Abstract: Some embodiments of the present disclosure relate to a material handling equipment, a controller, and a method for determining an extrinsic parameter. The material handling equipment includes a controller. The controller is configured to execute program instructions, to implement the following actions: obtaining a relative pose between a carrier and the material handling equipment as a first pose; obtaining a second pose by using a sensor, the second pose being a pose of the carrier or a pose of a partial structure of the carrier; and determining, based on the first pose and the second pose, an extrinsic parameter of the sensor relative to the material handling equipment.

Abstract: A control method for a material handling equipment includes: controlling the material handling equipment to transport a first stacking object to a stacking preparation position; acquiring pre-alignment target data of a second stacking object by using a first sensor; and controlling, based on the pre-alignment target data, the material handling equipment to move, until a pose error of the material handling equipment relative to the second stacking object is within a first preset threshold range, where the pose error of the material handling equipment relative to the second stacking object is a position and an orientation of the material handling equipment relative to the second stacking object in a three-dimensional space. In the present disclosure, a pre-alignment method is provided to significantly improve accuracy and efficiency of a stacking operation.

Abstract: A method for determining an alignment state includes: acquiring, by using a sensor, target images of a first stacking object and a second stacking object; acquiring, from the target images, a first target image region of the first stacking object and a second target image region of the second stacking object; and determining a pixel difference between the first target image region and the second target image region, and comparing the pixel difference with a threshold, to determine an alignment state between the first stacking object and the second stacking object. Embodiments of the present disclosure are used to implement alignment between a first stacking object and a second stacking object during stacking.

Abstract: A method for determining an alignment state includes: acquiring, by using a sensor, target images of a first stacking object and a second stacking object; acquiring, from the target images, a first target image region of the first stacking object and a second target image region of the second stacking object; and determining a pixel difference between the first target image region and the second target image region, and comparing the pixel difference with a threshold, to determine an alignment state between the first stacking object and the second stacking object. Embodiments of the present disclosure are used to implement alignment between a first stacking object and a second stacking object during stacking.

Abstract: In some aspects, a target following method for a panoramic unmanned aerial vehicle (UAV) is provided. An image captured by the panoramic UAV is obtained. In response to a trigger operation for a target following function, a target object can be determined based on the image. The panoramic UAV can be controlled to follow the target object.

Abstract: Embodiments of the present disclosure provide three-dimensional (3D) imaging systems and methods. In one example, a non-interferometric ODT system is provided that utilizes a fully-switchable angle scanning component/module, composed of a digital micromirror device (DMD) and microlens array (MLA). The example system allows completely independent generation of each illumination angle or imaging configuration while also optimizing its power efficiency based on the density of illumination angles.

Abstract: Disclosed are a method for determining an alignment state, a controller, and material handling equipment. A main technical solution includes: acquiring, by using a sensor, images and point clouds; extracting first target image data of a first target region from an image of a first stacking object, and extracting second target image data of a second target region from an image of a second stacking object; extracting, based on the first target image data, first target point cloud data; extracting, based on the second target image data, second target point cloud data; determining a pose of the first stacking object, and determining a pose of the second stacking object; determining a difference between the pose of the first stacking object and the pose of the second stacking object, and comparing the difference with a threshold to determine an alignment state between the first stacking object and the second stacking object.

Abstract: A method for determining a center of material handling equipment, which includes a fork assembly, a first wheel assembly, and a second wheel assembly, includes: acquiring first point cloud data corresponding to the fork assembly, second point cloud data corresponding to the first wheel assembly, and third point cloud data corresponding to the second wheel assembly; determining, based on the first point cloud data, a first point cloud plane corresponding to the fork assembly; determining, based on the second point cloud data, a second point cloud plane corresponding to the first wheel assembly; determining, based on the third point cloud data, a third point cloud plane corresponding to the second wheel assembly; and determining, based on the first point cloud plane, the second point cloud plane and the third point cloud plane, the center of the material handling equipment.

Abstract: This application discloses a posture data completion method for a three-dimensional object performed by a computer device. The method includes: obtaining three-dimensional incomplete posture data of a three-dimensional object in a preset posture, wherein the three-dimensional incomplete posture data includes first three-dimensional joint point data of the three-dimensional object; generating a two-dimensional posture image of the three-dimensional object in the preset posture by applying the three-dimensional incomplete posture data and a posture description text to a text-to-image model of the preset posture; performing joint point recognition on the two-dimensional posture image to obtain second three-dimensional joint point data of the three-dimensional object; and combining the second three-dimensional joint point data and the three-dimensional incomplete posture data to obtain three-dimensional complete posture data of the three-dimensional object.

Abstract: Disclosed are an aligning method, a controller, and material handling equipment. A major technical solution includes: acquiring target data of a first stacking object and a second stacking object by using a first sensor; extracting, from the target data, first target data of the first stacking object and second target data of the second stacked object; calculating a relative pose of the first stacking object relative to the second stacking object based on the first target data and the second target data; and controlling, based on the relative pose, material handling equipment to move, to align the first stacking object with the second stacking object. In the present disclosure, a relative pose between two stacking objects is corrected by simultaneously acquiring and processing target data of the two stacking objects, thereby significantly improving accuracy and efficiency of a stacking operation.

Abstract: Disclosed are an aligning method, a controller, and material handling equipment. A major technical solution includes: acquiring target data of a first stacking object and a second stacking object by using a first sensor; extracting, from the target data, first target data of the first stacking object and second target data of the second stacked object; calculating a relative pose of the first stacking object relative to the second stacking object based on the first target data and the second target data; and controlling, based on the relative pose, material handling equipment to move, to align the first stacking object with the second stacking object. In the present disclosure, a relative pose between two stacking objects is corrected by simultaneously acquiring and processing target data of the two stacking objects, thereby significantly improving accuracy and efficiency of a stacking operation.

Abstract: Disclosed are an aligning method, a controller, and material handling equipment. A major technical solution includes: acquiring target data of a first stacking object and a second stacking object by using a first sensor; extracting, from the target data, first target data of the first stacking object and second target data of the second stacked object; calculating a relative pose of the first stacking object relative to the second stacking object based on the first target data and the second target data; and controlling, based on the relative pose, material handling equipment to move, to align the first stacking object with the second stacking object. In the present disclosure, a relative pose between two stacking objects is corrected by simultaneously acquiring and processing target data of the two stacking objects, thereby significantly improving accuracy and efficiency of a stacking operation.

Abstract: A method for determining an alignment state includes: acquiring, by using a sensor, target images of a first stacking object and a second stacking object; acquiring, from the target images, a first target image region of the first stacking object and a second target image region of the second stacking object; and determining a pixel difference between the first target image region and the second target image region, and comparing the pixel difference with a threshold, to determine an alignment state between the first stacking object and the second stacking object. Embodiments of the present disclosure are used to implement alignment between a first stacking object and a second stacking object during stacking.

Abstract: Disclosed are a method for determining an alignment state, a controller, and material handling equipment. A main technical solution includes: acquiring, by using a sensor, a target point cloud of a first stacking object and a target point cloud of a second stacking object; determining, based on the target point cloud of the first stacking object, a first pseudo image corresponding to the first stacking object; determining, based on the target point cloud of the second stacking object, a second pseudo image corresponding to the second stacking object; determining relative pose data between the first stacking object and the second stacking object based on the first pseudo image and the second pseudo image; and comparing the relative pose data with a threshold to determine an alignment state between the first stacking object and the second stacking object.

Abstract: In non-limiting examples of the present disclosure, systems, methods and devices for surfacing email suggestions are presented. A first user account associated with a composer of an email may be identified. Core working hour and a time zone associated with that first user account may be determined. One or more recipient user accounts included in the email may be identified. Core working hours and a time zone associated with the recipient user accounts may be identified. If more than a threshold number, percentage, and/or ratio of the recipient users is not currently in core working hours when the email is being drafted/sent, a suggestion may be surfaced in association with the email to send the email at a later time when more recipient users are in their core working hours.

Abstract: A system and method for computing a metric indicating a user operation of an application is described. The system accesses online activity data of a user operation of the application. The system filters the online activity data based on a preset time range. An after-hours activity score is calculated based on a type of activity or a duration of an activity from the filtered online activity data, and a weight assigned to the type of activity or the duration of the activity. The system computes an after-hours metric based on the after-hours activity score. A configuration setting for the application based on the after-hours metric is applied to the application.

Abstract: In non-limiting examples of the present disclosure, systems, methods and devices for surfacing email suggestions are presented. A first user account associated with a composer of an email may be identified. Core working hour and a time zone associated with that first user account may be determined. One or more recipient user accounts included in the email may be identified. Core working hours and a time zone associated with the recipient user accounts may be identified. If more than a threshold number, percentage, and/or ratio of the recipient users is not currently in core working hours when the email is being drafted/sent, a suggestion may be surfaced in association with the email to send the email at a later time when more recipient users are in their core working hours.

Abstract: A system and method for computing a metric indicating a user operation of an application is described. The system accesses online activity data of a user operation of the application. The system filters the online activity data based on a preset time range. An after-hours activity score is calculated based on a type of activity or a duration of an activity from the filtered online activity data, and a weight assigned to the type of activity or the duration of the activity. The system computes an after-hours metric based on the after-hours activity score. A configuration setting for the application based on the after-hours metric is applied to the application.

Abstract: A method may include receiving an electronic meeting request for a user, the meeting request indicating a date for a proposed meeting; presenting a body of the electronic meeting request within a client application when a user selects the electronic meeting request in the client application; for the week of the date of the proposed meeting, calculating a busy metric, the focus metric based on an amount and duration of scheduled meetings for the week retrieved from an electronic calendar of the user; when the busy metric exceeds a threshold, presenting a notification in the client application, the notification including an option to schedule an appointment classified as focus time on the electronic calendar.