Disney’s Humanoid Stunt Robots Throw Multiple Backflips No Sweat

July 8, 2018 by Mike Szczys 19 Comments

What’s the biggest problem right now with humanoid robots? They fall down. Disney seems to have solved that problem here by making robots that are meant to fall down and be caught by a net. Disney’s research arm (you may know them as Imagineers) is showing off a robot called Stuntronic which can perform controlled somersaults as it flies through the air. Check the video below, you really have to watch a few times to make sure this is a robot and not a person.

It’s really interesting to follow the evolution of this robot. It began with BRICK, a limbless rectangular bot that could shift its center of gravity to control orientation while moving through the air. From there, Stickman adapted those concepts into a stick-shaped robot that had two hinged portions which allowed for controlled somersaults as it flew through the air. Stuntronic feels like a big leap from that design.

As with Stickman, it can bend to control somersaults mid-air, but with the addition of articulated arms, Stuntronic can also add twists to the acrobatic bag of tricks. To our eye, this is very lifelike and manages to completely escape the uncanny valley. This is a ringing endorsement since one of the proposed purposes of this research is for live performances at Disney’s theme parks.

The Hall of Presidents was a marvel of its time, as robots presented famous speeches while decorated in the likeness of the leaders who originally delivered them. But to stand and deliver is a trick of decades past. We hope this is a trick of next year and not something we’ll have to wake decades into the future to see in person.

Oh, and for those wondering if Stuntronic stuck the landing? The controlled delivery into the net’s warm embrace is equally impressive. Hopefully, successful landings are commonplace because they’re launching these bots with some really wicked force! In addition to the gyroscopes and accelerometers you’d expect to find in a motion-aware machine, the design uses a trio of laser rangefinders that triangulate ground position to spot the optimal landing. We haven’t seen a publication for this bot yet but check the Stickman info for more on these sensors.

Continue reading “Disney’s Humanoid Stunt Robots Throw Multiple Backflips No Sweat” →

Disney’s New Robot Limbs Trained Using Neural Networks

July 3, 2018 by Steven Dufresne 9 Comments

Disney is working on modular, intelligent robot limbs that snap into place with magnets. The intelligence comes from a reasonable sized neural network that also incorporates some modularity. The robot is their Snapbot whose base unit can fit up to eight of limbs, and so far they’ve trained with up to three together.

The modularity further extends to a choice of three types of limb. One with roll and pitch, another with yaw and pitch, and a third with roll, yaw, and pitch. Interestingly, of the three types, the yaw-pitch one seems most effective.

In this age of massive, deep neural networks requiring GPUs or even online services for training in a reasonable amount of time, it’s refreshing to see that this one’s only two layers deep and can be trained in three hours on a single-core, 3.4 GHz Intel i7 processor. Three hours may still seem long, but remember, this isn’t a simulation in a silicon virtual world. This is real-life where the servo motors have to actually move. Of course, they didn’t want to sit around and reset it after each attempt to move across the table so they built in an automatic mechanism to pull the robot back to the starting position before trying to cross the table again. To further speed training, they found that once they’d trained for one limb, they could then copy the last of the network’s layers to get a head starting on the training for two limbs.

Why do training? Afterall, we’ve seen pretty awesome multi-limbed robots working with manual coding, an example being this hexapod tank based on one from the movie Ghost in the Shell. They did that too and then compared the results of the manual approach with those of the trained one and the trained one moved further in the same amount of time. At a minimum, we can learn a trick or two from this modular crawler.

Check out their article for the details and watch it in action in its learning environment below.

Continue reading “Disney’s New Robot Limbs Trained Using Neural Networks” →

Suddenly, Wireless Power Transmission Is Everywhere

February 23, 2017 by Brian Benchoff 91 Comments

Wireless power transfer exists right now, but it’s not as cool as Tesla’s Wardenclyffe tower and it’s not as stupid as an OSHA-unapproved ultrasonic power transfer system. Wireless power transfer today is a Qi charger for your phone. It’s low power – just a few amps — and very short range. This makes sense; after all, we’re dealing with the inverse square law here, and wireless power transfer isn’t very efficient.

Now, suddenly, we can transfer nearly two kilowatts wirelessly to electronic baubles scattered all over a room. It’s a project from Disney Research, it’s coming out of Columbia University, it’s just been published in PLOS one, and inexplicably it’s also an Indiegogo campaign. Somehow or another, the stars have aligned and 2017 is the year of wirelessly powering your laptop.

The first instance of wireless power transfer that’s more than just charging a phone comes from Disney Research. This paper describes quasistatic cavity resonance (QSCR) to transfer up to 1900 Watts to a coil across a room. In an experimental demonstration, this QSCR can power small receivers scattered around a 50 square meter room with efficiencies ranging from 40% to 95%. In short, the abstract for this paper promises a safe, efficient wireless power transfer that completely removes the need for wall outlets.

In practice, the QSCR from Disney Research takes the form of a copper pole situated in the center of a room with the walls, ceiling, and floor clad in aluminum. This copper pole isn’t continuous from floor to ceiling – it’s made of two segments, connected by capacitors. When enough RF energy is dumped into this pole, power can be extracted from a coil of wire. The video below does a good job of walking you through the setup.

As with all wireless power transmission schemes, there is the question of safety. Using finite element analysis, the Disney team found this room was safe, even for people with pacemakers and other implanted electronics. The team successfully installed lamps, fans, and a remote-controlled car in this room, all powered wirelessly with three coils oriented orthogonally to each other. The discussion goes on to mention this setup can be used to charge mobile phones, although we’re not sure if charging a phone in a Faraday cage makes sense.

If the project from Disney research isn’t enough, here’s the MotherBox, a completely unrelated Indiegogo campaign that was launched this week. This isn’t just any crowdfunding campaign; this work comes straight out of Columbia University and has been certified by Arrow Electronics. This is, by all accounts, a legitimate thing.

The MotherBox crowdfunding campaign promises true wireless charging. They’re not going for a lot of power here – the campaign only promises enough to charge your phone – but it does it at a distance of up to twenty inches.

At the heart of the MotherBox is a set of three coils oriented perpendicular to each other. The argument, or sales pitch, says current wireless chargers only work because the magnetic fields are oriented to each other. The coil in the phone case is parallel to the coil in the charging mat, for instance. With three coils arranged perpendicular to each other, the MotherBox allows for ‘three-dimensional charging’.

Does the MotherBox work? Well, if you dump enough energy into a coil, something is going to happen. The data for the expected charging ranges versus power delivered is reasonably linear, although that doesn’t quite make sense in a three-dimensional universe.

Is it finally time to get rid of all those clumsy wall outlets? No, not quite yet. The system from Disney Research works, but you have to charge your phone in a Faraday cage. It would be a great environment to test autonomous quadcopters, though. For MotherBox, Ivy League engineers started a crowdfunding campaign instead of writing a paper or selling the idea to an established company. It may not be time to buy a phone case so you can charge your phone wirelessly at Starbucks, but at least people are working on the problem. This time around, some of the tech actually works.

Continue reading “Suddenly, Wireless Power Transmission Is Everywhere” →

Creating Full Color Images On Thermoformed Parts

May 4, 2016 by James Hobson 21 Comments

In a race to produce the cheapest and most efficient full-color 3D object, we think Disney’s Research facility (ETH Zurich and the Interactive Geometry Lab) may have found the key. Combining hydrographic printing techniques with plastic thermoforming.

You might remember our article last year on creating photorealistic images on 3D objects using a technique called hydrographic printing, where essentially you print a flattened 3D image using a regular printer on special paper to transfer it to a 3D object in a bath of water. This is basically the same, but instead of using the hydrographic printing technique, they’ve combined the flattened image transfer with thermoforming — which seems like an obvious solution!

Continue reading “Creating Full Color Images On Thermoformed Parts” →