Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

One tool to handle them all! 🧰 Traditional suction-based systems struggle with over 30% of SKUs. Mesh bags, loose apparel, and porous items often lead to failed picks or damaged goods. Nexera Robotics (Nexera Robotics) is pushing that ceiling to more than 95% by innovating the hardware, not just...

lukas_m_ziegler's profile picture

Lukas Ziegler

60,051 subscribers

23,230 Aufrufe • vor 7 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

A 40-year-old patent has finally been brought to life. That's the Y-zipper. A 3D-printed three-sided fastener that transitions any object from flexible to rigid and back again. The robotics application is the one that caught my attention. A quadruped robot that adjusts its leg stiffness depending on terrain, switching between rigid and flexible in real time without additional motors or complex mechanical systems. But this goes way beyond robotics. A wrist cast that loosens during the day and stiffens at night. A tent that pops into shape in 90 seconds instead of six minutes. The idea sat in a patent filing for four decades. It took 3D printing to finally make it real. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
3:58

A 40-year-old patent has finally been brought to life. That's the Y-zipper. A 3D-printed three-sided fastener that transitions any object from flexible to rigid and back again. The robotics application is the one that caught my attention. A quadruped robot that adjusts its leg stiffness depending on terrain, switching between rigid and flexible in real time without additional motors or complex mechanical systems. But this goes way beyond robotics. A wrist cast that loosens during the day and stiffens at night. A tent that pops into shape in 90 seconds instead of six minutes. The idea sat in a patent filing for four decades. It took 3D printing to finally make it real. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

1,805,759 Aufrufe • vor 4 Monaten

This is not a 2050 warehouse. This is a modern air hub of Amazon. Amazon uses robots to help sort and ship billions of packages each year. At Amazon Air, the company's main air hub in Kentucky, hundreds of self-charging robots zoom across the warehouse floor to organize orders. These robots, called “drives,” follow small stickers on the floor to know where to go and when to speed up or slow down. Amazon has more than ONE MILLION robots in its facilities, and it’s even deploying more new types of robots that can sort items of different shapes and sizes. P.S. Can you guess how many robots they had back in 2013? ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:23

This is not a 2050 warehouse. This is a modern air hub of Amazon. Amazon uses robots to help sort and ship billions of packages each year. At Amazon Air, the company's main air hub in Kentucky, hundreds of self-charging robots zoom across the warehouse floor to organize orders. These robots, called “drives,” follow small stickers on the floor to know where to go and when to speed up or slow down. Amazon has more than ONE MILLION robots in its facilities, and it’s even deploying more new types of robots that can sort items of different shapes and sizes. P.S. Can you guess how many robots they had back in 2013? ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

178,090 Aufrufe • vor 1 Monat

This is what open robotics actually looks like! 🔓 I was in Bordeaux, sitting inside Pollen Robotics, and had a chance to play around with their humanoid robot Reachy 2. It’s expressive, modular, and can even bring you coffee, and of course runs Python or Rust. I was talking with Reachy in 3 different languages, tele-operating it and manipulating kitchen stuff, and make it even mimic my gestures. The best part is that there are no locked APIs, or hidden stuff, just an open platform that you can build upon. The connection with Hugging Face makes it super easy to start, as the open source approach allows everyone to contribute, experiment and add their own things. I already ordered his little brother Reachy Mini, let's see what a robotics rookie can do with that robot! 👀 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
1:36

This is what open robotics actually looks like! 🔓 I was in Bordeaux, sitting inside Pollen Robotics, and had a chance to play around with their humanoid robot Reachy 2. It’s expressive, modular, and can even bring you coffee, and of course runs Python or Rust. I was talking with Reachy in 3 different languages, tele-operating it and manipulating kitchen stuff, and make it even mimic my gestures. The best part is that there are no locked APIs, or hidden stuff, just an open platform that you can build upon. The connection with Hugging Face makes it super easy to start, as the open source approach allows everyone to contribute, experiment and add their own things. I already ordered his little brother Reachy Mini, let's see what a robotics rookie can do with that robot! 👀 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

19,433 Aufrufe • vor 8 Monaten

A simple CNC machine. Wood. A rotating tool. And yet the pattern shifts from circles to perfect hexagons with a level of accuracy most factories still struggle to hit. I worked five years in manufacturing at Siemens, and this is the part people often overlook. The real magic is not new or loud. It is stability. Repeatability. Tool paths that were tuned forever. Precision that just keeps working. Robotics is in a hype cycle right now, but manufacturing has delivered quiet perfection long before anyone talked about foundation models. Sometimes the most interesting engineering is the part that does not ask for attention. —- Weekly robotics and AI insights. Subscribe free:
0:26

A simple CNC machine. Wood. A rotating tool. And yet the pattern shifts from circles to perfect hexagons with a level of accuracy most factories still struggle to hit. I worked five years in manufacturing at Siemens, and this is the part people often overlook. The real magic is not new or loud. It is stability. Repeatability. Tool paths that were tuned forever. Precision that just keeps working. Robotics is in a hype cycle right now, but manufacturing has delivered quiet perfection long before anyone talked about foundation models. Sometimes the most interesting engineering is the part that does not ask for attention. —- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

164,829 Aufrufe • vor 9 Monaten

Something must change in robotics! 😖 As more billion-dollar players enter the space, more systems are closing off. APIs move behind paywalls, platforms lock down, and robots turn into black boxes. Pollen Robotics is taking the opposite route. With Reachy 2, everything is open: the code, the CAD files, the ROS 2 interfaces, the communication stack. If you want to swap the camera, redesign the gripper, or fork the whole system, you can, and that’s the point. It creates a culture where universities can run real experiments without licensing drama, and startups can prototype without waiting for vendor permission. Clone it on GitHub. Add behaviors. Share datasets. Fork the models. Push improvements upstream. The Hugging Face influence is real. It’s two open ecosystems aligning around the same idea: robotics should be built by more than a handful of companies. It was so cool to meet the team behind Reachy 2 in Bordeaux! 🔥 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
1:16

Something must change in robotics! 😖 As more billion-dollar players enter the space, more systems are closing off. APIs move behind paywalls, platforms lock down, and robots turn into black boxes. Pollen Robotics is taking the opposite route. With Reachy 2, everything is open: the code, the CAD files, the ROS 2 interfaces, the communication stack. If you want to swap the camera, redesign the gripper, or fork the whole system, you can, and that’s the point. It creates a culture where universities can run real experiments without licensing drama, and startups can prototype without waiting for vendor permission. Clone it on GitHub. Add behaviors. Share datasets. Fork the models. Push improvements upstream. The Hugging Face influence is real. It’s two open ecosystems aligning around the same idea: robotics should be built by more than a handful of companies. It was so cool to meet the team behind Reachy 2 in Bordeaux! 🔥 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

21,046 Aufrufe • vor 9 Monaten

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 Aufrufe • vor 3 Monaten

Balloon-powered robots! 🎈 Surely one of the coolest and craziest robot project I've seen this year. Buoyant Choreographies by RoMeLa is a fun art project shown at ICRA in Atlanta last year. It uses special robots made from helium balloons and moving legs that float and walk around. People can play with the robots using touch, game controllers, or even by blowing air. The robots react by changing colors, moving differently, and showing emotions. Dennis Hong, that's so cool, what's next?! 🤯 Here's the paper behind it: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:27

Balloon-powered robots! 🎈 Surely one of the coolest and craziest robot project I've seen this year. Buoyant Choreographies by RoMeLa is a fun art project shown at ICRA in Atlanta last year. It uses special robots made from helium balloons and moving legs that float and walk around. People can play with the robots using touch, game controllers, or even by blowing air. The robots react by changing colors, moving differently, and showing emotions. Dennis Hong, that's so cool, what's next?! 🤯 Here's the paper behind it: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

53,302 Aufrufe • vor 2 Tagen

Awesome Robotics! 💾 Building your own robot just got a lot easier. MathWorks have released an open-source GitHub repository packed with robotics resources for anyone interested in getting hands-on. The repo includes examples for robot arms, ground vehicles, and drones, with projects that show how to connect with ROS and ROS2 or even deploy Simulink models directly as ROS nodes. There are also more advanced demos, like modeling off-road environments and testing navigation algorithms in photorealistic simulations. Everything is well-documented, with tutorials and links that make it easy to go from concept to prototype. 📑 Whether you’re a student, researcher, or just curious, there’s material here for every level. And since it’s an open community project, you can not only explore but also share your own contributions. For anyone looking to learn robotics by doing, this is a solid place to start! Here’s the link: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
1:08

Awesome Robotics! 💾 Building your own robot just got a lot easier. MathWorks have released an open-source GitHub repository packed with robotics resources for anyone interested in getting hands-on. The repo includes examples for robot arms, ground vehicles, and drones, with projects that show how to connect with ROS and ROS2 or even deploy Simulink models directly as ROS nodes. There are also more advanced demos, like modeling off-road environments and testing navigation algorithms in photorealistic simulations. Everything is well-documented, with tutorials and links that make it easy to go from concept to prototype. 📑 Whether you’re a student, researcher, or just curious, there’s material here for every level. And since it’s an open community project, you can not only explore but also share your own contributions. For anyone looking to learn robotics by doing, this is a solid place to start! Here’s the link: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

59,232 Aufrufe • vor 3 Monaten

This robot is playing Tetris! 🧊 AGILOX dropped something exciting at LogiMAT. One of the most requested robot use cases finally automated: Manual truck loading. What I'm really impressed of is the high precision positioning of pallets directly next to the truck or container wall. It's 2026 and I love that fact that AMR companies are not just moving goods from A to B anymore, but they innovate and look for more value-adding tasks across logistics sites and manufacturing plants! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:28

This robot is playing Tetris! 🧊 AGILOX dropped something exciting at LogiMAT. One of the most requested robot use cases finally automated: Manual truck loading. What I'm really impressed of is the high precision positioning of pallets directly next to the truck or container wall. It's 2026 and I love that fact that AMR companies are not just moving goods from A to B anymore, but they innovate and look for more value-adding tasks across logistics sites and manufacturing plants! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

11,998 Aufrufe • vor 5 Monaten

That's how parts get inspected! 🪡 The pace is ridiculous. Imagine people still doing this instead of machines. Renishaw’s system is one of the biggest shifts in coordinate-measuring machines (CMMs). Instead of moving the entire machine to capture each point, REVO uses a 5-axis scanning head that collects data through rapid angular motion. Combined with automated probe and stylus changes, the system can handle complex geometries and full surface scans that traditionally required slow, point-by-point probing. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:49

That's how parts get inspected! 🪡 The pace is ridiculous. Imagine people still doing this instead of machines. Renishaw’s system is one of the biggest shifts in coordinate-measuring machines (CMMs). Instead of moving the entire machine to capture each point, REVO uses a 5-axis scanning head that collects data through rapid angular motion. Combined with automated probe and stylus changes, the system can handle complex geometries and full surface scans that traditionally required slow, point-by-point probing. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

243,475 Aufrufe • vor 9 Monaten

Awesome! This is literally a superhuman hand. 🤖✋ ChangingTek Robotics just dropped a dexterous hand that actually morphs between left and right hand configurations on the fly. It uses cable-driven tech to pull off shapes and reverse bends that human hands can't even dream of doing. The power is real too, with a 50N grip force and 10N at the fingertips while staying precise within 0.1N. It is kind of like a rigid octopus, meaning it is tough enough to crank a wrench or screwdriver but smooth enough to grab a drink. Having this much range of motion in a single hand basically doubles the efficiency of any robotic arm in tight spots. Source: ChangingTek Robotics #Robot #Humanoid #Robotics #AI #EmbodiedAI #PhysicalAI #ChangingTek #DexterousHand #Bionics
0:33

Awesome! This is literally a superhuman hand. 🤖✋ ChangingTek Robotics just dropped a dexterous hand that actually morphs between left and right hand configurations on the fly. It uses cable-driven tech to pull off shapes and reverse bends that human hands can't even dream of doing. The power is real too, with a 50N grip force and 10N at the fingertips while staying precise within 0.1N. It is kind of like a rigid octopus, meaning it is tough enough to crank a wrench or screwdriver but smooth enough to grab a drink. Having this much range of motion in a single hand basically doubles the efficiency of any robotic arm in tight spots. Source: ChangingTek Robotics #Robot #Humanoid #Robotics #AI #EmbodiedAI #PhysicalAI #ChangingTek #DexterousHand #Bionics

RoboHub🤖

13,855 Aufrufe • vor 5 Monaten

Robots are coming for one of agriculture's most delicate jobs. Picking berries! 🍓 This is Fieldwork Robotics' Fieldworker 1 platform, designed to autonomously harvest raspberries at speeds comparable to human workers. That might sound simple, but berry picking is one of the hardest challenges in agricultural robotics. The robot needs to identify ripe fruit, avoid damaging fragile berries, and operate efficiently in a constantly changing environment. Fieldworker 1 uses custom AI systems and spectral analysis to assess ripeness and is designed so that a single operator can supervise multiple robots in the field. Agriculture continues to face labor shortages across many regions, while growers are under pressure to improve productivity and reduce waste. That's creating a strong demand for automation solutions that can work alongside existing operations. Fieldwork is already running trials with Costa Group, one of Australia's largest fruit growers, and joins a growing group of companies proving that robotic harvesting is moving from research projects into commercial deployments. That's a great market to look out for robotic solutions. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:24

Robots are coming for one of agriculture's most delicate jobs. Picking berries! 🍓 This is Fieldwork Robotics' Fieldworker 1 platform, designed to autonomously harvest raspberries at speeds comparable to human workers. That might sound simple, but berry picking is one of the hardest challenges in agricultural robotics. The robot needs to identify ripe fruit, avoid damaging fragile berries, and operate efficiently in a constantly changing environment. Fieldworker 1 uses custom AI systems and spectral analysis to assess ripeness and is designed so that a single operator can supervise multiple robots in the field. Agriculture continues to face labor shortages across many regions, while growers are under pressure to improve productivity and reduce waste. That's creating a strong demand for automation solutions that can work alongside existing operations. Fieldwork is already running trials with Costa Group, one of Australia's largest fruit growers, and joins a growing group of companies proving that robotic harvesting is moving from research projects into commercial deployments. That's a great market to look out for robotic solutions. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

25,447 Aufrufe • vor 1 Monat

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 →
0:56

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 7 Monaten

A system with moving transfer plates! 🍽️ Modular transfer plates that move items in any direction! These systems from Festo give factories something traditional conveyors can’t: fine, reconfigurable motion that adapts as layouts or processes change. Because they can route items in multiple directions, you can run inspections, branch flows based on sensor data, or perform operations directly on the moving parts. It could even power fully automated storage: shelves that reposition items based on real-time demand. I'd love to see more of them in 3PL centers. Where would you use them? 👀 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:25

A system with moving transfer plates! 🍽️ Modular transfer plates that move items in any direction! These systems from Festo give factories something traditional conveyors can’t: fine, reconfigurable motion that adapts as layouts or processes change. Because they can route items in multiple directions, you can run inspections, branch flows based on sensor data, or perform operations directly on the moving parts. It could even power fully automated storage: shelves that reposition items based on real-time demand. I'd love to see more of them in 3PL centers. Where would you use them? 👀 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

327,650 Aufrufe • vor 9 Monaten

Not all automation needs an arm 🦾I That’s right, AmbiRobotics just released their new product - a palletizing gantry system. It’s called AmbiStack, and at first glance, it looks like a 3D tetris. 🥞 It’s a mechanical system designed to automate the stacking and packing of items in warehouses. The system uses Sim2Real reinforcement learning and advanced AI vision technology to optimize how items are sorted and stacked. Even without prior knowledge of their size, shape, or appearance. 📦 AmbiStack can stack items densely onto pallets or into walled containers, maximizing space and reducing warehouse transportation costs. It is a multipurpose solution that can be used for different applications, such as building pallets for retail distribution or stacking items directly on the floor. The system is highly adaptable, able to handle both single-SKU and mixed-SKU cases, and can stack items in any orientation for maximum flexibility. AmbiStack features multi-pick-and-place capabilities, allowing it to pick and place multiple items at once, significantly improving workflow efficiency. P.S. Yes, I know that gantry is technically a three-axis robot.
0:27

Not all automation needs an arm 🦾I That’s right, AmbiRobotics just released their new product - a palletizing gantry system. It’s called AmbiStack, and at first glance, it looks like a 3D tetris. 🥞 It’s a mechanical system designed to automate the stacking and packing of items in warehouses. The system uses Sim2Real reinforcement learning and advanced AI vision technology to optimize how items are sorted and stacked. Even without prior knowledge of their size, shape, or appearance. 📦 AmbiStack can stack items densely onto pallets or into walled containers, maximizing space and reducing warehouse transportation costs. It is a multipurpose solution that can be used for different applications, such as building pallets for retail distribution or stacking items directly on the floor. The system is highly adaptable, able to handle both single-SKU and mixed-SKU cases, and can stack items in any orientation for maximum flexibility. AmbiStack features multi-pick-and-place capabilities, allowing it to pick and place multiple items at once, significantly improving workflow efficiency. P.S. Yes, I know that gantry is technically a three-axis robot.

Lukas Ziegler

24,133 Aufrufe • vor 1 Jahr

A system with moving transfer plates! 🍽️ Modular transfer plates that move items in any direction. These systems from Festo give factories something really cool; reconfigurable motion that adapts as layouts or processes change. Because they can route items in multiple directions, you can run inspections, branch flows based on sensor data, or perform operations directly on the moving parts. It could even power fully automated storage: shelves that reposition items based on real-time demand. I'd love to see more of them in 3PL centers. Where would you use them? 👀 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:25

A system with moving transfer plates! 🍽️ Modular transfer plates that move items in any direction. These systems from Festo give factories something really cool; reconfigurable motion that adapts as layouts or processes change. Because they can route items in multiple directions, you can run inspections, branch flows based on sensor data, or perform operations directly on the moving parts. It could even power fully automated storage: shelves that reposition items based on real-time demand. I'd love to see more of them in 3PL centers. Where would you use them? 👀 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

215,294 Aufrufe • vor 1 Monat

Magnetic levitation for surgical robots! 🧲 A research team working on minimally invasive surgery just introduced a remote magnetic levitation to move things inside our bodies. Their main goal is to control guidewires and catheters inside the body using magnetic fields. But levitation is unstable and extreme, it forces them to solve fundamental control problems they can't avoid. They have to handle strong magnetic field nonlinearities, develop real-time invertible models, and create control methods that work on any eMNS (electroMagnetic Navigation System) and any object. The real challenge is the position and orientation feedback. You can control a magnet outside the body, but once a catheter or drug-delivery robot is inside a patient, you can't see it. There's no vision, but just magnetic fields and current measurements. That's huge news coming out of ETH Zurich! Here's the paper: Mentioned all authors on Li, but coulnd't find them here! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:20

Magnetic levitation for surgical robots! 🧲 A research team working on minimally invasive surgery just introduced a remote magnetic levitation to move things inside our bodies. Their main goal is to control guidewires and catheters inside the body using magnetic fields. But levitation is unstable and extreme, it forces them to solve fundamental control problems they can't avoid. They have to handle strong magnetic field nonlinearities, develop real-time invertible models, and create control methods that work on any eMNS (electroMagnetic Navigation System) and any object. The real challenge is the position and orientation feedback. You can control a magnet outside the body, but once a catheter or drug-delivery robot is inside a patient, you can't see it. There's no vision, but just magnetic fields and current measurements. That's huge news coming out of ETH Zurich! Here's the paper: Mentioned all authors on Li, but coulnd't find them here! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

121,585 Aufrufe • vor 2 Monaten

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 Aufrufe • vor 9 Monaten

Foundation models are enough to solve robotics! Unfortunately, this is not true. We keep hearing that Vision-Language-Action (VLA) models struggle because of the gap between static training and the dynamic real world. A German startup (Sereact) just released a solution that bridges this gap perfectly. They are introducing a new paradigm called Interactive RL Policy Patching. It's a distributed framework that allows robots to self-learn from human corrections without needing full retraining. When a robot fails, a human operator provides a brief "patch" or demonstration. The system then uses online off-policy reinforcement learning to update the behavior instantly. This is powered by a massive foundation model trained on hundreds of millions of interactions from over 100 deployed robot stations. The best part is the distributed parameter synchronization... When one robot learns a fix, the update is published fleet-wide... meaning the entire swarm gets smarter from a single human intervention. They are already proving this on complex manipulation tasks like shoe unboxing and screw sorting, drastically reducing the data needed to handle edge cases. Real-world environments are unforgiving, and I love seeing systems that can actually adapt on the fly! 📍 More info:
0:38

Foundation models are enough to solve robotics! Unfortunately, this is not true. We keep hearing that Vision-Language-Action (VLA) models struggle because of the gap between static training and the dynamic real world. A German startup (Sereact) just released a solution that bridges this gap perfectly. They are introducing a new paradigm called Interactive RL Policy Patching. It's a distributed framework that allows robots to self-learn from human corrections without needing full retraining. When a robot fails, a human operator provides a brief "patch" or demonstration. The system then uses online off-policy reinforcement learning to update the behavior instantly. This is powered by a massive foundation model trained on hundreds of millions of interactions from over 100 deployed robot stations. The best part is the distributed parameter synchronization... When one robot learns a fix, the update is published fleet-wide... meaning the entire swarm gets smarter from a single human intervention. They are already proving this on complex manipulation tasks like shoe unboxing and screw sorting, drastically reducing the data needed to handle edge cases. Real-world environments are unforgiving, and I love seeing systems that can actually adapt on the fly! 📍 More info:

Ilir Aliu

18,210 Aufrufe • vor 7 Monaten