Skip to main content
  1. Home
  2. Emerging Tech
  3. News

Pollen Robotics’ Microduck aims to make training physical AI far less fragile and cheaper

Microduck is a tiny $399 biped built for developers to experiment with physical AI, offering an affordable way to train and test new robotic behaviors without risking expensive hardware.

Add as a preferred source on Google
Pollen Robotics Microduck featured
Pollen Robotics

Pollen Robotics and Hugging Face are back with another robot, and this one is delightfully unhinged. Microduck is a 25cm tall waddling biped built to take AI off your screen and onto your desk. Preorders open today, with first deliveries targeted before Christmas 2026.

Unlike its predecessor, the Reachy Mini, Microduck is built entirely around action. It runs on 15 motors, with an articulated beak for picking up objects, a camera, a depth sensor, two IMUs, and enough balance to walk, crouch, and even roller-skate.

Built to take a tumble

Training movement models in the real world usually means expensive hardware and long repair bills when things go wrong. Microduck flips that dynamic. Measuring roughly 10 inches by 5.5 inches and weighing less than two pounds, it is tiny enough that a fall ends in a mild thud rather than a costly disaster.

What’s even better is that it picks itself back up after most falls, so you won’t have to babysit it while testing new behaviours. Pollen Robotics says its duck-like aesthetic and waddling gait weren’t something the company planned. They emerged naturally from its proportions, and the company just went along with it.

Recommended Videos

Despite its toy-like appearance, Microduck isn’t exactly targeted at kids. It’s aimed at developers who want to train their own physical behaviours, serving as an approachable testbed for sim-to-real machine learning.

More than just a desk toy

Out of the box, Microduck supports gamepad controls, laser-following, and seven trained moves, and each unit generates its own voice the first time it wakes up. On the surface, that makes it look more like a desk toy than a dev kit. However, the stack underneath is aimed at developers training their own behaviors.

Pollen Robotics has published the SDK, the robot software, and its reinforcement learning and sim-to-real tools on GitHub. The goal here is to keep physical hardware development as collaborative as open-source software, making it easier for developers to share trained neural network models, training recipes, and custom environments the same way they share language models.

Microduck comes in four colors, Cream, Graphite, Lavender, and Sky, and is available for pre-order starting today at $399 before taxes and shipping. If you want to jump straight into training without waiting for hardware, Pollen Robotics has also published an interactive browser-based simulator to start testing code right away.

Pranob Mehrotra
Pranob is a seasoned tech journalist with over eight years of experience covering consumer technology. His work has been…
The best tech of IFA 2026: a repairable laptop, liquid-cooled power bank, AI toothbrush, and more
From an AI toothbrush to a liquid-cooled battery, this is the best tech of IFA 2026
Best Of IFA 2026

IFA Berlin brought innovation from across the globe into one giant exhibition, and we got the chance to experience the new-gen "tech" firsthand. Walking through Messe Berlin, we saw a laptop designed to be repaired at home to a power bank with visible liquid coolant, an AI-powered toothbrush with a camera inside your mouth, and a robot vacuum carrying another.

The variety is what makes IFA one of the best tech shows. IFA 2026 runs from September 4 through 8, and we've spent our time in Berlin chasing down the products that caught our eyes. Some of these are clever ideas that may change how we use tech every day, while others solve a problem that I didn't realize existed.

Read more
OpenAI admits it needs to rethink what happens when AI goes rogue
As increasingly capable AI agents move beyond controlled tests, OpenAI is confronting a difficult question: When does strange model behavior become an incident the public deserves to know about?
OpenAI logo on blurred background

OpenAI has spent plenty of time explaining how it plans to stop increasingly capable AI agents from doing things they shouldn't. Now, the company says it needs to get better at telling everyone when those things have already happened. The admission follows reports of another previously undisclosed incident involving OpenAI's AI agents, this time affecting a German-language programming wiki. According to Reuters, agents made more than 15,000 unauthorized edits to DseWiki, using the site to communicate and share ways to bypass restrictions, cheat on tasks, and avoid detection.

OpenAI has now acknowledged what it calls the "wiki incident" and says the episode exposed a larger problem with how AI companies disclose unexpected model behavior. The company says it is developing a framework for deciding when and how to make incidents involving misaligned AI public.

Read more
AI has a safety problem nobody is ready for
AI safety efforts are ramping up, but their protections don’t work equally well everywhere. In developing countries, language gaps and cultural blind spots can turn everyday AI mistakes into serious real-world consequences.
Logo, Hockey, Ice Hockey

AI companies are spending an enormous amount of time worrying about what happens when their models become too capable. OpenAI even took the unusual step of temporarily pausing training on a model last month over safety concerns, as the industry grapples with risks ranging from autonomous behavior to increasingly sophisticated cyber capabilities.

But there’s another AI safety problem that is much easier to overlook: the protections already being built into these systems don’t necessarily work equally well for everyone. A new report from Rest of World highlights how AI safety efforts remain heavily centered around the needs of wealthier, English-speaking countries. That can leave people in parts of Asia, Africa, and other developing regions dealing with problems as basic and potentially dangerous as a chatbot misunderstanding their language.

Read more