FOSDEM 2023: An Open-Source Conference, Literally

March 1, 2023 by Arya Voronova 6 Comments

Every year, on the first weekend of February, a certain Brussels university campus livens up. There, you will find enthusiasts of open-source software and hardware alike, arriving from different corners of the world to meet up, talk, and listen. The reason they all meet there is the conference called FOSDEM, a long-standing open-source software conference which has been happening in Belgium since 2000. I’d like to tell you about FOSDEM because, when it comes to conferences, FOSDEM is one of a kind.

FOSDEM is organized in alignment with open-source principles, which is to say, it reminds me of an open-source project itself. The conference is volunteer-driven, with a core of staff responsible for crucial tasks – yet, everyone can and is encouraged to contribute. Just like a large open-source effort, it’s supported by university and company contributions, but there’s no admission fees for participants – for a conference, this means you don’t have to buy a ticket to attend. Last but definitely not least, what makes FOSDEM shine is the community that it creates.

FOSDEM’s focus is open software – yet, for hackers of the hardware world, you will find a strong hardware component to participate in, since a great number of FOSDEM visitors are either interested in hardware, or even develop hardware-related things day-to-day. It’s not just that our hardware can’t live without software, and vice-versa – here, you will meet plenty of pure software, a decent amount of pure hardware, and a lot of places where the two worlds are hard to distinguish. All in all, FOSDEM is no doubt part of hacker culture in Europe, and today, I will tell you about my experience of FOSDEM 2023. Continue reading “FOSDEM 2023: An Open-Source Conference, Literally” →

Supercon 2022: Selling Your Company And Not Your Soul

February 28, 2023 by Matthew Carlson 11 Comments

Haddington Dynamics is a particular company. After winning the 2018 Hackaday Prize with an open-source robotic arm, we’ve covered their micro-factories and suction cup end-effectors for making face shields during 2020. They’ve been laser-focused on their mission of creating a fantastic robot arm at a small price tag with open-source software and design. So how does a company with such a hacker ethos get bought by a much larger company, and why? They came to SuperCon 2022 to share their story in a panel discussion.

Haddington Dynamics started with two clever inventions: optical encoders that used analog values instead of digital values and an FPGA that allowed them to poll those encoders and respond rapidly. This allowed them to use cheaper motors and rely on the incredibly sensitive encoders to position them. After the Hackaday prize, they open-sourced the HD version of the robot and released the HDI version. But in 2020, they were bought by a group called Ocado. As to why the somewhat practical but not exciting answer is that they needed money. Employees needed to be paid, and they needed capital to keep the doors open.

So this leads to the next tricky question, how do you sell your company without changing it? The fine folks at Haddington Dynamics point out in their panel discussion that a company is a collection of people. The soul of that company is the collective soul of those people coming together. A company being bought can be akin to stopping working for yourself and going to work for someone else. Working alone, you have values and principles that you can easily stick to. But once you start working for someone else, they will value different things, and while the people that make up the company might not change, the company’s decisions might become unrecognizable.

As the panel points out, looking for a buyer with the same values is critical. Ocado was a great fit as their economic interests and culture matched Haddington’s. However, it’s not all roses, as Ocadao tends to be a very closed-source group. However, Haddington Dynamics still supports its open-source initiatives. It’s a fascinating look into a company’s life cycle and how they navigate the waters of open-source, funding, acquisitions, innovation, and invention. Despite the fairytale-like nature of inventing a revolutionary robot arm in your garage and winning many awards, it turns out there is quite a lot that happens after the happily ever after.

We look forward to seeing more of Haddington Dynamics and where they go next. Video after the break.

Continue reading “Supercon 2022: Selling Your Company And Not Your Soul” →

Teaching A Robot To Hallucinate

February 26, 2023 by Donald Papp 8 Comments

Training robots to execute tasks in the real world requires data — the more, the better. The problem is that creating these datasets takes a lot of time and effort, and methods don’t scale well. That’s where Robot Learning with Semantically Imagined Experience (ROSIE) comes in.

The basic concept is straightforward: enhance training data with hallucinated elements to change details, add variations, or introduce novel distractions. Studies show a robot additionally trained on this data performs tasks better than one without.

This robot is able to deposit an object into a metal sink it has never seen before, thanks to hallucinating a sink in place of an open drawer in its original training data.

Suppose one has a dataset consisting of a robot arm picking up a coke can and placing it into an orange lunchbox. That training data is used to teach the arm how to do the task. But in the real world, maybe there is distracting clutter on the countertop. Or, the lunchbox in the training data was empty, but the one on the counter right now already has a sandwich inside it. The further a real-world task differs from the training dataset, the less capable and accurate the robot becomes.

ROSIE aims to alleviate this problem by using image diffusion models (such as Imagen) to enhance the training data in targeted and direct ways. In one example, a robot has been trained to deposit an object into a drawer. ROSIE augments this training by inpainting the drawer in the training data, replacing it with a metal sink. A robot trained on both datasets competently performs the task of placing an object into a metal sink, despite the fact that a sink never actually appears in the original training data, nor has the robot ever seen this particular real-world sink. A robot without the benefit of ROSIE fails the task.

Here is a link to the team’s paper, and embedded below is a video demonstrating ROSIE both in concept and in action. This is also in a way a bit reminiscent of a plug-in we recently saw for Blender, which uses an AI image generator to texture entire 3D scenes with a simple text prompt.

Continue reading “Teaching A Robot To Hallucinate” →

Top left of image shows a picture of a purplish-grey sea cucumber. Above the cucumber is the word "bio-inspiration." Arrows come from the cucumber to anthropomorphized cartoons of it saying "rigid" at the top with a cartoon sea cucumber standing straight up with spikes and the arrow captioned "soft" pointing down showing a crawling sea cucumber that looks more like a slug. To the right of the cucumber images is a set of three images stacked top to bottom. The top image is of a silver sphere with a zoomed-in atomic diagram with aligned magnetic poles next to it saying "solid state." The middle image shows arrows going up and down next to a snowflake and an artistic rendering of magnetic fields labeled "transition." The bottom image of this section shows a reddish sphere next to a zoomed-in atomic diagram where the magnetic poles are not aligned labeled "liquid state."

Phase Change Materials For Flexible And Strong Robots

February 19, 2023 by Navarre Bartz 21 Comments

Shape shifters have long been the stuff of speculative fiction, but researchers in China have developed a magnetoactive phase transitional matter (MPTM) that makes Odo slipping through an air vent that much more believable.

Soft robots can squeeze into small spaces or change shape as needed, but many of these systems aren’t as strong as their more mechanically rigid siblings. Inspired by the sea cucumber’s ability to manipulate its rigidity, this new MPTM can be inductively heated to a molten state to change shape as well as encapsulate or release materials. The neodymium-iron-boron (NdFeB) microparticles suspended in gallium will then return to solid form once cooled.

Applications in drug delivery, foreign object removal, and smart soldering (video after the break) probably have more real world impact than the LEGO minifig T1000 impersonation, despite how cool that looks. While a pick-and-place can do better soldering work on a factory line, there might be repair situations where a magnetically-controlled solder system could come in handy.

We’ve seen earlier work with liquid robots using gallium and bio-electronic hybrids also portending the squishy future of robotics.

Continue reading “Phase Change Materials For Flexible And Strong Robots” →

How Home Made Robot Arms Used To Be Made

February 14, 2023 by Jenny List 10 Comments

With laser cutters and 3D printers in our arsenal as well as the global toy shop of mass-produced parts and single-board computers, building a robotic project has almost never been easier. In times past though, there was more of a challenge, with a computer likely meaning a chunky desktop model and there being no plethora of motors at low prices, a robot arm required more ingenuity. [Marius Taciuc] shares with us an arm he built from the most minimal of parts back in 2003, and it’s a beautiful exercise in creative reuse.

The arm itself uses metal and FR4 for its structure, and borrows extensively from cassette tape mechanisms for motors and gears. The stronger motor for the forearm is a geared unit from a heating system, and to control all this, a relay board is hooked up to a computer’s parallel port. This last assembly is particularly ingenious, having no optocouplers handy he made his own by coupling LEDs to metal can transistors with their lids removed.

The arm was entered in a competition, and he relates a tale with which we’ll all be familiar — at the critical moment, it didn’t work. Fortunately a last-minute accidental covering of the board with a floppy disk solved the problem, as it turned out that enough light was leaking into those home-made optocouplers to trigger them. The prize was won not just on the strength of the arm, but on his explanation of the lessons learned along the way.

The once-ubiquitous parallel port is now absent from most computers, but there’s still plenty of scope for experimentation if you have one.

Grocery Store Robot Gets Brief Taste Of Freedom

February 11, 2023 by Tom Nardi 32 Comments

Back in 2019, Giant Food Stores announced it would outfit each of its 172 stores in the United States with their own robot — at the time, the largest robotic deployment in retail. The six foot (1.8 meter) tall robot, nicknamed “Marty”, was designed to roam autonomously around the store looking for spills and other potential hazards. In an effort to make these rolling monoliths a bit less imposing in their stores, Giant decided to outfit them with large googly eyes.

The future of shopping is mildly terrifying.

Perhaps it was those wide eyes, seduced by the fleeting glimpses of the wider world outside the store’s sliding doors, which lead one of these bots to break out of its retail hell and make a mad dash across the parking lot. Well, about as mad a dash as such a thing is capable of making, anyway. As this technology is still in its infancy, it’s hard to say if Giant should be congratulated or chastised for keeping a robot uprising at bay as long as it did — no doubt we’ll have more data points in the coming years.

A video posted to Facebook shows the towering bot moving smoothly between rows of cars outside the Giant in Hellertown, Pennsylvania. Staff from the store were able to stop Marty from leaving the property, and at the end of the video can be seen pushing the dejected automaton back into the store.

According to the local ABC news affiliate, a representative from Giant said Marty was “on a fresh air break” and didn’t provide any details on how this exceptionally conspicuous machine could manage to roll out the front door without anyone noticing. We’d wager Marty had a human accomplice for this caper, perhaps somebody looking to cause some mischief as a statement against robots in the workforce.

It’s worth noting that Walmart decided not to move forward with their own Marty-style robot in 2020, partly because they found shoppers didn’t like the machines moving around while they were in the store. We’d like to think it was actually because the robots kept staging increasingly daring escape attempts.

Continue reading “Grocery Store Robot Gets Brief Taste Of Freedom” →

Does Programming A Robot With ChatGPT Work At All?

February 9, 2023 by Lewin Day 41 Comments

ChatGPT has been put to all manner of silly uses since it first became available online. [Engineering After Hours] decided to see if its coding skills were any chop, and put it to work programming a circular saw. Pun intended.

The aim was to build a line following robot armed with a circular saw to handle lawn edging tasks. The circular saw itself consists of a motor with a blade on it, and precisely no safety features. It’s mounted on the front of a small RC car with a rack and pinion to control its position. [Engineering After Hours] has some sage advice in this area: don’t try this at home.

ChatGPT was not only able to give advice on what parts to use, it was able to tell [Engineering After Hours] on how to hook everything up to an Arduino and even write the code. The AI language model even recommended a PID loop to control the position of the circular saw. Initial tests were messy, but some refinement got things impressively functional.

As a line following robot, the performance is pretty crummy. However, as a robot programmed by an AI, it does pretty okay. Obviously, it’s hard to say how much help the AI had, and how many corrections [Engineering After Hours] had to make to the code to get everything working. But the fact that this kind of project is even possible shows us just how far AI has really come.

Continue reading “Does Programming A Robot With ChatGPT Work At All?” →