What is it that compels us about a secret door? It’s almost as if the door itself and the promise of mystery is more exciting than whatever could lay beyond. In any case, [Scott Monaghan] is a lover of the form, and built his own secret door hidden in a bookshelf, as all good secret doors should be.
The door is activated by pulling down on the correct book. This then reveals a fingerprint scanner. Upon presenting the right digit, the door will elegantly swing open to reveal the room beyond. Secret door experts will note there’s an obvious tell due to the light spilling through the cracks, however [Scott] reports that the finishing stages of the build solved this issue. The door was also fitted with a manual release for easier daily use.
Details are light, but the basics are all there. Really all you need is a cheap hardware store door opener, a secret activation lever or authentication method, and a well-hinged bookcase to achieve this feat yourself. We’ve seen some other great secret doors before, too. Video after the break.
Continue reading “Secret Bookshelf Door Uses Hidden Fingerprint Scanner”
AR and VR developer [Skarredghost] got pretty excited about a virtual blue cube, and for a very good reason. It marked a successful prototype of an augmented reality experience in which the logic underlying the cube as a virtual object was changed by AI in response to verbal direction by the user. Saying “make it blue” did indeed turn the cube blue! (After a little thinking time, of course.)
It didn’t stop there, of course, and the blue cube proof-of-concept led to a number of simple demos. The first shows off a row of cubes changing color from red to green in response to musical volume, then a bundle of cubes change size in response to microphone volume, and cubes even start moving around in space.
The program accepts spoken input from the user, converts it to text, sends it to a natural language AI model, which then creates the necessary modifications and loads it into the environment to make runtime changes in Unity. The workflow is a bit cumbersome and highlights many of the challenges involved, but it works and that’s pretty nifty.
The GitHub repository is here and a good demonstration video is embedded just under the page break. There’s also a video with a much more in-depth discussion of what’s going on and a frank exploration of the technical challenges.
If you’re interested in this direction, it seems [Skarredghost] has rounded up the relevant details. And should you have a prototype idea that isn’t necessarily AR or VR but would benefit from AI-assisted speech recognition that can run locally? This project has what you need.
Continue reading “Simple Cubes Show Off AI-Driven Runtime Changes In VR”
When science fiction authors imagined robots in the 20th century, many of them were huge imposing steel automatons. [Shane]’s designs for the Pretty Small Robot are quite contrary to that, being tiny in stature and cute in affect.
The whole robot is an exploration in nifty engineering. It uses an easy clip-together structure with fasteners and glue not required. The chassis is 3D printed, with all the components sliding into place. Two small DC gearmotors are used for differential drive, with each side of the robot having a pair of wheels wrapped in a rubber band for traction. The brains of the robot is an ESP32, providing it with both plenty of processing power and good connectivity options. Control is over WiFI via MQTT.
At this stage the robot doesn’t do a whole lot, though [Shane] has some exciting plans. He’d like to add a camera in future and let it explore a maze under human command.
If you’ve ever wanted to build a robot with an almost coin-sized foot print, this build is for you. Files are available on GitHub for those wishing to dive deeper. Video after the break.
Continue reading “Pretty Small Robot Is Capable, Nonetheless”
[Stephen Carey] had previously relied on an Insteon garage door controller, only to have it perform poorly and fail at integrating with Alexa properly. Thus, he did what any good hacker would do, and built his own system instead.
The garage door was first outfitted with a pair of reed switches to sense when it was fully open or fully closed. The drive sprocket of the garage door was also set up to be monitored with magnets and Hall effect sensors, essentially creating a rotary encoder. This allows a ESP32 to monitor the door’s direction of travel, it’s position, and when it has hit the end stop in either direction. Using Micropython, [Stephen] whipped up some code to tie the garage door controls in with Home Assistant, complete with a neat visual display of the current door position.
There are millions of home automation products out there, many of which make annoying compromises that frustrate the end user. Sometimes, doing it your own way is the only way to get satisfaction!
For those with strokes or other debilitating conditions, control over one’s eyelid can be one of the last remaining motor functions. Inspired by [Jeremiah Denton] blinking in Morse code on a televised interview, [MBW] designed an ESP32-based device to decode blinks into words.
While an ESP32 offers Bluetooth for simulating a keyboard and has a relatively low power draw, getting a proper blink detection system to run at 20 frames per second in a constrained environment is challenging. Earlier attempts used facial landmarks to try and determine, based on ratios, whether an eye was open or closed. A cascade detector combined with an XGBoost classifier offered excellent performance but struggled when the eye wasn’t centered. Ultimately a 50×50, 4-layer CNN in TensorFlow Lite processes the camera frames, producing a single output, eye open or closed. For debugging purposes, it streams camera frames over Wi-Fi with annotations via OpenCV, though getting OpenCV to compile for ESP32 was also nontrivial.
[MBW] trained the model using the MRL dataset and then quantized to int8. Getting the Bluetooth and Wi-Fi stacks to run concurrently was a bit of a pain, as was managing RAM. After exhausting SRAM and IRAM, [MBW] had to move to PRAM. The entire system is built into some lightweight goggles and makes for a fairly comfortable experience.
While TensorFlow and microcontrollers might seem like a bit of an odd couple, at the end of the day, the inference engine is just doing some math on an array of inputs with some weights. We’ve even seen TensorFlow Lite on a Commodore 64. If you don’t know about [Admiral Jerimiah Denton] we can shed some light on it for you.
Continue reading “Hackaday Prize 2023: EyeBREAK Could Be A Breakthrough”
How do you approach your robot designs? Maybe, you do it from a ‘oh, I have these cool parts’ position, or from a ‘I want to make a platform on wheels for my experiments’ perspective. In that case, consider that there’s a different side to robot building – one where you account for your robot’s influence on what other people around feel about them, and can get your creations the attention they deserve. [Jorvon ‘Odd-Jayy’ Moss]’s robots are catchy in a way that many robot designs aren’t, and they routinely go viral online. What are his secrets to success? A combination of an art background, a Bachelor of Fine Arts in illustration, and a trove of self-taught electronics skills helped him develop a standout approach to robot building.
Now, [Jorvon] has quite a few successful robot projects under his belt, and at Supercon 2022, he talks about how our robots’ looks and behaviour shapes their perception. How do your own robots look to others, and what feelings do they evoke? With [Jorvon], you will go through fundamentals of what makes a robot look lively, remarkable, catchy or creepy, and it’s his unique backgrounds that let him give you a few guidelines on what you should and should not do when building a certain kind of robot.
You’ll do good watching this video – it’s short and sweet, and shows you a different side to building robots of your dreams; plus, the robot riding around on the stage definitely makes this presentation one of a kind. No matter your robot’s technical complexity, it’s significant that it can make people go ‘wow’ when they see it. Not all robots are there to single-mindedly perform a simple task, after all – some are meant to travel around the world.
Continue reading “Supercon 2022: [Jorvon Moss] Gives His Robots A Soul”
Measuring local rainfall has real practical uses, especially in agriculture, but most of us will have to admit that it’s at least partly about drawing cool graphs on a screen. Whatever your motivation, you can build this open source electronic rain gauge designed by [Sebastian] of Smart Solutions for Home, and integrate it with Home Assistant.
This 3D printed rain gauge is of the ubiquitous tipping bucket type and uses a magnet and hall effect sensor to detect every time the bucket tips out. The sensor is soldered to a custom PCB with ESP32 configured using ESP Home. By keeping it in deep sleep most of the time and only waking up when the tip of the bucket, [Sebastian] estimates it can run about a year on four AA batteries, depending on rainfall. The hinge mechanism is adjustable to ensure that both buckets will tip with the same volume of water.
FDM 3D printed enclosures are not known for being waterproof, so [Sebastian] coated the PCB with varnish to protect it from moisture. This worked well enough that he could leave it running in a bowl of water for a few hours without any ill effects. The end result looks good and should be able to handle the outdoors for a long time.
Building a weather station is a popular DIY project. Some of the interesting varieties we’ve seen are powered by supercapacitors, show readings on antique analog dials and convert parking distance sensor kit into a wind gauge.
Continue reading “DIY 3D Printed Rain Gauge Connects To Home Assistant”