Amazon Technologies, Inc.

Vishnu R Ayyagari

Aayush Aggarwal

James Plumley

Matthew Paul Bell

Sarfraz Banglawala

Amanda Adkins

Sidney Yu-Heng Ng

Aspects described herein include a computer-implemented method of generating a floor plan for use by a plurality of mobile drive units within an inventory system. The method comprises defining a grid according to predefined grid rules, placing inventory station blocks, placing predefined travel blocks, and placing predefined storage blocks. Predefined connection rules specify which faces of the different predefined blocks are permitted to connect. The method further comprises outputting a map representing the floor plan. The map comprises location information for fiducial markers corresponding to the predefined blocks.

Structured field map generation for inventory system

Aspects of augmented reality (AR)-based facility mapping are described. In some examples, an AR device detects optical data using an optical device, and position data using a position detection device. An AR-based modification user interface is displayed using the AR device. The AR-based modification user interface includes an AR map and an AR object. The AR-based modification user interface is generated using the facility data and the sensor data. The AR-based modification user interface identifies a user action that modifies the AR object.

Augmented-reality-based facility semantic mapping

Systems and methods are provided herein for obstacle detection and avoidance. An obstacle (e.g., a fallen object, an area of congestion, etc.) may be detected utilizing sensor data and/or navigational information provided by various components of a workspace (e.g., mobile drive units, standalone sensors, etc.). Obstacle information corresponding to the obstacle may be utilized to identify tasks within the workspace that may be affected by the obstacle. Paths for these affected tasks may be altered and any subsequent path generated by the system may be generated based at least in part on the obstacle, so long as the obstacle exists. Utilizing the techniques provided herein, the workflows/tasks/paths of the components of the system may be managed so as to avoid interactions between the components of the system and any known obstacle.

Techniques for obstacle detection and avoidance

Systems and methods are provided herein for detecting congestion within a workspace. Historical navigational data may be obtained that indicates a number of locations for mobile drive units of the workspace over various historical time periods. Planned path data for each MDU may be obtained, the planned path data may indicate planned paths of travel for each MDU. A grid of overlapping volumes may be generated for the workspace and each instance of historical navigational data and/or planned path data may be utilized to map historical and/or future locations of the MDUs to corresponding volumes of the grid. A protocol set may be implemented to detect congested volumes based at least in part on the historical navigational data and/or the planned path data for each volume of the grid over one or more time periods. In response to detecting a congested volume, one or more remedial actions may be performed.

Techniques for detecting and managing congestion within a workspace

Systems and methods described herein pertain to maintaining a virtual representation of a workspace in a material handling system and updating the virtual representation. Methods described include maintaining the virtual representation of a material handling grid, maintaining one or more clients operable to direct movement of the plurality of drive units in the workspace; receiving an instruction to update the virtual representation of the drive-unit navigable grid including an updated virtual representation of the workspace; and querying a subset of the one or more clients to determine whether the update to the virtual representation would cause one conflicts within the workspace. Potential conflicts include, but are not limited to, 'stranded' resources which are no longer positioned on the material handling grid, and/or workstations that have not yet been suspended prior to the update. Methods further include, upon determining that the updated virtual representation would not cause a conflict, deploying the updated virtual representation to replace an existing virtual representation of the workspace.

Rapid workspace representation deployment for inventory systems

Methods and related systems employ an unmanned fiducial marker application unit to deploy new fiducial markers to a floor of a material handling facility, such as an inventory facility. A system for managing inventory items includes an unmanned fiducial marker application unit, initial fiducial markers distributed in a pattern on a floor of an inventory facility, at least one tangible memory device, and at least one processor configured to receive new fiducial marker data indicative of a location for each of one or more new fiducial markers to be applied to the floor and instruct the unmanned fiducial marker application unit to apply at least one of the one or more new fiducial markers to the floor in accordance with the new fiducial marker data.

Growing community of inventors

Boxboro, MA, United States of America

Vishnu R Ayyagari