World’s Biggest, Most Useless AI Machine

September 23, 2016 by Steven Dufresne 11 Comments

In a time when we’re inundated with talk of an impending AI apocalypse it’s nice to see an AI that’s intentionally useless. That AI is HAL 9000. No, not the conflicted HAL from the movie 2001: A Space Odyssey but the World’s Biggest AI Useless Machine HAL built by [Rafael], [Mickey] and [Eyal] for GeekCon 2016 in Israel.

Standing tall, shiny and black, the box it’s housed in reminds us a bit of the monolith from the movie. But, in a watchful position near the top is HAL’s red eye. As we approach, HAL’s voice from the movie speaks to us asking “Just what do you think you’re doing, Dave?” as the eye changes diameter in keeping with the speech’s amplitude. And at the bottom is a bright, yellow lever marked ON, which of course we just have to turn off. When we do, a panel opens up below it and a rod extends upward to turn the lever back to the ON position.

Behind the scenes are two Arduinos. One Arduino manages servos for the panel and rod as well as playing random clips of HAL from the movie. The other Arduino uses the Arduino TVout library to output to a projector that sits behind the red diffuser that is the eye. That Arduino also takes input from a microphone and based on the amplitude, has the projector project a white circle of corresponding diameter, making the eye’s appearance change. You can see all this in action in the video after the break.

Continue reading “World’s Biggest, Most Useless AI Machine” →

Canary Island Team Wins World Robotic Sailing 2016

September 22, 2016 by Elliot Williams 10 Comments

If you’re like us, you had no idea that there even was a World Robotic Sailing Championship. But we’re glad that we do now! And congratulations to the team of A-Tirma G2, the winning boat. (Link in Spanish, difficult to translate — if you can figure out how, post in the comments?)

The Championship has apparently been going on for nine years now, and moves to a different location around the world each year. The contests for 2016 (PDF) are by no means trivial. Besides a simple there-and-back regatta, the robot boats have to hold position, scan a prescribed area, and avoid a big obstacle and return quickly back to their lane. All of this with wind power, of course.

The winning boat used solid sails, which act essentially as vertical wings, and was designed for rough weather. This paid off in the area-scanning test; the winds were so strong that the organizers considered calling it off, but team A-Tirma’s boat navigated flawlessly, giving them enough points to win the event even though camera malfunction kept them from completing the obstacle avoidance.

Unless you’ve sailed, it’s hard to appreciate the difficulty of these challenges to an autonomous vehicle. It’s incredibly hard to plan far ahead because the boat’s motive power source, the wind, isn’t constant. But the boat has, relatively speaking, a lot of inertia and no brakes, so the robot has to plan fairly far in advance. That any of the 2-4 meter long boats could stay inside a circle of 20 meters is impressive. Oh, and did we mention that A-Tirma did all of this calculating and reacting on solar power?

Because the wind is so fickle, drone sailboats are much less popular than drone motorboats — at least using the Hackaday Blogpost Metric ™. The hackerboat project is trying out sails, but they’re still mostly working on powered propulsion. We do have an entry in the 2016 Hackaday Prize, but it’s looking like the development process is in the doldrums. Still, sailing is the best way to go in the end, because windpower is essentially free on the open ocean, which means less work for the solar panels.

As far as role-models go, you’ve basically got the entrants in the World Robotic Sailing Championships. So kudos to the A-Tirma team, and thanks [Nikito] for the tip!

Real, Life-Sized Transformers

September 19, 2016 by Moritz Walter 23 Comments

Ever dreamed of a real, life-sized Transformer in your garage? The Turkish startup Letrons now offers you exactly that: Their animatronic Autobot drives like a car, transforms like a Transformer, and supposedly fights off space threats with its built-in smoke machine and sound effects.

Letrons’s Transformer seems to be built upon a BMW E92 coupé chassis. According to the company, the beast is packed with powerful hydraulics and servo motors, allowing it to transform and move fast. Sensors all around the chassis give it some interactivity and prevent it from crushing innocent bystanders when in remote-control mode. Interestingly, its movable arms aren’t attached to the body, but to its extendable side-wings and feature hands with actuated wrists and fingers. The Autobot also can move its head, which pops right out of the hood.

Admittedly, Letrons must have spent a lot of time on the dark side of the moon and working in secrecy before they released footage of a working and polished prototype. It’s unclear if Letron’s Transformers will cooperate with the US military in solving armed conflicts, but they are certainly good for a show. Enjoy the video below!

Continue reading “Real, Life-Sized Transformers” →

Grand Theft Auto V Used To Teach Self-Driving AI

September 16, 2016 by James Hobson 29 Comments

For all the complexity involved in driving, it becomes second nature to respond to pedestrians, environmental conditions, even the basic rules of the road. When it comes to AI, teaching machine learning algorithms how to drive in a virtual world makes sense when the real one is packed full of squishy humans and other potential catastrophes. So, why not use the wildly successful virtual world of Grand Theft Auto V to teach machine learning programs to operate a vehicle?

The hard problem with this approach is getting a large enough sample for the machine learning to be viable. The idea is this: the virtual world provides a far more efficient solution to supplying enough data to these programs compared to the time-consuming task of annotating object data from real-world images. In addition to scaling up the amount of data, researchers can manipulate weather, traffic, pedestrians and more to create complex conditions with which to train AI.

It’s pretty easy to teach the “rules of the road” — we do with 16-year-olds all the time. But those earliest drivers have already spent a lifetime observing the real world and watching parents drive. The virtual world inside GTA V is fantastically realistic. Humans are great pattern recognizers and fickle gamers would cry foul at anything that doesn’t analog real life. What we’re left with is a near-perfect source of test cases for machine learning to be applied to the hard part of self-drive: understanding the vastly variable world every vehicle encounters.

A team of researchers from Intel Labs and Darmstadt University in Germany created a program that automatically indexes the virtual world (as seen above), creating useful data for a machine learning program to consume. This isn’t a complete substitute for real-world experience mind you, but the freedom to make a few mistakes before putting an AI behind the wheel of a vehicle has the potential to speed up development of autonomous vehicles. Read the paper the team published Playing for Data: Ground Truth from Video Games.

Continue reading “Grand Theft Auto V Used To Teach Self-Driving AI” →

Robotic Arm From Cardboard

September 14, 2016 by Al Williams 7 Comments

Google showed the world that you could make a virtual reality headset from cardboard. We figure that might have been [Uladz] inspiration for creating a robotic arm also made out of cardboard. He says you can reproduce his design in about two hours.

You’ll need an Arduino and four hobby servo motors. The cardboard doesn’t weigh much, so you could probably use fairly small motors. In addition to the cardboard, there’s a piece of hardboard for the base and a few metal clips. You can control it all from the Arduino program or add an IR receiver if you want to run it by remote control. There’s a video of the arm–called CARDBIRD–in action, below.

Continue reading “Robotic Arm From Cardboard” →

Furuta Style Inverted Pendulum Is King Of Geek Desk Ornaments

September 14, 2016 by Gerrit Coetzee 19 Comments

Newton’s Cradle is thought of as the most elegant of executive desk toys. But that 20th-century dinosaur just got run off the road as [Ben Katz]’s Furuta pendulum streaks past in the fast lane, flipping the bird and heralding a new king of desk adornments.

This Furata pendulum has wonderfully smooth movement. You can watch it go through its dance in the video after the break. Obviously you agree that this is the desk objet d’art for the modern titan of industry (geek). Just don’t stop at watching it in action. The best part is the build log that [Ben] put together — this project has a little bit of everything!

Continue reading “Furuta Style Inverted Pendulum Is King Of Geek Desk Ornaments” →

Sewbo Robot Sews Up Automated Garment Manufacturing

September 12, 2016 by Moritz Walter 42 Comments

While robots enter other industries in herds, the assembly of garments has long been a tedious, human privilege. Now, for the first time, a robot has sewn an entire, wearable piece of garment. Sewbo, an industrial robot programmed to tackle the tricky task, assembles clothes and makes it look easy.

Continue reading “Sewbo Robot Sews Up Automated Garment Manufacturing” →