Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

A Switzerland-based startup Flexion has created a robotic brain that helps the Unitree G1 move smoothly and work on its own. It uses reinforcement learning, where the robot trains in simulations to learn walking, balancing, and picking objects. In tests, it cleaned a space by finding and placing items... show more

Space and Technology

30,820 subscribers

17,557 views • 2 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Researchers developed Hitter, a humanoid robot that can play table tennis in real-world settings. It was trained on the Unitree G1 robot to predict the ball’s path, choose the right shot, and react in less than a second. In tests, it achieved 106 consecutive shots with a human and even rallied with another humanoid robot.

Researchers developed Hitter, a humanoid robot that can play table tennis in real-world settings. It was trained on the Unitree G1 robot to predict the ball’s path, choose the right shot, and react in less than a second. In tests, it achieved 106 consecutive shots with a human and even rallied with another humanoid robot.

Space and Technology

25,681 views • 2 months ago

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 views • 4 months ago

This is NASA’s Astrobee, a cube-shaped robot that flies freely inside the ISS to help astronauts with daily tasks. It can move using built-in fans, navigate with vision sensors, and work either on its own or be controlled from Earth. Some versions have robotic arms that can detect and grab objects, and this tech could be used in the future to remove space debris or service satellites.

This is NASA’s Astrobee, a cube-shaped robot that flies freely inside the ISS to help astronauts with daily tasks. It can move using built-in fans, navigate with vision sensors, and work either on its own or be controlled from Earth. Some versions have robotic arms that can detect and grab objects, and this tech could be used in the future to remove space debris or service satellites.

Space and Technology

51,832 views • 2 months ago

Domino’s Tests Pizza-Delivering Robot Dog in England In the UK, Domino’s is testing a robot dog named Domidog to deliver pizzas. On the way, little can threaten it — it scares off seagulls with barking and skillfully uses its robotic arm.

Domino’s Tests Pizza-Delivering Robot Dog in England In the UK, Domino’s is testing a robot dog named Domidog to deliver pizzas. On the way, little can threaten it — it scares off seagulls with barking and skillfully uses its robotic arm.

NEXTA

40,396 views • 11 months ago

This week, Amazon introduced Vulcan! 🌋 Amazon has created a new robot called Vulcan, and it's the first one with a real sense of touch. I visited one of the fulfillment centers of Amazon to shoot their latest picking robot for you! Vulcan doesn’t just “see” like most robots—it can also feel what it’s touching, like a human hand. 🪬 This helps it do tricky tasks, such as picking items out of crowded bins, without damaging anything nearby. Vulcan is powered by physical AI, which means it uses both sight and touch to understand and move through the world. In Amazon’s warehouses, items are stored tightly in small compartments, which used to be hard for robots to handle. Their new system with Universal Robots arms changes that, it can gently pick up or place items in these tight spaces by knowing how much pressure to apply. The robot uses special tools and sensors to know when it touches something and how hard it’s pressing. 🤏🏼 It helps make the workplace safer by doing tasks that used to require employees to use ladders or reach overhead. Over time, Vulcan will become even smarter by learning from its mistakes and gaining more experience, just like a person does.

This week, Amazon introduced Vulcan! 🌋 Amazon has created a new robot called Vulcan, and it's the first one with a real sense of touch. I visited one of the fulfillment centers of Amazon to shoot their latest picking robot for you! Vulcan doesn’t just “see” like most robots—it can also feel what it’s touching, like a human hand. 🪬 This helps it do tricky tasks, such as picking items out of crowded bins, without damaging anything nearby. Vulcan is powered by physical AI, which means it uses both sight and touch to understand and move through the world. In Amazon’s warehouses, items are stored tightly in small compartments, which used to be hard for robots to handle. Their new system with Universal Robots arms changes that, it can gently pick up or place items in these tight spaces by knowing how much pressure to apply. The robot uses special tools and sensors to know when it touches something and how hard it’s pressing. 🤏🏼 It helps make the workplace safer by doing tasks that used to require employees to use ladders or reach overhead. Over time, Vulcan will become even smarter by learning from its mistakes and gaining more experience, just like a person does.

Lukas Ziegler

16,413 views • 1 year ago

Boston Dynamics has demonstrated its new Atlas humanoid robot lifting and carrying a 50-pound fridge. The robot uses its whole body to balance and move the heavy object in a natural, human-like way. Before doing it in the real world, Atlas practiced the task for millions of hours in a virtual simulation.

Boston Dynamics has demonstrated its new Atlas humanoid robot lifting and carrying a 50-pound fridge. The robot uses its whole body to balance and move the heavy object in a natural, human-like way. Before doing it in the real world, Atlas practiced the task for millions of hours in a virtual simulation.

Space and Technology

179,609 views • 23 days ago

Push a human off balance and they react instantly. Now try building that into a robot… During a recent visit to Hangzhou, hosted by the Zhejiang Provincial Government, we saw a live balance test from Unitree robotics G1 robot. This is where control, perception, and hardware have to move as one in real time.

Push a human off balance and they react instantly. Now try building that into a robot… During a recent visit to Hangzhou, hosted by the Zhejiang Provincial Government, we saw a live balance test from Unitree robotics G1 robot. This is where control, perception, and hardware have to move as one in real time.

Megatron

43,080 views • 1 month ago

🇨🇭 BADMINTON-BOT TAKES THE COURT IN SWITZERLAND A Swiss team built a four-legged robot that plays badminton against humans and actually returns shots like it means it. Created with ETH Zurich, this bot uses artificial intelligence to teach itself how to move, see, and hit the shuttlecock with freakish precision. It learns through reinforcement learning which is a fancy way of saying it fails over and over until it figures things out. A special vision system helps it track the birdie while running around like a robot goat with a grudge. It even adjusts its movement to avoid messing up its own view. Researcher, Yuntao Ma: "We believe that this project demonstrates the potential of artificial intelligence to advance legged robots in complex tasks, paving the way for advances in autonomous and intelligent systems, including humanoids. The control algorithm generalizes to other robotic platforms such as humanoids, as well as to other tasks such as search and rescue and home services." Source: Telegrafi Media Source: The Independent On Youtube

🇨🇭 BADMINTON-BOT TAKES THE COURT IN SWITZERLAND A Swiss team built a four-legged robot that plays badminton against humans and actually returns shots like it means it. Created with ETH Zurich, this bot uses artificial intelligence to teach itself how to move, see, and hit the shuttlecock with freakish precision. It learns through reinforcement learning which is a fancy way of saying it fails over and over until it figures things out. A special vision system helps it track the birdie while running around like a robot goat with a grudge. It even adjusts its movement to avoid messing up its own view. Researcher, Yuntao Ma: "We believe that this project demonstrates the potential of artificial intelligence to advance legged robots in complex tasks, paving the way for advances in autonomous and intelligent systems, including humanoids. The control algorithm generalizes to other robotic platforms such as humanoids, as well as to other tasks such as search and rescue and home services." Source: Telegrafi Media Source: The Independent On Youtube

Mario Nawfal

76,687 views • 1 year ago

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

1,331,117 views • 11 months ago

One of my favorite works in the "robot learning from human videos" space that I have seen lately. This is because it offers a really coherent and unique way to represent robot skills without a lot of the downsides we see from estimation-based approaches.

One of my favorite works in the "robot learning from human videos" space that I have seen lately. This is because it offers a really coherent and unique way to represent robot skills without a lot of the downsides we see from estimation-based approaches.

Chris Paxton

78,416 views • 8 months ago

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 views • 5 months ago

"A parcel with snacks has been delivered for Flexion. Retrieve it using the stairs and come up using the elevator. Then unpack it and place the items into the empty drawer on the shelf in the snack area." One instruction. No human operator. Everything that follows is autonomous. Today we're introducing Reflect v1.0, our robotics intelligence platform for long-horizon work. From a single natural-language command, the robot understands the task, navigates a multi-floor building, calls elevators, handles doors, uses tools to unpack a box, and puts the items away. The biggest shift in v1.0 is that we use reinforcement learning across every layer, from low-level control to high-level reasoning. Long-horizon autonomy is unforgiving. The robot must recover on its own when things don't go to plan because in the real world, they never do. Combining reasoning, perception, physical execution and runtime robustness into a single mission-capable system is the foundation required to solve humanoid autonomy. Our team is just getting started. #HumanoidRobots #Flexion

"A parcel with snacks has been delivered for Flexion. Retrieve it using the stairs and come up using the elevator. Then unpack it and place the items into the empty drawer on the shelf in the snack area." One instruction. No human operator. Everything that follows is autonomous. Today we're introducing Reflect v1.0, our robotics intelligence platform for long-horizon work. From a single natural-language command, the robot understands the task, navigates a multi-floor building, calls elevators, handles doors, uses tools to unpack a box, and puts the items away. The biggest shift in v1.0 is that we use reinforcement learning across every layer, from low-level control to high-level reasoning. Long-horizon autonomy is unforgiving. The robot must recover on its own when things don't go to plan because in the real world, they never do. Combining reasoning, perception, physical execution and runtime robustness into a single mission-capable system is the foundation required to solve humanoid autonomy. Our team is just getting started. #HumanoidRobots #Flexion

Flexion Robotics

107,209 views • 1 day ago

Wow. This is crazy. A developer trained an AI agent in simulation and deployed it onto a real robotic air hockey table using reinforcement learning. This robot can track the puck with millimeter-level accuracy and react in roughly 20 milliseconds, fast enough to challenge even skilled human players. We’re moving from robots that follow programmed rules to machines that learn strategies in simulation and execute them in the physical world.

Wow. This is crazy. A developer trained an AI agent in simulation and deployed it onto a real robotic air hockey table using reinforcement learning. This robot can track the puck with millimeter-level accuracy and react in roughly 20 milliseconds, fast enough to challenge even skilled human players. We’re moving from robots that follow programmed rules to machines that learn strategies in simulation and execute them in the physical world.

SciTech Era

1,582,875 views • 28 days ago

notes on my reinforcement learning for rocket league side quest so far: i’m in awe that — we live in a time where i can train a reinforcement learning model that is learning to play rocket league and at the same time, test community made rocket league models. where, both processes can run in parallel & locally on my hardware. in the game window — i’m playing against a reinforcement learning ppo model that’s running locally. and in the vscode window — i’m training my own reinforcement learning model (just a dummy example script for now). also, the rocket league botting ecosystem has incredible tooling where you can test out different reinforcement learning ideas against other algorithms + it has great documentation for linux and windows. it’s honestly a beautiful hidden gem of a rabbit hole :)

notes on my reinforcement learning for rocket league side quest so far: i’m in awe that — we live in a time where i can train a reinforcement learning model that is learning to play rocket league and at the same time, test community made rocket league models. where, both processes can run in parallel & locally on my hardware. in the game window — i’m playing against a reinforcement learning ppo model that’s running locally. and in the vscode window — i’m training my own reinforcement learning model (just a dummy example script for now). also, the rocket league botting ecosystem has incredible tooling where you can test out different reinforcement learning ideas against other algorithms + it has great documentation for linux and windows. it’s honestly a beautiful hidden gem of a rabbit hole :)

naklecha

46,302 views • 1 year ago

Another robot from Disney! 🕺🏻 Just look at this dancing fella created by Disney Research. Creating control policies that work on real robots and handling diverse, unseen motions in physics-based character control is still difficult. The Disney team proposes a two-state solution. The first step involves learning a latent space encoding with an autoencoder. After encoding, the policy is trained to map kinematic input to dynamic output, ensuring accurate and adaptable movement. This method eliminates common mode collapse issues and improves motion encoding by separating these stages. This technique has proven effective in real robots in simulations, marking a significant leap forward in robot control. Can't wait for it in action live in 2025 :) ~~~ RT to help 1 robot find a new workplace.

Another robot from Disney! 🕺🏻 Just look at this dancing fella created by Disney Research. Creating control policies that work on real robots and handling diverse, unseen motions in physics-based character control is still difficult. The Disney team proposes a two-state solution. The first step involves learning a latent space encoding with an autoencoder. After encoding, the policy is trained to map kinematic input to dynamic output, ensuring accurate and adaptable movement. This method eliminates common mode collapse issues and improves motion encoding by separating these stages. This technique has proven effective in real robots in simulations, marking a significant leap forward in robot control. Can't wait for it in action live in 2025 :) ~~~ RT to help 1 robot find a new workplace.

Lukas Ziegler

65,887 views • 1 year ago

Meet Phantom, a humanoid robot built for battlefield missions by San Francisco–based startup Foundation Future Industries. The robot can walk across rough terrain, enter buildings, and scan dangerous areas before soldiers move in. Phantom uses AI to detect people and understand its surroundings, while human operators stay in control of critical decisions.

Meet Phantom, a humanoid robot built for battlefield missions by San Francisco–based startup Foundation Future Industries. The robot can walk across rough terrain, enter buildings, and scan dangerous areas before soldiers move in. Phantom uses AI to detect people and understand its surroundings, while human operators stay in control of critical decisions.

Space and Technology

21,468 views • 1 month ago

🇨🇳 It has started. A new home service in China pairs human cleaners with autonomous AI robots to tackle household chores. Residents in Shenzhen can now book a service where a human professional and an autonomous robot arrive together to clean their home. Real houses present a chaotic mess of dropped toys and random furniture that confuse traditional machines. X Square Robot and a major service platform named 58[.]com decided to tackle this chaos by launching China's first robot cleaner service in March-26. Customers use an application to hire a cleaning crew that consists of 1 human worker and 1 robot. The human takes care of the tricky chores that require complex judgment. The robot handles the repetitive physical work like picking up trash and wiping down flat surfaces. This machine runs on a system called WALL-A, which acts as a single continuous AI brain rather than a list of pre-written rules. They built this AI foundation model to perceive its surroundings and make its own decisions without human guidance. It processes visual data and plans multi-step actions. And deploying these robots into actual homes now provides the massive amounts of extremely important training data to improve it continuously. Alibaba and ByteDance backed this project. IMO, if the foundational model behind it figures out how to navigate a messy living room without getting stuck, it can learn to operate in almost any other physical environment.

🇨🇳 It has started. A new home service in China pairs human cleaners with autonomous AI robots to tackle household chores. Residents in Shenzhen can now book a service where a human professional and an autonomous robot arrive together to clean their home. Real houses present a chaotic mess of dropped toys and random furniture that confuse traditional machines. X Square Robot and a major service platform named 58[.]com decided to tackle this chaos by launching China's first robot cleaner service in March-26. Customers use an application to hire a cleaning crew that consists of 1 human worker and 1 robot. The human takes care of the tricky chores that require complex judgment. The robot handles the repetitive physical work like picking up trash and wiping down flat surfaces. This machine runs on a system called WALL-A, which acts as a single continuous AI brain rather than a list of pre-written rules. They built this AI foundation model to perceive its surroundings and make its own decisions without human guidance. It processes visual data and plans multi-step actions. And deploying these robots into actual homes now provides the massive amounts of extremely important training data to improve it continuously. Alibaba and ByteDance backed this project. IMO, if the foundational model behind it figures out how to navigate a messy living room without getting stuck, it can learn to operate in almost any other physical environment.

Rohan Paul

52,925 views • 3 months ago

Mantis is an autonomous construction robot built by the London-based company All3. It uses AI to place parts, fasten, finish, and inspect work on real construction sites without human help. It can carry up to 100 kg, switch tools, and move accurately using real building data.

Mantis is an autonomous construction robot built by the London-based company All3. It uses AI to place parts, fasten, finish, and inspect work on real construction sites without human help. It can carry up to 100 kg, switch tools, and move accurately using real building data.

Space and Technology

30,600 views • 2 months ago

Unitree Robotics modified its G1 humanoid robot by replacing its feet with wheels, roller skates, and ice skates. This allows the robot to move faster and more smoothly on different surfaces. The upgrade shows how one robot can adapt to multiple types of movement with simple changes.

Unitree Robotics modified its G1 humanoid robot by replacing its feet with wheels, roller skates, and ice skates. This allows the robot to move faster and more smoothly on different surfaces. The upgrade shows how one robot can adapt to multiple types of movement with simple changes.

Space and Technology

24,428 views • 29 days ago

Swedish AI startup IntuiCell says it has created a robot dog named Luna that has a functional digital nervous system capable of learning and adapting like humans and many animals

Swedish AI startup IntuiCell says it has created a robot dog named Luna that has a functional digital nervous system capable of learning and adapting like humans and many animals

Reuters

40,470 views • 1 year ago