Abstract: A layer pick system optimizes usage of a layer picker gantry or robotic arm by arranging and/or displacing the gantry or arm in optimal locations with respect to one or more groups of pallets, and/or by grouping pallets by their attributes and arranging the same group of pallets close to each other. In some implementations, a plurality of pallets is categorized into multiple groups by different velocities.

Abstract: Systems, methods, devices, and other techniques for heating a lens to mitigate fogging. The methods can include identifying a temperature of the lens, identifying an ambient temperature of an environment of the lens, determining whether the lens is susceptible to fogging based at least on the temperature of the lens and the ambient temperature of the environment of the lens, and in response to determining that the lens is susceptible to fogging, causing a heating element to apply heat to the lens to mitigate fogging of the lens.

Abstract: A system is provided for automatic identification and annotation of objects in a point cloud in real time. The system can automatically annotate a point cloud that identifies coordinates of objects in three-dimensional space while data is being collected for the point cloud. The system can train models of physical objects based on training data, and apply the models to point clouds that are generated by various point cloud generating devices to annotate the points in the point clouds with object identifiers. The solution of automatically annotated point cloud can be used for various applications, such as blueprints, map navigation, and determination of robotic movement in a warehouse.

Abstract: This specification describes systems and methods for refining point cloud data. Methods can include receiving point cloud data for a physical space, iteratively selecting points along an x, y, and z dimension, clustering the selected points into 2D histograms, determining a slope value for each 2D histogram, and removing, based on the slope value exceeding a predetermined value, points from the point cloud data. Methods can also include iteratively voxelizing each 2D histogram into predetermined mesh sizes, summating points in each voxelized 2D histogram, removing, based on determining the summation is below a predetermined sum value, points from the point cloud data, keeping, based on determining that a number of points in each voxelized 2D histogram exceeds a threshold value, a center point, selecting, for each histogram, a point, identifying, nearest neighbors in the point cloud data, removing the identified nearest neighbors from the data, and returning remaining points.

Abstract: A layer pick system optimizes usage of a layer picker gantry or robotic arm by arranging and/or displacing the gantry or arm in optimal locations with respect to one or more groups of pallets, and/or by grouping pallets by their attributes and arranging the same group of pallets close to each other. In some implementations, a plurality of pallets is categorized into multiple groups by different velocities.

Abstract: This specification describes systems and methods for generating a mapping of a physical space from point cloud data for the physical space. The methods can include receiving the point cloud data for the physical space, filtering the point cloud data to, at least, remove sparse points from the point cloud data, aligning the point cloud data along x, y, and z dimensions that correspond to an orientation of the physical space, and classifying the points in the point cloud data as corresponding to one or more types of physical surfaces. The methods can also include identifying specific physical structures in the physical space based, at least in part, on classifications for the points in the point cloud data, and generating the mapping of the physical space to identify the specific physical structures and corresponding contours for the specific physical structures within the orientation of the physical space.

Abstract: In general, one aspect of the subject matter described in this specification can be embodied in an anti-fogging apparatus for a camera assembly. The anti-fogging apparatus includes a camera affixed to a substrate, and a thermally conductive plate, the thermally conductive plate positioned in front of the substrate and defining a first aperture aligned with a lens of the camera. The anti-fogging apparatus includes a transparent plate positioned in front of the thermally conductive plate such that the transparent plate covers said first aperture. The anti-fogging apparatus includes an insulating element positioned in front of the transparent plate and defining a second aperture aligned with the first aperture. The anti-fogging apparatus includes a heating element affixed to the thermally conductive plate. The anti-fogging apparatus includes a case enclosing the camera, the thermally conductive plate, the transparent plate, the insulating element, and the heating element.

Abstract: A metal detector that uses a verity of sensors as input for a neural network to optimize discrimination and detection of known or unknown objects. The detector will also have employ an user defined frequencies that will help to create custom settings. The detector will be able to use the sweeping motion of the detector head to create many frames of reference for understanding the composition, depth, size, type, approximant length of time it had remained, and to some extent orientation of known/unknown objects. This will be fed back to a user who can help identify the object once it is found. If it is different or new, the user can enter what it was into a database that can be used to train signals for future use, such as through using the data for training and/or updating machine learning models which can be used to accurately identify object.

Abstract: An image sensing assembly includes an enclosure that defines a first viewport aperture in a front wall of the enclosure. The image sensing assembly includes a first image sensor attached within the enclosure, the first image sensor aligned with the first viewport aperture in the front wall of the enclosure to capture image data representative of a scene viewed through the first viewport aperture. The image sensing assembly includes a bracket attached to the enclosure at a first portion of the bracket and attached to a first mounting plate at a second portion of the bracket. The image sensing assembly includes a vibration dampening mount located between the bracket and the first mounting plate to at least partially isolate the enclosure from vibration of the first mounting plate.

Abstract: This specification describes systems and methods for refining point cloud data. Methods can include receiving point cloud data for a physical space, iteratively selecting points along an x, y, and z dimension, clustering the selected points into 2D histograms, determining a slope value for each 2D histogram, and removing, based on the slope value exceeding a predetermined value, points from the point cloud data. Methods can also include iteratively voxelizing each 2D histogram into predetermined mesh sizes, summating points in each voxelized 2D histogram, removing, based on determining the summation is below a predetermined sum value, points from the point cloud data, keeping, based on determining that a number of points in each voxelized 2D histogram exceeds a threshold value, a center point, selecting, for each histogram, a point, identifying, nearest neighbors in the point cloud data, removing the identified nearest neighbors from the data, and returning remaining points.

Abstract: An image sensing assembly includes an enclosure that defines a first viewport aperture in a front wall of the enclosure. The image sensing assembly includes a first image sensor attached within the enclosure, the first image sensor aligned with the first viewport aperture in the front wall of the enclosure to capture image data representative of a scene viewed through the first viewport aperture. The image sensing assembly includes a bracket attached to the enclosure at a first portion of the bracket and attached to a first mounting plate at a second portion of the bracket. The image sensing assembly includes a vibration dampening mount located between the bracket and the first mounting plate to at least partially isolate the enclosure from vibration of the first mounting plate.

Abstract: An image sensing assembly includes an enclosure that defines a first viewport aperture in a front wall of the enclosure. The image sensing assembly includes a first image sensor attached within the enclosure, the first image sensor aligned with the first viewport aperture in the front wall of the enclosure to capture image data representative of a scene viewed through the first viewport aperture. The image sensing assembly includes a bracket attached to the enclosure at a first portion of the bracket and attached to a first mounting plate at a second portion of the bracket. The image sensing assembly includes a vibration dampening mount located between the bracket and the first mounting plate to at least partially isolate the enclosure from vibration of the first mounting plate.

Abstract: A system is provided for automatic identification and annotation of objects in a point cloud in real time. The system can automatically annotate a point cloud that identifies coordinates of objects in three-dimensional space while data is being collected for the point cloud. The system can train models of physical objects based on training data, and apply the models to point clouds that are generated by various point cloud generating devices to annotate the points in the point clouds with object identifiers. The solution of automatically annotated point cloud can be used for various applications, such as blueprints, map navigation, and determination of robotic movement in a warehouse.

Abstract: In general, one aspect of the subject matter described in this specification can be embodied in an anti-fogging apparatus for a camera assembly. The anti-fogging apparatus includes a camera affixed to a substrate, and a thermally conductive plate, the thermally conductive plate positioned in front of the substrate and defining a first aperture aligned with a lens of the camera. The anti-fogging apparatus includes a transparent plate positioned in front of the thermally conductive plate such that the transparent plate covers said first aperture. The anti-fogging apparatus includes an insulating element positioned in front of the transparent plate and defining a second aperture aligned with the first aperture. The anti-fogging apparatus includes a heating element affixed to the thermally conductive plate. The anti-fogging apparatus includes a case enclosing the camera, the thermally conductive plate, the transparent plate, the insulating element, and the heating element.

Abstract: In one implementation, a system for controlling defrost of a chilled environment includes a camera configured to capture images of one or more objects located in the chilled environment and a defrost control unit. The defrost control unit is configured to: receive an image of the one or more objects from the camera, analyze the image of the one or more objects to quantify an amount of frost formation on the one or more objects, determine when to initiate a defrost cycle in the chilled environment based on the amount of frost formation on the one or more objects, and in response to determining to initiate the defrost cycle, initiating the defrost cycle by sending a defrost control signal to a defroster. The defroster is configured to perform the defrost cycle within the chilled environment in response to receiving the defrost control signal.

Abstract: This specification generally discloses technology for tracking vehicle positions in a warehouse environment. A system receives stereoscopic image data from a camera on a forklift, in some implementations. The system recognizes an object that is represented in the stereoscopic image data, identifies a representation of the recognized object in a spatial model that identifies, for each of a plurality of objects in an environment, a corresponding location of the object in the environment, determines the location of the recognized object in the environment, determines a relative position between the forklift and the recognized object, based on a portion of the received stereoscopic image data that represents the recognized object, and determines a location of the forklift in the environment, based on the determined location of the recognized object in the environment, and the determined relative position between the forklift and the recognized object.

Abstract: A layer pick system optimizes usage of a layer picker gantry or robotic arm by arranging and/or displacing the gantry or arm in optimal locations with respect to one or more groups of pallets, and/or by grouping pallets by their attributes and arranging the same group of pallets close to each other. In some implementations, a plurality of pallets is categorized into multiple groups by different velocities.

Abstract: An automated warehouse system can include automated pallet movers, a physical space in which the automated pallet movers operate, and a control system to provide commands to each of the automated pallet movers for operating in the physical space. The commands can include a pallet transportation command including a pallet identifier of a pallet to be transported by the automated pallet mover in the physical space, and a destination location to which the pallet is to be transported by the automated pallet mover. The commands can also include a control algorithm command that specifies a control algorithm for moving through the physical space. The automated pallet mover can be configured to transport the pallet to the destination location according to a route resulting from performance of the control algorithm, while other automated pallet movers concurrently transport other pallets to other destination locations.

Abstract: In one implementation, a system for controlling defrost of a chilled environment includes a camera configured to capture images of one or more objects located in the chilled environment and a defrost control unit. The defrost control unit is configured to: receive an image of the one or more objects from the camera, analyze the image of the one or more objects to quantify an amount of frost formation on the one or more objects, determine when to initiate a defrost cycle in the chilled environment based on the amount of frost formation on the one or more objects, and in response to determining to initiate the defrost cycle, initiating the defrost cycle by sending a defrost control signal to a defroster. The defroster is configured to perform the defrost cycle within the chilled environment in response to receiving the defrost control signal.

Abstract: A system for optimizing storage racks in a warehouse that includes a plurality of storage racks that each include one or more horizontal bars that are adjustable along a plurality of elevations on the storage racks, placement of the one or more horizontal bars defining a plurality of rack openings within each storage racks; a historical inventory database that is programmed to store historical inventory data for the warehouse, the historical inventory data identifying pallets stored in the warehouse and times at which the pallets were stored; and a computer system including one or more processors that are programmed to determine a pallet distribution profile for the warehouse, to determine a plurality of rack types and quantity of rack types for the warehouse, and to designate each of the plurality of storage racks as one of the plurality of rack types to generate a rack arrangement for the warehouse.