Disney’s new robot is a cartoon came to life

And it took just months to build, rather than the usual years.
Sign up for the Freethink Weekly newsletter!
A collection of our favorite stories straight to your inbox

An adorable new Disney robot may be the most lifelike and expressive bot ever made by the entertainment giant.

It was developed in a fraction of the usual time, thanks to a combination of 3D printing, off-the-shelf parts, and computer simulations, and researchers think it could be just the first of many personable robots to come.

Charm-bots: Teaching a robot to walk on two legs is notoriously tricky, but designers building bots for Disney theme parks and attractions have an even greater challenge: because those robots are supposed to be characters, they need to walk with personality.

“[O]ur robots may have to strut, prance, sneak, trot, or meander to convey the emotion that we need them to,” Morgan Pope, a Disney research scientist, told IEEE Spectrum.

Pope recently took the stage at the 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) to co-present a new Disney robot, along with Moritz Bächer, who led the bot’s development.

“[O]ur robots may have to strut, prance, sneak, trot, or meander to convey the emotion that we need them to.”

Morgan Pope

As others have pointed out, the toddler-sized bot appears to be based directly on Star Wars’ CGI robot BD-1, and in demo videos, it truly looks like an animated character come to life, with a bouncy walk and expressive antennae.

Perhaps even more impressive than the bot’s emotive movements, though, is the new pipeline used to create it, which Bächer told IEEE Spectrum slashes the amount of time it takes to build a new Disney robot from years to just months.

Building a bot: One major time saver in robot development for Disney: using off-the-shelf actuators and 3D-printed parts, which can be modified or replaced far more quickly than traditionally manufactured hardware.

Computer simulations and a trial-and-error-based AI training technique called “reinforcement learning” hastened the process even more dramatically.

Making a new Disney robot is a back-and-forth process between animators, who come up with ideas for how the bot should look and move, and engineers, who need to build something that can actually navigate reality.

“In general, animation tools don’t have physics built into them,” said Bächer. “So that makes it hard for artists to design animations that will work in the real world.”

To speed up this process, the team added computer simulations that do replicate the physics of the real world to the workflow. The animator can then see the difference between their vision for how the bot should move and how physics dictates it’ll actually move. They then have the opportunity to tweak their animations before a single robot part is actually built.

“If we wanted to … make an entirely new character with a completely different morphology, we can rapidly teach it new behaviors.”

Moritz Bächer

Using these computer simulations and reinforcement learning, the team can teach the AI that will eventually control the robot how it should move while navigating a variety of real-world situations, such as slippery or uneven terrain, without ever breaking character.

“The idea is that this is a platform that’s hardware agnostic,” said Bächer. “So if we wanted to add more legs, or add arms, or make an entirely new character with a completely different morphology, we can rapidly teach it new behaviors.”

Looking ahead: There’s no word on what’s next for this adorable new Disney robot, but according to Bächer, the approach his team developed to create the bot can be used to quickly create others.

“The off-the-shelf actuators, the 3D-printed components, our adaptable reinforcement-learning framework — these can all be applied to robots that are widely different in how they look and move,” he said. “This robot is a promising first step on that journey.”

We’d love to hear from you! If you have a comment about this article or if you have a tip for a future Freethink story, please email us at [email protected].

Sign up for the Freethink Weekly newsletter!
A collection of our favorite stories straight to your inbox
Related
Should we turn the electricity grid over to AI?
AI could one day be woven throughout the grid management system — here are the pros and cons.
AI skeptic Gary Marcus on AI’s moral and technical shortcomings
From hallucinations to regulatory battles, Gary Marcus argues the AI status quo has failed us and it’s time citizens demand something more.
Flexport is using generative AI to create the “holy grail” of shipping
Flexport is using generative AI to read documents, talk to truckers, and create a “knowledge agent” that’s an expert in shipping.
The West needs more water. This Nobel winner may have the answer.
Paul Migrom has an Emmy, a Nobel, and a successful company. There’s one more big problem on the to-do list.
Can we automate science? Sam Rodriques is already doing it.
People need to anticipate the revolution that’s coming in how humans and AI will collaborate to create discoveries, argues Sam Rodrigues.
Up Next
A laptop screen with a question mark on it.
Subscribe to Freethink for more great stories