Amazon Technologies, Inc.

Kun Qian

Gopi Prashanth Gopal

Navid Shiee

Ohil Krishnamurthy Manyam

Ramanathan Palaniappan

Connor Spencer Blue Worley

Jack G Song

Dilip Kumar

Sridhar Boyapati

Steven Augustine Wilson

Wyatt David Camp

Justin Joel Krohn

An inventory location, such as a shelf, may be used to stow different types of items in different areas of the shelf. Interactions may take place, such as the pick or place of items from the shelf. Weight data acquired from weight sensors at the shelf may be used to generate a set of hypotheses to describe types and quantities of items added to or removed from the shelf during an interaction. One or more of these hypotheses may be eliminated from consideration or selected as a solution based on activity data related to the shelf. The activity data is based on non-weight data from a non-weight sensor associated with the shelf. As an example, image data from a camera directed to the shelf can help identify presence of a user or a change in appearance at an area of the shelf to help evaluate hypotheses.

Evaluation of weight hypotheses using non-weight data

An inventory location such as a shelf may be used to stow different types of items. Interactions may take place, such as the pick or place of one or more items from the inventory location. Weight data may be acquired from weight sensors coupled to the shelf. A measured change in weight is used to determine a first group of hypotheses. Each of the hypotheses may be descriptive of a different permutation of products being added to or removed from the shelf that could account for the measured change in weight. The weight data is also processed to determine a weight distribution of the items on the shelf. Information about the weight distribution may be used to select a subset of the first group of hypotheses. The subset may be used to determine what items were interacted with, quantity involved, and so forth.

Item determination based on weight data

Described are systems for processing sensor data associated with an inventory location for the purpose of identifying stable and unstable states in the sensor data. The stable and unstable states can be determined by fitting a line or curve to a portion of the sensor data occurring during a window of time and calculating a corresponding slope value of the line or curve. By comparing the slope value of the line or curve to a threshold value, stable and unstable states can be determined for the sensor data. Once stable states have been identified, a change in sensor data can be determined and used to identify a change in quantity of items at the inventory location.

Sensor data processing for detection of changes in item quantities

Described are systems for processing sensor data obtained from a sensor such as a weight sensor. In one implementation, a line may be fit to a set of sensor data occurring during a window of time. A slope value of the line may be calculated and provided as input to a change detector. The change detector may implement a cumulative sum (CUSUM) algorithm to determine when the slope value is indicative of a stable or unstable state. Values of sensor data associated with times indicated as having a stable state may be used to determine weight data.

Sensor data processing system

This disclosure describes the establishment, use and adjustment of timeout durations for individual RFID tags. Each RFID tag within an inventory system has a timeout duration that is based at least in part on a time duration between receipts of a RFID tag identifier associated with the RFID tag.

Growing community of inventors

Seattle, WA, United States of America

Kun Qian