Robust Grasping

Picking objects out of clutter is where we excel at. We create robotic systems that can pick out of a jumbled mess of objects from standard warehouse totes and into cardboard boxes. Repeatedly. Reliably.

Pick and Place Robots

Our robotic systems aim to be robust in a large variety of scenarios. Thanks to our modular design we can design, test and improve on new capabilities quickly.

Reliable Integration

We create systems that are robust and reliable thanks to a tight integration of perception, action and learning. Our robots can operate autonomous in a variety of dynamic and challenging environments.

Fast Learning

Our deep neural network based system for visual detection is able to deal with adding a dozen of new objects in just under half an hour of training. See how we used it to win the Amazon Robotics Challenge, a worldwide competition to automate order picking and object stowing!

Warehousing

Tasks such as:
  • Order Picking
  • Restocking
  • Unboxing
  • and many more...
Contact us
to learn more

Agriculture

Tasks such as:
  • Fruit Picking
  • Quality Inspection
  • Sorting and Packing
  • and many more...
Contact us
to learn more
Our founders

How it started

From creating robots that see
to robots that do!

LYRO is building on the research the team developed in the Australian Centre for Robotic Vision (ACRV). It was spun out after the 2017 win of the Amazon Robotics Challenge by Team ACRV.

Amazon’s New Robo-Picker Champion Is Proudly Inhuman
It only needs to see seven images of a new object before it can reliably spot and grab it.
MIT TechReview Article