NVIDIA and Hugging Face Demonstrate Microduck Sim-to-Real Training
NVIDIA and Hugging Face published a walkthrough for training the open-source Microduck bipedal robot with NVIDIA Isaac Lab and Newton, then transferring the learned locomotion policy to physical hardware. The workflow uses AI agents to plan a simulated obstacle course and prepare assets, while Isaac Sim evaluates trained policies on RTX Spark; the demonstrations show Microduck walking and recovering from a fall. Pollen Robotics says the robot stands 25 centimeters tall, weighs under 800 grams and has 15 motors, with preorders priced at $399 before taxes and shipping.
The workflow provides a concrete, reproducible example of reinforcement learning and AI-assisted preparation moving from simulation to a physical robot, although the published demonstrations do not establish real-world repeatability.
Meet Microduck, a tiny robot that can learn to walk in a virtual world before trying those moves in real life. Nvidia and Hugging Face have published a new walkthrough showing how developers can train the duck-shaped robot to walk, handle uneven ground, and recover after falling over.
The Oct. 21 demonstration uses Nvidia’s Isaac Lab and Newton simulation tools. Instead of teaching the robot every movement by hand, developers let simulated versions practice until they develop a walking strategy that can be transferred to physical hardware.
Meet Microduck, the $399 robot with 15 motors
Microduck was developed by Pollen Robotics and Hugging Face. It’s an open-source, two-legged robot designed for students, researchers, and developers experimenting with physical AI.
According to Pollen Robotics, Microduck stands just 25 centimeters tall, weighs less than 800 grams, and has 15 motors.
It also has a camera, depth sensor, two motion sensors, and an articulated beak that can pick up small objects.
#Microduck#NVIDIA#Hugging Face#Pollen Robotics#NVIDIA Isaac Lab#Newton#NVIDIA Isaac Sim#NVIDIA RTX Spark#Nemotron 3.5 Bolt#Hermes#Astra