Smart shelf system that integrates images and quantity sensors

US10586208B2 · kind B2 · utility

Assignee

• ACCEL ROBOTICS CORPORATION · US

Inventors

• Marius Buibas · San Diego, US
• John Quinn · Loomis, US
• Kaylee Feigum · San Diego, US
• Csaba Petre · San Diego, US
• Filip Piekniewski · San Diego, US
• Aleksander BAPST · San Diego, US
• Soheyl YOUSEFISAHI · San Diego, US
• Chin-Chang Kuo · Taipei, TW

Key dates

• Filing date: Jul 16, 2019
• Grant date: Mar 10, 2020
• Expiry date: Jul 16, 2039

Classification

• Technology area (CPC G): Physics
• CPC primary: G06T2210/21
• WIPO field: Audio-visual technology
• WIPO sector: Electrical engineering

Abstract

A system that integrates camera images and quantity sensors to determine items taken from, placed on, or moved on a shelf or other area in an autonomous store. The items and actions performed may then be attributed to a shopper near the area. Shelves may be divided into storage zones, such as bins or lanes, and a quantity sensor may measure the item quantity in each zone. Quantity changes indicate that a shopper has taken or placed items in the zone. Distance sensors, such as LIDAR, may be used for shelves that push items towards the front. Strain gauges may be used for bins or hanging rods. Quantity changes may trigger analysis of camera images of the shelf to identify the items taken or replaced. Images from multiple cameras that view a shelf may be projected to a vertical plane at the front of the shelf to simplify analysis.