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: An imaging system includes a focal plane array, readout electronics, and a computing system in which the number of active pixels is either set at a low-fraction of the total pixels thereby reducing the effect of radiation damage, or radiation damage over time is detected and automatically compensated. Machine learning is used to identify radiation damaged pixels and damaged regions which are subsequently eliminated and replaced by the computational system. The machine learning is used to identify changes in the fixed pattern signal/noise and/or noise of the system, and is then computationally corrected.

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: 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 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 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 power distributor (200) with at least two incoming lines (101-103) and a method for manufacturing such a power distributor is suggested. Each incoming line comprises a conductor (106,107) and an individual screen (114). The conductors of the incoming lines are connected at a connection point (V1,V2), which is enclosed by a screen shield (201) that contacts each individual screen (114) of the incoming lines. The screen shield (201) is made from electrically conducting plastic material. Screen shields made from electrically conducting plastic material is easier to manufacture and less expensive than metal screen shields.

Abstract: A process for the post-deposition treatment of colloidal quantum dot films to improve photodetector performance. A colloidal quantum dot film is first deposited on a suitable substrate or device structure, given a ligand exchange, and then allowed to dry into a completed film. Next, a solution is prepared consisting of dilute H2O2 mixed with a polar solvent such as isopropyl alcohol solution. The prepared film and substrate are then immersed into the prepared solution over a set interval of time. After which, the film is removed and rinsed with solvent, then dried with clean N2 gas. After this treatment, the colloidal quantum dot film is ready for use as a photodetector.

Abstract: A cable distributor for individual cables that are shielded by an electrically conductive shield. The cable distributor has an electrically insulating outer housing, which receives a connection piece at which at least two individual cables are connected to each another. The shields of the connected individual cables are connected to each other by means of an electrically conductive shield housing, as a result of which a continuous shielding of the current-carrying parts of the cable distributor is achieved. A method for producing such a cable distributor is also proposed.

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: 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: A method of substantially real-time image restoration of an infrared camera includes the steps of: analyzing the last X number of video frames; classifying the last X number of video frames as to the source of noise in the last X number of video frames; selecting a noise suppression transform based on the source of the noise; receiving real time video frames; correcting the real time video frames using the selected noise suppression transform.

Abstract: A hyperspectral infrared imaging system includes optical components, multi-color focal plane array or arrays, readout electronics, control electronics, and a computing system. The system measures a limited number of spatial and spectral points during image capture and the full dataset is computationally generated.

Abstract: A method uses inpainting, whereby the ability to optimize the reconstruction of images at high resolution and sensitivity with minimal pixels is hard wired into the IRFPA. By combining several of these systems, or by selecting different pixels in the array to form images of different colors, hyperspectral images and 3-D tomograms can also be obtained with a significantly smaller number of pixels.

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.