learn (or worse, require multiple environments running in parallel). Atari games are simple enough that we should be able to show learning on them in a short amount of time with no prior knowledge. Since then, I've realized that this setup is also a good way to compare different paradigms in robotics in a principled way. These paradigms are sim2real, learning from tele-operated data, and learning directly on the robots. So far, I have observed that getting sim2real to work reliably is hard. It requires tweaks that don't scale. Policies that can play perfectly in simulation fall apart because of latencies and the messiness of the real world. These aspects could be modeled to improve the simulation, but not without sinking significant human engineering hours. I have higher hopes for learning from tele-operated data, but that requires a human to learn the task first. These experiments are on my to-do list. I have to learn to play some of the games well through the robot. I’m half-decent at playing Pong and Ms Pacman now. Learning directly on robots is looking like the most promising approach. This approach takes away pesky distribution shifts and makes it possible to have algorithms that continually improve with more data and time without any human intervention. It feels great to let experiments run overnight and wake up to find improved policies. With learning on robots, I should, in principle, be able to go on a long vacation and come back to find better policies for complex tasks beyond Atari games. Whether that is possible with current learning algorithms is a different question.

Khurram Javed

52,110 Aufrufe • vor 7 Monaten