MIT’s Hair-Brushing Robot Untangles Difficult Robotics Problem

Whether you care to admit it or not, hair is important to self-image, and not being able to deal with it yourself feels like a real loss of independence. To help people with limited mobility, researchers at MIT CSAIL have created a hair-brushing robot that combines a camera with force feedback and closed-loop control to adjust to any hair type from straight to curly on the fly. They achieved this by examining hair as double helices of soft fibers and developed a mathematical model to untangle them much like a human would — by working from the bottom up.

It may look like a hairbrush strapped to a robot arm, but there’s more to it than that. Before it ever starts brushing, the robot’s camera takes a picture that gets cropped down to a rectangle of pure hair data. This image is converted to grayscale, and then the program analyzes the x/y image gradients. The straighter the hair, the more edges it has in the x-direction, whereas curly hair is more evenly distributed. Finally, the program computes the ratio of straightness to curliness, and uses this number to set the pain threshold.

The brush is equipped with sensors that measure the forces being exerted on the hair and scalp as it’s being brushed, and compares this input to a baseline established by a human who used it to brush their own hair. We think it would be awesome if the robot could grasp the section of hair first so the person can’t feel the pull against their scalp, and start by brushing out the ends before brushing from the scalp down, but we admit that would be asking a lot. Maybe they could get it to respond to exclamations like ‘ow’ and ‘ouch’. Human trials are still in the works. For now, watch it gently brush out various wigs after the break.

Even though we have wavy hair that tangles quite easily, we would probably let this robot brush our hair. But this haircut robot? We’re not that brave.

Continue reading “MIT’s Hair-Brushing Robot Untangles Difficult Robotics Problem”

Building A Robotic Band To Make Up For Lack Of Practice

Learning to play a musical instrument well requires a significant time investment. [Ivan Miranda] had dreamt of doing this but made peace with the fact that his talents and motivation lay in building machines. However, he has decided to play to his strengths and is building a robotic band. See the videos after the break.

So far he has mechanized a hi-hat, snare drum, and a very basic guitar. The guitar is nothing more than a single string stretched across an aluminum frame, with an electronic pickup. Most of the work has gone into the solenoid-driven picking mechanism. He wanted to avoid picking the string when the solenoid is turned of, so he created a simple little mechanism that only comes in contact with the string when it’s moving in one direction. A bistable solenoid might be a simpler option here.

For the high hat, [Ivan] built a custom stand with two bistable solenoids to lift and drop the top cymbal. A solenoid-driven drumstick was also added. The snare drum uses a similar mechanism, but with a larger solenoid. So far he hasn’t really worked on a control system, focusing mainly on electronics.

[Ivan] points out several times that he has knows very little about making music, but we do enjoy watching him explore and experiment with this new world. Usually, his projects involve a lot more 3D printing, like when he built a giant nerf bazooka or a massive 3D printed tank. Continue reading “Building A Robotic Band To Make Up For Lack Of Practice”

Prioritising Mechanical Multiplexer

When automating almost any moderately complex mechanical task, the actuators and drive electronics can get expensive quickly. Rather than using an actuator for every motion, mechanical multiplexing might be an option. [James Bruton] has considered using it in some of his many robotics projects, so he built a prioritizing mechanical multiplexer to demonstrate the concept.

The basic idea is to have a single actuator and dynamically switch between different outputs. For his demonstration, [James] used a motor mounted on a moving platform actuated by a lead screw that can engage a number of different output gears. Each output turns a dial, and the goal is to match the position of the dial to the position of a potentiometer. The “prioritizing” part comes in where a number of outputs need to be adjusted, and the system must choose which to do first. This quickly turns into a task scheduling problem, since there are a number of factors that can be used to determine the priority. See the video after the break to see different algorithms in action.

Instead of moving the actuator, all the outputs can connect to a single main shaft via clutches as required. Possible use cases for mechanical multiplexers include dispensing machines and production line automation. Apparently, the Armatron robotic arm sold by Radioshack in the ’80s used a similar system, controlling all its functions with a single motor.

[James] knows or two about robotics, having built many of them over the last few years. Just take a look at OpenDog and his Start Wars robots. Continue reading “Prioritising Mechanical Multiplexer”

Robotic Gripper From A Squishy Ball

Soft robotic grippers have some interesting use cases, but the industrial options are not cheap. [James Bruton] was fascinated by the $4000 “bean bag” gripper from Empire Robotics, so he decided to build his own.

The gripper is just a flexible rubber membrane filled with small beads. When it is pushed over a object and the air is sucked out, it holds all the beads together, molded to the shape of the object. For his version [James] used a soft rubber ball filled with BBs. To create a vacuum, he connected a large 200cc syringe to the ball via a hose, and actuated it with a high torque servo.

It worked well for small, light objects but failed on heavier, smooth objects with no edges to grip onto. This could possibly be improved if the size and weight of the beads/BBs are reduced.

For some more soft robotics, check out this soft 3D printed hand, and the flexible electrically driven actuators. Continue reading “Robotic Gripper From A Squishy Ball”

Guitar Hero Robot Actually Shreds

Once a popular craze, most of the public has sold or stashed away their plastic video game instruments and forgotten the likes of Guitar Hero and Rockband. Having never been quite satisfied with his scores, [Nick O’Hara] set out to create a robot that could play a Guitar Hero controller. It would be easy enough to use transistors to actuate the buttons or even just a Teensy to emulate a controller and have it play the perfect game, but [Nick] wanted to replicate what it was really like to play. So after burning out a fair number of solenoids (driving them over spec) and learning on his feet, [Nick] slowly began to dial in his robot, Jon Bot Jovi.

The brains of the bot are a Raspberry Pi running some OpenCV-based code that identifies blobs of different colors. The video feed comes from a PS2 via an HDMI capture card. Solenoids are driven via an 8 channel driver board, controlled by the Pi. While it missed a few notes here and there, we loved seeing the strumming solenoid whammy rapidly on the strummer. All in all, it’s a great project, and we love the design of the robot. Whether played by a robot, turned into a synthesizer, or recreated from toy pianos and mechanical keyboards, Guitar Hero controllers offer many hacking opportunities.

Continue reading “Guitar Hero Robot Actually Shreds”

Apple-Picking Robot Stems From Labor Shortage

Among all the job-related problems wrought by the pandemic, here is another one that comes as the result of people generally staying home: there are hardly any backpackers to do traditional transient backpacker jobs like picking apples. Researchers at Monash University’s Department of Mechanical and Aerospace engineering found a way to fill in the gap by building a pneumatic robot arm that can harvest an apple every seven seconds at top speed.

A suite of cameras and algorithms look for fruit amongst the foliage and carefully remove it by gripping it gently and twisting, much like a human would. In order to do this, the robot must consider the shape of the fruit, the way it’s hanging, and where to separate it from the tree while keeping damage to a minimum. A suction system helps pull the apple into the soft, four-fingered grip and then the arm twists and turns to deposit the apple into the bin.

There are a lot of upsides to this robot, including the fact that it works in any lighting and weather conditions and can ID an apple in less than 200 milliseconds. The only problem is that this operation results in the occasional missing stem — a cosmetic problem that sounds nit-picky, but would definitely prevent some stores from buying the fruit. Well, that, and there only seems to be one of these robots so far.

There are two videos after the break — a short one that gives you the gist, and a much longer one that offers a view of the suction cup, which emerges from the middle of the fingers like a xenomorph’s little mouth.

Some readers may be wondering why apples are still picked individually when shaking harvesters exists. “Shake-and-catch” tends to bruise apples, making them undesirable for produce sellers, however, apples destined for juicing have no issue with being handled roughly by the harvesters as shown in this fascinating harvest video. Robot grippers are gentle and we’ve seen all shapes and sizes that are suited to a particular need. When the needs are more general, rollers or squishy spheres might be the answer.

Continue reading “Apple-Picking Robot Stems From Labor Shortage”

Disney Imagineering’s “Project Kiwi” Bears Groot

Some days, we might be forgiven for believing Boston Dynamics has cornered the market on walking robots. They (and other players) are making incredible progress in their field, but three years ago Disney, trying to create autonomous, free-walking robotic actors for some of their more diminutive film characters, found none of the existing platforms were appropriate. So they set their Imagineering department to work on “Project Kiwi”, and we are now seeing the fruits of those efforts.

Research on bipedal robots has amassed over the years, and as the saying goes, if these Imagineers saw further it was by standing on the shoulders of larger robotic platforms. However, the Project Kiwi designers have made a laundry list of innovations in their process of miniaturization, from the “marrow conduit” cooling system which forces air through hollow bones, to gearing that allows actuators to share motors even across joints. The electronics are distributed around the skeleton on individual PCBs with ribbon flex cables to reduce wiring, and almost every component is custom fabricated to meet the complex size and weight requirements.

Even in this early prototype, Disney’s roots in life-like animatronics are evident. Groot’s movements are emotive, if a bit careful, and software can express a variety of personalities through his gaits and postures. The eyes and face are as expressive as we’ve come to expect (though a keen eye for seams puts off some definite Westworld vibes). Reportedly, this version can handle gentle shoves and contact, but we do spot a safety cable still attached to the head. So there’s probably some way to go before we’ll see this interacting with the general public in a park.

Disney’s Imagineering department has been doing some amazing work with robotics and they continue to make significant innovations in the more traditional fields of animatronics. It certainly looks like one of the coolest places to work right now, and now we’re itching to build our own bipedal friends to play with.

Continue reading “Disney Imagineering’s “Project Kiwi” Bears Groot”