Cheat At Cornhole With A Bazillion-Dollar Robot

April 4, 2021 by Bryan Cockfield 19 Comments

While the days of outdoor cookouts may be a few months away for most of us, that certainly leaves plenty of time to prepare for that moment. While some may spend that time perfecting recipies or doing various home improvement projects during their remaining isolation time, others are practicing their skills at the various games played at these events. Specifically, this group from [Dave’s Armory] which have trained a robot that helps play the perfect game of cornhole. (Video, embedded below.)

While the robot in question is an industrial-grade KUKA KR-20 robot with a hefty price tag of $32,000 USD, the software and control system that the group built are fairly accessible for most people. The computer vision is handled by an Nvidia Jetson board, a single-board computer with extra parallel computing abilities, which runs OpenCV. With this setup and a custom hand for holding the corn bags, as well as a decent amount of training, the software is easily able to identify the cornhole board and instruct the robot to play a perfect game.

While we don’t all have expensive industrial robots sitting around in our junk drawer, the use of OpenCV and an accessible computer might make this project a useful introduction to anyone interested in computer vision, and the group made the code public on their GitHub page. OpenCV can be used for a lot of other things besides robotics as well, such as identifying weeds in a field or using a Raspberry Pi for facial recognition.

Continue reading “Cheat At Cornhole With A Bazillion-Dollar Robot” →

3D Printer As Robot: The Functograph

April 3, 2021 by Al Williams 12 Comments

A 3D printer is really a specialized form of robot. Sure, it isn’t exactly Data from Star Trek, but it isn’t too far from many industrial robots. Researchers from Meiji University made the same observation and decided to create a 3D printer that could swap a hot end for other types of robotic manipulators. They call their creation the Functgraph. (Video, embedded below.)

Some of the tasks the Functgraph can do including joining printed parts into an assembly, breaking support material, and more. The surprise twist is that — unlike traditional tool change schemes — the printer prints its own end effectors together with the print job and picks them up off the build plate.

Continue reading “3D Printer As Robot: The Functograph” →

Ultrasonic Sonar Detects Hidden Objects

April 2, 2021 by Bryan Cockfield 14 Comments

While early scientists and inventors famously underestimated the value of radar, through the lens of history we can see how useful it became. Even though radar uses electromagnetic waves to detect objects, the same principle has been used with other propagating waves, most often sound waves. While a well-known use of this is sonar, ultrasonic sensors can also be put to use to make a radar-like system.

This ultrasonic radar project is from [mircemk] who uses a small ultrasonic distance sensor attached to a rotating platform. A motor rotates it around a 180-degree field-of-view and an Arduino takes and records measurements during its trip. It interfaces with an application running on a computer which shows the data in real-time and maps out the location of all of the objects around the sensor. With some upgrades to the code, [mircemk] is also able to extrapolate objects hidden behind other objects as well.

While the ultrasonic sensor used in this project has a range of about a meter, there’s no reason that this principle couldn’t be used for other range-finding devices to extend its working distance. The project is similar to others we’ve seen occasionally before, but the upgrade to the software to allow it to “see” around solid objects is an equally solid upgrade.

Boston Dynamics Stretch Robot Trades Lab Coat For Work Uniform

March 31, 2021 by Roger Cheng 30 Comments

Boston Dynamics has always built robots with agility few others could match. While great for attention-getting demos, from outside the company it hasn’t been clear how they’ll translate acrobatic skills into revenue. Now we’re getting a peek at a plan in an interview with IEEE Spectrum about their new robot Stretch.

Most Boston Dynamics robots have been research projects, too expensive and not designed for mass production. The closest we got to date was Spot, which was offered for sale and picked up a few high profile jobs like inspecting SpaceX test sites. But Spot was still pretty experimental without an explicit application. In contrast, Stretch has a laser-sharp focus made clear by its official product page: this robot will be looking for warehouse jobs. Specifically, Stretch is designed to handle boxes up to 50 lbs (23 kg). Loading and unloading them, to and from pallets, conveyer belts, trucks, or shipping containers. These jobs are repetitive and tedious back-breaking work with a high injury rate, a perfect opportunity for robots.

But warehouse logistics aren’t as tightly structured as factory automation, demanding more adaptability than typical industrial robots can offer. A niche Boston Dynamics learned it can fill after releasing an earlier demo video showing their research robot Atlas moving some boxes around: they started receiving inquiries into how much that would cost. Atlas is not a product, but wheels were set in motion leading to their Handle robot. Learning from what Handle did well (and not well) in a warehouse environment, the designed evolved to today’s Stretch. The ostrich-like Handle prototype is now relegated to further research into wheeled-legged robots and the occasional fun dance video.

The Stretch preproduction prototypes visible in these videos lacks acrobatic flair of its predecessors, but they still have the perception and planning smarts that made those robots possible. Those skills are just being applied to a narrower problem scope. Once production models are on the job, we look forward to reading some work performance reviews.

Continue reading “Boston Dynamics Stretch Robot Trades Lab Coat For Work Uniform” →

Putting Perseverance Rover’s View Into Satellite View Context

March 30, 2021 by Roger Cheng 3 Comments

It’s always fun to look over aerial and satellite maps of places we know, seeing a perspective different from our usual ground level view. We lose that context when it’s a place we don’t know by heart. Such as, say, Mars. So [Matthew Earl] sought to give Perseverance rover’s landing video some context by projecting onto orbital imagery from ESA’s Mars Express. The resulting video (embedded below the break) is a fun watch alongside the technical writeup Reprojecting the Perseverance landing footage onto satellite imagery.

Some telemetry of rover position and orientation were transmitted live during the landing process, with the rest recorded and downloaded later. Surprisingly, none of that information was used for this project, which was based entirely on video pixels. This makes the results even more impressive and the techniques more widely applicable to other projects. The foundational piece is SIFT (Scale Invariant Feature Transform), which is one of many tools in the OpenCV toolbox. SIFT found correlations between Perseverance’s video frames and Mars Express orbital image, feeding into a processing pipeline written in Python for results rendered in Blender.

While many elements of this project sound enticing for applications in robot vision, there are a few challenges touched upon in the “Final Touches” section of the writeup. The falling heatshield interfered with automated tracking, implying this process will need help to properly understand dynamically changing environments. Furthermore, it does not seem to run fast enough for a robot’s real-time needs. But at first glance, these problems are not fundamental. They merely await some motivated people to tackle in the future.

This process bears some superficial similarities to projection mapping, which is a category of projects we’ve featured on these pages. Except everything is reversed (camera instead of video projector, etc.) making the math an entirely different can of worms. But if projection mapping sounds more to your interest, here is a starting point.

[via Dr. Tanya Harrison @TanyaOfMars]

Continue reading “Putting Perseverance Rover’s View Into Satellite View Context” →

Putting Your Time In

March 27, 2021 by Elliot Williams 28 Comments

I was absolutely struck by a hack this week — [Adam Bäckström]’s amazing robot arm built with modified hobby servos. Basically, he’s taken apart and re-built some affordable off-the-shelf servo motors, and like the 6-Million-Dollar Man, he’s rebuilt them better, stronger, faster. OK, and smoother. We have the technology.

The results are undeniably fantastic, and enable the experienced hacker to get champagne robot motion control on a grape-juice budget by employing some heavy control theory, and redundant sensors to overcome geartrain backlash, which is the devil of cheap servos. But this didn’t come out of nowhere. In his writeup, [Adam] starts off with “You could say this project started when I ordered six endless servos in middle school, more than 15 years ago.” And it shows.

Go check out this video of his first version of the modified servos, from a six-axis arm he built in 2009(!). He’s built in analog position sensors in the motors, which lets him control the speed and makes it work better than any other hobby servo arm you’ve ever seen, but there’s still visible backlash in the gears. A mere twelve years later, he’s got magnetic encoders on the output and a fast inner loop compensates for the backlash. The result is that the current arm moves faster and smoother, while retaining accuracy.

Twelve years. I assume that [Adam] has had some other projects on his plate as well, but that’s a long term project by any account. I’m stoked to see his work, not the least because it should help a lot of others who are ready to step up their desktop servo-arm projects. But the real take-home lesson here is that if you’ve got a tough problem that you’re hacking on, you don’t have to get it done this weekend. You don’t have to get it done next weekend either. Keep hammering on it as long as you need, but keep on hammering. When you get it done, the results will be all the better for the long, slow, brewing time. What’s the longest project that you’ve ever worked on?

Skid Steer Robot Chassis Takes A Beating

March 26, 2021 by Lewin Day 5 Comments

[Engineering After Hours] wanted a highly maneuverable robot chassis with a tight turning radius. Skid steering seemed to be the perfect solution, but the available commercial options didn’t take his fancy. Thus, a custom build was the answer – with impressive results.

The build packs two large RC motors, one for each side, with each driving two wheels through a belt drive. This reduces the electronics required to the bare minimum for skid steering. It’s all assembled within a plasma-cut metal chassis which is more than tough enough to take some hard knocks.

One of the primary goals on the build was to eliminate the risk of vibrations and shock damaging the motors and gearboxes. Many off-the-shelf designs couple the wheels directly to gearbox output shafts, potentially damaging the expensive components over time. In this design, a separate bearing assembly is used to take the load from the wheels instead.

It’s a great example of how an engineering-first approach can build a sturdy ‘bot with a minimum of fuss. Outfitted with some fat off-road tyres the performance is impressive, with the ‘bot having no trouble tearing it up in mud, snow, and water.

We’ve seen other great builds from [Engineering After Hours] before, like the active aero RC build. Video after the break.

Continue reading “Skid Steer Robot Chassis Takes A Beating” →