Abstract: A layer destacking system, for destacking a layer from a stacked layer pallet load, including a layer seating platform configured so as to seat the destacked layer on the layer seating platform, a slip sheet detection sensor arranged to sense a slip sheet in contact with the seated destacked layer, a slip sheet pickup removal mechanism, and a controller that receives a signal from the slip sheet detection sensor identifying presence of the slip sheet. The controller is operably connected to the slip sheet pickup removal mechanism so as to actuate the slip sheet pickup removal mechanism effecting discharge of the slip sheet off the layer seating platform.

Abstract: A computer-implemented method for model training is provided. The method includes receiving, by a hardware processor, sets of images, each set corresponding to a respective task. The method further includes training, by the hardware processor, a task-based neural network classifier having a center and a covariance matrix for each of a plurality of classes in a last layer of the task-based neural network classifier and a plurality of convolutional layers preceding the last layer, by using a similarity between an image feature of a last convolutional layer from among the plurality of convolutional layers and the center and the covariance matrix for a given one of the plurality of classes, the similarity minimizing an impact of a data model forgetting problem.

Abstract: A method of inspecting cased goods includes advancing at least one case of goods on a conveyor, generating an illumination sheet of parallel illuminating rays with at least one electromagnetic source, and capturing an image, formed by the illumination sheet passing through a diffuser with at least one camera located so as to capture illumination from diffused parallel rays of the light sheet, where the image case embodies a goods image that is generated by the case goods moving between the light source and the at least one camera, where part of the parallel sheet of light is at least partially blocked by the case of goods, thus generating a gray level image.

Abstract: A vision-assisted robotized depalletizer receives at a pallet station a pallet loaded with products and outputs on a conveyor unitized products aligned in a desired orientation. Such depalletizers include a vision system having one or more image acquisition sensors that are positioned relative to the pallet station so as to have a field of view covering a top portion of the pallet. The sensors send to a controller one or more image of the top portion of the pallet that the controller uses along to determine the position of each product in the top portion of the pallet. The depalletizer further includes a robot equipped with a depalletizing tool that is coupled to the vision system controller for receiving information indicative of the position of each product from the top portion and uses that information to pick and position on the output conveyor each product from the top portion.

Abstract: A method of inspecting cased goods includes advancing at least one case of goods on a conveyor, generating an illumination sheet of parallel illuminating rays with at least one electromagnetic source, and capturing an image, formed by the illumination sheet passing through a diffuser with at least one camera located so as to capture illumination from diffused parallel rays of the light sheet, where the image case embodies a goods image that is generated by the case goods moving between the light source and the at least one camera, where part of the parallel sheet of light is at least partially blocked by the case of goods, thus generating a gray level image.

Abstract: An inspection apparatus, for inspection of cased goods, includes at least one conveyor, at least one camera for capturing case image data of each of the cased goods advanced with the at least one conveyor past the inspection apparatus, and a processor configured to receive the case image data from the at least one camera. The processor is configured to characterize, from the case image data, a case exterior protrusion of the case good as a case flap in open condition, wherein the processor is configured to resolve the case image data and determine the case exterior protrusion is a coherent planar surface, and is programmed with a parameter array of physical characteristic parameters that describe case flap coherency attributes determinative of the coherent planar surface defining an open case flap condition.

Abstract: A vision-assisted robotized depalletizer receives at a pallet station a pallet loaded with products and outputs on a conveyor unitized products aligned in a desired orientation. Such depalletizers include a vision system having one or more image acquisition sensors that are positioned relative to the pallet station so as to have a field of view covering a top portion of the pallet. The sensors send to a controller one or more image of the top portion of the pallet that the controller uses along to determine the position of each product in the top portion of the pallet. The depalletizer further includes a robot equipped with a depalletizing tool that is coupled to the vision system controller for receiving information indicative of the position of each product from the top portion and uses that information to pick and position on the output conveyor each product from the top portion.

Abstract: In implementations of trajectory-based viewport prediction for 360-degree videos, a video system obtains trajectories of angles of users who have previously viewed a 360-degree video. The angles are used to determine viewports of the 360-degree video, and may include trajectories for a yaw angle, a pitch angle, and a roll angle of a user recorded as the user views the 360-degree video. The video system clusters the trajectories of angles into trajectory clusters, and for each trajectory cluster determines a trend trajectory. When a new user views the 360-degree video, the video system compares trajectories of angles of the new user to the trend trajectories, and selects trend trajectories for a yaw angle, a pitch angle, and a roll angle for the user. Using the selected trend trajectories, the video system predicts viewports of the 360-degree video for the user for future times.

Abstract: A method of inspecting cased goods includes advancing at least one case of goods on a conveyor, generating an illumination sheet of parallel illuminating rays with at least one electromagnetic source, and capturing an image, formed by the illumination sheet passing through a diffuser with at least one camera located so as to capture illumination from diffused parallel rays of the light sheet, where the image case embodies a goods image that is generated by the case goods moving between the light source and the at least one camera, where part of the parallel sheet of light is at least partially blocked by the case of goods, thus generating a gray level image.

Abstract: A vision-assisted robotized depalletizer receives at a pallet station a pallet loaded with products and outputs on a conveyor unitized products aligned in a desired orientation. Such depalletizers include a vision system having one or more image acquisition sensors that are positioned relative to the pallet station so as to have a field of view covering a top portion of the pallet. The sensors send to a controller one or more image of the top portion of the pallet that the controller uses along to determine the position of each product in the top portion of the pallet. The depalletizer further includes a robot equipped with a depalletizing tool that is coupled to the vision system controller for receiving information indicative of the position of each product from the top portion and uses that information to pick and position on the output conveyor each product from the top portion.

Abstract: A pallet building apparatus for automatically building a pallet load of pallet load article units onto a pallet support including a frame defining a pallet building base, at least one articulated robot to transport and place the pallet load article units, a controller to control articulated robot motion and effect therewith a pallet load build, at least one three-dimensional, time of flight, camera to generate three-dimensional imaging of the pallet support and pallet load build, wherein the controller registers, from the three-dimensional camera, real time three-dimensional imaging data embodying different corresponding three-dimensional images of the pallet support and pallet load build, to determine, in real time, from the corresponding real time three-dimensional imaging data, a pallet support variance or article unit variance and generate in real time an articulated robot motion signal, the articulated robot motion signal being generated real time so as to be performed real time by the at least one artic

Abstract: A depalletizer having a pallet station for receiving a pallet load of cases disposed in pallet load layers, a robot with an end effector having a grip to grip and pick at least one of the layers and having a grip engagement interface defining a predetermined layer engagement position and orientation for the layer(s), relative to the depalletizing end effector, a vision system to image the pallet load of cases and generate at least one image of a top portion of the layer(s) independent of robot motion, and a controller that receives the image(s) and effects determination of a layer position and orientation of the layer(s) relative to the predetermined layer engagement position and orientation of the grip engagement interface, and the controller is operably coupled to the robot so as to position the grip and capture and hold the layer(s) with the grip at the grip engagement interface.

Abstract: A vision-assisted robotized depalletizer receives at a pallet station a pallet loaded with products and outputs on a conveyor unitized products aligned in a desired orientation. Such depalletizers include a vision system having one or more image acquisition sensors that are positioned relative to the pallet station so as to have a field of view covering a top portion of the pallet. The sensors send to a controller one or more image of the top portion of the pallet that the controller uses along to determine the position of each product in the top portion of the pallet. The depalletizer further includes a robot equipped with a depalletizing tool that is coupled to the vision system controller for receiving information indicative of the position of each product from the top portion and uses that information to pick and position on the output conveyor each product from the top portion.

Abstract: A method of inspecting cased goods includes advancing at least one case of goods on a conveyor, generating an illumination sheet of parallel illuminating rays with at least one electromagnetic source, and capturing an image, formed by the illumination sheet passing through a diffuser with at least one camera located so as to capture illumination from diffused parallel rays of the light sheet, where the image case embodies a goods image that is generated by the case goods moving between the light source and the at least one camera, where part of the parallel sheet of light is at least partially blocked by the case of goods, thus generating a gray level image.

Abstract: In implementations of trajectory-based viewport prediction for 360-degree videos, a video system obtains trajectories of angles of users who have previously viewed a 360-degree video. The angles are used to determine viewports of the 360-degree video, and may include trajectories for a yaw angle, a pitch angle, and a roll angle of a user recorded as the user views the 360-degree video. The video system clusters the trajectories of angles into trajectory clusters, and for each trajectory cluster determines a trend trajectory. When a new user views the 360-degree video, the video system compares trajectories of angles of the new user to the trend trajectories, and selects trend trajectories for a yaw angle, a pitch angle, and a roll angle for the user. Using the selected trend trajectories, the video system predicts viewports of the 360-degree video for the user for future times.

Abstract: A pallet building apparatus for automatically building a pallet load of pallet load article units onto a pallet support including a frame defining a pallet building base, at least one articulated robot to transport and place the pallet load article units, a controller to control articulated robot motion and effect therewith a pallet load build, at least one three-dimensional, time of flight, camera to generate three-dimensional imaging of the pallet support and pallet load build, wherein the controller registers, from the three-dimensional camera, real time three-dimensional imaging data embodying different corresponding three-dimensional images of the pallet support and pallet load build, to determine, in real time, from the corresponding real time three-dimensional imaging data, a pallet support variance or article unit variance and generate in real time an articulated robot motion signal, the articulated robot motion signal being generated real time so as to be performed real time by the at least one artic

Abstract: In implementations of trajectory-based viewport prediction for 360-degree videos, a video system obtains trajectories of angles of users who have previously viewed a 360-degree video. The angles are used to determine viewports of the 360-degree video, and may include trajectories for a yaw angle, a pitch angle, and a roll angle of a user recorded as the user views the 360-degree video. The video system clusters the trajectories of angles into trajectory clusters, and for each trajectory cluster determines a trend trajectory. When a new user views the 360-degree video, the video system compares trajectories of angles of the new user to the trend trajectories, and selects trend trajectories for a yaw angle, a pitch angle, and a roll angle for the user. Using the selected trend trajectories, the video system predicts viewports of the 360-degree video for the user for future times.

Abstract: In implementations of trajectory-based viewport prediction for 360-degree videos, a video system obtains trajectories of angles of users who have previously viewed a 360-degree video. The angles are used to determine viewports of the 360-degree video, and may include trajectories for a yaw angle, a pitch angle, and a roll angle of a user recorded as the user views the 360-degree video. The video system clusters the trajectories of angles into trajectory clusters, and for each trajectory cluster determines a trend trajectory. When a new user views the 360-degree video, the video system compares trajectories of angles of the new user to the trend trajectories, and selects trend trajectories for a yaw angle, a pitch angle, and a roll angle for the user. Using the selected trend trajectories, the video system predicts viewports of the 360-degree video for the user for future times.

Abstract: A vision-assisted robotized depalletizer receives at a pallet station a pallet loaded with products and outputs on a conveyor unitized products aligned in a desired orientation. Such depalletizers include a vision system having one or more image acquisition sensors that are positioned relative to the pallet station so as to have a field of view covering a top portion of the pallet. The sensors send to a controller one or more image of the top portion of the pallet that the controller uses along to determine the position of each product in the top portion of the pallet. The depalletizer further includes a robot equipped with a depalletizing tool that is coupled to the vision system controller for receiving information indicative of the position of each product from the top portion and uses that information to pick and position on the output conveyor each product from the top portion.

Abstract: A vision-assisted robotized depalletizer receives at a pallet station a pallet loaded with products and outputs on a conveyor unitized products aligned in a desired orientation. Such depalletizers include a vision system having one or more image acquisition sensors that are positioned relative to the pallet station so as to have a field of view covering a top portion of the pallet. The sensors send to a controller one or more image of the top portion of the pallet that the controller uses along to determine the position of each product in the top portion of the pallet. The depalletizer further includes a robot equipped with a depalletizing tool that is coupled to the vision system controller for receiving information indicative of the position of each product from the top portion and uses that information to pick and position on the output conveyor each product from the top portion.