Loading video...

Video Failed to Load

Go Home

A flapping-wing drone that actually handles its own vibrations. BionicBird’s X-Fly is not a propeller drone. It is an ornithopter with a six-axis gyro and precision G-sensors designed specifically to deal with the chaotic dynamics of wing flapping. • Sensor fusion tuned for flapping flight, not propeller stability •...

IlirAliu_'s profile picture

Ilir Aliu

53,904 subscribers

36,291 views • 8 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Flapping-wing drones have been around for years... but the X-Fly Bionic Bird takes a different approach. Designed to mimic the motion of a real bird, it combines mechanical wing flapping with onboard stabilization for controlled flight. A six-axis gyro and G-sensors help counteract the vibrations caused by flapping, keeping it steady even in windy conditions. It has a 150-meter range, a replaceable battery for extended use, and a flexible frame designed to withstand crashes. Whether it’s a novelty or a step forward for bio-inspired flight remains to be seen!
1:08

Flapping-wing drones have been around for years... but the X-Fly Bionic Bird takes a different approach. Designed to mimic the motion of a real bird, it combines mechanical wing flapping with onboard stabilization for controlled flight. A six-axis gyro and G-sensors help counteract the vibrations caused by flapping, keeping it steady even in windy conditions. It has a 150-meter range, a replaceable battery for extended use, and a flexible frame designed to withstand crashes. Whether it’s a novelty or a step forward for bio-inspired flight remains to be seen!

Circuit

19,397 views • 1 year ago

Bio-inspired engineering by Festo. Nature has already solved many of the problems we deal with every day. 🌱 Festo produces mechanical animals called Bionics series. It combines mechanical engineering with biology and nature. Nature is a great teacher and can teach us a lot! From a flapping-wing robot that flies using bird-like wing twisting, to bionic ants that cooperate through swarm intelligence, these projects study how animals solve different problems. 🐜 Just look at these! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:32

Bio-inspired engineering by Festo. Nature has already solved many of the problems we deal with every day. 🌱 Festo produces mechanical animals called Bionics series. It combines mechanical engineering with biology and nature. Nature is a great teacher and can teach us a lot! From a flapping-wing robot that flies using bird-like wing twisting, to bionic ants that cooperate through swarm intelligence, these projects study how animals solve different problems. 🐜 Just look at these! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

15,518 views • 15 days ago

For the first time in history, GPT-6 Astra created a fly that is simply a fly. Not a chatbot pretending to be a fly. Not a simplified animation. A digital fly running its own connectome brain, perceiving a real room through its own senses and interacting with the environment using the power of AR. The entire loop is surprisingly wild: Spectacles capture the retina, light rays, hands, and the surrounding room → the room is converted into an inventory → sensory information is fed into the fly’s neural system → the MaleCNS connectome processes it → descending neurons and motor pools generate actions → the commands return to the Spectacles → wings, legs, and head respond. In other words, the fly sees through its own eyes, processes the world through its own simulated brain, and acts through its own virtual body. We are moving from AI that generates outputs to AI that actually has a body, senses, a brain, and a closed perception-action loop. The 🪰 is no longer just simulated. It is experiencing a world The developer Pavlo Tkachenko is pinned below in the post
0:28

For the first time in history, GPT-6 Astra created a fly that is simply a fly. Not a chatbot pretending to be a fly. Not a simplified animation. A digital fly running its own connectome brain, perceiving a real room through its own senses and interacting with the environment using the power of AR. The entire loop is surprisingly wild: Spectacles capture the retina, light rays, hands, and the surrounding room → the room is converted into an inventory → sensory information is fed into the fly’s neural system → the MaleCNS connectome processes it → descending neurons and motor pools generate actions → the commands return to the Spectacles → wings, legs, and head respond. In other words, the fly sees through its own eyes, processes the world through its own simulated brain, and acts through its own virtual body. We are moving from AI that generates outputs to AI that actually has a body, senses, a brain, and a closed perception-action loop. The 🪰 is no longer just simulated. It is experiencing a world The developer Pavlo Tkachenko is pinned below in the post

Zentrix⌚️

321,272 views • 10 days ago

A robot that swims underwater, then flies straight out of it! 🦢 Water is 1,000 times denser than air. Moving through one or the other normally means two completely different machines. Around 100 bird species disagree. Loons, gulls, puffins and petrels dive after prey, then leap back into the sky. Engineers at MIT and EPFL built a robot that does the same thing. It's a flapping-wing aerial-aquatic vehicle, it weighs under 300 grams, and the results are out in Science. Raphael Zufferey who runs the AURA Lab at MIT, is lead author. A waterproof motor drives a crankshaft that pumps two flexible wings up and down at set frequencies, and a motorised tail changes angle to climb or dive. The wing membranes are coated with hydrophobic nanoparticles so water sheds off them. Wing flexibility turned out to be the whole game. Flexible enough to keep flapping amplitude low in water, firm enough to hold the robot up in air. → Swims at almost 1 m/s flapping at around 5 Hz → Flies at around 6 m/s at a similar frequency, close to real diving birds → The water-to-air transition needs a pitch of around 70°. Shallower and the wingtips catch the surface, steeper and it falls back in My favourite finding is the one about feet. Puffins and ducks paddle at the surface to get airborne, so the team assumed a robot would need something equivalent. It doesn't. Wings and tail alone are enough. Funded in part by a Marie Skłodowska-Curie fellowship 🇵🇱 Read more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:23

A robot that swims underwater, then flies straight out of it! 🦢 Water is 1,000 times denser than air. Moving through one or the other normally means two completely different machines. Around 100 bird species disagree. Loons, gulls, puffins and petrels dive after prey, then leap back into the sky. Engineers at MIT and EPFL built a robot that does the same thing. It's a flapping-wing aerial-aquatic vehicle, it weighs under 300 grams, and the results are out in Science. Raphael Zufferey who runs the AURA Lab at MIT, is lead author. A waterproof motor drives a crankshaft that pumps two flexible wings up and down at set frequencies, and a motorised tail changes angle to climb or dive. The wing membranes are coated with hydrophobic nanoparticles so water sheds off them. Wing flexibility turned out to be the whole game. Flexible enough to keep flapping amplitude low in water, firm enough to hold the robot up in air. → Swims at almost 1 m/s flapping at around 5 Hz → Flies at around 6 m/s at a similar frequency, close to real diving birds → The water-to-air transition needs a pitch of around 70°. Shallower and the wingtips catch the surface, steeper and it falls back in My favourite finding is the one about feet. Puffins and ducks paddle at the surface to get airborne, so the team assumed a robot would need something equivalent. It doesn't. Wings and tail alone are enough. Funded in part by a Marie Skłodowska-Curie fellowship 🇵🇱 Read more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

151,682 views • 17 days ago

An open source project developing a desktop “Pick-and-Place” machine. (📍All of the source on GitHub) The LumenPnP can be used for assembling electronic components onto circuit boards! The project is getting a huge update with a whole new control box, integrating the pneumatics required to pick the parts, and a custom controller. > The controller uses Marlin firmware as the brain, and controls six stepper motors to move the machine. > It also controls two pneumatic pumps and valves for actually picking up the parts with the machine's nozzle tips. All of the source for the machine are available on GitHub!: Credit: Opulo with the awesome Stephen Hawes 👋 —- Weekly robotics and AI insights. Subscribe free:
0:55

An open source project developing a desktop “Pick-and-Place” machine. (📍All of the source on GitHub) The LumenPnP can be used for assembling electronic components onto circuit boards! The project is getting a huge update with a whole new control box, integrating the pneumatics required to pick the parts, and a custom controller. > The controller uses Marlin firmware as the brain, and controls six stepper motors to move the machine. > It also controls two pneumatic pumps and valves for actually picking up the parts with the machine's nozzle tips. All of the source for the machine are available on GitHub!: Credit: Opulo with the awesome Stephen Hawes 👋 —- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

101,551 views • 7 months ago

This is what the avionics bay of a fly-by-wire Boeing 787 Dreamliner looks like, hidden underneath the floor where passengers sit. Its computing architecture includes 16 general processing modules and 21 remote data concentrators spread throughout the aircraft. When the pilot or co-pilot makes a control input, there is no conventional mechanical linkage to the primary flight surfaces. The input is sensed electronically, processed through redundant flight control computers and networks, then sent to the actuators that move the required surfaces all within milliseconds. The B787 also replaced traditional bleed air systems for engine starting, cabin pressurisation and wing anti-icing with electrically powered systems. So each engine drives two 250 kVA starter generators, backed by another two 225 kVA generators on the APU. That's nearly 1.5 MW of electrical generating capacity onboard. And the redundancy runs deep enough that the aircraft is designed to maintain safe flight and landing even after losing five of its six generator channels. That is what fly by wire really means, the pilot moves the controls, but an entire airborne computing and power system sits between that movement and the wing. Source, Igede Widhiyasa
0:41

This is what the avionics bay of a fly-by-wire Boeing 787 Dreamliner looks like, hidden underneath the floor where passengers sit. Its computing architecture includes 16 general processing modules and 21 remote data concentrators spread throughout the aircraft. When the pilot or co-pilot makes a control input, there is no conventional mechanical linkage to the primary flight surfaces. The input is sensed electronically, processed through redundant flight control computers and networks, then sent to the actuators that move the required surfaces all within milliseconds. The B787 also replaced traditional bleed air systems for engine starting, cabin pressurisation and wing anti-icing with electrically powered systems. So each engine drives two 250 kVA starter generators, backed by another two 225 kVA generators on the APU. That's nearly 1.5 MW of electrical generating capacity onboard. And the redundancy runs deep enough that the aircraft is designed to maintain safe flight and landing even after losing five of its six generator channels. That is what fly by wire really means, the pilot moves the controls, but an entire airborne computing and power system sits between that movement and the wing. Source, Igede Widhiyasa

Ammanichanda

191,766 views • 28 days ago

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

164,931 views • 10 months ago

A flying robot that moves like a snake in the air. 🐍🤖 This multi-jointed aerial robot can bend its body mid-flight and grasp objects with precision. A new generation of drones is going beyond flying they’re learning how to interact with the world. 🎥 Media: JSK Lab at The University of Tokyo ⚠️ This content is shared for informational purposes only. CTO Robotics Media is a media platform and does not own or develop the technology shown. Credit belongs to the original creators. #Robotics #Engineering #Drone #AI
0:38

A flying robot that moves like a snake in the air. 🐍🤖 This multi-jointed aerial robot can bend its body mid-flight and grasp objects with precision. A new generation of drones is going beyond flying they’re learning how to interact with the world. 🎥 Media: JSK Lab at The University of Tokyo ⚠️ This content is shared for informational purposes only. CTO Robotics Media is a media platform and does not own or develop the technology shown. Credit belongs to the original creators. #Robotics #Engineering #Drone #AI

CTO ROBOTICS Media

197,980 views • 2 months ago

Energy efficient morphing drones inspired by birds. A new control system for avian-inspired drones developed at EPFL is taking adaptive flight to the next level. Designed with morphing wings and tails, these drones offer exceptional agility and energy efficiency, mimicking the dynamics of bird flight. The system leverages all available actuators to maintain stability—even in turbulent air or with partial system failures—making it incredibly resilient. Using in-flight optimization, the drones improve energy efficiency by up to 11.5% at speeds of 8, 10, and 12 m/s. This tech could reshape autonomous drone operations, from navigating diverse wind conditions to maximizing energy conservation.
1:04

Energy efficient morphing drones inspired by birds. A new control system for avian-inspired drones developed at EPFL is taking adaptive flight to the next level. Designed with morphing wings and tails, these drones offer exceptional agility and energy efficiency, mimicking the dynamics of bird flight. The system leverages all available actuators to maintain stability—even in turbulent air or with partial system failures—making it incredibly resilient. Using in-flight optimization, the drones improve energy efficiency by up to 11.5% at speeds of 8, 10, and 12 m/s. This tech could reshape autonomous drone operations, from navigating diverse wind conditions to maximizing energy conservation.

Circuit

25,738 views • 1 year ago

166,000 neurons from a dead fruit fly now pilot a robot that drives and flies. It's the wildest piece of engineering on the internet right now, and the pilot has been dead the whole time. The robot rolls across a bedroom floor like a toy until the wheels stop being wheels: 4 propellers inside the rims spin up, and it lifts off, hangs at desk height, turns and lands. The body came out of a cardboard box of drone parts, and the brain it copies is smaller than a poppy seed and was never designed by a human. Janelia and Google spent years turning 1 male fruit fly into a spreadsheet, with every neuron and up to 125M synapses labeled, and on September 3 they posted it free for anyone to download. To build it, the fly was cut into thousands of layers and traced cell by cell under an electron microscope. Camera frames get turned into what a fly's eyes would see. The spikes run through the real wiring, where each neuron is 1 equation that rests at -52 mV and fires at -45. When something rushes at the lens, LPLC2 and LC4 light up, the same cells a fly uses to dodge your swatter, while DNg02 at the far end sets climb and turn. Inside the brain there's no flight code, no PID loop and no line that says "avoid the bed." Tesla's self-driving learned from billions of miles of driving, and this pilot learned from 400 million years of flies that didn't get swatted. A real fly walks on 6 legs and flies on 2 wings, and this one got 4 wheels and 4 propellers. The fly is dead, the brain is a file, and the file just took off.
0:27

166,000 neurons from a dead fruit fly now pilot a robot that drives and flies. It's the wildest piece of engineering on the internet right now, and the pilot has been dead the whole time. The robot rolls across a bedroom floor like a toy until the wheels stop being wheels: 4 propellers inside the rims spin up, and it lifts off, hangs at desk height, turns and lands. The body came out of a cardboard box of drone parts, and the brain it copies is smaller than a poppy seed and was never designed by a human. Janelia and Google spent years turning 1 male fruit fly into a spreadsheet, with every neuron and up to 125M synapses labeled, and on September 3 they posted it free for anyone to download. To build it, the fly was cut into thousands of layers and traced cell by cell under an electron microscope. Camera frames get turned into what a fly's eyes would see. The spikes run through the real wiring, where each neuron is 1 equation that rests at -52 mV and fires at -45. When something rushes at the lens, LPLC2 and LC4 light up, the same cells a fly uses to dodge your swatter, while DNg02 at the far end sets climb and turn. Inside the brain there's no flight code, no PID loop and no line that says "avoid the bed." Tesla's self-driving learned from billions of miles of driving, and this pilot learned from 400 million years of flies that didn't get swatted. A real fly walks on 6 legs and flies on 2 wings, and this one got 4 wheels and 4 propellers. The fly is dead, the brain is a file, and the file just took off.

Spike 1%

54,969 views • 5 days ago

An ultra compact, high precision industrial robot arm. This one stood out to me because it targets a part of automation that is usually glossed over. Extreme precision in very small spaces. According to Oleksandr Stepanenko, the arm is designed from the ground up with fully custom electronics, software, and calibration, paired with industrial components from Harmonic Drive and maxon. Reported specs are notable: • Repeatability better than 0.001 mm • Payload 250 g • Reach 250 mm • Total mass 1.5 kg This kind of form factor opens up use cases that traditional industrial arms struggle with. Think PCB assembly, micro soldering, precision pick and place of irregular parts, and medical or micro robotics components. ❗️What I find interesting is not just the numbers, but the direction… Smaller, lighter, highly precise systems could unlock automation in environments where space, inertia, and tolerance are the real constraints. Credit to Oleksandr Stepanenko for the original work and post. —- Weekly robotics and AI insights. Subscribe free:
0:43

An ultra compact, high precision industrial robot arm. This one stood out to me because it targets a part of automation that is usually glossed over. Extreme precision in very small spaces. According to Oleksandr Stepanenko, the arm is designed from the ground up with fully custom electronics, software, and calibration, paired with industrial components from Harmonic Drive and maxon. Reported specs are notable: • Repeatability better than 0.001 mm • Payload 250 g • Reach 250 mm • Total mass 1.5 kg This kind of form factor opens up use cases that traditional industrial arms struggle with. Think PCB assembly, micro soldering, precision pick and place of irregular parts, and medical or micro robotics components. ❗️What I find interesting is not just the numbers, but the direction… Smaller, lighter, highly precise systems could unlock automation in environments where space, inertia, and tolerance are the real constraints. Credit to Oleksandr Stepanenko for the original work and post. —- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

74,345 views • 9 months ago

🇺🇸 The MQ-9 Reaper is a large military drone. Its body is made from special lightweight materials that are still very strong. The landing gear uses tough titanium parts so it can handle landings better. At the front is a small sensor called the Angle of Attack sensor. It tells the drone how the air is moving around it so the drone can fly smoothly and stay stable. Right behind that are the GPS units for navigation and the batteries that supply power. Further back is the Lynx SAR radar. Normal cameras need light to see, but this radar does not. It sends out radio waves downward. When those waves hit something on the ground like a vehicle or a building, they bounce back. Source: AI Telly
2:22

🇺🇸 The MQ-9 Reaper is a large military drone. Its body is made from special lightweight materials that are still very strong. The landing gear uses tough titanium parts so it can handle landings better. At the front is a small sensor called the Angle of Attack sensor. It tells the drone how the air is moving around it so the drone can fly smoothly and stay stable. Right behind that are the GPS units for navigation and the batteries that supply power. Further back is the Lynx SAR radar. Normal cameras need light to see, but this radar does not. It sends out radio waves downward. When those waves hit something on the ground like a vehicle or a building, they bounce back. Source: AI Telly

Mario Nawfal

175,715 views • 5 months ago

The world's smallest industrial robot arm Built for sub-micrometer precision. Here’s a behind-the-scenes look at how to control what is likely the world’s smallest and most precise industrial robot arm using custom software. The stack includes online and offline programming with simulation, an analytical kinematics solver, a singularity-aware trajectory planner, and an API layer for integration with external systems. It’s designed for applications where positioning error is measured in micrometers, not millimeters. Microelectronics, semiconductor handling, photonics alignment, medical device assembly, lab automation. When parts are tiny and tolerances are unforgiving, the control architecture matters as much as the mechanics. This is from Oleksander Stepanenko (Oleksandr Stepanenko), if you don’t follow him and his YouTube channel… no one can help you. ——- Weekly robotics and AI insights. Subscribe free:
0:28

The world's smallest industrial robot arm Built for sub-micrometer precision. Here’s a behind-the-scenes look at how to control what is likely the world’s smallest and most precise industrial robot arm using custom software. The stack includes online and offline programming with simulation, an analytical kinematics solver, a singularity-aware trajectory planner, and an API layer for integration with external systems. It’s designed for applications where positioning error is measured in micrometers, not millimeters. Microelectronics, semiconductor handling, photonics alignment, medical device assembly, lab automation. When parts are tiny and tolerances are unforgiving, the control architecture matters as much as the mechanics. This is from Oleksander Stepanenko (Oleksandr Stepanenko), if you don’t follow him and his YouTube channel… no one can help you. ——- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

60,285 views • 6 months ago

THIS GUY JUST BUILT A DRONE THAT TRACKS TARGETS WITH A LASER USING CLAUDE > No robotics team > No engineering degree > No budget He used Claude Code to write the entire system in Python - a drone that locks onto a target, follows it with a laser and corrects its own aim automatically after every attempt. The AI gets more accurate the longer it runs because it learns from every single shot. He's still improving it and this is only the beginning. You have the same tool he used. The article below is about how to actually use it to its full potential.
0:39

THIS GUY JUST BUILT A DRONE THAT TRACKS TARGETS WITH A LASER USING CLAUDE > No robotics team > No engineering degree > No budget He used Claude Code to write the entire system in Python - a drone that locks onto a target, follows it with a laser and corrects its own aim automatically after every attempt. The AI gets more accurate the longer it runs because it learns from every single shot. He's still improving it and this is only the beginning. You have the same tool he used. The article below is about how to actually use it to its full potential.

Anatoli Kopadze

276,199 views • 4 months ago

THIS GUY BUILT REAL FLYING SWORD DRONES AND CONTROLS THEM WITH HAND GESTURES fan shisan is a physics student in chengdu who coded and built flying drones shaped like actual swords he controls them entirely with hand gestures. no controller or a phone. just his hands wave your hand and the sword follows. point and it flies where you direct it. multiple swords in the air at the same time responding to different gestures he built the gesture recognition system HIMSELF and coded the flight control algorithms. designed the drone hardware in the shape of swords. the gesture tracking uses sensors that read the position and movement of his hands in real time and translate them into flight commands for each drone independently he even built one large enough to ride on a physics student with coding skills just brought something straight out of a kung fu movie into the real world the line between science fiction and side projects is getting thinner every month
0:23

THIS GUY BUILT REAL FLYING SWORD DRONES AND CONTROLS THEM WITH HAND GESTURES fan shisan is a physics student in chengdu who coded and built flying drones shaped like actual swords he controls them entirely with hand gestures. no controller or a phone. just his hands wave your hand and the sword follows. point and it flies where you direct it. multiple swords in the air at the same time responding to different gestures he built the gesture recognition system HIMSELF and coded the flight control algorithms. designed the drone hardware in the shape of swords. the gesture tracking uses sensors that read the position and movement of his hands in real time and translate them into flight commands for each drone independently he even built one large enough to ride on a physics student with coding skills just brought something straight out of a kung fu movie into the real world the line between science fiction and side projects is getting thinner every month

Om Patel

308,000 views • 4 months ago

Odyssey is now previewing Odyssey-3, a world model that it calls a Physics Agent! The model was designed to learn how the world behaves from visual observation and then apply that understanding to control both real and simulated systems. Odyssey-3 can run across different machines and games, with a small amount of task-specific experience teaching it each set of controls. The preview covers humanoids, robot arms, a car and a drone being controlled by an AI model, playable video games, and training runs for other AI agents.
0:30

Odyssey is now previewing Odyssey-3, a world model that it calls a Physics Agent! The model was designed to learn how the world behaves from visual observation and then apply that understanding to control both real and simulated systems. Odyssey-3 can run across different machines and games, with a small amount of task-specific experience teaching it each set of controls. The preview covers humanoids, robot arms, a car and a drone being controlled by an AI model, playable video games, and training runs for other AI agents.

🚨 AI News | TestingCatalog

23,779 views • 8 days ago

I GAVE A DRONE THE BRAIN OF A FRUIT FLY Not a toy network with a handful of fake neurons. The actual wiring diagram of a real fly. 166,700 neurons, 25.6 million connections, mapped one synapse at a time. I call it FlyDrones. The drone's camera becomes the fly's eyes. Motion lights up the same neurons a real fly uses to see. Spikes race through the connectome down to the neurons that drive the wings. Those spikes become throttle and yaw. The brain has zero lines of flight code, just wiring. Swing a fly swatter at it. If the giant fiber (the fly's escape neuron) fires in time, the drone dodges. Open palm, fist, rush at the camera and it reacts like a fly. Built for Tello, Crazyflie, ArduPilot/PX4 and Betaflight quads via ESP32. Code is MIT, powered by Claude. Fork it and give your drone a brain.
0:27

I GAVE A DRONE THE BRAIN OF A FRUIT FLY Not a toy network with a handful of fake neurons. The actual wiring diagram of a real fly. 166,700 neurons, 25.6 million connections, mapped one synapse at a time. I call it FlyDrones. The drone's camera becomes the fly's eyes. Motion lights up the same neurons a real fly uses to see. Spikes race through the connectome down to the neurons that drive the wings. Those spikes become throttle and yaw. The brain has zero lines of flight code, just wiring. Swing a fly swatter at it. If the giant fiber (the fly's escape neuron) fires in time, the drone dodges. Open palm, fist, rush at the camera and it reacts like a fly. Built for Tello, Crazyflie, ArduPilot/PX4 and Betaflight quads via ESP32. Code is MIT, powered by Claude. Fork it and give your drone a brain.

Spike 1%

14,678 views • 7 days ago

Ever seen a robot print metal instead of welding it? Robotic 3D printing builds parts layer by layer straight from a digital design. No molds, no tools... just speed, precision, and flexibility. - Perfect for small-batch production - Handles complex geometries that traditional methods struggle with - Already in use across aerospace, automotive, marine, and energy How far metal additive manufacturing with robots has come... crazy! Would you trust a robot-printed metal part in a jet engine or car? —- Weekly robotics and AI insights. Subscribe free:
0:54

Ever seen a robot print metal instead of welding it? Robotic 3D printing builds parts layer by layer straight from a digital design. No molds, no tools... just speed, precision, and flexibility. - Perfect for small-batch production - Handles complex geometries that traditional methods struggle with - Already in use across aerospace, automotive, marine, and energy How far metal additive manufacturing with robots has come... crazy! Would you trust a robot-printed metal part in a jet engine or car? —- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

96,577 views • 9 months ago

A lightweight arm doing heavier work than you would expect. This one weighs 9.2 kg and can lift up to 12 kg. That already tells you a lot about the mechanical design and power density. A few details that stood out to me: • Controlled via a PlayStation joystick, simple and practical • Designed to operate in rain and dust • Clearly aimed at mobile robots and outdoor use, not just clean factory floors This kind of arm makes sense when space, weight, and deployment flexibility matter more than raw reach or speed. Not flashy. Just very usable. Credit to Duatic for the build. —- Weekly robotics and AI insights. Subscribe free:
0:29

A lightweight arm doing heavier work than you would expect. This one weighs 9.2 kg and can lift up to 12 kg. That already tells you a lot about the mechanical design and power density. A few details that stood out to me: • Controlled via a PlayStation joystick, simple and practical • Designed to operate in rain and dust • Clearly aimed at mobile robots and outdoor use, not just clean factory floors This kind of arm makes sense when space, weight, and deployment flexibility matter more than raw reach or speed. Not flashy. Just very usable. Credit to Duatic for the build. —- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

25,726 views • 9 months ago