The SiftAI Robotic Sorter combines a delta robot with an AI-based vision inspection system. Each system is programmed with AI models for overall potato size and shape or presence of defects like bruises, cracks, percent green, and other cosmetic features. Installed over a roller table, the SiftAI cameras collect images of all sides of the potato. For any potatoes that grade outside the AI model's acceptance criteria, the system triggers the robotic arm to pick up and remove the potato from the product stream at rates between 80-100 picks per minute with two-robot system configurations. The SiftAI Robotic Sorter inspects potatoes with the same dexterity and speed as a human inspector but with much higher accuracy that increases profitability and reduces customer chargebacks.
Currently, the industry goal is to have no more than 5% of defective potatoes reaching customers, which is the limit set by the US Department of Agriculture. What's more, human inspectors typically discard 10 to 20% of acceptable potatoes, reducing profits. In beta testing, the new AI-enabled robotic sorter dramatically reduced the percentage of missed defects and mis-graded potatoes.
Adding increased profitability to the labour savings, the financial impact of automation is significant. The investment pays for itself in fewer than two years.
"Because of potato oversupply and rising wages in North America, many potato processors are losing money on every box shipped," said Curtis Koelling, vice president of product development and innovation for Smart Vision Works, a KPM Analytics brand. "Managers are eager to identify technology that can lower their production costs," he said. "When they see a competitor managing final inspection without labour costs, they become very interested in the technology."
