PACKSIZE LLC

A system for splicing together multiple sheets of generally rigid material into a continuous sheet. The system includes a cart with a cutting mechanism and a sealing mechanism. The cutting mechanism is configured to cut a pattern of segments through the sheet materials that can be interlocked to form a seam. The interlocking segments may include asymmetrical features. The sealing mechanism can apply tape to the seal to secure it. The splicing system may be used while one of the multiple sheets of generally rigid material is concurrently in use by a packaging machine without interruption to the packaging machine.

A system for packaging one or more items includes an order arrangement station where the one or more items can be arranged into a stack with a desired configuration. A dimensioning mechanism determines the outer dimensions of the stack and a converting assembly creates a box template that when erected forms a box that is custom sized to the dimensions of the stack. A crowder assembly holds and maintains the stack in the desired configuration while the box template is at least partially folded around the stack. The box template is secured around the stack in the form of a box.

A foldable template for forming an envelope includes a central panel, a top glue flap, a bottom glue flap, a first intermediate panel, a second intermediate panel, a first back panel, and a second back panel. The first intermediate panel extends from a first side of the central panel and is separated therefrom by a first curved crease. The second intermediate panel extends from a second side of the central panel and is separated therefrom by a second curved crease. The first back panel extends from the first intermediate panel and is separated therefrom by a third curved crease. The second back panel extends from the second intermediate panel and is separated therefrom by a fourth curved crease.

A method for computing dimensions of an object in a scene includes: controlling, by a processor, a depth camera system to capture at least a frame of the scene, the frame including a color image and a depth image arranged in a plurality of pixels; detecting, by the processor, an object in the frame; determining, by the processor, a ground plane in the frame, the object resting on the ground plane; computing, by the processor, a rectangular outline bounding a projection of a plurality of pixels of the object onto the ground plane; computing, by the processor, a height of the object above the ground plane; and outputting, by the processor, computed dimensions of the object in accordance with a length and a width of the rectangular outline and the height.

A method for calibrating a camera group includes: controlling a first and second cameras to capture first and second images of a first scene, the first camera having a first field of view FOV), the second camera having a second FOV overlapping the first FOV in a first overlap region; the first scene including a calibration target in the first overlap region; computing a first relative pose based on the first and second images; controlling the second camera and a third camera to capture third and fourth images of a second scene, the third camera having a third FOV overlapping the second FOV in a second overlap region, the second scene including a calibration target in the second overlap region; computing a second relative pose based on the third and fourth images; and computing a third relative pose based on the first and second relative poses.

A computer system for optimizing node and edge selections within a digital graph model accesses a digital graph model of a physical warehouse location. The digital graph model comprises information indicating a location of multiple specific items of inventory among shelves in the physical warehouse location. The computer system identifies a set of orders that each comprise one or more items and an order priority. The computer system then maps each item in each order selected from the set or orders to the multiple nodes within the digital graph model. The computer system identifies a ranking node from the multiple nodes. The computer system then traverses one or more edges that extend from the ranking node to identify a shortest path within the digital graph model to fill a digital model of a picking cart above a packing threshold level.

A system for forming boxes includes a folding and glue module. The folding and glue module includes a side folding unit configured to fold opposing sidewalls of a box template, a glue system configured to apply glue to selected portions of the box template as the box template advances through the side folding unit, a front folding unit configured to fold front glue flaps and a front wall panel of the box template, and a rear folding unit configured to fold rear glue flaps and a rear wall panel of the box template.

A method for making a dual fluted corrugated board includes providing a first single face corrugated board having a liner layer and a fluted layer attached to the liner layer and providing a second single face corrugated board having a liner layer and a fluted layer attached to the liner layer. The method also includes arranging the first single face corrugated board and the second single face corrugated board such that the fluted layers thereof face one another and attaching the first single face corrugated board to the second single face corrugated board.

A keypoint detection system includes: a camera system including at least one camera; and a processor and memory, the processor and memory being configured to: receive an image captured by the camera system; compute a plurality of keypoints in the image using a convolutional neural network including: a first layer implementing a first convolutional kernel; a second layer implementing a second convolutional kernel; an output layer; and a plurality of connections between the first layer and the second layer and between the second layer and the output layer, each of the connections having a corresponding weight stored in the memory; and output the plurality of keypoints of the image computed by the convolutional neural network.

A system forming packaging template or boxes from a sheet material includes an infeed and separation assembly, a print assembly downstream of the infeed and separation assembly, and a cut and crease assembly downstream of the print assembly. The system can also include an erecting assembly and an outfeed assembly.