Loading video...

Video Failed to Load

Go Home

Learn the differences between motion profiles! 💨 A real demonstration of engineering skills. In each robotic arm, in each legged robot, you will discover actuators that make the robot move! Let's compare two motion profiles: rectangular and trapezoid. - A rectangular motion profile is like a car with abrupt...

lukas_m_ziegler's profile picture

Lukas Ziegler

56,487 subscribers

112,270 views • 7 months ago •via X (Twitter)

EducationHealth & WellnessScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

A toilet-cleaning robot from Reflex Robotics. The best part is when the robot dries its hands... That might be the future of robots doing chores for us. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
1:00

A toilet-cleaning robot from Reflex Robotics. The best part is when the robot dries its hands... That might be the future of robots doing chores for us. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

15,766 views • 3 months ago

Turning video into humanoid robot motion! 🤳🏼 Training humanoid robots needs huge amounts of motion data, but real-world capture doesn’t scale. Mocap is expensive, dangerous edge cases are rare, and you can’t ask humans to repeatedly fall or crash. Video2Robot tackles this by converting videos into physics-grounded humanoid simulations. Motion is generated to respect balance, inertia, ground contact, and joint limits, then directly retargeted to robot simulators. One prompt can generate a full humanoid motion sequence, including multi-agent interactions and failure cases like falls or collisions, scenarios that are hard or impossible to capture safely in the real world. The pipeline is model-agnostic and works with existing video generators, making it a practical way to scale data for robots. If robots are going to operate in the real world, they need to be trained on the failures too, not just the perfect demos. Here's the GitHub: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:26

Turning video into humanoid robot motion! 🤳🏼 Training humanoid robots needs huge amounts of motion data, but real-world capture doesn’t scale. Mocap is expensive, dangerous edge cases are rare, and you can’t ask humans to repeatedly fall or crash. Video2Robot tackles this by converting videos into physics-grounded humanoid simulations. Motion is generated to respect balance, inertia, ground contact, and joint limits, then directly retargeted to robot simulators. One prompt can generate a full humanoid motion sequence, including multi-agent interactions and failure cases like falls or collisions, scenarios that are hard or impossible to capture safely in the real world. The pipeline is model-agnostic and works with existing video generators, making it a practical way to scale data for robots. If robots are going to operate in the real world, they need to be trained on the failures too, not just the perfect demos. Here's the GitHub: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

59,708 views • 6 months ago

Gravity-defying robot! 🦎 VertiGo is a wall-climbing robot created by Disney Research and ETH Zürich that can transition between ground and wall. The robot can move on a wall quickly and with agility. VertiGo has four wheels, two tiltable propellers, and two tiltable propellers. One pair of wheels is steerable, and each propeller has two degrees of freedom for adjusting the direction of thrust. The choice of two propellers rather than one enables a floor-to-wall transition, thrust is applied both towards the wall using the rear propeller and in an upward direction using the front propeller, resulting in a flip onto the wall. P.S. Can you guess the year of development? 👀 ~~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:33

Gravity-defying robot! 🦎 VertiGo is a wall-climbing robot created by Disney Research and ETH Zürich that can transition between ground and wall. The robot can move on a wall quickly and with agility. VertiGo has four wheels, two tiltable propellers, and two tiltable propellers. One pair of wheels is steerable, and each propeller has two degrees of freedom for adjusting the direction of thrust. The choice of two propellers rather than one enables a floor-to-wall transition, thrust is applied both towards the wall using the rear propeller and in an upward direction using the front propeller, resulting in a flip onto the wall. P.S. Can you guess the year of development? 👀 ~~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

189,501 views • 4 months ago

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 →
0:24

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 views • 3 months ago

We asked Angus about the future of robotics and AI training. “I built an industrial-grade kinematic solver for 6 degrees of freedom motion, with full path planning and joint control." "You can stream AI model outputs into it, or run it like a traditional industrial robot." "The benefit of that is all of that information you can stream and record from those joints… you can use that as the training data." "Frankly, moving a robot with a lever is really crap data for training robots. But this gives you smooth, high-quality motion, without needing two robots.”
2:16

We asked Angus about the future of robotics and AI training. “I built an industrial-grade kinematic solver for 6 degrees of freedom motion, with full path planning and joint control." "You can stream AI model outputs into it, or run it like a traditional industrial robot." "The benefit of that is all of that information you can stream and record from those joints… you can use that as the training data." "Frankly, moving a robot with a lever is really crap data for training robots. But this gives you smooth, high-quality motion, without needing two robots.”

TBPN

18,811 views • 1 year ago

The robot is used to inspect the walls of ships. 🚢 The Magnet Crawler introduced by the University of Bremen is a lightweight and compact climbing robot for magnetic surfaces. The robot has two magnetic wheels driven by geared motors and an elastic tail to improve stability. In the front part of the robot, there is a miniature wireless camera. The robot is remotely teleoperated & the video signal from the camera is displayed to the operator on a portable screen. Let's wait and perhaps the robot will become more autonomous over time. Big fan of robots that make the world a safer place for humans. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:51

The robot is used to inspect the walls of ships. 🚢 The Magnet Crawler introduced by the University of Bremen is a lightweight and compact climbing robot for magnetic surfaces. The robot has two magnetic wheels driven by geared motors and an elastic tail to improve stability. In the front part of the robot, there is a miniature wireless camera. The robot is remotely teleoperated & the video signal from the camera is displayed to the operator on a portable screen. Let's wait and perhaps the robot will become more autonomous over time. Big fan of robots that make the world a safer place for humans. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

21,587 views • 1 month ago

Six months later, Vietnamese robotics company VinMotion has launched Motion 2, a general-purpose humanoid robot. Compared to Motion 1, Motion 2 features a more natural gait, faster walking speed, and greater agility, and can carry a load of 40kg. It can also recover from falls independently, and features autonomous charging and battery swapping. Currently, this humanoid robot is being tested in industrial logistics scenarios, with the goal of integrating it into business systems to achieve intelligent automation of tasks in factories and warehouses. It also integrates multi-language interaction capabilities (Vietnamese, English, etc.), laying the foundation for future service-oriented applications. BTW, VinMotion will showcase its progress at CES 2026.
0:58

Six months later, Vietnamese robotics company VinMotion has launched Motion 2, a general-purpose humanoid robot. Compared to Motion 1, Motion 2 features a more natural gait, faster walking speed, and greater agility, and can carry a load of 40kg. It can also recover from falls independently, and features autonomous charging and battery swapping. Currently, this humanoid robot is being tested in industrial logistics scenarios, with the goal of integrating it into business systems to achieve intelligent automation of tasks in factories and warehouses. It also integrates multi-language interaction capabilities (Vietnamese, English, etc.), laying the foundation for future service-oriented applications. BTW, VinMotion will showcase its progress at CES 2026.

CyberRobo

60,689 views • 6 months ago

A robot that will bend metal for you! 🤘🏼 This is what optimized robotic press brake operation looks like. A well-tuned program, an additional seventh axis for extended reach, smart gripper design, and a workpiece reversal mechanism to handle parts without human intervention. This combination is invaluable for automated press brake operation. Cycle time is on fire! 🔥 KUKA robots are a solid choice for metal forming. They're built for high-payload, high-precision tasks and have a strong track record in automotive and heavy industry applications where reliability matters the most! :) ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:22

A robot that will bend metal for you! 🤘🏼 This is what optimized robotic press brake operation looks like. A well-tuned program, an additional seventh axis for extended reach, smart gripper design, and a workpiece reversal mechanism to handle parts without human intervention. This combination is invaluable for automated press brake operation. Cycle time is on fire! 🔥 KUKA robots are a solid choice for metal forming. They're built for high-payload, high-precision tasks and have a strong track record in automotive and heavy industry applications where reliability matters the most! :) ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

38,749 views • 5 months ago

This robot explores the world like a mouse! 🐁 That's an OG project, guess the year ;) A mouse-inspired bot called WhiskEye travels the world with 24 artificial whiskers and spiking neurons that mimic a nervous system. Recognizing familiar places is essential for engineering applications like robot navigation, where interactions with the real world are key. Combining information from multiple senses helps to make better accuracy and robustness, but challenges like mismatched data and sensor errors complicate this process. Inspired by how animals navigate seamlessly, researchers developed predictive coding, a self-supervised learning method based on the brain's visual cortex model. It combines visual and tactile cues from a robot, outperforming existing methods in recognizing places, even when some sensors fail. What a great project from BristolRoboticsLab and Sheffield Robotics! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:34

This robot explores the world like a mouse! 🐁 That's an OG project, guess the year ;) A mouse-inspired bot called WhiskEye travels the world with 24 artificial whiskers and spiking neurons that mimic a nervous system. Recognizing familiar places is essential for engineering applications like robot navigation, where interactions with the real world are key. Combining information from multiple senses helps to make better accuracy and robustness, but challenges like mismatched data and sensor errors complicate this process. Inspired by how animals navigate seamlessly, researchers developed predictive coding, a self-supervised learning method based on the brain's visual cortex model. It combines visual and tactile cues from a robot, outperforming existing methods in recognizing places, even when some sensors fail. What a great project from BristolRoboticsLab and Sheffield Robotics! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

36,775 views • 6 months ago

Safety in mobile robotics! 👷🏼‍♂️ Robots navigating through crowds is one of the hardest problems in mobile robotics, uncertainty, human motion, and real-time constraints don’t mix well. A team at TU Delft has introduced DRA-MPPI, a new motion-planning method that lets robots move safely through dense pedestrian traffic without freezing or taking overly conservative paths. Instead of assuming people move predictably, the system handles non-Gaussian, uncertain human motion, even cases where someone might suddenly turn or change direction. It uses a fast Monte Carlo approximation to estimate collision probability across hundreds of sampled trajectories in real time. If a trajectory’s risk crosses a threshold, it gets rejected. If not, risk becomes part of the cost function. In testing a Clearpath Jackal navigated real crowds while keeping collision risk under a defined limit, outperforming approaches like Scenario-based MPC and standard MPPI. It’s another step toward robots that behave safely and naturally around people, even when humans don’t behave predictably! 🔥 Here's the project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
1:03

Safety in mobile robotics! 👷🏼‍♂️ Robots navigating through crowds is one of the hardest problems in mobile robotics, uncertainty, human motion, and real-time constraints don’t mix well. A team at TU Delft has introduced DRA-MPPI, a new motion-planning method that lets robots move safely through dense pedestrian traffic without freezing or taking overly conservative paths. Instead of assuming people move predictably, the system handles non-Gaussian, uncertain human motion, even cases where someone might suddenly turn or change direction. It uses a fast Monte Carlo approximation to estimate collision probability across hundreds of sampled trajectories in real time. If a trajectory’s risk crosses a threshold, it gets rejected. If not, risk becomes part of the cost function. In testing a Clearpath Jackal navigated real crowds while keeping collision risk under a defined limit, outperforming approaches like Scenario-based MPC and standard MPPI. It’s another step toward robots that behave safely and naturally around people, even when humans don’t behave predictably! 🔥 Here's the project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

86,933 views • 7 months ago

me: wants to become a master of disaster in electronics and microprocessors son of my mother's friend: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:24

me: wants to become a master of disaster in electronics and microprocessors son of my mother's friend: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

86,527 views • 7 months ago

MotionGPT: Human Motion as a Foreign Language paper page: Though the advancement of pre-trained large language models unfolds, the exploration of building a unified model for language and other multi-modal data, such as motion, remains challenging and untouched so far. Fortunately, human motion displays a semantic coupling akin to human language, often perceived as a form of body language. By fusing language data with large-scale motion models, motion-language pre-training that can enhance the performance of motion-related tasks becomes feasible. Driven by this insight, we propose MotionGPT, a unified, versatile, and user-friendly motion-language model to handle multiple motion-relevant tasks. Specifically, we employ the discrete vector quantization for human motion and transfer 3D motion into motion tokens, similar to the generation process of word tokens. Building upon this "motion vocabulary", we perform language modeling on both motion and text in a unified manner, treating human motion as a specific language. Moreover, inspired by prompt learning, we pre-train MotionGPT with a mixture of motion-language data and fine-tune it on prompt-based question-and-answer tasks. Extensive experiments demonstrate that MotionGPT achieves state-of-the-art performances on multiple motion tasks including text-driven motion generation, motion captioning, motion prediction, and motion in-between.
0:48

MotionGPT: Human Motion as a Foreign Language paper page: Though the advancement of pre-trained large language models unfolds, the exploration of building a unified model for language and other multi-modal data, such as motion, remains challenging and untouched so far. Fortunately, human motion displays a semantic coupling akin to human language, often perceived as a form of body language. By fusing language data with large-scale motion models, motion-language pre-training that can enhance the performance of motion-related tasks becomes feasible. Driven by this insight, we propose MotionGPT, a unified, versatile, and user-friendly motion-language model to handle multiple motion-relevant tasks. Specifically, we employ the discrete vector quantization for human motion and transfer 3D motion into motion tokens, similar to the generation process of word tokens. Building upon this "motion vocabulary", we perform language modeling on both motion and text in a unified manner, treating human motion as a specific language. Moreover, inspired by prompt learning, we pre-train MotionGPT with a mixture of motion-language data and fine-tune it on prompt-based question-and-answer tasks. Extensive experiments demonstrate that MotionGPT achieves state-of-the-art performances on multiple motion tasks including text-driven motion generation, motion captioning, motion prediction, and motion in-between.

AK

125,319 views • 3 years ago

I grew up in neighborhoods where you learned early that LA is complicated — it’s diverse, it’s imperfect, and always in motion, and I learned that the measure of a city — and of a person — is who you lift up along the way.
0:44

I grew up in neighborhoods where you learned early that LA is complicated — it’s diverse, it’s imperfect, and always in motion, and I learned that the measure of a city — and of a person — is who you lift up along the way.

Mayor Karen Bass

53,143 views • 5 months ago

Tired of teleoperation? One human video → 1,000s of robot demos. (📍GitHub ) Scaling Robot Data Without Dynamics Simulation or Robot Hardware Real2Render2Real (R2R2R) is a new way to scale robot data without physics simulation or hardware. You take a phone scan + a single monocular human demo. It tracks the motion, renders photorealistic scenes, and generates diverse, robot-agnostic trajectories ready for training. > No teleop, no sim, no robot, just a phone and a video > Train VLA models and diffusion policies directly on the output > Supports multiple robot embodiments with kinematic consistency > 1000s of demos in 1/27 the time of real-world collection Thank you, Max Fu, for sharing!! Project: Paper: Code coming soon: It shows that with the right pipeline, you can scale robot learning data without touching a robot. One of the most interesting directions in scalable robotics today. —— Weekly robotics and AI insights. Subscribe free:
0:29

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

Ilir Aliu

42,804 views • 5 months ago

DOBOT robotics' humanoid robot is making a big leap in industrial applications, achieving cross-scenario, multi-task generalization. This is thanks to two major breakthroughs: efficient human-to-robot motion mapping and knowledge-driven generative VLA tech. ► The robot handles complex tasks like precision assembly and can work reliably in temperatures over 50°C (122°F). ► It excels at multi-robot collaborative tasks and can adaptively grasp soft or irregularly shaped objects. With a repeatability of ±0.05mm, this model demonstrates strong adaptability and reliability in dynamic industrial settings. It's now being applied in warehouse anomaly handling and quality inspection.
2:09

DOBOT robotics' humanoid robot is making a big leap in industrial applications, achieving cross-scenario, multi-task generalization. This is thanks to two major breakthroughs: efficient human-to-robot motion mapping and knowledge-driven generative VLA tech. ► The robot handles complex tasks like precision assembly and can work reliably in temperatures over 50°C (122°F). ► It excels at multi-robot collaborative tasks and can adaptively grasp soft or irregularly shaped objects. With a repeatability of ±0.05mm, this model demonstrates strong adaptability and reliability in dynamic industrial settings. It's now being applied in warehouse anomaly handling and quality inspection.

RoboHub🤖

91,953 views • 10 months ago

A versatile robot helping out airports! 🛩️ Meet a two-wheeled robot from Fraunhofer IML! 🦿 This balancing robot with gripping arms successfully completed its initial practical tests at the cargo terminal of Munich Airport a while ago. It transported goods, supported loading and unloading, and assisted with physically demanding logistics tasks. This robot can carry loads of up to 100 kg and reach speeds of around 60 km/h. That’s far beyond what most AMRs can handle, yet it still has arms and a form of mobility that lets it work in spaces designed for people. P.S. What other applications would you use this robot for?! 🦾 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:49

A versatile robot helping out airports! 🛩️ Meet a two-wheeled robot from Fraunhofer IML! 🦿 This balancing robot with gripping arms successfully completed its initial practical tests at the cargo terminal of Munich Airport a while ago. It transported goods, supported loading and unloading, and assisted with physically demanding logistics tasks. This robot can carry loads of up to 100 kg and reach speeds of around 60 km/h. That’s far beyond what most AMRs can handle, yet it still has arms and a form of mobility that lets it work in spaces designed for people. P.S. What other applications would you use this robot for?! 🦾 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

29,688 views • 6 months ago

Is Santiago Bernabéu one of the biggest robots?🤯 Its retractable pitch is basically a massive AS/RS system hidden under the field. The engineering numbers are wild: → Six segments, each ~1,500 tons → Perfectly synchronized drives → Millimeter-accurate positioning inside the underground hypogeum How cool is that! Did you see a bigger robot!? ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:24

Is Santiago Bernabéu one of the biggest robots?🤯 Its retractable pitch is basically a massive AS/RS system hidden under the field. The engineering numbers are wild: → Six segments, each ~1,500 tons → Perfectly synchronized drives → Millimeter-accurate positioning inside the underground hypogeum How cool is that! Did you see a bigger robot!? ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

73,827 views • 7 months ago

This robot can juggle! 🤹🏼‍♀️ A great engineering showcase as a part of a master's thesis at the Brno University of Technology! CableEndy is a cable-driven parallel robot project at the B&R Industrial Automation Brno office. The robot was created most probably to make all professional Kendama players feel insecure :) Guess the year btw! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:53

This robot can juggle! 🤹🏼‍♀️ A great engineering showcase as a part of a master's thesis at the Brno University of Technology! CableEndy is a cable-driven parallel robot project at the B&R Industrial Automation Brno office. The robot was created most probably to make all professional Kendama players feel insecure :) Guess the year btw! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

31,055 views • 1 month ago

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 →
0:47

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 views • 6 months ago