Pollen Robotics Released Microduck Bipedal Robot
The new open-source bipedal robot is designed to bridge the gap between simulation and real-world hardware.
Updated on Oct. 2, 2026 in Robotics

Live Poll
Do you prefer technology designed for industrial utility over devices with personalities or playful features?
Pollen Robotics has launched Microduck, a small-scale bipedal robot designed to lower the costs and risks of training physical artificial intelligence. The platform allows developers to train behaviors in simulations before deploying them to the physical hardware.
Why it matters
Microduck aims to solve the technical divide between computer simulations and real-world robotics. By using this platform, researchers can avoid the high risks and expenses typically associated with training large humanoid machines.
Microduck stands 25 centimetres tall and weighs 780 grams. The hardware includes 15 individual motors, a front-facing camera, LiDAR, and dual inertial measurement units to manage movement via a 50 Hz control loop.
The players
Pollen Robotics
This is a robotics company that focuses on developing open-source hardware and software platforms.
GitHub
This is a widely used software hosting platform that facilitates code collaboration and version control for developers.
Hugging Face
This is a technology platform that hosts machine learning models and datasets for the open-source community.
The details
The robot comes with seven pre-trained behaviors and an integrated self-recovery routine for when it falls. Developers can access the full software stack on GitHub and Hugging Face to iterate on their own motion designs.
Timeline
The official article describing the Microduck robot was published on October 2, 2026.
The Tech Race
The introduction of Microduck signals a strategic shift toward miniaturized, low-cost robotics research rather than massive, high-risk hardware development. This approach replaces the reliance on expensive, full-sized systems with accessible platforms that mirror the capabilities of larger robots.
Developers and researchers can utilize the open-source code to experiment with robotics without needing specialized lab equipment. This makes complex motion training significantly more accessible for hobbyists and smaller academic groups.
The takeaway
Microduck demonstrates that advanced bipedal locomotion can be studied on a compact, affordable scale. By lowering the barrier to entry, it invites broader innovation in how artificial intelligence interacts with the physical world.
Further reading
For more developments in this field, explore our latest updates on Robotics.
Source note: This article includes information reported by LAFM.
Live Poll
Do you prefer technology designed for industrial utility over devices with personalities or playful features?







