Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

@DisneyResearch introduces their new robot at #IROS2023! Trained in simulation with #reinforcementlearning! ieeeIROS

davsca1's profile picture

Davide Scaramuzza

18,764 subscribers

1,314,035 görüntüleme • 2 yıl önce •via X (Twitter)

Bilim & TeknolojiEğitim#IROS2023#reinforcementlearning
LIVE

Anya Rossi• Live Now

Private livecam show

10 Yorum

Serial experiments Luna profil fotoğrafı
Serial experiments Luna2 yıl önce

@DisneyResearch @ieeeiros They built BD-1 for real.

ashley 🔜 Megacon Orlando 2025! profil fotoğrafı
ashley 🔜 Megacon Orlando 2025!2 yıl önce

@DisneyResearch @ieeeiros PLEASE BD1 IM BEGGING

Ace Velasquez profil fotoğrafı
Ace Velasquez2 yıl önce

@DisneyResearch @ieeeiros BD1?! #CalKestis

Witchbearer profil fotoğrafı
Witchbearer2 yıl önce

@DisneyResearch @ieeeiros That is literally BD-1.

Eric Jang profil fotoğrafı
Eric Jang2 yıl önce

@DisneyResearch @ieeeiros very cool! is that a person driving it with a joystick behind the robot?

Sid Uppal profil fotoğrafı
Sid Uppal2 yıl önce

@DisneyResearch @ieeeiros Where’s the stripe preorder link?

⛓️ FetteredRat🐀⛓️ profil fotoğrafı
⛓️ FetteredRat🐀⛓️2 yıl önce

@DisneyResearch @ieeeiros I must know what motors they're using *,..,* That's still steppers right? Planetary gears? Seems a bit too quick for belts. Their simulated mass must have been spot on, its so dam stable. Also did Disney just accidentally become a defense contractor?

corscorpii profil fotoğrafı
corscorpii2 yıl önce

@y_nakajima_ @DisneyResearch @ieeeiros

ソノヤマ・タカスケ profil fotoğrafı
ソノヤマ・タカスケ2 yıl önce

@DisneyResearch @ieeeiros Awesome!! I think this robot has the potential to create new positive interactions with humans. I'd like to design the personal robot like this.

Mortisdeum_lost profil fotoğrafı
Mortisdeum_lost2 yıl önce

@mwins_in_caps @DisneyResearch @ieeeiros How long till we get this?

Benzer Videolar

A Roboticist’s Dream World at #IROS2023 🤩🤖🦿
0:39

A Roboticist’s Dream World at #IROS2023 🤩🤖🦿

ieeeIROS

46,123 görüntüleme • 2 yıl önce

Boston Dynamics collaborated with NVIDIA to demonstrate DextrAH-RGB, a workflow for dexterous grasping from stereo RGB input. The end-to-end policy for Atlas robot, trained entirely in NVIDIA Isaac Lab, transfers zero-shot from simulation to the real robot.
2:01

Boston Dynamics collaborated with NVIDIA to demonstrate DextrAH-RGB, a workflow for dexterous grasping from stereo RGB input. The end-to-end policy for Atlas robot, trained entirely in NVIDIA Isaac Lab, transfers zero-shot from simulation to the real robot.

The Humanoid Hub

79,743 görüntüleme • 1 yıl önce

I placed 🥈 2nd in the LeHome Challenge (at IEEE ICRA 2026) earlier this month, and before that I was 🥇 1st of 62 teams in the simulation round. Now I am sharing my solution — with a detailed logic walkthrough and open-source code. The task was to teach a cheap two-armed robot to fold different garments in simulation and on a real robot. I trained a VLA policy with an RL loop to make it work. Let's break it down 👇
0:33

I placed 🥈 2nd in the LeHome Challenge (at IEEE ICRA 2026) earlier this month, and before that I was 🥇 1st of 62 teams in the simulation round. Now I am sharing my solution — with a detailed logic walkthrough and open-source code. The task was to teach a cheap two-armed robot to fold different garments in simulation and on a real robot. I trained a VLA policy with an RL loop to make it work. Let's break it down 👇

Ilia

21,948 görüntüleme • 2 ay önce

This driving simulation station built with a Kuka industrial robot [video:
1:05

This driving simulation station built with a Kuka industrial robot [video:

Massimo

1,117,607 görüntüleme • 3 yıl önce

Qwen-VLA feels like one of the first real robotics foundation models. A single system trained across robot manipulation, navigation, egocentric human video, simulation, and vision-language reasoning instead of isolated robot policies.
2:52

Qwen-VLA feels like one of the first real robotics foundation models. A single system trained across robot manipulation, navigation, egocentric human video, simulation, and vision-language reasoning instead of isolated robot policies.

Robots Digest 🤖

14,722 görüntüleme • 3 ay önce

I have designed, built, trained and programmed Bipedal Robot. I call it Swiss Bipedal Robot. More details in my new YouTube video: #skyentific NVIDIA Robotics
0:27

I have designed, built, trained and programmed Bipedal Robot. I call it Swiss Bipedal Robot. More details in my new YouTube video: #skyentific NVIDIA Robotics

Skyentific

52,386 görüntüleme • 6 ay önce

NVIDIA’s new robot looks like CGI...but nope, it’s real. Congrats, the simulation just got physically uploaded.
2:05

NVIDIA’s new robot looks like CGI...but nope, it’s real. Congrats, the simulation just got physically uploaded.

Mario Nawfal

2,485,516 görüntüleme • 1 yıl önce

#puffco introduces their new device. The Pivot Thoughts?
1:06

#puffco introduces their new device. The Pivot Thoughts?

LMC

164,531 görüntüleme • 1 yıl önce

The coolest part of Microduck might not be the robot. It's how it learns to move. This repo shows the full reinforcement learning pipeline behind Microduck. The robot learns in simulation using MuJoCo, PPO and GPU-based training, then the trained policy is exported to ONNX and deployed on the real robot. But the real challenge is sim-to-real. The simulation models things like actuator behavior, battery voltage, command delays, friction and even gear backlash. That helps make the learned policy work when it moves from simulation to the physical robot. The repo includes policies for walking, fall recovery, sitting, standing, kicking, ground picking and even roller skating. Train in simulation. Test the behavior. Export the policy. Run it on a real robot.
1:01

The coolest part of Microduck might not be the robot. It's how it learns to move. This repo shows the full reinforcement learning pipeline behind Microduck. The robot learns in simulation using MuJoCo, PPO and GPU-based training, then the trained policy is exported to ONNX and deployed on the real robot. But the real challenge is sim-to-real. The simulation models things like actuator behavior, battery voltage, command delays, friction and even gear backlash. That helps make the learned policy work when it moves from simulation to the physical robot. The repo includes policies for walking, fall recovery, sitting, standing, kicking, ground picking and even roller skating. Train in simulation. Test the behavior. Export the policy. Run it on a real robot.

Praveen Kumar Verma

136,567 görüntüleme • 17 gün önce

Swaying and bouncing, robot dogs stole the show with their dance performance at an exhibition in Beijing.
0:33

Swaying and bouncing, robot dogs stole the show with their dance performance at an exhibition in Beijing.

People's Daily, China

10,796 görüntüleme • 7 ay önce

.Sakura Rabbit 樱花兔 explores tension simulation of nylon in their new Unity project.
0:21

.Sakura Rabbit 樱花兔 explores tension simulation of nylon in their new Unity project.

80 LEVEL

32,811 görüntüleme • 26 gün önce

Watch rain sliding down a MetaHuman face in Keonyong Moon's new simulation made with Unreal Engine 5. Niagara at its best:
0:26

Watch rain sliding down a MetaHuman face in Keonyong Moon's new simulation made with Unreal Engine 5. Niagara at its best:

80 LEVEL

55,795 görüntüleme • 1 yıl önce

More than 200 companies showcase their latest innovations at the World Robot Conference in Beijing, China. Al Jazeera’s Katrina Yu comes face-to-face with the latest in robot technology.
1:59

More than 200 companies showcase their latest innovations at the World Robot Conference in Beijing, China. Al Jazeera’s Katrina Yu comes face-to-face with the latest in robot technology.

Al Jazeera English

28,818 görüntüleme • 1 yıl önce

Real → Sim → Robot — fast. With Gaussian splats, GRID brings physical assets into simulation tools like AirGen and NVIDIA Isaac Sim, enabling AI skills to be tested in sim and deployed to real robots in minutes. #Robotics #PhysicalAI #Simulation
0:58

Real → Sim → Robot — fast. With Gaussian splats, GRID brings physical assets into simulation tools like AirGen and NVIDIA Isaac Sim, enabling AI skills to be tested in sim and deployed to real robots in minutes. #Robotics #PhysicalAI #Simulation

General Robotics

12,257 görüntüleme • 1 yıl önce

The Queen Need new drones , step in to the simulation with me
0:44

The Queen Need new drones , step in to the simulation with me

Queen Of The North

20,591 görüntüleme • 1 ay önce

Spotted at #NeurIPS2023: Disney Research demos a RL-trained remote control robot! Super impressive work!
0:36

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

Tanishq Mathew Abraham, Ph.D.

169,970 görüntüleme • 2 yıl önce

Prophet Kanyari introduces his children to their new mum - Marion Naipei.
2:42

Prophet Kanyari introduces his children to their new mum - Marion Naipei.

Ⓝⓖ'ⓞⓡⓞⓡⓘⓔⓣ🐐🇰🇪

28,964 görüntüleme • 7 ay önce