Despite the fact that it constantly seems like we’re in the midst of a robotics- and artificial intelligence-driven revolution, there are a number of tasks that continue to elude even the best machine learning algorithms and robots. The clothing industry is an excellent example, where the flimsy materials can easily trip up robotic manipulators. But one task like this that seems like it might soon be solve is packing cargo into trucks, as FedEx is trying to do with one of their new robots.
Part of the reason this task is so difficult is that packing problems, similar to “traveling salesman” problems, are surprisingly complex. The packages are not presented to the robot in any particular order, and need to be efficiently placed according to weight and size. This robot, called DexR, uses artificial intelligence paired with an array of sensors to get an idea of each package’s dimensions, which allows it to then plan stacking and ordering configurations and ensure secure fits between all of the other packages. The robot must also be capable of quickly adapting if any packages shift during stacking and re-order or re-stack them.
As robotics platforms and artificial intelligence continue to improve, it’s likely we’ll see a flurry of complex problems like these solved by machine instead of by human. Tackling real-world tasks are often more complex than they seem, as anyone with a printer an a PC LOAD LETTER error can attest to, even handling single sheets of paper can be a difficult task for a robot. Interfacing with these types of robots can be a walk in the park, though, provided you read the documentation first.
If you live in a place where you can buy Arduinos and Raspberry Pis locally, you probably don’t spend much time worrying about your water supply. But in some parts of the world, it is nothing to take for granted, bad water accounts for as many as 500,000 deaths worldwide every year. Scientists have reported a graphene sensor they say costs a buck and can detect dangerous bacteria and heavy metals in drinking water.
The sensor uses a GFET — a graphene-based field effect transistor to detect lead, mercury, and E. coli bacteria. Interestingly, the FETs transfer characteristic changes based on what is is exposed to. We were, frankly, a bit surprised that this is repeatable enough to give you useful data. But apparently, it is especially when you use a neural network to interpret the results.
What’s more, there is the possibility the device could find other contaminants like pesticides. While the materials in the sensor might have cost a dollar, it sounds like you’d need a big equipment budget to reproduce these. There are silicon wafers, spin coating, oxygen plasma, and lithography. Not something you’ll whip up in the garage this weekend.
Still, it is interesting to see a FET used this way and a cheap way to monitor water quality would be welcome. Using machine learning with water sensors isn’t a new idea. Of course, the sensor is one part of the equation. Monitoring is the other.
Building a weather station is a fairly common project that plenty of us have taken on, and for good reason. They can be built around virtually any microcontroller or full-scale computer, can have as many or few sensors as needed, and range from simple, straightforward projects to more complex systems capable of doing things like sending data off to weather services like Weather Underground. This weather station features a few innovations we don’t often see, though, with a modular and wireless design that makes it versatile and easy to scale up or down as needed.
Each of the modules in this build use the ESP32 platform, which simplifies design and also takes care of the wireless capability needed. The base station gets a few extra sensors including those for carbon dioxide, volatile organic compounds, and nitrogen oxides. It also includes a screen which can be used to display a wide variety of data gathered locally but also includes forecast information fetched from the free OpenWeatherMap API. For the sensor modules, BME280 sensors are used for temperature, pressure, and humidity and each module includes its own solar panel and battery with the ESP32 chips set to operate using as little energy as possible.
One of the things that helps easily integrate all of the sensor modules is the use of ESP-NOW, which we have seen a few times before. It essentially eliminates the need for a router and allows ESP modules to connect directly with one another. The build also goes into detail about most of the aspects of this project including the programming of the GUI that the ESP32 base station displays on its screen, so for anyone looking to start their own weather station project this should be an excellent guide. Make sure to check out this one as well if you want to send all of your weather data to Weather Underground.
Radio trackers have become an important part of studying the movements of wildlife, but keeping one running for the life of an animal has been challenging. Researchers have now developed a way to let wildlife recharge trackers via their movements.
With trackers limited to less than 5% of an animal’s total mass to prevent limitations to the their movement, it can be especially difficult to fit trackers with an appropriately-sized battery pack to last a lifetime. Some trackers have been fitted with solar cells, but besides issues with robustness, many animals are nocturnal or live in dimly-lit spaces making this solution less than ideal. Previous experiments with kinetically-charged trackers were quite bulky.
The Kinefox wildlife tracking system uses an 18 g, Kinetron MSG32 kinetic energy harvesting mechanism to power the GPS and accelerometer. Similar to the mechanical systems found in automatic winding watches, this energy harvester uses a pendulum glued to a ferromagnetic ring which generates power as it moves around a copper coil. Power is stored in a Li-ion capacitor rated for 20,000 charge/discharge cycles to ensure better longevity than would be afforded by a Li-ion battery. Data is transmitted via Sigfox to a cloud-based database for easy access.
If you want to build one to track your own pets, the files and BOM are available on GitHub. We’ve featured other animal trackers before for cats and dogs which are probably also applicable to bison.
For as much advancement as humanity has made in modern medicine even in the last century alone, there’s still plenty we don’t understand about the human body. That’s particularly true of the brain, where something as common as dreams are the subject of active debate about their fundamental nature, if they serve any purpose, and where they originate. One research team is hoping to probe a little further into this mystery, and has designed a special glove to help reach a little deeper into the subconscious brain.
The glove, called Dormio, has a number of sensors and feedback mechanisms which researchers hope will help explore the connection between dreaming and creativity. Volunteers were allowed to take a nap while wearing the glove, which can detect the moment they began entering a specific stage of sleep. At that point, the device would provide an audio cue to seed an idea into the dreams, in this case specifically prompting the sleeper to think about trees. Upon awakening, all reported dreaming about trees specifically, and also demonstrated increased creativity in tests compared to control groups.
While this might not have the most obvious of implications, opening the brain up to being receptive of more creative ideas can have practical effects beyond the production of art or music. For example, the researchers are also investigating whether the glove can help individuals with post-traumatic stress disorder manage nightmares. From a technical perspective this glove isn’t much different from some other devices we’ve seen before, and replicating one to perform similar functions might be possible for most of us willing to experiment on ourselves.
Harmful Algal Blooms (HABs) can have negative consequences for both marine life and human health, so it can be helpful to have early warning of when they’re on the way. Algal blooms deep below the surface can be especially difficult to detect, which is why [kutluhan_aktar] built an AI-assisted algal bloom detector.
After taking images of deep algal blooms with a boroscope, [kutluhan_aktar] trained a machine learning algorithm on them so a Raspberry Pi 4 could recognize future occurrences. For additional water quality information, the device also has an Arduino Nano connected to pH, TDS (total dissolved solids), and water temperature sensors which then are fed to the Pi via a serial connection. Once a potential bloom is spotted, the user can be notified via WhatsApp and appropriate measures taken.
If you’re looking for more environmental sensing hacks, check out the OpenCTD, this swarm of autonomous boats, or this drone buoy riding the Gulf Stream.
While bicycles appear to have standardized around a relatively common shape and size, parts for these bikes are another story entirely. It seems as though most reputable bike manufacturers are currently racing against each other to see who can include the most planned obsolescence and force their customers to upgrade even when their old bikes might otherwise be perfectly fine. Luckily, the magic of open source components could solve some of this issue, and this open-source bike computer is something you’ll never have to worry about being forced to upgrade.
The build is based around a Raspberry Pi Zero in order to keep it compact, and it uses a small 2.7 inch LCD screen to display some common information about the current bike ride, including location, speed, and power input from the pedals. It also includes some I2C sensors including pressure and temperature as well as an accelerometer. The system can also be configured to display a map of the current ride as well thanks to the GPS equipment housed inside. It keeps a log in a .fit file format as well so that all rides can be archived.
When compared against a commercial offering it seems to hold up pretty well, and we especially like that it’s not behind a walled garden like other products which could, at any point, decide to charge for map upgrades (or not offer them at all). It’s a little more work to set up, of course, but worth it in the end. It might also be a good idea to pair it with other open source bicycle components as well.
Thanks to [Richard] for the tip!