Abstract: Techniques for improving the performance of an autonomous vehicle (AV) by automatically annotating objects surrounding the AV are described herein. A system can obtain sensor data from a sensor coupled to the AV and generate an initial object trajectory for an object using the sensor data. Additionally, the system can determine a fixed value for the object size of the object based on the initial object trajectory. Moreover, the system can generate an updated initial object trajectory, wherein the object size corresponds to the fixed value. Furthermore, the system can determine, based on the sensor data and the updated initial object trajectory, a refined object trajectory. Subsequently, the system can generate a multi-dimensional label for the object based on the refined object trajectory. A motion plan for controlling the AV can be generated based on the multi-dimensional label.

Abstract: Generally, the disclosed systems and methods implement improved detection of objects in three-dimensional (3D) space. More particularly, an improved 3D object detection system can exploit continuous fusion of multiple sensors and/or integrated geographic prior map data to enhance effectiveness and robustness of object detection in applications such as autonomous driving. In some implementations, geographic prior data (e.g., geometric ground and/or semantic road features) can be exploited to enhance three-dimensional object detection for autonomous vehicle applications. In some implementations, object detection systems and methods can be improved based on dynamic utilization of multiple sensor modalities. More particularly, an improved 3D object detection system can exploit both LIDAR systems and cameras to perform very accurate localization of objects within three-dimensional space relative to an autonomous vehicle.

Abstract: This application provides an application deployment method, including: obtaining a configuration template provided by a user, where the configuration template includes a first configuration item and a second configuration item, and a value of the first configuration item is configured by the user; obtaining at least one available resource that matches the second configuration item and that is in a cloud environment; and determining a value of the second configuration item based on the at least one available resource, to deploy an application on a cloud based on the first configuration item, the value that is of the first configuration item and that is specified by the user, the second configuration item, and the value that is of the second configuration item and that is automatically determined by an application deployment apparatus.

Abstract: Systems and methods are provided for forecasting the motion of actors within a surrounding environment of an autonomous platform. For example, a computing system of an autonomous platform can use machine-learned model(s) to generate actor-specific graphs with past motions of actors and the local map topology. The computing system can project the actor-specific graphs of all actors to a global graph. The global graph can allow the computing system to determine which actors may interact with one another by propagating information over the global graph. The computing system can distribute the interactions determined using the global graph to the individual actor-specific graphs. The computing system can then predict a motion trajectory for an actor based on the associated actor-specific graph, which captures the actor-to-actor interactions and actor-to-map relations.

Abstract: An air gun including: a cylinder, a cartridge, an air valve, a stop piece. The air valve includes an assembly channel, a communication port, and an air passage connected to the assembly channel through the communication port. The cartridge is disposed in the assembly channel and includes an ejection channel communicating with the air passage through the communication port. The stop piece is disposed on the air valve to push the cartridge towards the communication port, thereby locking the cartridge onto the air valve, and tightly fitting the cartridge and the air valve at least at an outer circumference of the communication port.

Abstract: Generally, the disclosed systems and methods implement improved detection of objects in three-dimensional (3D) space. More particularly, an improved 3D object detection system can exploit continuous fusion of multiple sensors and/or integrated geographic prior map data to enhance effectiveness and robustness of object detection in applications such as autonomous driving. In some implementations, geographic prior data (e.g., geometric ground and/or semantic road features) can be exploited to enhance three-dimensional object detection for autonomous vehicle applications. In some implementations, object detection systems and methods can be improved based on dynamic utilization of multiple sensor modalities. More particularly, an improved 3D object detection system can exploit both LIDAR systems and cameras to perform very accurate localization of objects within three-dimensional space relative to an autonomous vehicle.

Abstract: An ambulance-type mobile catheter room for cardiovascular interventional surgery enables interventional diagnosis and treatment devices for acute and severe cardiovascular diseases to be deployed quickly, is flexible and high in adaptability, and provides hardware devices for cardiovascular diagnosis and treatment interventional surgeons to timely diagnose and treat patients. The ambulance-type mobile catheter room for cardiovascular interventional surgery includes an ambulance. The ambulance is internally provided with an antibacterial internal environment, a robotic angiography machine system, a wireless medical Internet of Things system, a self-generating system and an auxiliary system.

Abstract: An air gun, includes: a cartridge including a launching chamber, a cylinder including an air chamber, an air valve, a first pin, and a second pin. The air valve is disposed in the air chamber and partially extends out of the cylinder to connect to the cartridge; the air valve is an integrally-formed structure and includes an air passage comprising an air inlet and an air outlet; the air inlet is connected to the air chamber, the air outlet is connected to the launching chamber; the first pin is movable relative to the cylinder to open and close the air inlet, and the second pin is movable relative to the cylinder to open and close the air outlet.

Abstract: The present disclosure relates to the field of computer technologies, and discloses a method and apparatus, an electronic device, and a storage medium for processing recommendation information. The method includes: displaying a content document on a document page, where the content document includes a plurality of content document pages; acquiring target position information of recommendation information to be processed in the content document, where the target position information is determined based on a statistical analysis result of display durations of the content document pages; and processing the recommendation information to be processed on the document page based on the target position information, where the processing includes displaying or issuing a recommendation request.

Abstract: A vehicle-mounted angiography machine with a double-robotic-arm type structure is used for interventional surgery diagnosis and treatment on patients on the site of cardiovascular diseases and on the way and occupies a small space. The vehicle-mounted angiography machine includes a six-degree-of-freedom robotic lower arm at the lower portion of an ambulance body space, a three-degree-of-freedom mobile table located in the middle of the space for moving a patient, and a seven-degree-of-freedom robotic upper arm at the upper portion of the space. An end portion of the upper arm is connected to a flat panel detector of the angiography machine, and an end portion of the lower arm is connected to an anode ball tube of the angiography machine, Large-scale isocentric detection is realized by cooperation of the central motion of the upper arm and the lower arm and the up-down, left-right and front-back motion of the table.

Abstract: Systems and methods for generating attention masks are provided. In particular, a computing system can access sensor data and map data for an area around an autonomous vehicle. The computing system can generate a voxel grid representation of the sensor data and map data. The computing system can generate an attention mask based on the voxel grid representation. The computing system can generate, by using the voxel grid representation and the attention mask as input to a machine-learned model, an attention weighted feature map. The computing system can determine using the attention weighted feature map, a planning cost volume for an area around the autonomous vehicle. The computing system can select a trajectory for the autonomous vehicle based, at least in part, on the planning cost volume.

Abstract: Systems and methods for generating attention masks are provided. In particular, a computing system can access sensor data and map data for an area around an autonomous vehicle. The computing system can generate a voxel grid representation of the sensor data and map data. The computing system can generate an attention mask based on the voxel grid representation. The computing system can generate, by using the voxel grid representation and the attention mask as input to a machine-learned model, an attention weighted feature map. The computing system can determine using the attention weighted feature map, a planning cost volume for an area around the autonomous vehicle. The computing system can select a trajectory for the autonomous vehicle based, at least in part, on the planning cost volume.

Abstract: An air gun including: a cylinder, a cartridge, an air valve, a stop piece. The air valve includes an assembly channel, a communication port, and an air passage connected to the assembly channel through the communication port. The cartridge is disposed in the assembly channel and includes an ejection channel communicating with the air passage through the communication port. The stop piece is disposed on the air valve to push the cartridge towards the communication port, thereby locking the cartridge onto the air valve, and tightly fitting the cartridge and the air valve at least at an outer circumference of the communication port.

Abstract: Systems and methods for generating simulation data based on real-world dynamic objects are provided. A method includes obtaining two- and three-dimensional data descriptive of a dynamic object in the real world. The two- and three-dimensional information can be provided as an input to a machine-learned model to receive object model parameters descriptive of a pose and shape modification with respect to a three-dimensional template object model. The parameters can represent a three-dimensional dynamic object model indicative of an object pose and an object shape for the dynamic object. The method can be repeated on sequential two- and three-dimensional information to generate a sequence of object model parameters over time. Portions of a sequence of parameters can be stored as simulation data descriptive of a simulated trajectory of a unique dynamic object. The parameters can be evaluated by an objective function to refine the parameters and train the machine-learned model.

Abstract: Techniques for improving the performance of an autonomous vehicle (AV) by automatically annotating objects surrounding the AV are described herein. A system can obtain sensor data from a sensor coupled to the AV and generate an initial object trajectory for an object using the sensor data. Additionally, the system can determine a fixed value for the object size of the object based on the initial object trajectory. Moreover, the system can generate an updated initial object trajectory, wherein the object size corresponds to the fixed value. Furthermore, the system can determine, based on the sensor data and the updated initial object trajectory, a refined object trajectory. Subsequently, the system can generate a multi-dimensional label for the object based on the refined object trajectory. A motion plan for controlling the AV can be generated based on the multi-dimensional label.

Abstract: An air gun, includes: a cartridge including a launching chamber, a cylinder including an air chamber, an air valve, a first pin, and a second pin. The air valve is disposed in the air chamber and partially extends out of the cylinder to connect to the cartridge; the air valve is an integrally-formed structure and includes an air passage comprising an air inlet and an air outlet; the air inlet is connected to the air chamber, the air outlet is connected to the launching chamber; the first pin is movable relative to the cylinder to open and close the air inlet, and the second pin is movable relative to the cylinder to open and close the air outlet.

Abstract: This disclosure describes systems and methods for metal foam cooling of vehicle electronic. An example apparatus may include an electronic control unit (ECU) comprising an electronic component included within a housing. The example apparatus may also include a metal foam configured to dissipate heat produced by the electronic component and also configured to facilitate electromagnetic interference (EMI) shielding for the electronic component. The example apparatus may also include an interface between the ECU and the metal foam, wherein the interface provides a connection between the ECU and metal foam to facilitate heat dissipation from the electronic component to a location outside of the housing.

Abstract: Systems and methods for generating simulation data based on real-world dynamic objects are provided. A method includes obtaining two- and three-dimensional data descriptive of a dynamic object in the real world. The two- and three-dimensional information can be provided as an input to a machine-learned model to receive object model parameters descriptive of a pose and shape modification with respect to a three-dimensional template object model. The parameters can represent a three-dimensional dynamic object model indicative of an object pose and an object shape for the dynamic object. The method can be repeated on sequential two- and three-dimensional information to generate a sequence of object model parameters over time. Portions of a sequence of parameters can be stored as simulation data descriptive of a simulated trajectory of a unique dynamic object. The parameters can be evaluated by an objective function to refine the parameters and train the machine-learned model.

Abstract: Example methods and apparatus for managing user information of an application are described. One example method is applied to a user management device of a cloud platform, where the cloud platform is configured to hear an application registered by a user with the cloud platform. The method includes receiving a user management registration request of a first application, where the first application is one of applications registered with the cloud platform, and the user management registration request of the first application carries an identifier of the first application. A user management instance is created for the first application according to the user management registration request and the identifier of the first application, where the user management instance is used to manage user information of the first application. The user management instance is invoked to process a service that is in the first application and related to the user information.

Abstract: Techniques for improving the performance of an autonomous vehicle (AV) by automatically annotating objects surrounding the AV are described herein. A system can obtain sensor data from a sensor coupled to the AV and generate an initial object trajectory for an object using the sensor data. Additionally, the system can determine a fixed value for the object size of the object based on the initial object trajectory. Moreover, the system can generate an updated initial object trajectory, wherein the object size corresponds to the fixed value. Furthermore, the system can determine, based on the sensor data and the updated initial object trajectory, a refined object trajectory. Subsequently, the system can generate a multi-dimensional label for the object based on the refined object trajectory. A motion plan for controlling the AV can be generated based on the multi-dimensional label.