A group of developers called [OpenWorm] have mapped the 302 neurons of the Caenorhabditis elegans species of roundworm and created a virtual neural network that can be used to solve all the types of problems a worm might encounter. Which, when you think about it, aren’t much different from those a floor-crawling robots would be confronted with.
In a demo video released by one of the projects founders, [Timothy Busbice], their network is used to control a small Lego-rover equipped with a forward sonar sensor. The robot is able to stop before it hits a wall and determine an appropriate response, which may be to stop, back up, or turn. This is all pretty fantastic when you compare these 302 neural connections to any code you’ve ever written to accomplish the same task! It might be a much more complex route to the same outcome, but its uniquely organic… which makes watching the little Lego-bot fascinating; its stumbling around even looks more like thinking than executing.
I feel obligated to bring up the implications of this project. Since we’re all thinking about it now, let’s all imagine the human brain similarly mapped and able to simulate complex thought processes. If we can pull this off one day, not only will we learn a lot more about how our squishy grey hard drives process information, artificial intelligence will also improve by leaps and bounds. An effort to do this is already in effect, called the connectome project, however since there are a few more connections to map than with the c. elegans’ brain, it’s a feat that is still underway.
The project is called “open”worm, which of course means you can download the code from their website and potentially dabble in neuro-robotics yourself. If you do, we want to hear about your wormy brain bot.
Continue reading “Gift Your Next Robot With the Brain of a Roundworm”
Somewhere down the road, you’ll find that your almighty autonomous robot chassis is going to need some sensor feedback. Otherwise, that next small step down the road may end with a blind leap off the coffee table. The first low-cost sensors we might throw at this problem would be sonars or IR rangefinders, but there’s a problem: those sensors only really provide distance data back from the pinpoint view directly ahead of them.
Rest assured, [Jonathan] wrote in to let us know that he’s got you covered. Combining a line laser, camera, and an FPGA, he’s able to detect obstacles that fall within the field of view of the camera and laser.
If you thought writing algorithms in software is tricky, wait till to you try hardware! (We know: division sucks!) [Jonathan] knows no fear though; he’s performing gradient computation on the FPGA directly to detect the laser in the camera image at a wicked 30 frames-per-second. Why roll up your sleeves and take the hardware route, you might ask? If we took a CPU-based approach at the tiny embedded-robot scale, Jonathan estimates a mere 10 frames-per-second. With an FPGA, we’re able to process images about as fast as they’re received.
Jonathan is using the Logi Board, a Kickstarter success we’ve visited in the past, and all of his code is up on the Githubs. If you crack it open, you’ll also find that many of his modules are Wishbone compliant, so developing your own projects with just some of these parts has been made much easier than trying to rip out useful features from a sea of hairy logic.
With computer-vision hardware keeping such a low profile in the hobbyist community, we’re excited to hear more about [Jonathan’s] FPGA-based robotics endeavors.
Continue reading “Robot Vision: Detecting Obstacles with FPGAs and line lasers”
Most of the legged robots we see here are of the hexapod variety, and with good reason. Hexapods are very stable and can easily move even if one or more of the legs has been disabled. [Radomir] has taken this a step farther and has become somewhat of an expert on the more technically difficult quadruped robot, building smaller and smaller ones each time. He has been hard at work on his latest four-legged creation called the Pico-Kubik, and this one will fit in the palm of your hand.
The Pico-Kubik runs Micropython on a VoCore board, which allows for it to have a small software footprint to complement its small hardware footprint. It accomplishes the latter primarily through the use of HK-282A Ultra-Micro Servos, an Arduino Pro Mini, and a tiny lithium ion battery. It’s still a work in progress, but the robot can already crawl across the tabletop.
This isn’t [Radomir]’s first time at the tiny quadruped rodeo, either. He has already built the Nano-Kubik and the µKubik, all of which followed the first (aptly-named) Kubik quadruped. Based on the use of SI prefixes, we can only assume the next one will be the hella-Kubik!
[Alex] posted up build details of his robot, Halfbot, on Tinkerlog. We’ve been big fans of his work ever since his Synchronizing Fireflies Instructable way back in the day. [Alex’s] work usually combines an unconventional idea with minimalistic design and precise execution, and Halfbot is no exception.
You’ll have to watch the video (embedded below the break) to fully appreciate the way it moves. The two big front legs alternate with the small front pads to make an always-stable tripod with the caster wheel at the back. It lifts itself up, moves a bit forward, and then rests itself down on the pads again while the legs get in position for the next step. It’s not going to win any speed tournaments, but it’s a great-looking gait.
The head unit also has two degrees of freedom, allowing it to scan around with its ultrasonic rangefinder unit, and adding a bit more personality to the whole affair.
[Alex] mentions that he’d recently gotten a lathe and then a CNC mill. So it’s no surprise that he made all the parts from scratch just to give the machines a workout. We think he did a great job with the overall aesthetics, and in particular the battery pack.
We’re excited to see how [Alex] adds new behaviors as he develops the firmware. No pressure!
Continue reading “The Halfbug”
What happens when you put a telepresence robot online for the world to try out for free? Hilarity of course. Double Robotics is a company that builds telepresence robots. The particular robot in question is kind of like a miniature Segway with a tablet computer on top. The idea is you can control it with your own tablet from a remote location. This robot drives around with your face on the screen, allowing you to almost be somewhere when you can’t (or don’t want to) be there in person.
Double Robotics decided to make one of these units accessible to the Internet as a public demonstration. Of course, they couldn’t have one of these things just roaming about their facility unrestrained. They ended up keeping it locked in an office. This gives users the ability to drive it around a little bit and get a feel for the robot. Of course it didn’t take long for users to start to wonder how they could break free from their confinement.
One day, a worker left the office door cracked open ever so slightly. A user noticed this and after enough patience and determination, managed to use the robot to get the door opened. It appears as though the office was closed at the time, so no one was around to witness the event. A joy ride ensued and the robot hid its tracks by locking itself back in the room and docking to the charging station.
While this isn’t a hack in the typical sense, this is a perfect example of the hacker mindset. You are given some new technology and explore it to the extent at which you are supposed too. After that, many people would just toss it aside and not give it a second thought. Those with the hacker mindset are different, though. Our next thought is usually, “What else can I do with it?” This video demonstrates that in a fun and humorous way. Hopefully the company learns its lesson and puts a leash on that thing. Continue reading “Telepresence Robot Demo Unit Breaks Free of It’s Confinement”
The selfie: pop culture’s most frivolous form of self-expression is also probably one of the most human acts you could find yourself doing in a day. Everyone is guilty of snapping a quick pic from time to time with the expectation that it will leave an impression on those who see it. All of the implications surrounding why we do this support our deep-seated need to sculpt an identity for ourselves using others as the hammer and chisel. So, consider how upside-down the world would feel if you caught a robot posing for a shot in the mirror? What about one whose sole function was to take selfies and post them? If this breaks your mind a little, that was the intention. This #selfie robot by artists [Radamés Ajna] and [Thiago Hersan] is the first development in a larger body of work called “memememe”, which is meant to comment on our culture’s obsession with the trending, selfing nature of social media. This specific project explores the relationship between conversation and identity in a situation where there is no second party.
Hardware-wise, the #selfie bot is a Stewart platform made from six servo motors and a few pieces of carefully measured pushrod connected with swivel-ball-links. An android phone is mounted on the end effector which acts functionally as the robot’s face and eyes. To make it self-aware in a sense, [Ajna] and [Hersan] created their own recognition software with Open CV using a collection of sample images of various phones as reference points. As soon as the robot recognizes itself in the mirror as indicated by specific words flashing on its screen, it takes a picture, immediately uploading it to its own tumblr account. [Ajna] and [Hersan] have a nice description of their process on the project’s Instructable’s page which you can check out to see how they used Haar Cascades to create their custom object recognition. Additionally, if you’d fancy building your own robot to covertly place in your living room to snap pictures of other phones, you could check out their code on github.
Watch it selfie :
Continue reading “Nothing’s as Vain as a Phone Taking a Selfie of Itself… with Itself”
When robots take over the earth, it will be important that they maneuver across various types of terrain quickly and effectively. Bipedal motion is a tricky feat to accomplish for machines, so [Carter Hurd] decided, why not invent a better wheel? Even wheels can be improved, right?
Making excellent use of the prototyping capabilities of a 3D printer, [Carter] designed a set of bulb-shaped mechanisms which act effectively to drive themselves around on a smooth surface. The bulb is split radially into a series of wedge slices which can articulate outward, transforming the robot into something of a spiky razor-beast, able to tear through piles of fall leaves or wakes of loose sand. In order to unfurl itself however, the shaft driving the central mounting plate of the wedges has to fight the robot’s own weight. To solves this, [Carter] modified his design so that the rest of the wedges would unfold around the one supporting the load, the wheels would then rotate to shift the weight, allowing the last piece to extend.
[Carter] shows a proof of concept from earlier this year, explaining his hinge design which stretches a tendon-like connector in order to tension the wedges in one state or the other. Since then it looks like his transforming wheel has evolved a bit. You can get a better view of his robot in action here :
Continue reading “Reinventing the Wheel Makes for a Better Wheel…”