Abstract: An energy conversion circuit, a control method based on the energy conversion circuit, and a vehicle are provided. The energy conversion circuit includes a primary bridge arm module, a resonant module, a secondary bridge arm module, and a control module. The primary bridge arm module includes a first bridge arm and a second bridge arm, and the secondary bridge arm module includes a first secondary switch and a second secondary switch. A drive signal for the first bridge arm, a drive signal for the second bridge arm, a drive signal for the first secondary switch, and a drive signal for the second secondary switch are controlled by the control module, to increase a voltage between the first DC positive terminal and the first DC negative terminal to a preset voltage.

Abstract: An efficient K-nearest neighbor (KNN) method for a single-frame point cloud of a LiDAR and an application of the efficient KNN method for the single-frame point cloud of the LiDAR are provided, where the efficient KNN method for the single-frame point cloud of the LiDAR is accelerated by a field-programmable gate array (FPGA). In the efficient KNN method for the single-frame point cloud of the LiDAR, a data structure is established based on point cloud projection and a distance scale. The data structure ensures that adjacent points in space are organized in adjacent memories. A new data structure is efficiently constructed. An efficient nearest point search mode is provided.

Abstract: Embodiments of the disclosure provide a method, an apparatus and an electronic device for displaying an image. One particular embodiment of the method includes: obtaining at least two real-scene images acquired by a virtual reality camera and image acquisition positions of the real-scene images; generating point cloud images corresponding to the real-scene images based on the real-scene images; determining display positions of image acquisition points in a position coordinate system based on the image acquisition positions of the real-scene images; displaying each of the point cloud images based on the display positions, where the displayed point cloud images are used to be spliced to generate panoramic point cloud data.

Abstract: Provided are a model training method, a vehicle control method, and a related apparatus, which may be applied to the field of artificial intelligence. The method includes: obtaining road condition information of a target vehicle; obtaining target information based on the road condition information by using a first neural network model, where the target information is a driving intention prediction of the target vehicle, a driving route prediction, or an interaction behavior prediction between the target vehicle and an environment; and updating the first neural network model based on the target information by using an expert system or a result obtained through processing the road condition information and a label corresponding to the road condition information by the expert system.

Abstract: A method and device for detecting the key point of an image. The method includes acquiring the image, performing preprocessing to generate a multi-channel image with a specific type, and inputting the image into a detection model. The detection model includes a regression branch and an inter-frame residual branch. If the image type is the discrete frame, the system determines coordinates of multiple key points in the image based on a regression prediction value outputted by the regression branch. If the image type is continuous frame, the system determines coordinates of multiple key points in the image based on a regression prediction value outputted by the regression branch and a residual prediction value outputted by the inter-frame residual branch. The method can be used in the detection of discrete frame and discrete frame type images and can improve the stability of key point detection of images.

Abstract: A display module and a display device are provided. The display module includes: a display panel including a display area and a non-display area surrounding the display area; an optical adhesive layer (2) located on a light emitting side of the display panel and covering the display area; and a cover plate, located on a side of the optical adhesive layer facing away from the display panel and covering the display panel and the optical adhesive layer. A limiting groove used for preventing an edge of the optical adhesive layer from overflowing is formed on a side of the cover plate facing the optical adhesive layer. A least the edge of the optical adhesive layer is in the limiting groove.

Abstract: The present disclosure relates to a cold-resistant medium-voltage power cable, includes a cable body, wherein a bending protection sleeve is slidably sleeved over an outer end of the cable body. Through the cooperative use of the bending protection sleeve, the clamping disc, the flexible electric heating patch, and the bending sensing assembly, on one hand, the arrangement reduces the difficulty in bending the cable body during installation, prevents damage to the cable body caused by excessive bending, and improves the efficiency and safety of installing the cable body in cold regions; on the other hand, the arrangement enables heating treatment at a bent installation section of the cable body. This configuration not only enhances flexibility of the cable body during installation, reducing damage to internal conductive cores of the cable body, but also provides continuous thermal protection to the bent installation section during subsequent operation of the cable body.

Abstract: Embodiments of this application provide a resource configuration method, an information sending method, and an apparatus. The resource configuration method includes: configuring, by a network device for a terminal device, a plurality of resources used to transmit uplink control information UCI; configuring, by the network device, same first indication information for all of the plurality of resources; and sending, by the network device, the first indication information to the terminal device, wherein the first indication information indicates the terminal device to multiplex first UCI and second UCI, and a type of the first UCI is different from a type of the second UCI. Therefore, the terminal device can determine whether to combine the first UCI and the second UCI.

Abstract: Provided is a support member of a flexible display module. The support member includes: a body portion and a plurality of outward protrusion portions. The plurality of outward protrusion portions are at least distributed at two opposite sides of the body portion and protrude outwards relative to the sides of the body portion. A positioning hole is formed in each of the outward protrusion portions.

Abstract: A method and an apparatus for determining a set of training samples, a method and an apparatus for training a model, and a method and an apparatus for detecting an object, the method including: performing a movement operation on an object region in a sample image to determine a plurality of enhanced object regions; and determining, based on a plurality of candidate regions corresponding to the sample image and the plurality of enhanced object regions, a set of training samples corresponding to the sample image to obtain an object detection model by training a network model based on the set of training samples corresponding to the sample image. A probability of a small object region being selected as a set of training samples is improved without affecting sample selection of a large-size object region, thereby improving detection accuracy of an object detection model in detecting the small object.

Abstract: An image rendering method includes the steps below. A model of an environmental object is rendered to obtain an image of the environmental object in a target perspective. An image of a target object in the target perspective and a model of the target object are determined according to a neural radiance field of the target object. The image of the target object is fused and rendered into the image of the environmental object according to the model of the target object.

Abstract: This disclosure relates to techniques for performing uplink port selection management in a wireless communication system. Information configuring a first antenna port for uplink communication may be received by a wireless device. The wireless device may determine to swap antenna ports for the uplink communication, and may perform the uplink communication using the swapped antenna ports.

Abstract: This disclosure provides a method, an apparatus, a device, a medium, and a program product for training a decision model. The method includes: determining a first policy using a supervised learning model and a second policy using a reinforcement learning model within the decision model based on training data; determining an imitation learning loss based on a difference between the first policy and the second policy; and training the decision model based on both the imitation learning loss and a reinforcement learning loss corresponding to the second policy. By combining the imitation learning loss and the reinforcement learning loss, a human-like decision model with excellent performance may be obtained, leveraging the expert data utilization capability of supervised learning and the strong generalization capacity of reinforcement learning. In some embodiments, the trained model is applied to autonomous driving for tasks such as lane-changing.

Abstract: A displaying module includes a transparent cover plate, a display panel and a heat dissipating film layer; the transparent cover plate covers a first surface of the display panel, an area of the display panel is less than an area of the transparent cover plate, and the first surface refers to a surface of the display panel where a light ray exits; and the heat dissipating film layer covers a second surface of the display panel, and at least part of an edge position of the heat dissipating film layer contacts an inner surface of the transparent cover plate, wherein the second surface refers to a surface of the display panel that is opposite to the first surface, the inner surface of the transparent cover plate refers to a surface of the transparent cover plate that contacts the display panel, and the heat dissipating film layer is electrically conductive.

Abstract: An integrated voltage regulator comprises a plurality of semiconductor devices and a circuit board including a plurality of thermally conductive inlays. At least one of the plurality of electronic devices is thermally coupled to at least one of the plurality of thermally conductive inlays. A substrate is thermally coupled to the circuit board and to the plurality of thermally conductive inlays.

Abstract: Provided are a short-cut carbon fiber composite (SCFC)-high strength steel (HSS) hybrid bionic structure battery box and its integrated forming method. A SCFC-HSS hybrid bionic structure lower box body includes a lower box framework made of high strength steel and a SCFC lower box matrix; and an upper box body and the lower box are connected by bolts to form a complete SCFC-HSS hybrid bionic structure battery box. A high strength steel lower box framework scheme is designed based on the principle of bionics, then welding and surface treatment are carried out to obtain a bionic lower box framework structure, and the bionic lower box framework structure is placed in a mold for integrated injection molding using a SCFC matrix material.

Abstract: A system for actuating closures of a vehicle includes drive units and latches. The drive units may couple to one of the closures and may be used to control movement of the closure relative to another closure. Using the latches, the closures may be coupled together and the same drive units can be used to control movement of both closures together. The controlled movement of the closures may be automated by using a controller and one or more motors.

Abstract: A method for planning a path for a mobile object is disclosed. The method includes: generating a plurality of costmap layers based at least on locations of the obstacles in a navigation area, current locations and/or current planned paths of other mobile objects in the navigation area, and historical locations of other mobile objects in the navigation area; generating a master costmap based on the plurality of costmap layers; and planning a path to a target location based on the master costmap. An apparatus for planning a path for a mobile object is also disclosed. A controller for a mobile object, a mobile object and a computer-readable storage medium are also disclosed.

Abstract: A method and an apparatus for evaluating an efficient lane change capability. The method involves assessing a vehicle's lane-change efficiency based an effectiveness score and/or a suppression loss score. For each lane-change period, an effectiveness score is calculated based on the traveling status information of the vehicle, the traffic scenario information, a lane change intention corresponding to the lane change decision instruction, and a lane change intention execution result. For each non-lane-change time period, a suppression loss score is computed to reflect missed opportunities. Finally, an overall efficiency score is derived from these values.

Abstract: Aspects of the invention include a method for synthesizing a peptide brush polymer, the method comprising: exposing a mixture comprising peptide-containing monomers, one or more photoinitiators, and one or more chain transfer agents to a light sufficient to induce photopolymerization, and photopolymerizing the peptide-containing monomers in the mixture; wherein: the resulting peptide brush polymer comprises at least one peptide-containing polymer block; the at least one peptide-containing polymer block is characterized by a degree of polymerization of at least 10 and a peptide graft density of 50% to 100%; and at least one peptide moiety of the at least one peptide-containing polymer block has 5 or more amino acid groups.