Skip to content
Main Site News Console

Simulation Training and Real-World Deployment: Microduck Based on Isaac Lab 3.0

· Hugging Face Translated
教程模型卡

Published on October 21, 2026

Image 2: Oluwaseun Doherty's avatar Oluwaseun Doherty seun-doherty Follow Image 3: NVIDIA's avatarnvidia

Image 4: Oyindamola Omotuyi's avatar Oyindamola Omotuyi OOyindamola Follow Image 5: NVIDIA's avatarnvidia

Image 6: Richard's avatar Richard AntRi31 Follow Image 7: NVIDIA's avatarnvidia

Image 8: Asier Arranz's avatar Asier Arranz asiernvidia Follow Image 9: NVIDIA's avatarnvidia

Image 10: Cover imageCo-authored with Antoine Pirrone, Augustin Crampette, Matthieu Lapeyre, Coralie Deplanne, Anne-Charlotte Passanisi, and Thomas Wolf.

TL;DR

Microduck is an affordable, open-source bipedal robot developed by Pollen Robotics in collaboration with Hugging Face. You can now train Microduck to walk using Isaac Lab and Newton. Test your policies, export them to ONNX, and deploy them directly onto physical hardware. Share your policies on the Hugging Face Hub, benchmark them in the Microduck Arena, and scale up to more advanced tasks with NVIDIA Isaac Lab.

Introduction

Walking policies trained in simulation must be robust enough to handle actuator friction, communication latency, and mechanical backlash on physical robots. NVIDIA Isaac Lab is an open-source framework designed to train policies across thousands of GPU-parallelized simulation environments. Powered by Newton, actuator modeling, and domain randomization, it prepares policies for real hardware. Microduck brings this workflow to…