Abstract: A method includes obtaining image frames from each camera disposed along a vehicle, where each image frame corresponds to a same timestamp. The method further includes constructing a first birds-eye view (BEV) image from each image frame with a first BEV module and constructing a second BEV image from each image frame by Inverse Perspective Mapping (IPM) with a second BEV module. The first BEV module extracts features of an external environment of the vehicle from each image frame, transforms the features to a three-dimensional space, and projects the three-dimensional space onto an overhead two-dimensional plane. Subsequently, a merging module merges the first and second BEV images to produce a hybrid BEV image. Features of an external environment of the vehicle within the hybrid BEV image are detected by a deep learning neural network and the hybrid BEV image is displayed to a user in the vehicle.

Abstract: A system for creating online vectorized maps for autonomous vehicles includes an image sensor and an electronic control unit (ECU). The image sensor captures a series of image frames. The ECU includes a memory, a central processing unit (CPU), and a transceiver. The memory stores a semantic segmentation deep learning model and a vectorization post-processing module as computer readable code. The CPU executes the semantic segmentation deep learning model and the vectorization post-processing module to output a vectorized map of an external environment of a vehicle. The transceiver uploads the vectorized map to a server such that the vectorized map can be accessed by a second vehicle that uses the vectorized map to traverse the external environment.

Abstract: Embodiments of the present disclosure relate to a method for molecular docking and an electronic device. The method comprises: determining a first binding site on a first molecular surface of a first molecule and a second binding site on a second molecular surface of a second molecule based on a first time-dependent evolution multiscale feature of the first molecule and a second time-dependent evolution multiscale feature of the second molecule; obtaining a first chemical feature of the first binding site and a second chemical feature of the second binding site; determining a functional mapping matrix between the first chemical feature and the second chemical feature through functional mapping; determining a correspondence between the first binding site and the second binding site based on the functional mapping matrix; and docking the first molecule and the second molecule through the first binding site and the second binding site based on the correspondence.

Abstract: Embodiments of the present disclosure relate to a molecular representation method and an electronic device. The molecular representation method comprises: determining a molecular surface of a molecule, the molecular surface being a continuous Riemannian manifold and the molecular surface comprising a plurality of discrete surface nodes; determining a geometric feature of the molecule based on the molecular surface; determining a chemical feature of the molecule by mapping atomic information inside the molecule to the plurality of surface nodes; determining a unified feature of the molecule by integrating the geometric feature and the chemical feature; and determining a time-dependent evolution multi-scale feature of the molecule based on the unified feature by using a time-dependent evolution neural network model.

Abstract: Methods and systems for assisting drivers in finding available parking spots by estimating parking spot availabilities. Vehicle image sensors, and associated image processing techniques, detect whether or not other vehicles are located in parking spaces. An occupancy status of each parking spot is determined over time based on these image processing results, and the occupancy status is stored, for example as historical data. The occupancy statuses can be stored or retrieved based on a particular geographical region. An estimated occupancy status of a first parking spot can be generated based upon a last-known occupancy status of that parking spot and the average parking spot availabilities of nearby parking spots in that geographic region. The estimated occupancy status can be displayed, for example as overlaid into a map or navigation application.

Abstract: A system for generating a map of a paved surface for a vehicle and localizing the vehicle on the map of the paved surface includes an imaging sensor, a vehicle odometry sensor, a memory, a processor, and a transceiver. The imaging sensor captures a series of image frames. The vehicle odometry sensor measures an orientation, a velocity, and an acceleration of the vehicle. The memory stores a mapping engine as computer readable code. The processor executes the mapping engine to generate a map. The transceiver uploads the map to a server such that the map is accessed by a second vehicle that uses the map to traverse the external environment.

Abstract: Methods and systems for assisting a vehicle to park using mixed-domain image data. Image-domain data is generated based on raw image data received from a plurality of cameras mounted on a vehicle. A bird's-eye-view (BEV) image is generated based on the raw image data. BEV-domain data associated with the BEV image is generated, which includes data associated with parking landmarks in the parking zone. A tri-perspective view (TPV) and associated data can be generated. A computing system localizes the vehicle within the parking zone based on the BEV-domain data, the image-domain data, and the TPV-domain data to generate localization data. The computing system performs mapping of the parking zone based on all three image-domain data and the localization data. A motion sensor such as an inertial measurement unit (IMU) can generate data that is used to compensate the various domain data.

Abstract: A system for creating online vectorized maps for autonomous vehicles includes an image sensor and an electronic control unit (ECU). The image sensor captures a series of image frames. The ECU includes a memory, a central processing unit (CPU), and a transceiver. The memory stores a semantic segmentation deep learning model and a vectorization post-processing module as computer readable code. The CPU executes the semantic segmentation deep learning model and the vectorization post-processing module to output a vectorized map of an external environment of a vehicle. The transceiver uploads the vectorized map to a server such that the vectorized map can be accessed by a second vehicle that uses the vectorized map to traverse the external environment.

Abstract: A method includes obtaining image frames from each camera disposed along a vehicle, where each image frame corresponds to a same timestamp. The method further includes constructing a first birds-eye view (BEV) image from each image frame with a first BEV module and constructing a second BEV image from each image frame by Inverse Perspective Mapping (IPM) with a second BEV module. The first BEV module extracts features of an external environment of the vehicle from each image frame, transforms the features to a three-dimensional space, and projects the three-dimensional space onto an overhead two-dimensional plane. Subsequently, a merging module merges the first and second BEV images to produce a hybrid BEV image. Features of an external environment of the vehicle within the hybrid BEV image are detected by a deep learning neural network and the hybrid BEV image is displayed to a user in the vehicle.

Abstract: Embodiments of the present disclosure provide a solution for conformation generation optimization. A method includes: determining a sequence feature representation and a conformation feature representation of a protein, the sequence feature representation characterizing an amino acid sequence of the protein and the conformation feature representation characterizing a conformation of the protein; fusing the sequence feature representation and the conformation feature representation based on a plurality of reference conformations in a conformation sequence of the protein, to obtain a fused feature representation; and generating a target conformation at a target temporal position in the conformation sequence at least based on the fused feature representation.

Abstract: A method that includes obtaining a first image from a first camera disposed on a vehicle and generating a birds-eye view (BEV) image using the first image. The method further includes processing, with a machine-learned model, the BEV image to produce parking slot prediction data. The parking slot prediction data includes a first center coordinate for a first available parking slot, a first parking slot confidence, and a first corner displacement data. The first corner displacement data includes a first relative coordinate pair that locates a first corner relative to the first center coordinate and a second relative coordinate pair that locates a second corner relative to the first center coordinate. The method further includes determining a first location of the first available parking slot using the parking slot prediction data and parking the vehicle in the first available parking slot when the first parking slot confidence meets a threshold.

Abstract: A method that includes obtaining a first image from a first camera disposed on a vehicle and generating a birds-eye view (BEV) image using the first image. The method further includes processing, with a machine-learned model, the BEV image to produce parking slot prediction data. The parking slot prediction data includes a first center coordinate for a first available parking slot, a first parking slot confidence, and a first corner displacement data. The first corner displacement data includes a first relative coordinate pair that locates a first corner relative to the first center coordinate and a second relative coordinate pair that locates a second corner relative to the first center coordinate. The method further includes determining a first location of the first available parking slot using the parking slot prediction data and parking the vehicle in the first available parking slot when the first parking slot confidence meets a threshold.

Abstract: A computer server controls access to a hosted service using digital certificates that are requested from each client attempting to access the service. When a particular client accesses the hosted service, the host service requests a digital certificate from the particular client and issues a challenge message. The particular client signs the challenge message and provides a client digital certificate to the hosted service. The hosted service confirms that the signature on the challenge message matches the client digital certificate, and that the client digital certificate is signed by a trusted entity. Trusted entities are defined by an administrator by uploading, to the hosted service, one or more trusted digital certificates associated with a trusted entities. Using the trusted digital certificates, the hosted service confirms that the digital certificate provided by the particular client is signed by at least one of the trusted entities.

Abstract: Embodiments of the present disclosure provide a method and apparatus for generating information, and relate to the field of cloud computation. The method may include: receiving a video and an audio of a user from a client; analyzing the video and the audio to determine an intention category of the user; generating feedback information according to the intention category of the user and a preset service information set; generating a video of a pre-established three-dimensional virtual portrait by means of an animation engine based on the feedback information; and transmitting the video of the three-dimensional virtual portrait to the client, for the client to present to the user.

Abstract: Embodiments of the present disclosure provide a method and apparatus for generating information, and relate to the field of cloud computation. The method may include: receiving a video and an audio of a user from a client; analyzing the video and the audio to determine an intention category of the user; generating feedback information according to the intention category of the user and a preset service information set; generating a video of a pre-established three-dimensional virtual portrait by means of an animation engine based on the feedback information; and transmitting the video of the three-dimensional virtual portrait to the client, for the client to present to the user.

Abstract: Embodiments of the present disclosure provide a method and apparatus for generating information, and relate to the field of cloud computation. The method may include: receiving a video and an audio of a user that are sent by a client by means of instant communication; generating user feature information and text reply information according to the video and the audio; generating a control parameter and a reply audio for a three-dimensional virtual portrait according to the user feature information and the text reply information; generating a video of the three-dimensional virtual portrait by means of an animation engine based on the control parameter and the reply audio; and transmitting the video of the three-dimensional virtual portrait to the client by means of instant communication, for the client to present to the user.

Abstract: Methods, systems, and computer-readable media for virtual desktop access using device-native user interfaces are disclosed. A virtual desktop instance is implemented on behalf of a user. One or more applications are installed on the virtual desktop instance and executed using a virtualized computing resource instance. Data associated with the virtual desktop instance is sent to a first user device that implements a first device platform. A first graphical user interface (GUI) for the virtual desktop interface is generated using the data and displayed on a first display of the first device. The data is sent to a second user device that implements a second device platform differing from the first device platform. A second GUI for the virtual desktop interface is generated using the data and displayed on a second display of the second device. The second GUI differs at least in part from the first GUI.