How it Works
When items are presented to the robot picking station in a pallet, the PickOne Perception Kit images the pallet.
The PickOne software analyses the 2-D, 3-D, and AI data to identify each pickable item in the scene and assigns each one an associated confidence level.
PickOne sends the robot controller an array of pick locations and poses for each pickable item via the PickOne API.
If no items in the scene have a high enough confidence, PickOne generates a Yonder request so that a Crew Chief can handle this exception by simply selecting an item in the scene to be picked.
In seconds, Yonder updates PickOne, and PickOne sends the data to the robot.
In parallel, Yonder stores the Crew Chief’s responses, allowing the machine-learning algorithms to make the system smarter as it works. This ensures even higher performance over time.
01 Key Benefits
- Enhanced operational decision making (with Yonder*)
- Promote associates from mundane tasks to value-added work
- Reduce employee turnover by improving job satisfaction
- Reduce per unit handling cost
- Increase operator safety by removing repetitive stress injury application
- Addresses key edge cases
- Industry-leading pick command processing speed between 250-500 ms
- Typical pick rates achieved: 350-650 cases per hour single pick and 700-1000 cases per hour multi-pick