Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Spotted at #NeurIPS2023: Disney Research demos a RL-trained remote control robot! Super impressive work!

Tanishq Mathew Abraham, Ph.D.

90,324 subscribers

169,970 views • 2 years ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

8 Comments

vittorio2 years ago

cute/acc

meowbooks --🩸/acc2 years ago

Disney/acc

Vicente Silveira2 years ago

And if you want for relevant papers for this area, just submit a picture to our GPT and we search across 4K #NeurIPS23 for the goods! try it out here:

time 🔮2 years ago

i want a few lil buddies like this i think

valar — e/acc2 years ago

it's way too adorable

Koningsbruggen2 years ago

amazing design

Keyzer Söze (faulsc/acc)2 years ago

What part of it is RL-trained if it is remote controlled?

Mariam3692 years ago

It's really amazing😳😳😳

Related Videos

The robot climbs stairs🏯, steps over stones 🪨, and runs in the wild🏞️, all in one policy, without any remote control! Our #CVPR2023 Highlight paper achieves this by using RL + a 3D Neural Volumetric Memory (NVM) trained with view synthesis!

The robot climbs stairs🏯, steps over stones 🪨, and runs in the wild🏞️, all in one policy, without any remote control! Our #CVPR2023 Highlight paper achieves this by using RL + a 3D Neural Volumetric Memory (NVM) trained with view synthesis!

Xiaolong Wang

113,042 views • 3 years ago

Wow. More great learning based bipedal control from Disney research. Doing this on low cost hardware is even more impressive.

Wow. More great learning based bipedal control from Disney research. Doing this on low cost hardware is even more impressive.

Simon Kalouche

52,133 views • 2 years ago

Another robot from Disney! 🕺🏻 Just look at this dancing fella created by Disney Research. Creating control policies that work on real robots and handling diverse, unseen motions in physics-based character control is still difficult. The Disney team proposes a two-state solution. The first step involves learning a latent space encoding with an autoencoder. After encoding, the policy is trained to map kinematic input to dynamic output, ensuring accurate and adaptable movement. This method eliminates common mode collapse issues and improves motion encoding by separating these stages. This technique has proven effective in real robots in simulations, marking a significant leap forward in robot control. Can't wait for it in action live in 2025 :) ~~~ RT to help 1 robot find a new workplace.

Another robot from Disney! 🕺🏻 Just look at this dancing fella created by Disney Research. Creating control policies that work on real robots and handling diverse, unseen motions in physics-based character control is still difficult. The Disney team proposes a two-state solution. The first step involves learning a latent space encoding with an autoencoder. After encoding, the policy is trained to map kinematic input to dynamic output, ensuring accurate and adaptable movement. This method eliminates common mode collapse issues and improves motion encoding by separating these stages. This technique has proven effective in real robots in simulations, marking a significant leap forward in robot control. Can't wait for it in action live in 2025 :) ~~~ RT to help 1 robot find a new workplace.

Lukas Ziegler

65,972 views • 1 year ago

New research: Quadruped robots climbing ladders! 🦾🚀 Using RL-based control and a hooked end-effector, we're expanding robot capabilities in industrial environments. More info in the paper: Video:

New research: Quadruped robots climbing ladders! 🦾🚀 Using RL-based control and a hooked end-effector, we're expanding robot capabilities in industrial environments. More info in the paper: Video:

Robotic Systems Lab

16,390 views • 1 year ago

Attention: this might be the video that opens the door to the future. When a SOTA agent model connects to a robot dog with no remote control— MiniMax M2.1 × Vbot, super-powered in action. A model trained in the virtual world now controls a robot in the physical world. Hello, humans. Welcome to the future.

Attention: this might be the video that opens the door to the future. When a SOTA agent model connects to a robot dog with no remote control— MiniMax M2.1 × Vbot, super-powered in action. A model trained in the virtual world now controls a robot in the physical world. Hello, humans. Welcome to the future.

MiniMax (official)

151,822 views • 8 months ago

Excited to share a new humanoid robot platform we’ve been working on. Berkeley Humanoid is a reliable and low-cost mid-scale research platform for learning-based control. We demonstrate the robot walking on various terrains and dynamic hopping with a simple RL controller.

Excited to share a new humanoid robot platform we’ve been working on. Berkeley Humanoid is a reliable and low-cost mid-scale research platform for learning-based control. We demonstrate the robot walking on various terrains and dynamic hopping with a simple RL controller.

Qiayuan Liao

80,436 views • 2 years ago

RobotMDM, by Disney Research, combines diffusion-based motion generation with RL to produce physics-aware humanoid motions from text prompts. Trained on human motion data with a reward surrogate for physical feasibility, it ensures realistic motions.

RobotMDM, by Disney Research, combines diffusion-based motion generation with RL to produce physics-aware humanoid motions from text prompts. Trained on human motion data with a reward surrogate for physical feasibility, it ensures realistic motions.

The Humanoid Hub

22,943 views • 1 year ago

Have a look at this impressive transforming robot rig created by Digital Artist Quasar using Maxon's Cinema 4D. More demos here: #cinema4d #c4d #maxon #rigging #3drigging #3drig #animation #3danimation

Have a look at this impressive transforming robot rig created by Digital Artist Quasar using Maxon's Cinema 4D. More demos here: #cinema4d #c4d #maxon #rigging #3drigging #3drig #animation #3danimation

80 LEVEL

351,525 views • 3 years ago

NVIDIA just revealed MotionBricks, a new AI model trained on more than 350,000 motion clips. What’s really impressive is that the same model can animate a digital character and control a humanoid robot in the real world.

NVIDIA just revealed MotionBricks, a new AI model trained on more than 350,000 motion clips. What’s really impressive is that the same model can animate a digital character and control a humanoid robot in the real world.

Justin Ryan

84,954 views • 1 month ago

A new paper by Disney Research introduces a 2-stage technique for motion tracking in physics-based character animation, using a pretrained latent space and RL to control diverse and unseen motions on both virtual and real-world humanoid robots. Paper:

A new paper by Disney Research introduces a 2-stage technique for motion tracking in physics-based character animation, using a pretrained latent space and RL to control diverse and unseen motions on both virtual and real-world humanoid robots. Paper:

The Humanoid Hub

20,088 views • 2 years ago

Boston Dynamics taught Atlas a Rabona kick. Learned from human mocap, retargeted to Atlas, trained in sim via RL, deployed zero-shot to the real robot. Soccer skills demand whole-body coordination, and similar recipe transfers to warehouse work.

Boston Dynamics taught Atlas a Rabona kick. Learned from human mocap, retargeted to Atlas, trained in sim via RL, deployed zero-shot to the real robot. Soccer skills demand whole-body coordination, and similar recipe transfers to warehouse work.

The Humanoid Hub

11,268 views • 3 months ago

Disney Research shared a new look at the Olaf animated character, included a closer look at the inner workings of the robot, walk cycle, impact reductions, and how they track the character's performance.

Disney Research shared a new look at the Olaf animated character, included a closer look at the inner workings of the robot, walk cycle, impact reductions, and how they track the character's performance.

Scott Gustin

226,232 views • 8 months ago

A robot reportedly went out of control at the 2026 World Robot Conference in Beijing after losing its remote connection, thrashing on the floor as operators struggled to shut it down. The incident has raised fresh concerns about robot safety and the need for reliable emergency control systems. Video Credit : MarioNwafal // X

A robot reportedly went out of control at the 2026 World Robot Conference in Beijing after losing its remote connection, thrashing on the floor as operators struggled to shut it down. The incident has raised fresh concerns about robot safety and the need for reliable emergency control systems. Video Credit : MarioNwafal // X

Vanguard Newspapers

110,283 views • 15 days ago

WOOOO! Robot models trained on 1 Sourccey robot now work (mostly 😂) on other robots! Took a lot of effort to get this working

WOOOO! Robot models trained on 1 Sourccey robot now work (mostly 😂) on other robots! Took a lot of effort to get this working

Nick Maselli

21,112 views • 6 months ago

Robot-free demos can be collected through our VR interface, inspected, trained, and evaluated in a closed loop. Cool thing is that a small amount of real-robot data mixed with large-scale robot-free data can reach comparable performance, while reducing real-robot data needs by up to 20x. Code: Paper:

Robot-free demos can be collected through our VR interface, inspected, trained, and evaluated in a closed loop. Cool thing is that a small amount of real-robot data mixed with large-scale robot-free data can reach comparable performance, while reducing real-robot data needs by up to 20x. Code: Paper:

X Square Robot

175,588 views • 2 months ago

We spotted a celebrity at Disney Springs, playing the piano, of course!

We spotted a celebrity at Disney Springs, playing the piano, of course!

WDW News Today

51,750 views • 1 year ago

Physical Intelligence's π₀, a general-purpose robot foundation model that combines Internet-scale vision-language pretraining with robot interaction data to execute tasks. They aim "to develop foundation models that can control any robot to perform any task" Autonomous demos:

Physical Intelligence's π₀, a general-purpose robot foundation model that combines Internet-scale vision-language pretraining with robot interaction data to execute tasks. They aim "to develop foundation models that can control any robot to perform any task" Autonomous demos:

The Humanoid Hub

196,055 views • 1 year ago

After flying swords, Dude and team made a remote control robot... or the arm of a robot😂 I think the inventions from China civilian douyin sector is enough to take back Taiwan...

After flying swords, Dude and team made a remote control robot... or the arm of a robot😂 I think the inventions from China civilian douyin sector is enough to take back Taiwan...

❌️

429,700 views • 5 months ago