Sudo Find Me A Parking Space; Machine Learning Ends Circling The Block

If you live in a bustling city and have anyone over who drives, it can be difficult for them to find parking. Maybe you have an assigned space, but they’re resigned to circling the block with an eagle eye. With those friends in  mind, [Adam Geitgey] wrote a Python script that takes the video feed from a web cam and analyzes it frame by frame to figure out when a street parking space opens up. When the glorious moment arrives, he gets a text message via Twilio with a picture of the void.

It sounds complicated, but much of the work has already been done. Cars are a popular target for machine learning, so large data sets with cars already exist. [Adam] didn’t have to train a neural network, either–he found a pre-trained Mask R-CNN model with data for 80 common objects like people, animals, and cars.

The model gives a lot of useful info, including a bounding box for each car with pixel coordinates. Since the boxes overlap, there needs be a way to determine whether there’s really a car in the space, or just the bumpers of other cars. [Adam] used intersection over union to do this, which is conveniently available as a function of the Mask R-CNN model’s library. The function returns a score, so it was just a matter of ignoring low-scoring bounding boxes.

[Adam] purposely made the script adaptable. A few changes here and there, and you could be picking up tennis balls with a robotic collector or analyzing human migration patterns on your block in no time. Or change it up and detect all the cars that run the stop sign by your house.

Thanks for the tip, [foamyguy].

A 3D Printed Robotic Chariot For Your Phone

As we’ve said many times in the past, the wide availability of low-cost modular components has really lowered the barrier to entry for many complex projects which previously would have been nigh-on impossible for the hobbyist to tackle. The field of robotics has especially exploded over the last few years, as now even $100 can put together a robust robotics experimentation platform which a decade ago might have been the subject of a DARPA grant.

But what if you want to go even lower? What’s the cheapest and easiest way to put together something like a telepresence robot? That’s exactly what [Advance Robotics] set out to determine with their latest project, and the gadget’s final form might be somewhat surprising. Leveraging the fact that nearly everyone has a device capable of video calls in their pocket, the kit uses simple hardware and 3D printed components to produce a vehicle that can carry around a smartphone. With the phone providing the audio and video link, the robot only needs to handle rolling around in accordance with the operators commands.

The robot chassis consists of a few simple 3D printed components, including the base which holds the phone and electronics, the wheels, and the two rear “spoons” which are used to provide a low-friction way of keeping the two-wheeled device vertical. To get it rolling, two standard DC gear motors are bolted to the sides. With the low cost of printer filament and the fact that these motors can be had for as little as $2 online, it’s hard to imagine a cheaper way to get your electronics moving.

As for the electronics, [Advance Robotics] is using the Wemos D1 Mini ESP8266 development board along with L298N motor controller, another very low-cost solution. The provided source code pulls together a few open source libraries and examples to provide a simple web-based user interface which allows the operator to connect to the bot from their browser and move it around with just a few clicks of the mouse.

If you like the idea of printing a rover to explore your living room but want something a bit more advanced, we’ve seen printable robotics platforms that are sure to meet your needs, no matter what your skill level is.

Continue reading “A 3D Printed Robotic Chariot For Your Phone”

This 3D Printer Is Soft On Robots

It always seems to us that the best robots mimic things that are alive. For an example look no further than the 3D printed mesh structures from researchers at North Carolina State University. External magnetic fields make the mesh-like “robot” flex and move while floating in water. The mechanism can grab small objects and carry something as delicate as a water droplet.

The key is a viscous toothpaste-like ink made from silicone microbeads, iron carbonyl particles, and liquid silicone. The resulting paste is amenable to 3D printing before being cured in an oven. Of course, the iron is the element that makes the thing sensitive to magnetic fields. You can see several videos of it in action, below.

Continue reading “This 3D Printer Is Soft On Robots”

Automate Your Comfort Food Prep With An IoT Grilled Cheese Robot

What exactly qualifies as comfort food is very much in the palate of the comfortee. Grilled cheese may not work for everyone under every circumstance, but we’ll risk a bet that the gooey delicacy is pretty close to universal, especially when you’re under the weather.

But if you’re too sick to grill up your own and don’t have anyone to do it for you, this grilled cheese sandwich-making robot might be the perfect kitchen accessory. Dubbed “The Cheeseborg” and built as a semester project by [Taylor Tabb], [Mitchell Riek], and [Evan Hill] at Carnegie-Mellon University, the bot takes a few shortcuts that might rankle the grilled cheese purist. Chief among these is the use of a sandwich press rather than a plain griddle. We understand that this greatly simplifies the flipping problem, but to us the flipping, especially the final high arcing double backflip onto the sandwich plate, is all part of the experience. Yes, a fair number of sandwiches end up going to the dog that way, but that’s beside the point.

As realized, Cheeseborg feeds bread and cheese from stacks using a vacuum arm, sprays the grill with butter, and uses a motorized arm to push the uncooked sandwich into the press. At the peak of grilled perfection, the press opens and ejects the sandwich to a waiting plate. As an added bonus, the whole thing is Google Assistant enabled so you can beseech Cheeseborg to fix you a sandwich from your sick bed. See it in action below.

This is far from the first culinary robot to grace our pages. There was the recent CNC sausage bot, we’ve seen plenty of pancake bots, and even [Ben Krasnow] once automated cookie making.

Continue reading “Automate Your Comfort Food Prep With An IoT Grilled Cheese Robot”

Robot Can’t Take Its Eyes Off The Bottle

Robots, as we currently understand them, tend to run on electricity. Only in the fantastical world of Futurama do robots seek out alcohol as both a source of fuel and recreation. That is, until [Les Wright] and his beer seeking robot came along. (YouTube, video after the break.)

A Raspberry Pi 3 provides the brains, with an Intel Neural Compute stick plugged in as an accelerator for neural network tasks. This hardware, combined with the OpenCV image detection software, enable the tracked robot to identify objects and track their position accordingly.

That a beer bottle was chosen is merely an amusing aside – the software can readily identify many different object categories. [Les] has also implemented a search feature, in which the robot will scan the room until a target bottle is identified. The required software and scripts are available on GitHub for your perusal.

Over the past few years, we’ve seen an explosion in accelerator hardware for deep learning and neural network computation. This is, of course, particularly useful for robotics applications where a link to cloud services isn’t practical. We look forward to seeing further development in this field – particularly once the robots are able to open the fridge, identify the beer, and deliver it to the couch in one fell swoop. The future will be glorious!

 

Continue reading “Robot Can’t Take Its Eyes Off The Bottle”

Arduino RC Transmitter For Homebrew Projects

The field of radio control has benefited much from the onward march of technology. Where a basic 2-channel setup would once have cost hundreds of dollars, it’s now possible to get a high-end 2.4GHz 9-channel rig for well under $100, shipped to your door. However, the vast majority of these systems are closed-source and built for purpose. Sometimes, there are benefits to doing things your own way, and that’s precisely what this project does.

At its heart, it’s a simple combination. An Arduino Pro Mini talks to a NRF24L01 which handles the wireless communication. At that point, it’s up to you – throw in as few or as many controls as you like. For this build, [HowToMechatronics] has gone with a twin-stick setup, with a pair of potentiometers and twin toggle switches to round out the options.

The build comes in handy, as it’s possible to program in whatever features you may need for a given project. [HowToMechatronics] has used it to control a hexapod robot, among other projects. It’s a build that shows that with cheap and readily available parts, it’s possible to whip up a custom solution to suit your needs.

If this topic interests you.it’s worth saying that even those closed source radio control products can sometimes be hacked.

[Thanks to Baldpower for the tip!]

Twelve Circuit Sculptures We Can’t Stop Looking At

Circuits are beautiful in their own way, and a circuit sculpture takes that abstract beauty and makes it into a purposeful art form. Can you use the wires of the circuits themselves as the structure of a sculpture, and tell a story with the use and placement of every component? Anyone can exercise their inner artist using this medium and we loved seeing so many people give it a try. Today we announce the top winners and celebrate four score of entries in the Hackaday Circuit Sculpture Contest.

Let’s take a look at twelve outstanding projects that caught (and held) our eye:

Continue reading “Twelve Circuit Sculptures We Can’t Stop Looking At”