Teaching our open humanoid @ROBOTIS AI Sapiens to dance! 🤖💃
We extracted 3D motion from raw 2D video (no MoCap device!) and trained it in NVIDIA Isaac Sim. Thanks to high-precision DYNAMIXEL-Q, we achieved an ultra-low Sim2Real gap for fluid movement!
- Video:
From its launch in 2017 to today, TurtleBot3 has continued to grow as an open, modular platform for ROS education, research, and prototyping.
TurtleBot3 Burger keeps that idea compact: Raspberry Pi 4, SLAM, navigation, simulation, and endless ways to build beyond with TurtleBot3
More information about DYNAMIXEL-Q will be uploaded to robotis.us/dynamixel-q/ as it becomes available.
As a reminder, the e-Manual has moved to docs.robotis.com
ROBOTIS DYNAMIXEL-Q is designed to support the next generation of humanoid robotics development in conjunction with next level tools like NVIDIA Isaac Sim™.
Watch how simulation-driven workflows and high-performance actuation merge to develop a humanoid robot capable of walking
Physical AI needs repeatable motion, real feedback, and hardware you can iterate on.
From data collection to real-world deployment, X-Series helps engineers close the loop between AI models and physical motion.
Check out the X-Series today: robotis.us/x-series/
The ROBOTIS Hand HX5-D20 is built around XM335-T323-T DYNAMIXEL actuators, giving each finger compact, direct-drive joint control for dexterous manipulation.
20 DOF. 5 fingers. 4 DOF per finger. 14 Max Finger Tip Force.
#ROBOTIS#DYNAMIXEL#RobotHand#Robotics
This demo shows AI Worker running in NVIDIA Isaac Sim, using VR to control the robot arm and a keyboard to drive the mobile base.
The DDS SDK Bridge connects ROS 2 commands to AI Worker, making it possible to test pick-and-place and mobile manipulation tasks in virtual table and
Researchers from @AxLab_UChicago have developed an Arduino MKR WiFi 1010-controlled system that bends pop tubes into 3D curves and shapes on demand. Introducing the PopTuber!