A self-balancing robot isn’t a new idea, but we liked the aesthetics of [Maker ATOM’s] build. The use of a breadboard and a printed bracket looks good, as you can see in the video, below.
Like most first-time projects, though, there were some lessons learned. The power supply needs a little work and the range of balance compliance didn’t meet expectations. But those problems are soluble and, as usual, you often learn more from working through issues like these.
While a line-following robot may not be the newest project idea in the book, this one from [Edison Science] is a clean build using modern components and gets a good speed thanks to PID control feedback instead of the more traditional bang-bang control you see in low-end robots.
Of course, PIDs need tuning and that seems to be the weak link — you’ll have to experiment with the settings. The sensors also require calibration, but we bet both of those issues could be fixed pretty easily.
With modern voice assistants we can tell a computer to play our favorite music, check the weather, or turn on a light. Like many of us, [nerdaxic] gave in to the convenience and perceived simplicity of various home automation products made by Google and Amazon. Also like many of us, he found it a bit difficult to accept the privacy implications that surround such cloud connected devices. But after selling his Home and Echo, [nerdaxic] missed the ability to control his smart home by voice command. Instead of giving in and buying back into the closed ecosystems he’d left behind, [nerdaxic] decided to open his home to a murderous, passive aggressive, sarcastic, slightly insane AI: GLaDOS, which you can see in action after the break.
Using open source designs from fellow YouTube creator [Mr. Volt], [nerdaxic] 3d printed as much of the GLaDOS animatronic model as he was able to, and implemented much of the same hardware to make it work. [nerdaxic] put more Open Source Software to use and has created a functional but somewhat limited home AI that can manage his home automation, give the weather, and tell jokes among other things. GLaDOS doesn’t fail to deliver some great one liners inspired by the original Portal games while heeding [nerdaxic]’s commands, either.
A ReSpeaker from Seeed Studio cleans up the audio sent to a Raspberry Pi 4, and allows for future expansion that will allow GLaDOS to look in the direction of the person speaking to it. With its IR capable camera, another enhancement will allow GlaDOS to stare at people as they walk around. That’s not creepy at all, right? [nerdaxic] also plans to bring speech-to-text processing in-house instead of the Google Cloud Speech-To-Text API used in its current iteration, and he’s made everything available on GitHub so that you too can have a villainous AI hanging on your every word.
Of course if having GLaDOS looming isn’t enough, you could always build a functional life size Portal turret or listen to the radio on your very own Portal Radio.
Continue reading “GLaDOS Voice Assistant Passive-Aggressively Automates Home”
You know how it goes, you’re just hanging out in the yard, there aren’t enough hours in the day, and weeding the lawn is just such a drag. Then an idea just pops into your head. How about we attach a gas powered flamethrower to a robot arm, drive it around on a tank-tracked robotic base, and have it operate autonomously with an AI brain? Yes, that sounds like a good idea. Let’s do that. And so, [Dave Niewinski] did exactly that with his Ultimate Weed Killing Robot.
And you thought the robot overlords might take a more subtle approach and take over the world one coffee machine at a time? No, straight for the fully-autonomous flamethrower it is then.
This build uses a Kinova Robots Gen 3 six-axis arm, mounted to an Agile-X Robotics Bunker base. Control is via a Connect Tech Rudi-NX box which contains an Nvidia Jetson Xavier NX Edge AI computing engine. Wow that was a mouthful!
Connectivity from the controller to the base is via CAN bus, but, sadly no mention of how the robot arm controller is hooked up. At least this particular model sports an effector mount camera system, which can feed straight into the Jetson, simplifying the build somewhat.
To start the software side of things, [Dave] took a video using his mobile phone while walking his lawn. Next he used RoboFlow to highlight image stills containing weeds, which were in turn used to help train a vision AI system. The actual AI training was written in Python using Google Collaboratory, which is itself based on the awesome Jupyter Notebook (see also Jupyter Lab on the main site. If you haven’t tried that yet, and if you do any data science at all, you’ll kick yourself for not doing so!) Collaboratory would not be all that useful for this by itself, except that it gives you direct, free GPU access, via the cloud, so you can use it for AI workloads without needing fancy (and currently hard to get) GPU hardware on your desk.
Details of the hardware may be a little sparse, but at least the software required can be found on the WeedBot GitHub. It’s not like most of us will have this exact hardware lying around anyway. For a more complete description of this terrifying contraption, checkout the video after the break.
Continue reading “Don’t Sleep On The Lawn, There’s An AI-Powered, Flamethrower-Wielding Robot About”
Wheels might be the simplest method of locomotion for robots, but walkers are infinitely more satisfying to watch. This is certainly the case for [Chen Liang’s] tiny Strider walker controlled by a ESP32 camera board.
The Strider mechanism might look similar to Strandbeest walkers, but it lifts its feet higher, allowing it to traverse rougher terrain. [Chen]’s little 3D printed version is driven by a pair of geared N20 motors, with three legs on each side. The ESP32 camera board allows for control and an FPV video feed using WiFi, with power coming from a 14500 LiFePO4 battery. The width required by the motors, leg mechanisms, and bearings means the robot is quite wide, to the point that it could get stuck on something that’s outside the camera’s field of view. [Chen] is working to make it narrower by using continuous rotation servos and a wire drive shaft.
We’ve seen no shortage or riffs on the many-legged walkers, like the TrotBot and Strider mechanism developed by [Wade] and [Ben Vagle], and their website is an excellent resource for prospective builders.
The hacker spirit is always alive and well in post-apocalyptic fiction, as characters throw together contraptions from whatever junk they can find. While these might not always be practical or possible in reality, their primary purpose is usually to look the part. This is definitely the case for [Danny Huynh]’s post-apocalyptic animatronic creations, which look like they can slot straight into Mad Max or Fallout.
[Danny] is an avid RC enthusiast, so many of the models are highly customized off-the-shelf RC cars. However, it’s the lifelike moving characters in these models that really catch the eye. Their hands and feet move with the steering and throttle, and in the motorcycle builds they will often lean with the turns. Other notable builds include a hexapedal taxi and a couple of animatronic bands.
All the vehicle builds are electric, but it looks like [Danny] often includes an audio module to simulate a roaring engine. He makes extensive use of servos and linkages for character movement, with wiring and electronics carefully hidden by paint or bodywork.
With all the CGI technology available today, great animatronic builds like an eerily lifelike heart, or a talking Nikola Tesla are all the more impressive to see.
Continue reading “Small Scale Mad Max: Danny Huynh’s Dystopian Animatronics”
One of the major challenges of animatronics is creating natural looking motion. You can build something with an actuator for every possible degree of freedom, but it will still be disappointing if you are unable to control it to smoothly play the part. [Mr. Volt] has developed a passion for animatronic projects, but found programming them tedious, and manual control with keyboard or controller difficult to do right. As an alternative, he is building Waldo, an electronic puppetry controller.
The Waldo rig is being developed in conjunction with [Mr. Volt]’s build of Wheatley, the talkative ball-shaped robot from the Portal 2 game. The puppetry rig consists of a series of rings for [Mr Volt]’s hand, with the position of each being read by angle sensors. This allows him to control Wheatley’s orientation of the body and eyeball, eyelids, and handles. Wheatley and Waldo both still need a few refinements, but we look forward to seeing the finished project in action.
The Portal games have inspired several featured projects, including GLaDOS, the turrets, and of course more Wheatly builds.
Continue reading “Animatronic Puppetry Controller Skips Joystick Or Keyboard”
