Training A Self-Driving Kart

December 21, 2024 by Bryan Cockfield 1 Comment

There are certain tasks that humans perform every day that are notoriously difficult for computers to figure out. Identifying objects in pictures, for example, was something that seems fairly straightforward but was only done by computers with any semblance of accuracy in the last few years. Even then, it can’t be done without huge amounts of computing resources. Similarly, driving a car is a surprisingly complex task that even companies promising full self-driving vehicles haven’t been able to deliver despite working on the problem for over a decade now. [Austin] demonstrates this difficulty in his latest project, which adds self-driving capabilities to a small go-kart.

[Austin] had been working on this project at the local park but grew tired of packing up all his gear when he wanted to work on his machine-learning algorithms. So he took all the self-driving equipment off of the first kart and incorporated it into a smaller kart with a very small turning radius so he could develop it in his shop.

He laid down some tape on the floor to create the track and then set up the vehicle to learn how to drive by watching and gathering data. The model is trained with a convolutional neural network and this data. The only inputs that the model gets are images from cameras at the front of the kart. At first, it could only change the steering angle, with [Austin] controlling the throttle to prevent crashes. Eventually, he gave it control of the throttle as well, which behaves well except at the fastest speeds.

There were plenty of challenges along the way, especially when compared to the models trained at the park; [Austin] correctly theorized that the cause of the hardship in the park was a lack of contrast at the boundary between the track and any out-of-bounds areas. With a few tweaks to the track, as well as adding some wide-angle lenses to his cameras, he was able to get a model that works fairly well. Getting started on a project like this doesn’t have as high of a barrier to entry as one might imagine, either. Take a look at this comprehensive open-source Python library for self-driving projects. If you want to start smaller, perhaps don’t start with a self-driving kart.

Continue reading “Training A Self-Driving Kart” →

Dog Poop Drone Cleans Up The Yard So You Don’t Have To

September 28, 2024 by Dan Maloney 20 Comments

Sometimes you instantly know who’s behind a project from the subject matter alone. So when we saw this “aerial dog poop removal system” show up in the tips line, we knew it had to be the work of [Caleb Olson].

If you’re unfamiliar with [Caleb]’s oeuvre, let us refresh your memory. [Caleb] has been on a bit of a dog poop journey, starting with a machine-learning system that analyzed security camera footage to detect when the adorable [Twinkie] dropped a deuce in the yard. Not content with just knowing when a poop event has occurred, he automated the task of locating the packages with a poop-pointing robot laser. Removal of the poop remained a manual task, one which [Caleb] was keen to outsource, hence the current work.

The video below, from a lightning talk at a conference, is pretty much all we have to go on, and the quality is a bit potato-esque. And while [Caleb]’s PoopCopter is clearly still a prototype, it’s easy to get the gist. Combining data from the previous poop-adjacent efforts, [Caleb] has built a quadcopter that can (or will, someday) be guided to the approximate location of the offending package, home in on it using a downward-looking camera, and autonomously whisk it away.

The retrieval mechanism is the high point for us; rather than a complicated, servo-laden “sky scoop” or something similar, the drone has a bell-shaped container on its belly with a series of geared leaves on the open end. The leaves are open when the drone descends onto the payload, and then close as the drone does a quick rotation around the yaw axis. And, as [Caleb] gleefully notes, the leaves can also open in midair with a high-torque yaw move in the opposite direction; the potential for neighborly hijinx is staggering.

All jokes and puns aside, this looks fantastic, and we can’t wait for more information and a better video. And lest you think [Caleb] only works on “Number Two” problems, never fear — he’s also put considerable work into automating his offspring and taking the awkwardness out of social interactions.

Continue reading “Dog Poop Drone Cleans Up The Yard So You Don’t Have To” →

Mothbox Watches Bugs, So You — Or Your Grad Students — Don’t Have To

September 19, 2024 by Dan Maloney 8 Comments

To the extent that one has strong feelings about insects, they tend toward the extremes of a spectrum that runs from a complete fascination with their diversity and the specializations they’ve evolved to exploit unique and ultra-narrow ecological niches, and “Eww, ick! Kill it!” It’s pretty clear that [Dr. Andy Quitmeyer] and his team tend toward the former, and while they love their bugs, spending all night watching them is a tough enough gig that they came up with Mothbox, the automated insect monitor.

Insect censuses are valuable tools for assessing the state of an ecosystem, especially insects’ vast numbers, short lifespan, and proximity to the base of the food chain. Mothbox is designed to be deployed in insect-rich environments and automatically recognize and tally the moths it sees. It uses an Arducam and Raspberry Pi for image capture, plus an array of UV and visible LEDs, all in a weatherproof enclosure. The moths are attracted to the light and fly between the camera and a plain white background, where an image is captured. YOLO v8 locates all the moths in the image, crops them out, and sends them to BioCLIP, a vision model for organismal biology that appears similar to something we’ve seen before. The model automatically sorts the moths by taxonomic features and keeps a running tally of which species it sees.

Mothbox is open source and the site has a ton of build information if you’re keen to start bug hunting, plus plenty of pictures of actual deployments, which should serve as nightmare fuel to the insectophobes out there.

Supercon 2023: Teaching Robots How To Learn

September 3, 2024 by Lewin Day 2 Comments

Once upon a time, machine learning was an arcane field, the preserve of a precious few researchers holed up in grand academic institutions. Progress was slow, and hard won. Today, however, just about anyone with a computer can dive into these topics and develop their own machine learning systems.

Shawn Hymel has been doing just that, in his work in developer relations and as a broader electronics educator. His current interest is reinforcement learning on a tiny scale. He came down to the 2023 Hackaday Supercon to tell us all about his work.

Continue reading “Supercon 2023: Teaching Robots How To Learn” →

Building AI Models To Diagnose HVAC Issues

August 8, 2024 by Bryan Cockfield 10 Comments

HVAC – heating, ventilation, and air conditioning – can account for a huge amount of energy usage of a building, whether it’s residential or industrial. Often it’s the majority energy consumer, especially in places with extreme climates or for things like data centers where cooling is a large design consideration. When problems arise with these complex systems, they can go undiagnosed for a time and additionally be difficult to fix, leading to even more energy losses until repairs are complete. With the growing availability of platforms that can run capable artificial intelligences, [kutluhan_aktar] is working towards a system that can automatically diagnose potential issues and help humans get a handle on repairs faster.

The prototype system is designed for hydronic (water-based) systems and uses two separate artificial intelligences, one to analyze thermal imagery of the system and look for problems like leaks, hot spots, or blockages, and the other to listen for anomalous sounds especially relating to the behavior of cooling fans. For the first, a CNC-like machine was built to move a thermal camera around a custom-built model HVAC system and report its images back to a central system where they can be analyzed for anomalies. The second system which analyses audio runs its artificial intelligence on a XIAO ESP32C6 and listens to the cooling fans running in the model.

One problem that had to be tackled before any of this could be completed was actually building an open-source dataset to train the AI on. That’s part of the reason for the HVAC model in this project; being able to create problems to train the computer to detect before rolling it out to a larger system. The project’s code and training models can be found on its GitHub page. It seems to be a fairly robust solution to this problem, though, and we’ll be looking forward to future versions running on larger systems. Not everyone has a hydronic HVAC system, though. As heat pumps become more and more popular and capable, you’ll need systems to control those as well.

Sealed Packs Of Pokémon Cards Give Up Their Secrets Without Opening Them

July 20, 2024 by Donald Papp 31 Comments

[Ahron Wayne] succeeded in something he’s been trying to accomplish for some time: figuring out what’s inside a sealed Pokémon card packet without opening it. There’s a catch, however. It took buying an X-ray CT scanner off eBay, refurbishing and calibrating it, then putting a load of work into testing and scanning techniques. Then finally combining the data with machine learning in order to make useful decisions. It’s a load of work but [Ahron] succeeded by developing some genuinely novel techniques.

While using an X-ray machine to peek inside a sealed package seems conceptually straightforward, there are in fact all kinds of challenges in actually pulling it off. There’s loads of noise. So much that the resulting images give a human eyeball very little to work with. Luckily, there are also some things that make the job a little easier.

For example, it’s not actually necessary to image an entire card in order to positively identify it. Teasing out the individual features such as a fist, a tentacle, or a symbol are all useful to eliminate possibilities. Interestingly, as a side effect the system can easily spot counterfeit cards; the scans show up completely different.

When we first covered [Ahron]’s fascinating journey of bringing CT scanners back to life, he was able to scan cards but made it clear he wasn’t able to scan sealed packages. We’re delighted that he ultimately succeeded, and also documented the process. Check it out in the video below.

Continue reading “Sealed Packs Of Pokémon Cards Give Up Their Secrets Without Opening Them” →

CUDA, But Make It AMD

July 16, 2024 by Lewin Day 40 Comments

Compute Unified Device Architecture, or CUDA, is a software platform for doing big parallel calculation tasks on NVIDIA GPUs. It’s been a big part of the push to use GPUs for general purpose computing, and in some ways, competitor AMD has thusly been left out in the cold. However, with more demand for GPU computation than ever, there’s been a breakthrough. SCALE from [Spectral Compute] will let you compile CUDA applications for AMD GPUs.

SCALE allows CUDA programs to run as-is on AMD GPUs, without modification. The SCALE compiler is also intended as a drop-in swap for nvcc, right down to the command line options. For maximum ease of use, it acts like you’ve installed the NVIDIA Cuda Toolkit, so you can build with cmake just like you would for a normal NVIDIA setup. Currently, Navi 21 and Navi 31 (RDNA 2.0 and RDNA 3.0) targets are supported, while a number of other GPUs are undergoing testing and development.

The basic aim is to allow developers to use AMD hardware without having to maintain an entirely separate codebase. It’s still a work in progress, but it’s a promising tool that could help break NVIDIA’s stranglehold on parts of the GPGPU market.