Abstract: The present disclosure provides a self-learning collaborative control method for active steering and yaw moment for a motor vehicle, including a first step of constructing fundamental formulas which are stored in a vehicle ECU, and a second step of calculating an active steering angle ?C and a yaw moment Mc on line by the vehicle ECU according to following sub-steps during a driving process of the motor vehicle, and controlling a driving state of the motor vehicle according to ?C and Mc. The second step includes a first sub-step of collecting raw real-time parameter values, a second sub-step of performing calculation by the identifier and the control target reference model, a third sub-step of calculating ?C and Mc. The present disclosure can realize the self-learning collaborative control of active steering and yaw moment without requiring a system control model and correct a driver's steering operation.

Abstract: The present invention relates to a method for manufacturing a toilet blank. The manufacturing method includes the following steps: a grouting step: producing a seat blank, an inner container blank and a main body blank; a first demolding step: demolding a part of a main body mold, a part of an inner container mold and a part of a seat mold; a first bonding step: bonding a first bonding surface of the inner container blank and a bonding surface of the main body blank to each other; a second demolding step: demolding another part of the inner container mold from the inner container blank; a second bonding step: bonding a bonding surface of the seat blank and a second bonding surface of the inner container blank to each other, and a third demolding step: demolding demolded parts of the seat mold, the inner container mold and the main body mold from a bonded toilet blank.

Abstract: A computer-implemented system and method includes generating first pseudo segment data from a first augmented image and generating second pseudo segment data from a second augmented image. The first augmented image and the second augmented image are in a dataset along with other augmented images. A machine learning system is configured to generate pixel embeddings based on the dataset. The first pseudo segment data and the second pseudo segment data are used to identify a first set of segments that a given pixel belongs with respect to the first augmented image and the second augmented image. A second set of segments is identified across the dataset. The second set of segments do not include the given pixel. A local segmentation loss is computed for the given pixel based on the corresponding pixel embedding that involves attracting the first set of segments while repelling the second set of segments.

Abstract: An autonomous vehicle longitudinal-and-lateral control method for preventing motion sickness is disclosed. Firstly, a vehicle dynamics model is established, and the current vehicle travelling state and road surface information are determined according to the vehicle dynamics model. After the vehicle travelling state and road surface information are acquired, the desired velocity, desired acceleration, and desired wheel turning angle are output according to a driver model for reducing occurrence of motion sickness while ensuring safety and efficiency, to carry out longitudinal-and-lateral control of the vehicle.

Abstract: The present disclosure provides a self-learning collaborative control method for active steering and yaw moment for a motor vehicle, including a first step of constructing fundamental formulas which are stored in a vehicle ECU, and a second step of calculating an active steering angle ?C and a yaw moment Mc on line by the vehicle ECU according to following sub-steps during a driving process of the motor vehicle, and controlling a driving state of the motor vehicle according to ?C and Mc. The second step includes a first sub-step of collecting raw real-time parameter values, a second sub-step of performing calculation by the identifier and the control target reference model, a third sub-step of calculating ?C and Mc. The present disclosure can realize the self-learning collaborative control of active steering and yaw moment without requiring a system control model and correct a driver's steering operation.

Abstract: A method for training a machine learning model. The method comprises receiving a training dataset that includes a plurality of images. The method also includes identifying, by a machine learning model, at least one portion of at least one image of the plurality of images in the training dataset associated with a first object type. The method further includes identifying other images having at least one portion that includes the first object type. The method also includes grouping the identified other images into a first image group. The method also includes generating for display a first user interface, that at least includes a rank matrix, wherein a first row of the rank matrix represents the images of the first image object. The user may provide feedback for the visualization using the first interface. The method may also include training the machine learning model based on the user feedback.

Abstract: Methods and systems for performing function testing for moveable objects. One system includes an electronic processor configured to access a driving scene including a moveable object. The electronic processor is also configured to perform spatial representation learning on the driving scene. The electronic processor is also configured to generate an adversarial example based on the learned spatial representation. The electronic processor is also configured to retrain the deep learning model using the adversarial example and the driving scene.

Abstract: Methods and systems for performing concept-based adversarial generation with steerable and diverse semantics. One system includes an electronic processor configured to access an input image. The electronic processor is also configured to perform concept-based semantic image generation based on the input image. The electronic processor is also configured to perform concept-based semantic adversarial learning using a set of semantic latent spaces generated as part of performing the concept-based semantic image generation. The electronic processor is also configured to generate an adversarial image based on the concept-based semantic adversarial learning. The electronic processor is also configured to test a target model using the adversarial image.

Abstract: A computer-implemented system and method includes generating first pseudo segment data from a first augmented image and generating second pseudo segment data from a second augmented image. The first augmented image and the second augmented image are in a dataset along with other augmented images. A machine learning system is configured to generate pixel embeddings based on the dataset. The first pseudo segment data and the second pseudo segment data are used to identify a first set of segments that a given pixel belongs with respect to the first augmented image and the second augmented image. A second set of segments is identified across the dataset. The second set of segments do not include the given pixel. A local segmentation loss is computed for the given pixel based on the corresponding pixel embedding that involves attracting the first set of segments while repelling the second set of segments.

Abstract: Embodiments of systems and methods for diagnosing an object-detecting machine learning model for autonomous driving are disclosed herein. An input image is received from a camera mounted in or on a vehicle that shows a scene. A spatial distribution of movable objects within the scene is derived using a context-aware spatial representation machine learning model. An unseen object is generated in the scene that is not originally in the input image utilizing a spatial adversarial machine learning model. Via the spatial adversarial machine learning model, the unseen object is moved to different locations to fail the object-detecting machine learning model. An interactive user interface enables a user to analyze performance of the object-detecting machine learning model with respect to the scene without the unseen object and the scene with the unseen object.

Abstract: A visual analytics workflow and system are disclosed for assessing, understanding, and improving deep neural networks. The visual analytics workflow advantageously enables interpretation and improvement of the performance of a neural network model, for example an image-based objection detection and classification model, with minimal human-in-the-loop interaction. A data representation component extracts semantic features of input image data, such as colors, brightness, background, rotation, etc. of the images or objects in the images. The input image data are passed through the neural network to obtain prediction results, such as object detection and classification results. An interactive visualization component transforms the prediction results and semantic features into interactive and human-friendly visualizations, in which graphical elements encoding the prediction results are visually arranged depending on the extracted semantic features of input image data.

Abstract: Methods and systems for performing function testing for moveable objects. One system includes an electronic processor configured to access a driving scene including a moveable object. The electronic processor is also configured to perform spatial representation learning on the driving scene. The electronic processor is also configured to generate an adversarial example based on the learned spatial representation. The electronic processor is also configured to retrain the deep learning model using the adversarial example and the driving scene.

Abstract: Methods and systems for performing concept-based adversarial generation with steerable and diverse semantics. One system includes an electronic processor configured to access an input image. The electronic processor is also configured to perform concept-based semantic image generation based on the input image. The electronic processor is also configured to perform concept-based semantic adversarial learning using a set of semantic latent spaces generated as part of performing the concept-based semantic image generation. The electronic processor is also configured to generate an adversarial image based on the concept-based semantic adversarial learning. The electronic processor is also configured to test a target model using the adversarial image.

Abstract: The disclosed embodiments enable a report to be generated using a template. The template may include one or more properties for which for which corresponding values are to be inherited by each copy of the template. A value of a property that is inherited may be overridden by modifying the inherited value. A copy of a template may be incorporated into a report design. Conversely, at least a portion of a report design may be saved as a template.

Abstract: The disclosed embodiments enable a report to be generated using a template. The template may include one or more properties for which for which corresponding values are to be inherited by each copy of the template. A value of a property that is inherited may be overridden by modifying the inherited value. A copy of a template may be incorporated into a report design. Conversely, at least a portion of a report design may be saved as a template.

Abstract: According to an example, association information of a target account is obtained. Recommendation information is generated for the target account according to the association information and is transmitted to the target account. After feedback information transmitted by the target account in response to the recommendation information is received, processing is performed according to the feedback information transmitted by the target account.

Abstract: The provided is an information prompting method and device for prompting a ticket drawing result. The method includes: scanning a graphic code of a ticket to obtain property information associated with the graphic code, the property information comprising a predetermined drawing time thread value of the ticket; adding a drawing prompt event corresponding to the predetermined drawing time thread value to a preset event list once a real-time current time value does not exceed the drawing time thread value; upon a condition that the drawing time thread value is up, triggering the drawing prompt event; according to triggering of the drawing prompt event, searching for check information associated with the property information from a ticket management server; generating result matching information of the ticket according to the check information, the result matching information comprising the drawing result; and prompting the result matching information in a sensible form.

Abstract: The disclosed embodiments enable a report to be generated using a template. The template may include one or more properties for which for which corresponding values are to be inherited by each copy of the template. A value of a property that is inherited may be overridden by modifying the inherited value. A copy of a template may be incorporated into a report design. Conversely, at least a portion of a report design may be saved as a template.

Abstract: Described relates to mobile Internet field, and described are a third application login method, a third application login apparatus and a third application login terminal. The third application login method includes: obtaining biologic feature information of a user; authenticating the biologic feature information of the user, when the biologic feature information passes authentication, reminding the user the third application is allowed to use; detecting a trigger instruction generated according to a user's response to a reminder and input by any third application; responding to the trigger instruction, sending an information obtaining request to a cloud server; the information obtaining request being configured to obtain a personal account of the third application, and receive the personal account of the third application sent from the cloud server; and logging in the third application with the personal account of the third application.

Abstract: In accordance with one aspect of the invention, methods and apparatus for providing information for use in generating or modifying an expression are disclosed. Input from a user is received within an expression. A list of one or more suggestions is provided in response to the input. A selection of one of the suggestions in the list is received. The expression is then built to include the selection.