Data fusion method and device of vehicle-mounted radar, vehicle and storage medium

Abstract

The invention relates to the technical field of vehicles, in particular to a vehicle-mounted radar data fusion method and device, a vehicle and a storage medium, and the method comprises the steps: obtaining the number of radars of a current vehicle, and determining at least one master radar, at least one slave radar and a radar network topology structure of the current vehicle; after the current vehicle is powered on and started, the master radar is controlled to send time synchronization information to the slave radar based on the radar network topology structure, and the slave radar is controlled to send the collected point cloud data and target data to the master radar; and performing fusion processing on the point cloud data and the target data based on a preset fusion strategy to obtain a sensing result. Therefore, the problems of incomplete environmental perception, low radar utilization efficiency and the like caused by independent work of the radars in the prior art are solved, and the use efficiency of the radars and the perception precision of the vehicle to the surrounding environment are remarkably improved by improving the communication mode and the data processing flow between the radars.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a data fusion method, device, vehicle and storage medium for a vehicle-mounted radar. Background Art

[0002] With the continuous improvement of the level of automobile intelligence, especially the rapid progress of autonomous driving technology, the installation and application of vehicle sensors are becoming more and more extensive. In order to realize a variety of assisted driving functions and even higher levels of autonomous driving, vehicles need to be equipped with various sensors to perceive the surrounding environment and the dynamics of other traffic participants in real time. Millimeter-wave radar has the ability to penetrate obstacles such as fog, smoke, and dust, and is not restricted by light and can work all day and all day. It can also detect and track multiple targets in real time with high precision, and has the advantages of high resolution and low power consumption. It shows broad application potential in the fields of intelligent transportation and autonomous driving.

[0003] At present, vehicle-mounted millimeter-wave radars such as front collision warning radars, millimeter-wave corner radars, and door collision avoidance radars are already common. However, these radar modules often only independently sense and detect targets and scenes within their field of view (FOV), resulting in incomplete environmental perception. In addition, since different radar modules may come from different suppliers, there is a lack of unified planning and management of millimeter-wave radars installed around the vehicle body, resulting in low radar utilization, which needs to be solved urgently. Summary of the invention

[0004] The present application provides a data fusion method, device, vehicle and storage medium for vehicle-mounted radars to solve the problems of incomplete environmental perception and low radar utilization efficiency caused by the independent operation of each radar in the prior art. By improving the communication mode and data processing flow between radars, the radar utilization efficiency and the vehicle's perception accuracy of the surrounding environment are significantly improved.

[0005] The first aspect of the present application provides a data fusion method for a vehicle-mounted radar, comprising the following steps:

[0006] Acquire the number of radars of the current vehicle, and determine a radar network topology structure of at least one master radar, at least one slave radar, and the current vehicle;

[0007] After the current vehicle is powered on, the master radar is controlled to send time synchronization information to the slave radar based on the radar network topology, and the slave radar is controlled to send the collected point cloud data and target data to the master radar;

[0008] The point cloud data and the target data are fused based on a preset fusion strategy to obtain a perception result.

[0009] According to one embodiment of the present application, the determining of the radar network topology of at least one master radar, at least one slave radar, and the current vehicle includes:

[0010] Determining whether the number of radars of the current vehicle is a preset number;

[0011] If the number of radars of the current vehicle is a preset number, it is determined that the radar network topology is a series topology or a bus topology.

[0012] According to an embodiment of the present application, after determining whether the number of radars of the current vehicle is a preset number, the method further includes:

[0013] If the number of radars of the current vehicle is greater than or equal to the preset number, it is determined that the radar network topology is the bus topology or the star topology.

[0014] According to one embodiment of the present application, after determining the radar network topology of at least one master radar, at least one slave radar and the current vehicle, the method further includes:

[0015] According to the installation position and design parameters of each radar, the field of view angle coverage of each radar is obtained, and the overlapping areas between multiple field of view angle coverages are identified.

[0016] According to one embodiment of the present application, before controlling the slave radar to send the collected point cloud data and target data to the master radar, it also includes:

[0017] According to the conversion relationship between the installation position of each radar and the body coordinate system where the current vehicle is located, the point cloud data and the target data are converted into data in the body coordinate system.

[0018] According to the data fusion method of the vehicle-mounted radar provided in the embodiment of the present application, after the current vehicle is powered on, the main radar is controlled to send time synchronization information to the slave radar based on the radar network topology structure, and the slave radar is controlled to send the collected point cloud data and target data to the main radar; the point cloud data and target data are fused and processed based on the preset fusion strategy to obtain the perception result. In this way, the problems of incomplete environmental perception and low radar utilization efficiency caused by the independent operation of each radar in the prior art are solved, and the communication mode and data processing flow between radars are improved, thereby significantly improving the radar utilization efficiency and the vehicle's perception accuracy of the surrounding environment.

[0019] A second aspect of the present application provides a data fusion device for a vehicle-mounted radar, comprising:

[0020] An acquisition and determination module, used to acquire the number of radars of the current vehicle, and determine the radar network topology of at least one master radar, at least one slave radar and the current vehicle;

[0021] a control module, configured to control the master radar to send time synchronization information to the slave radar based on the radar network topology after the current vehicle is powered on, and control the slave radar to send the collected point cloud data and target data to the master radar;

[0022] The fusion processing module is used to fuse the point cloud data and the target data based on a preset fusion strategy to obtain a perception result.

[0023] According to one embodiment of the present application, the acquisition and determination module is used to:

[0024] Determining whether the number of radars of the current vehicle is a preset number;

[0025] If the number of radars of the current vehicle is a preset number, it is determined that the radar network topology is a series topology or a bus topology.

[0026] According to an embodiment of the present application, after determining whether the number of radars of the current vehicle is a preset number, the acquisition and determination module is further used to:

[0027] If the number of radars of the current vehicle is greater than or equal to the preset number, it is determined that the radar network topology is the bus topology or the star topology.

[0028] According to one embodiment of the present application, after determining the radar network topology of at least one master radar, at least one slave radar and the current vehicle, the acquisition and determination module is further used to:

[0029] According to the installation position and design parameters of each radar, the field of view angle coverage of each radar is obtained, and the overlapping areas between multiple field of view angle coverages are identified.

[0030] According to one embodiment of the present application, before controlling the slave radar to send the collected point cloud data and target data to the master radar, the control module is further used to:

[0031] According to the conversion relationship between the installation position of each radar and the body coordinate system where the current vehicle is located, the point cloud data and the target data are converted into data in the body coordinate system.

[0032] According to the data fusion device of the vehicle-mounted radar provided in the embodiment of the present application, after the current vehicle is powered on, the main radar is controlled to send time synchronization information to the slave radar based on the radar network topology structure, and the slave radar is controlled to send the collected point cloud data and target data to the main radar; the point cloud data and target data are fused and processed based on the preset fusion strategy to obtain the perception result. In this way, the problems of incomplete environmental perception and low radar utilization efficiency caused by the independent operation of each radar in the prior art are solved, and the communication mode and data processing flow between radars are improved, thereby significantly improving the radar utilization efficiency and the vehicle's perception accuracy of the surrounding environment.

[0033] The third aspect of the present application provides a vehicle, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the data fusion method of the vehicle-mounted radar as described in the above embodiment.

[0034] A fourth aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the data fusion method for the vehicle-mounted radar as described in the above embodiment.

[0035] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0037] Figure 1 A flow chart of a data fusion method for a vehicle-mounted radar provided according to an embodiment of the present application;

[0038] Figure 2 is a schematic diagram of a series topology structure according to an embodiment of the present application;

[0039] Figure 3 is a schematic diagram of a bus topology structure according to an embodiment of the present application;

[0040] Figure 4 is a schematic diagram of a star topology structure according to an embodiment of the present application;

[0041] Figure 5 is a block diagram of a data fusion device for a vehicle-mounted radar according to an embodiment of the present application;

[0042] Figure 6 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0044] The following describes the data fusion method, device, vehicle and storage medium of the vehicle-mounted radar in the embodiments of the present application with reference to the accompanying drawings.

[0045] Before introducing the data fusion method of the vehicle-mounted radar in the embodiment of the present application, a brief introduction to the vehicle-mounted radar in the related art is first given.

[0046] In the related technology, at present, the more common configuration is to install two rear corner millimeter-wave radars on the inside of the rear bumper of the vehicle to detect the situation of the side rear area of ​​the vehicle or the adjacent lane. The rear corner radars can be hung on the CAN bus separately in the form of a bus, or they can be connected together in a master-slave series manner. For vehicles equipped with a higher level of assisted driving system, two additional front corner millimeter-wave radars are usually installed on the inside of the front bumper to sense the situation of the side front area of ​​the vehicle and the adjacent lane. The connection method of these two front corner radars is usually the same as that of the rear corner radar. In addition, there is a forward millimeter-wave radar under the front license plate of the vehicle to detect the environmental conditions directly in front of the vehicle.

[0047] Each radar independently completes the target tracking and detection tasks within its field of view and can support the development of subsequent functions. Alternatively, they can upload the collected point cloud data and target information to the autonomous driving domain controller or forward-looking integrated machine, and fuse it with other sensor information such as video data to achieve a higher level of assisted driving functions. Door collision avoidance radar is currently mainly used in high-end models to sense the side of the vehicle to protect the door and its surrounding vulnerable traffic participants. With the improvement of the modularity of radar technology and the reduction of costs, it is expected that door collision avoidance radar will be used in more models.

[0048] In summary, most of the existing vehicle-mounted millimeter-wave radar systems operate independently or pass the collected data to a higher-level controller for integration with other sensor data. Although there is communication between radars, it is mainly limited to the forwarding of vehicle body message data or other information, and there is less deep data fusion processing between radars. Therefore, the current radar installation and communication mode is relatively fixed, lacks unified planning and overall management, and has limited scalability. With the continuous improvement of the intelligence level of passenger cars, the demand for optimizing the layout and utilization efficiency of vehicle sensors is becoming increasingly urgent to better meet the requirements of intelligent driving and improve the utilization efficiency of sensors.

[0049] Based on the above-mentioned problems existing in the prior art, the present application proposes a data fusion method for vehicle-mounted radar, which can significantly improve the utilization efficiency of millimeter-wave radar and enhance the perception accuracy of the radar field of view coverage area, especially the overlapping area.

[0050] Specifically, Figure 1 A schematic flow chart of a data fusion method for a vehicle-mounted radar provided in an embodiment of the present application.

[0051] like Figure 1 As shown, the data fusion method of the vehicle-mounted radar includes the following steps:

[0052] In step S101 , the number of radars of the current vehicle is obtained, and a radar network topology structure of at least one master radar, at least one slave radar, and the current vehicle is determined.

[0053] Among them, the radar in the embodiment of the present application can be a vehicle-mounted millimeter-wave radar, that is, a millimeter-wave radar installed around the vehicle body and capable of covering different sensing areas.

[0054] Specifically, the embodiments of the present application can determine the radar network topology of the current vehicle and key elements such as the communication method and communication protocol adopted based on the specific number and deployment plan of the on-board millimeter-wave radars.

[0055] Specifically, when the current vehicle is equipped with more than one millimeter wave radar, the embodiment of the present application can designate one or more of the radars as the main radar module according to the actual situation, and the remaining radars as slave radars. Depending on the number and installation location of the radars, there are different network topology connection methods to choose from.

[0056] For example, Figure 2 The serial connection mode shown in the figure, in which the two radars are divided into a master radar and a slave radar. The slave radar is connected to the master radar, and the master radar is connected to the CAN (Controller Area Network) network of the vehicle body.

[0057] In addition, the network topology structure of the embodiment of the present application can also be as follows: Figure 3 As shown in the bus connection mode, in the bus connection mode, all radars will send data to the bus, and the radar modules receiving data will filter out and receive the data they need from the bus by identifying the message identifier.

[0058] In addition, the network topology structure of the embodiment of the present application can also be as follows: Figure 4 The star connection mode shown is shown. In the star connection mode, all slave radar modules communicate with the master radar through a single-point connection, and the slave radar sends data to the master radar.

[0059] It should be noted that in the embodiment of the present application, when the vehicle is powered on, all radar modules (including the main radar and the slave radar) start working.

[0060] Therefore, through the networking strategy of the embodiment of the present application, different network topologies such as series, bus, star, etc. are used to organize all millimeter-wave radars according to the number of millimeter-wave radars used and the way the radars send data, thereby ensuring the effective transmission and processing of radar data and improving the reliability and efficiency of the entire system.

[0061] Furthermore, in some embodiments, determining the radar network topology of at least one master radar, at least one slave radar and the current vehicle includes: determining whether the number of radars of the current vehicle is a preset number; if the number of radars of the current vehicle is the preset number, determining whether the radar network topology is a series topology or a bus topology.

[0062] The preset number may be 2, which is not specifically limited here.

[0063] For example, assuming that the preset number is two, if the current vehicle is equipped with two radars, such as two rear-corner millimeter-wave radars or two front-corner millimeter-wave radars, the radar network topology can be in series, such as Figure 2 As shown in the figure, in the serial mode, the two radars are divided into a master radar and a slave radar. The slave radar is connected to the master radar, and the master radar is connected to the CAN network of the vehicle body. Through such a configuration, the master radar can not only receive the vehicle body information and forward the received vehicle body information to the slave radar, but also receive the target data and functional application messages sent by the slave radar, and perform fusion processing on the received vehicle body information, target data and functional application message data, and upload the processed results to a higher-level system.

[0064] In addition, in addition to the above-mentioned serial connection method, the embodiment of the present application can also adopt the following method for connecting and communicating two radars: Figure 3 The bus connection mode shown is as follows. In the bus connection mode, all radars will send data to the bus, and the radar modules receiving the data will filter out and receive the data they need from the bus by identifying the message identifier.

[0065] Furthermore, in some embodiments, after determining whether the number of radars of the current vehicle is a preset number, it also includes: if the number of radars of the current vehicle is greater than or equal to the preset number, determining that the radar network topology is a bus topology or a star topology.

[0066] Specifically, when the number of radars is greater than or equal to the preset number, it is necessary to comprehensively consider whether to adopt a bus topology or a star topology for layout based on multiple factors such as the specific number of radars, communication method, bus load, etc. If a bus connection method or a star connection method is selected, it is necessary to assign a unique identifier to the data sent by each radar to distinguish them.

[0067] It should be noted that in order to more effectively cover the radar's field of view and achieve accurate perception, the embodiment of the present application can designate one of the radars as the main radar module according to actual conditions. Since the main radar needs to integrate and analyze data from all other radars, it must have stronger data processing capabilities. In contrast, other slave radars only serve as perception units, responsible for directly sending the collected point cloud data to the main radar, so these slave radars can omit the hardware of the data processing module, thereby reducing the hardware cost of a single radar.

[0068] In the case of star connection, the current system can also introduce an independent millimeter-wave radar domain controller to receive radar data from various directions and positions, and convert these data into the vehicle body coordinate system to ensure the consistency of data coordinates. Furthermore, the domain controller fuses these data and ultimately provides stable and accurate perception and tracking capabilities for the environment around the vehicle body.

[0069] Optionally, in the selection of radar communication mode, the embodiment of the present application can adopt the currently widely used CAN / CANFD (CAN with Flexible Data rate) format, or use an Ethernet interface for communication. The specific selected communication mode can be uniformly planned in combination with the radar's hardware composition, network topology and other information, and is not specifically limited here.

[0070] Furthermore, in some embodiments, after determining the radar network topology of at least one master radar, at least one slave radar and the current vehicle, it also includes: obtaining the field of view angle coverage of each radar according to the installation position and design parameters of each radar, and identifying the overlapping area between multiple field of view angle coverages.

[0071] Specifically, the embodiments of the present application can accurately depict the FOV coverage of each radar through simulation analysis based on the actual installation position of the vehicle-mounted millimeter-wave radar and its design parameters (such as the field of view FOV), and identify the overlapping areas between the FOVs of multiple radars.

[0072] Furthermore, in some embodiments, before controlling the slave radar to send the collected point cloud data and target data to the main radar, it also includes: converting the point cloud data and target data into data in the vehicle body coordinate system according to the conversion relationship between the installation position of each radar and the vehicle body coordinate system of the current vehicle.

[0073] Specifically, due to the specificity of the installation position and orientation of the radar, each radar must first track and process the target within its own field of view to obtain the point cloud data sensed by each radar. It is understandable that since the point cloud data sensed by the radar is expressed in polar coordinates relative to the radar coordinate system, it is necessary to uniformly convert these polar coordinate data into rectangular coordinate system data.

[0074] Furthermore, according to the conversion relationship between each radar installation position and the vehicle body coordinate system, the data sensed by each radar is mapped to the vehicle body coordinate system. In other words, the slave radar converts the sensed point cloud data and target data into data in the vehicle body coordinate system, and sends this information to the master radar, which also needs to uniformly convert the data sensed by itself into data in the vehicle body coordinate system.

[0075] In step S102, after the current vehicle is powered on, the master radar is controlled to send time synchronization information to the slave radar based on the radar network topology, and the slave radar is controlled to send the collected point cloud data and target data to the master radar.

[0076] Specifically, after the current vehicle system is started and powered on, according to the previously determined network topology and communication method, the master radar will be responsible for sending time synchronization reference information to the slave radar. The slave radar will use this time information as a reference to correct the timestamp of its own data transmission, thereby completing the time synchronization within the millimeter-wave radar local area network segment, that is, ensuring time synchronization within the millimeter-wave radar local area network segment.

[0077] Furthermore, according to the installation position of the radar, the coverage area of ​​each radar's field of view and the area where the fields of view of multiple radars overlap are analyzed. For those areas covered by only one radar FOV, the corresponding radar module performs target detection and tracking alone. For those areas overlapped by multiple radar FOVs, the slave radar module will send the target point cloud data or target data detected by itself to the master radar module, which will perform the fusion processing of the point cloud data and target data.

[0078] In step S103, the point cloud data and the target data are fused based on a preset fusion strategy to obtain a perception result.

[0079] Optionally, the preset fusion strategy of the embodiment of the present application may adopt a clustering algorithm such as K-MEANS (k-means clustering algorithm), DBSCAN (Density-Based Spatial Clustering of Applications with Noise, density-based clustering algorithm), etc., which is not specifically limited here.

[0080] Specifically, when the main radar is tracking a target, especially for targets in the overlapping area of ​​the two radars’ field of view, it is necessary to comprehensively consider the data provided by the slave radar and perform unified fusion and clustering of the data from the two radars according to a predetermined fusion strategy. In this process, clustering algorithms such as K-MEANS and DBSCAN can be used to improve the accuracy and efficiency of data processing.

[0081] Furthermore, based on the field of view coverage of the two radars, the system will uniformly output all target information perceived and tracked by the two radars, that is, the perception results. This processing method can ensure the system's comprehensive perception and accurate understanding of the surrounding environment.

[0082] Therefore, the data fusion method of the embodiment of the present application improves the accuracy of target detection by processing the overlapping areas of the field of view of different millimeter-wave radars and integrating the perception data of multiple radars. At the same time, this method can also increase the density of the point cloud, thereby helping to more accurately determine higher-dimensional data features such as the shape of the target.

[0083] According to the data fusion method of the vehicle-mounted radar proposed in the embodiment of the present application, after the current vehicle is powered on, the main radar is controlled to send time synchronization information to the slave radar based on the radar network topology structure, and the slave radar is controlled to send the collected point cloud data and target data to the main radar; the point cloud data and target data are fused and processed based on the preset fusion strategy to obtain the perception result. In this way, the problems of incomplete environmental perception and low radar utilization efficiency caused by the independent operation of each radar in the prior art are solved, and the communication mode and data processing flow between radars are improved, thereby significantly improving the radar utilization efficiency and the vehicle's perception accuracy of the surrounding environment.

[0084] Next, the data fusion device of the vehicle-mounted radar proposed in accordance with the embodiment of the present application is described with reference to the accompanying drawings.

[0085] Figure 5 It is a block diagram of a data fusion device for a vehicle-mounted radar according to an embodiment of the present application.

[0086] like Figure 5 As shown, the data fusion device 10 of the vehicle-mounted radar includes: an acquisition and determination module 100 , a control module 200 and a fusion processing module 300 .

[0087] Among them, the acquisition and determination module 100 is used to obtain the number of radars of the current vehicle, and determine at least one main radar, at least one slave radar and the radar network topology of the current vehicle; the control module 200 is used to control the main radar to send time synchronization information to the slave radar based on the radar network topology after the current vehicle is powered on and started, and control the slave radar to send the collected point cloud data and target data to the main radar; the fusion processing module 300 is used to fuse the point cloud data and target data based on a preset fusion strategy to obtain a perception result.

[0088] Furthermore, in some embodiments, the acquisition and determination module 100 is used to: determine whether the number of radars of the current vehicle is a preset number; if the number of radars of the current vehicle is the preset number, determine whether the radar network topology is a series topology or a bus topology.

[0089] Furthermore, in some embodiments, after determining whether the number of radars of the current vehicle is a preset number, the acquisition and determination module 100 is also used to: if the number of radars of the current vehicle is greater than or equal to the preset number, determine whether the radar network topology is a bus topology or a star topology.

[0090] Furthermore, in some embodiments, after determining the radar network topology of at least one master radar, at least one slave radar and the current vehicle, the acquisition and determination module 100 is also used to: obtain the field of view angle coverage of each radar according to the installation position and design parameters of each radar, and identify the overlapping area between multiple field of view angle coverages.

[0091] Furthermore, in some embodiments, before controlling the slave radar to send the collected point cloud data and target data to the master radar, the control module 200 is also used to: convert the point cloud data and target data into data in the vehicle body coordinate system according to the conversion relationship between the installation position of each radar and the vehicle body coordinate system in which the current vehicle is located.

[0092] It should be noted that the above explanation of the embodiment of the data fusion method for the vehicle-mounted radar is also applicable to the data fusion device for the vehicle-mounted radar of this embodiment, and will not be repeated here.

[0093] According to the data fusion device of the vehicle-mounted radar proposed in the embodiment of the present application, after the current vehicle is powered on, the main radar is controlled to send time synchronization information to the slave radar based on the radar network topology structure, and the slave radar is controlled to send the collected point cloud data and target data to the main radar; the point cloud data and target data are fused and processed based on the preset fusion strategy to obtain the perception result. In this way, the problems of incomplete environmental perception and low radar utilization efficiency caused by the independent operation of each radar in the prior art are solved, and the communication mode and data processing flow between radars are improved, thereby significantly improving the radar utilization efficiency and the vehicle's perception accuracy of the surrounding environment.

[0094] Figure 6 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application. The vehicle may include:

[0095] A memory 601 , a processor 602 , and a computer program stored in the memory 601 and executable on the processor 602 .

[0096] When the processor 602 executes the program, the data fusion method of the vehicle-mounted radar provided in the above embodiment is implemented.

[0097] Furthermore, the vehicle also includes:

[0098] The communication interface 603 is used for communication between the memory 601 and the processor 602 .

[0099] The memory 601 is used to store computer programs that can be executed on the processor 602 .

[0100] The memory 601 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0101] If the memory 601, the processor 602 and the communication interface 603 are implemented independently, the communication interface 603, the memory 601 and the processor 602 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0102] Optionally, in a specific implementation, if the memory 601, the processor 602 and the communication interface 603 are integrated on a chip, the memory 601, the processor 602 and the communication interface 603 can communicate with each other through an internal interface.

[0103] The processor 602 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0104] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the data fusion method of the vehicle-mounted radar as described above is implemented.

[0105] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0106] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0107] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0108] The logic or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection with one or N wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0109] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0110] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0111] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0112] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A data fusion method for vehicle-mounted radar, characterized in that: The following steps are involved: Acquire the number of radars of the current vehicle, and determine a radar network topology structure of at least one master radar, at least one slave radar, and the current vehicle; After the current vehicle is powered on, the master radar is controlled to send time synchronization information to the slave radar based on the radar network topology, and the slave radar is controlled to send the collected point cloud data and target data to the master radar; The point cloud data and the target data are fused based on a preset fusion strategy to obtain a perception result.

2. The method according to claim 1, characterized in that The determining of the radar network topology of at least one master radar, at least one slave radar and the current vehicle comprises: Determining whether the number of radars of the current vehicle is a preset number; If the number of radars of the current vehicle is a preset number, it is determined that the radar network topology is a series topology or a bus topology.

3. The method according to claim 2, characterized in that After determining whether the number of radars of the current vehicle is a preset number, the method further includes: If the number of radars of the current vehicle is greater than or equal to the preset number, it is determined that the radar network topology is the bus topology or the star topology.

4. The method according to claim 1, characterized in that: After determining the radar network topology of at least one master radar, at least one slave radar and the current vehicle, the method further includes: According to the installation position and design parameters of each radar, the field of view angle coverage of each radar is obtained, and the overlapping areas between multiple field of view angle coverages are identified.

5. The method according to claim 1, characterized in that Before controlling the slave radar to send the collected point cloud data and target data to the master radar, the method further includes: According to the conversion relationship between the installation position of each radar and the body coordinate system where the current vehicle is located, the point cloud data and the target data are converted into data in the body coordinate system.

6. A data fusion device for a vehicle-mounted radar, characterized in that: include: An acquisition and determination module, used to acquire the number of radars of the current vehicle, and determine the radar network topology of at least one master radar, at least one slave radar and the current vehicle; a control module, configured to control the master radar to send time synchronization information to the slave radar based on the radar network topology after the current vehicle is powered on, and control the slave radar to send the collected point cloud data and target data to the master radar; The fusion processing module is used to fuse the point cloud data and the target data based on a preset fusion strategy to obtain a perception result.

7. The device according to claim 6, characterized in that The acquisition and determination module is used to: Determining whether the number of radars of the current vehicle is a preset number; If the number of radars of the current vehicle is a preset number, it is determined that the radar network topology is a series topology or a bus topology.

8. The device according to claim 7, characterized in that After determining whether the number of radars of the current vehicle is a preset number, the acquisition and determination module is further used to: If the number of radars of the current vehicle is greater than or equal to the preset number, it is determined that the radar network topology is the bus topology or the star topology.

9. A vehicle, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the data fusion method for the vehicle-mounted radar according to any one of claims 1 to 5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the data fusion method of the vehicle-mounted radar as described in any one of claims 1 to 5.

Images