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.

Gemini + π0 = actually useful robots! (Similar to what Physical Intelligence did with "Hi Robot") I can now verbally tell the robot that I'm building a red Lego wall or wooden tower, and it will infer the next steps by itself and pass me the necessary pieces, tools,... or materials, ha! You can also just ask it to bring you things! The pipeline works as follows: - OpenAI Whisper (local) → speech to text - Gemini → makes sense of user requests, converts to robot tasks, bounding boxes, grasping points, etc. (System 2 thinking FTW!) - π0 → robotic actions The π0 was finetuned just for pick-and-place Lego bricks only, and it generalizes beautifully to all kinds of tasks. However, there's lots of room for improvement when it comes to grasping & accuracy. Things that could help: - Conditioning on grasping points - Better data collection (I'm not that great at teleop) - Lots more synthetic data and simulationsshow more

Shreyas Gite

2,204 subscribers

25,485 views • 1 year ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 Comments

Shreyas Gite1 year ago

And sometimes when pi0 wakes-up it does a wild-drunken behaviours:D But super exciting, thanks @RemiCadene and @LeRobotHF community! We are at stage we can actually build useful robots for constrained environments and specific tasks that genuinely generate economic value.

Shreyas Gite1 year ago

Here is the video with Legos. Also one of the wooden bars is too far to reach, so the arm moves to the next target. I think with the next generation of VLA models trained on top of video generation models, we should automatically see a step-change improvement in accuracy.

Saketh Saketh1 year ago

@physical_int Try GROOT Mimic

Tran Nguyen Le1 year ago

@physical_int Hi @shreyasgite, great work! I will soon get my hand on the SO-ARM101, and I would like to apply pi0 for the arm as well. Any guidance how to get on with it? Thanks :D

Shreyas Gite1 year ago

@physical_int For training you can use lerobot as it is; for inference I changed few things in control_utils.py file under robot devices;) Will make a quick tutorial this week or next✌️

H4sh31 year ago

@physical_int Did you finetune or something?

Saba Khalilnaji1 year ago

@physical_int Totally sick!! What are you using the grasping points for if you’re using pi0 and not conditioning with it? Also which gemni model?

Shreyas Gite1 year ago

@physical_int Gemini 2.0 flash. Not using grasping points in this one, but used it for other training set as grasping the objects correctly is still a bit tricky.

Krishna1 year ago

@physical_int Maybe a simple Readme about how all the pieces fit together, please? Will get us noobs acclimated super-fast. Thank you for your valuable contributions.

Shreyas Gite1 year ago

@physical_int Here you go;)

Related Videos

The $10k robot arms that can learn from a handful of demos: Most robots still lose the cost equation. They’re slow, expensive, and take months to deploy, which means… they only make sense for huge factories. The The Robot Learning Company (YC X25) is building affordable, general-purpose robot arms that can pick up new tasks from just a few human demonstrations. Why it matters: ✅ Under $10k per pair of stationary arms ✅ Adapts to new tasks with imitation + reinforcement learning ✅ Deployable in days, not months From small manufacturers to service providers, this makes robotic labor accessible to companies that could never justify it before. Saying hi to founder Jannik Grothusen 👋 More here:

The $10k robot arms that can learn from a handful of demos: Most robots still lose the cost equation. They’re slow, expensive, and take months to deploy, which means… they only make sense for huge factories. The The Robot Learning Company (YC X25) is building affordable, general-purpose robot arms that can pick up new tasks from just a few human demonstrations. Why it matters: ✅ Under $10k per pair of stationary arms ✅ Adapts to new tasks with imitation + reinforcement learning ✅ Deployable in days, not months From small manufacturers to service providers, this makes robotic labor accessible to companies that could never justify it before. Saying hi to founder Jannik Grothusen 👋 More here:

Ilir Aliu - eu/acc

36,336 views • 11 months ago

Boom! Open source LegoGPT is a building AI, and sure it can be used for Legos but it can also be used for Lego-like building of homes. LegoGPT converts meshes to Lego in one step using 1×1, 1×2, 1×4, 1×6, 1×8, 2×2, 2×4, and 2×6 bricks. Then they evaluate the stability of the design. Finally, they render an image and ask GPT-4o to produce captions to go with the image. This sent to robots and they complete the real-time build. This can absolutely scale and as with Legos, you can use smaller pieces for higher resolution. Testing it detail now with robot assembly. Link:

Boom! Open source LegoGPT is a building AI, and sure it can be used for Legos but it can also be used for Lego-like building of homes. LegoGPT converts meshes to Lego in one step using 1×1, 1×2, 1×4, 1×6, 1×8, 2×2, 2×4, and 2×6 bricks. Then they evaluate the stability of the design. Finally, they render an image and ask GPT-4o to produce captions to go with the image. This sent to robots and they complete the real-time build. This can absolutely scale and as with Legos, you can use smaller pieces for higher resolution. Testing it detail now with robot assembly. Link:

Brian Roemmele

22,363 views • 1 year ago

.Ilya Sutskever on why OpenAI gave up on robotics: "Progress comes from the combination of compute and data. There was no path to data from robotics. I'd say that now it is possible to create a path forward, but one needs to really commit. You could imagine a gradual path of improvement where you build more robots, they do more things, you collect more data and so on. But you need to really love robots and need to be really willing to solve all the physical and logistical problems of dealing with them. It's not the same as software at all."

.Ilya Sutskever on why OpenAI gave up on robotics: "Progress comes from the combination of compute and data. There was no path to data from robotics. I'd say that now it is possible to create a path forward, but one needs to really commit. You could imagine a gradual path of improvement where you build more robots, they do more things, you collect more data and so on. But you need to really love robots and need to be really willing to solve all the physical and logistical problems of dealing with them. It's not the same as software at all."

Dwarkesh Patel

325,857 views • 2 years ago

It's a 3D printer, and 3D assembly station! 🖨️ The Functgraph developed at Meiji University starts as a regular 3D printer but upgrades itself into a mini factory. It can print parts for its own tools, pick them up, clean them, and put them together, all by itself. Think of it like a robot that can 3D print a spatula, assemble it, and then use it to flip pancakes. 🥞 Instead of just printing objects, the Functgraph can actually perform physical tasks, like folding laundry or slicing vegetables, by using printed and assembled tools. It’s a step toward the idea of a robot that can download "apps" as physical skills, much like your phone downloads software! 👀

It's a 3D printer, and 3D assembly station! 🖨️ The Functgraph developed at Meiji University starts as a regular 3D printer but upgrades itself into a mini factory. It can print parts for its own tools, pick them up, clean them, and put them together, all by itself. Think of it like a robot that can 3D print a spatula, assemble it, and then use it to flip pancakes. 🥞 Instead of just printing objects, the Functgraph can actually perform physical tasks, like folding laundry or slicing vegetables, by using printed and assembled tools. It’s a step toward the idea of a robot that can download "apps" as physical skills, much like your phone downloads software! 👀

Lukas Ziegler

149,742 views • 1 year ago

🤯incredible,its playability and usability are outstanding. Tron2 is a LEGO robot. It can be assembled into various forms depending on the scenario, including bipedal, wheeled, and humanoid torso configurations, and its end effectors are also interchangeable. Each form of the robot is driven by a VLA model. It can perform complex movements and can also be integrated into existing workflows to perform tasks. It's worth mentioning that this solves the problem of which type of humanoid robot to use. Each user can assemble the robot in a configuration that suits their specific scenario, making it truly flexible and versatile – it doesn't necessarily have to be bipedal or wheeled... I look forward to seeing more real-world use cases.

🤯incredible,its playability and usability are outstanding. Tron2 is a LEGO robot. It can be assembled into various forms depending on the scenario, including bipedal, wheeled, and humanoid torso configurations, and its end effectors are also interchangeable. Each form of the robot is driven by a VLA model. It can perform complex movements and can also be integrated into existing workflows to perform tasks. It's worth mentioning that this solves the problem of which type of humanoid robot to use. Each user can assemble the robot in a configuration that suits their specific scenario, making it truly flexible and versatile – it doesn't necessarily have to be bipedal or wheeled... I look forward to seeing more real-world use cases.

CyberRobo

67,287 views • 6 months ago

Robot for railway inspections! 🚂 This robot from Shenhao Robotics International is equipped with a self-moving motion platform and intelligent sensor modules to detect any track defects and anomalies. By using it, track inspectors can complete nighttime route inspection tasks and solve problems related to heavy tasks. There are fewer and fewer people who can perform inspection tasks, so this robot makes sure that these routine tasks are performed timely and with high quality! It can be great when it comes to track geometry measurement or fastener defects detection. The robot moves at a speed of 5~15km/h and can be operated remotely or be fully autonomous. P.S. What is your opinion? Can it become a standard?

Robot for railway inspections! 🚂 This robot from Shenhao Robotics International is equipped with a self-moving motion platform and intelligent sensor modules to detect any track defects and anomalies. By using it, track inspectors can complete nighttime route inspection tasks and solve problems related to heavy tasks. There are fewer and fewer people who can perform inspection tasks, so this robot makes sure that these routine tasks are performed timely and with high quality! It can be great when it comes to track geometry measurement or fastener defects detection. The robot moves at a speed of 5~15km/h and can be operated remotely or be fully autonomous. P.S. What is your opinion? Can it become a standard?

Lukas Ziegler

29,375 views • 11 months ago

A robot hand grasp over 500 totally new objects without fail? Zero-shot, single-view & super reliable ⬇️ + Paper Grasping random objects is hard for robots, especially when shapes, weights, and materials vary. RobustDexGrasp solves this with a smart new way of seeing and controlling the hand, leading to near-perfect grasping, even in noisy or cluttered scenes. Thank you for sharing, Hui Zhang 🙏 Follow him!! What makes it special ✅ Grabs 500+ unseen objects with 94.6% success using only single-view input ✅ Learns local shapes, not full geometry, for better generalization ✅ Trained with just 35 objects in sim but works in the real world with hundreds more ✅ Adapts to noise, unexpected forces, and even plays chess with VLM planning It shows that smart sensing and adaptive control can take dexterous grasping to the next level. Project: Paper:

A robot hand grasp over 500 totally new objects without fail? Zero-shot, single-view & super reliable ⬇️ + Paper Grasping random objects is hard for robots, especially when shapes, weights, and materials vary. RobustDexGrasp solves this with a smart new way of seeing and controlling the hand, leading to near-perfect grasping, even in noisy or cluttered scenes. Thank you for sharing, Hui Zhang 🙏 Follow him!! What makes it special ✅ Grabs 500+ unseen objects with 94.6% success using only single-view input ✅ Learns local shapes, not full geometry, for better generalization ✅ Trained with just 35 objects in sim but works in the real world with hundreds more ✅ Adapts to noise, unexpected forces, and even plays chess with VLM planning It shows that smart sensing and adaptive control can take dexterous grasping to the next level. Project: Paper:

Ilir Aliu

37,980 views • 1 year ago

Learning from Human Demonstrations: Show the Robot How to Act! The pipeline is very similar to older experiments using Gemini & pi0 with LeRobot. Pi-zero runs locally, while Gemini Flash generates the affordances and the high-level task. (More details are in the thread.) The new component is learning from demonstrations via Gemini 2.5 Pro. I capture a video while demoing & take one of the last frames. Gemini 2.5 Pro then extracts the instructions & passes them to Gemini Flash to process the scene. The fun part is that there's no fancy insight that came from me; other than the days spent figuring out the right prompts. It's the bitter lesson hitting you in the face -> Enhanced Gemini capabilities make this possible. For example, Gemini Flash cannot do Russian doll stacking, but Gemini 2.5 Pro can do it consistently. The current limitation is low-level manipulation: - As you can see, I'm aligning the objects so they are easy to grasp using the same technique from the training data. I couldn't get Gemini Flash to consistently output an accurate grasping angle, and Gemini 1.5 Pro was too expensive and slow for real-time deployment. - Getting a symmetrical gripper should also help a lot. Adding rubber to the tips would probably also help prevent objects from slipping. Collecting & curating the data was the most time consuming & labor intensive part. Next, to improve low-level manipulation and make the system more real-time, I'm shifting to focus more on sims & synthetic data. This aligns better with my core competence. I'm open to tips and suggestions.

Learning from Human Demonstrations: Show the Robot How to Act! The pipeline is very similar to older experiments using Gemini & pi0 with LeRobot. Pi-zero runs locally, while Gemini Flash generates the affordances and the high-level task. (More details are in the thread.) The new component is learning from demonstrations via Gemini 2.5 Pro. I capture a video while demoing & take one of the last frames. Gemini 2.5 Pro then extracts the instructions & passes them to Gemini Flash to process the scene. The fun part is that there's no fancy insight that came from me; other than the days spent figuring out the right prompts. It's the bitter lesson hitting you in the face -> Enhanced Gemini capabilities make this possible. For example, Gemini Flash cannot do Russian doll stacking, but Gemini 2.5 Pro can do it consistently. The current limitation is low-level manipulation: - As you can see, I'm aligning the objects so they are easy to grasp using the same technique from the training data. I couldn't get Gemini Flash to consistently output an accurate grasping angle, and Gemini 1.5 Pro was too expensive and slow for real-time deployment. - Getting a symmetrical gripper should also help a lot. Adding rubber to the tips would probably also help prevent objects from slipping. Collecting & curating the data was the most time consuming & labor intensive part. Next, to improve low-level manipulation and make the system more real-time, I'm shifting to focus more on sims & synthetic data. This aligns better with my core competence. I'm open to tips and suggestions.

Shreyas Gite

22,555 views • 1 year ago

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 views • 1 year ago

More moves to AI-first living. Got the Genspark browser that just came out. One thing I notice is that I like having separate browsers working on different tasks. I'm not a big user of MCPs, since I'm not really a developer. Are you? They have a store of a bunch of MCPs available to use. Most of my AI work is research related, or answering emails and scheduling things, I'm focusing more of my effort there. Genspark has been shipping a ton of stuff the past few weeks, from ability to make slides to a new AI secretary that can schedule things, or help you answer your emails. First I looked at, "does it make sense to move over to this new way of working?" The problem with that is you gotta learn a new browser. Well, it looks like Google Chrome, except it has a prompt window. Click the icons underneath it and you will see you can add X, Notion, Google stuff like calendar and gmail, or a variety of others. But the real power is just talking to it. I asked it what kinds of tasks it can do, and it answered: "Just tell me what you want to accomplish! For example: "Research the latest developments in spatial computing and create a presentation" "Analyze my Gmail for any important emails from this week" "Find information about AI robotics companies and create a spreadsheet" "Generate a video about emerging tech trends" "Help me plan a trip to CES 2026" And so further into AI-first living I go. Have you tried it yet? What do you suggest I do next to use more AI to run my life and build my business? I have another browser tab building a video for me. What a beautiful time to be alive. Download it at:

More moves to AI-first living. Got the Genspark browser that just came out. One thing I notice is that I like having separate browsers working on different tasks. I'm not a big user of MCPs, since I'm not really a developer. Are you? They have a store of a bunch of MCPs available to use. Most of my AI work is research related, or answering emails and scheduling things, I'm focusing more of my effort there. Genspark has been shipping a ton of stuff the past few weeks, from ability to make slides to a new AI secretary that can schedule things, or help you answer your emails. First I looked at, "does it make sense to move over to this new way of working?" The problem with that is you gotta learn a new browser. Well, it looks like Google Chrome, except it has a prompt window. Click the icons underneath it and you will see you can add X, Notion, Google stuff like calendar and gmail, or a variety of others. But the real power is just talking to it. I asked it what kinds of tasks it can do, and it answered: "Just tell me what you want to accomplish! For example: "Research the latest developments in spatial computing and create a presentation" "Analyze my Gmail for any important emails from this week" "Find information about AI robotics companies and create a spreadsheet" "Generate a video about emerging tech trends" "Help me plan a trip to CES 2026" And so further into AI-first living I go. Have you tried it yet? What do you suggest I do next to use more AI to run my life and build my business? I have another browser tab building a video for me. What a beautiful time to be alive. Download it at:

Robert Scoble

84,349 views • 1 year ago

New Gemini Robotics 1.5 models will enable robots to better reason, plan ahead, use digital tools like Search, and transfer learning from one kind of robot to another. Our next big step towards general-purpose robots that are truly helpful — you can see how the robot reasons as it sorts laundry in the video below.

New Gemini Robotics 1.5 models will enable robots to better reason, plan ahead, use digital tools like Search, and transfer learning from one kind of robot to another. Our next big step towards general-purpose robots that are truly helpful — you can see how the robot reasons as it sorts laundry in the video below.

Sundar Pichai

496,266 views • 9 months ago

Elon Musk: Autonomy and Optimus will actually happen. “At a very high level, I'd say that autonomy is an insanely fundamental breakthrough. And no one is even close to Tesla for solving generalized autonomy or generalized self-driving vehicles. No one's even close. With self-driving, the car becomes roughly five times more useful, but it costs the same to build. Can you imagine what would happen if a company were doing a 25% to 30% percent gross margins, but suddenly that same thing was five times more valuable. What would that do to the value of Tesla ? And the value of that car? It boggles the mind, actually. If you actually do the math on that, it's insane. There's also the Optimus program, which is our humanoid robot, where we will leverage our manufacturing expertise and the intelligence we've developed for self-driving to have a useful humanoid robot. The economy is fundamentally GDP per capita times capita. If you no longer have a constraint on capita because of a useful humanoid robot, it's not clear that there's any limit to the size of the economy. And these things will actually happen.” Baron Investment Conference, 2022

Elon Musk: Autonomy and Optimus will actually happen. “At a very high level, I'd say that autonomy is an insanely fundamental breakthrough. And no one is even close to Tesla for solving generalized autonomy or generalized self-driving vehicles. No one's even close. With self-driving, the car becomes roughly five times more useful, but it costs the same to build. Can you imagine what would happen if a company were doing a 25% to 30% percent gross margins, but suddenly that same thing was five times more valuable. What would that do to the value of Tesla ? And the value of that car? It boggles the mind, actually. If you actually do the math on that, it's insane. There's also the Optimus program, which is our humanoid robot, where we will leverage our manufacturing expertise and the intelligence we've developed for self-driving to have a useful humanoid robot. The economy is fundamentally GDP per capita times capita. If you no longer have a constraint on capita because of a useful humanoid robot, it's not clear that there's any limit to the size of the economy. And these things will actually happen.” Baron Investment Conference, 2022

ELON CLIPS

34,124 views • 1 year 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:

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

Zack Snyder on his dyslexia: "It was a challenge for me when I was, you know, young in school, and all I wanted to do was make movies because that was the thing that I got great pleasure from and reward from. I love books, and I'm an avid reader, but I just have a hard time because of the way that I perceive. "I've had a great sort of - one side of me anyways - was really satisfied by art and drawing and sculpture and sort of visual expression. And I think that that started to, you know, was the thing that kind of made me feel un-frustrated. And also the way the system was designed, sort of not to support me when I was in high school at that time. "It was very difficult, you know, there was a lot of, you know, just, difficulty. My English teacher in high school was worried about what my career would be, and I'm like. He would be happy to know that I'm in the Writers Guild of America now. "But, I think that that all those things are, they're all... you can transcend all those things with perseverance and with interest and with with help. And I think that that's an important part of it. "And I just think I've had to adapt, and sort of... I have my own style of the way I write, I write all, you know, but I'm pretty prolific. And I love- I listen to tons of audio books on tape, unabridged hours and hours and hours. That's all I do when I'm driving in the car or wherever I'm doing. And it's helped me a lot. "And yeah, I mean, I just hope that anyone who is- feels trapped or frustrated by the world in general. You know, they need to just, I think that we all have like a magic spark, and you need to just find the thing that makes you, you know, inspires you and, and gets you excited and pursue it as hard as you can find your passion in the world. That's a, that's a great motivator."

Zack Snyder on his dyslexia: "It was a challenge for me when I was, you know, young in school, and all I wanted to do was make movies because that was the thing that I got great pleasure from and reward from. I love books, and I'm an avid reader, but I just have a hard time because of the way that I perceive. "I've had a great sort of - one side of me anyways - was really satisfied by art and drawing and sculpture and sort of visual expression. And I think that that started to, you know, was the thing that kind of made me feel un-frustrated. And also the way the system was designed, sort of not to support me when I was in high school at that time. "It was very difficult, you know, there was a lot of, you know, just, difficulty. My English teacher in high school was worried about what my career would be, and I'm like. He would be happy to know that I'm in the Writers Guild of America now. "But, I think that that all those things are, they're all... you can transcend all those things with perseverance and with interest and with with help. And I think that that's an important part of it. "And I just think I've had to adapt, and sort of... I have my own style of the way I write, I write all, you know, but I'm pretty prolific. And I love- I listen to tons of audio books on tape, unabridged hours and hours and hours. That's all I do when I'm driving in the car or wherever I'm doing. And it's helped me a lot. "And yeah, I mean, I just hope that anyone who is- feels trapped or frustrated by the world in general. You know, they need to just, I think that we all have like a magic spark, and you need to just find the thing that makes you, you know, inspires you and, and gets you excited and pursue it as hard as you can find your passion in the world. That's a, that's a great motivator."

Zack Snyder Film

11,128 views • 6 months ago

Today we’re rolling out a beta version of tasks—a new way to ask ChatGPT to do things for you at a future time. Whether it's one-time reminders or recurring actions, tell ChatGPT what you need and when, and it will automatically take care of it.

Today we’re rolling out a beta version of tasks—a new way to ask ChatGPT to do things for you at a future time. Whether it's one-time reminders or recurring actions, tell ChatGPT what you need and when, and it will automatically take care of it.

OpenAI

3,500,470 views • 1 year ago

It's a 3D printer, and 3D assembly station! 🖨️ The Functgraph developed at Meiji University starts as a regular 3D printer but upgrades itself into a mini factory. It can print parts for its own tools, pick them up, clean them, and put them together, all by itself. Think of it like a robot that can 3D print a spatula, assemble it, and then use it to flip pancakes. 🥞 Instead of just printing objects, the Functgraph can actually perform physical tasks, like folding laundry or slicing vegetables, by using printed and assembled tools. It’s a step toward the idea of a robot that can download "apps" as physical skills, much like your phone downloads software! 👀 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

It's a 3D printer, and 3D assembly station! 🖨️ The Functgraph developed at Meiji University starts as a regular 3D printer but upgrades itself into a mini factory. It can print parts for its own tools, pick them up, clean them, and put them together, all by itself. Think of it like a robot that can 3D print a spatula, assemble it, and then use it to flip pancakes. 🥞 Instead of just printing objects, the Functgraph can actually perform physical tasks, like folding laundry or slicing vegetables, by using printed and assembled tools. It’s a step toward the idea of a robot that can download "apps" as physical skills, much like your phone downloads software! 👀 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

139,414 views • 2 months ago