Method, device and equipment for matching target vehicle and computer storage medium

Abstract

The invention relates to the technical field of computers, and provides a target vehicle matching method, device and equipment and a computer storage medium, and the method comprises the steps: continuously obtaining environment perception data and self-positioning data of a target vehicle; the environment sensing data comprises the environment position of each sensing vehicle in the environment where the target vehicle is located; the self-positioning data comprises a physical position of the target vehicle obtained based on a positioning network; when the self-positioning data obtained at the target moment cannot indicate the physical position of the target vehicle, based on each historical environment position of each historical sensing vehicle and each historical physical position of the target vehicle, which are obtained within a preset time range before the target moment, determining the physical position of the target vehicle in each historical sensing vehicle; screening out at least one historical matching vehicle; and based on the at least one historical matching vehicle and the continuously acquired environment sensing data, acquiring a target matching vehicle matched with the target vehicle from the target sensing vehicles corresponding to the target moment.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device and equipment for matching a target vehicle, and a computer storage medium. Background Art

[0002] With the continuous development of science and technology, the mapping of the target environment in the virtual space through digital twin technology has been applied in many different fields. For example, in the field of vehicle driving, the road conditions during the vehicle driving process can be completely mapped in the virtual space through the real-time twin technology. In this way, when the ambient light is poor or the driver has a large visual blind spot, the personnel in the vehicle can understand the current vehicle driving conditions through the mapping of the surrounding environment in the virtual space, thereby avoiding the occurrence of dangerous situations.

[0003] In order to realize the real-time twin technology as described above, the computing device responsible for twin view generation needs to combine the perception module and positioning module contained in the target vehicle to accurately generate the twin view. Figure 1 As shown, the twin view of vehicle-road collaboration takes the target vehicle as the first perspective.

[0004] Specifically, when the computing device constructs a twin view of the road conditions to which the target vehicle belongs, it is first necessary to perceive the road conditions of the road on which the target vehicle is currently located through the perception module on the target vehicle; among them, the road conditions perceived by the perception module generally include: vehicles traveling on the road (hereinafter referred to as perception vehicles, including the target vehicle), road signs on the road where the target vehicle is located, etc.

[0005] After the computing device creates a twin view of the road where the target vehicle is located through the perception module, it also needs to obtain the location information of the target vehicle through the positioning module in the target vehicle, so that the computing device can obtain a matching vehicle from all the perception vehicles whose position error with the target vehicle is less than a preset range. In this way, the computing device can use the perspective of the matching vehicle as the perspective of the target vehicle, and finally generate the following Figure 1 As shown, the twin view takes the target vehicle as the first perspective.

[0006] However, in the actual vehicle driving process, due to the complex and changeable road conditions, the positioning module on the target vehicle often cannot play its role in determining the location of the target vehicle. For example, near densely built places in the city, the positioning signal that the target vehicle can receive during driving may be very weak, resulting in the target vehicle being unable to accurately locate its own position. For another example, in an underground passage or a mountain tunnel, the target vehicle may not be able to receive the positioning signal at all, resulting in the complete inability to locate the location of the target vehicle.

[0007] In this case, since the location information of the target vehicle cannot be obtained, the computing device cannot determine the corresponding matching vehicle from several perceived vehicles based on the location of the target vehicle and the location of the perceived vehicle as mentioned above; this results in the computing device ultimately being unable to generate a twin view with the target vehicle itself as the first perspective.

[0008] Therefore, how to accurately match the correct target vehicle from several perceived vehicles obtained by the vehicle perception module when the positioning signal is weak or there is no positioning signal at all is an urgent problem to be solved. Summary of the invention

[0009] The present application provides a method, device, equipment and computer storage medium for matching a target vehicle, so as to achieve accurate matching between a target vehicle and a perception vehicle in the absence of a positioning signal or a weak positioning signal.

[0010] The specific technical solutions provided by the embodiments of this application are as follows:

[0011] In a first aspect, the present application provides a method for matching a target vehicle, the method being applied to a target vehicle and comprising:

[0012] Continuously acquire the target vehicle's environmental perception data and self-positioning data; wherein the environmental perception data at least includes: the environmental position of each perception vehicle in the target vehicle's environment; the self-positioning data includes: the physical position of the target vehicle obtained based on the positioning network;

[0013] When the self-positioning data obtained at the target time cannot indicate the physical position of the target vehicle, based on the historical environmental positions of the historically perceived vehicles and the historical physical positions of the target vehicle acquired within a preset time range before the target time, at least one historical matching vehicle is selected from the historically perceived vehicles, and the error between the historical environmental position of the historical matching vehicle and the historical physical position of the target vehicle is less than a first threshold;

[0014] Based on at least one historical matching vehicle and continuously acquired environmental perception data, a target matching vehicle that matches the target vehicle is obtained from each target perception vehicle corresponding to the target moment.

[0015] In a second aspect, the present application provides a device for matching a target vehicle, the device is applied to the target vehicle and includes:

[0016] An acquisition module is used to continuously acquire environmental perception data and self-positioning data of the target vehicle; wherein the environmental perception data at least includes: the environmental position of each perception vehicle in the environment where the target vehicle is located; the self-positioning data includes: the physical position of the target vehicle obtained based on the positioning network;

[0017] A processing module, configured to, when the self-positioning data obtained at the target time cannot indicate the physical position of the target vehicle, screen out at least one historical matching vehicle from among the historical perception vehicles based on the historical environmental positions of the historical perception vehicles and the historical physical positions of the target vehicle acquired within a preset time range before the target time, wherein the error between the historical environmental position of the historical matching vehicle and the historical physical position of the target vehicle is less than a first threshold;

[0018] The matching module is used to obtain a target matching vehicle that matches the target vehicle from each target perception vehicle corresponding to the target time based on at least one historical matching vehicle and the continuously acquired environmental perception data.

[0019] Optionally, each perception vehicle has a vehicle identification; the matching module is used to obtain a target matching vehicle that matches the target vehicle from each target perception vehicle corresponding to the target time based on at least one historical matching vehicle and the continuously acquired environmental perception data, specifically for:

[0020] If there is a target perception vehicle matching the vehicle identification of at least one historical matching vehicle among the target perception vehicles corresponding to the target time, the matching target perception vehicle is used as the target matching vehicle matching the target vehicle;

[0021] If there is no target perception vehicle that matches the vehicle identification of at least one historical matching vehicle among the target perception vehicles corresponding to the target moment, then based on the historical physical position of at least one historical matching vehicle and the continuously acquired environmental perception data, the predicted physical position of the target vehicle at the target moment is obtained, and based on the predicted physical position, a target matching vehicle that matches the target vehicle is obtained from the target perception vehicles at the target moment.

[0022] Optionally, the matching module is used to obtain the predicted physical position of the target vehicle at the target time based on the historical physical position of at least one historical matching vehicle and the continuously acquired environmental perception data, specifically for:

[0023] Based on the historical physical positions of the historical matching vehicles and the historical environmental positions of the historical perception vehicles corresponding to each individual moment within a preset time range, the relative position relationships between the historical matching vehicles and the historical perception vehicles are obtained;

[0024] When, based on each relative position relationship, it is determined that there is no adjacent vehicle among each historically perceived vehicle whose relative position relationship with the historically matched vehicle meets the preset conditions, the predicted physical position of the target vehicle at the target time is obtained based on the historical physical position of the historically matched vehicle and the driving information of the target vehicle within a preset time range.

[0025] Optionally, the driving information includes at least one of the following: driving speed, driving time, and driving angle.

[0026] Optionally, the matching module is used to obtain the predicted physical position of the target vehicle at the target time based on the historical physical position of the historical matching vehicle and the driving information of the target vehicle within a preset time range, specifically for:

[0027] Based on the historical physical location of the historical matching vehicle and the driving information of the target vehicle within a preset time range, the pending physical location of the target vehicle at the target time is obtained;

[0028] Based on the environmental perception data of the target vehicle at the target time, the road centerline position of the road centerline in the environment where the target vehicle is located is obtained;

[0029] The determined physical position and the road centerline position are weighted to obtain the predicted physical position of the target vehicle at the target time.

[0030] Optionally, the matching module is used to obtain the predicted physical position of the target vehicle at the target time based on the historical physical position of at least one historical matching vehicle and the continuously acquired environmental perception data, specifically for:

[0031] Based on the historical physical positions of the historical matching vehicles and the historical environmental positions of the historical perception vehicles corresponding to each individual moment within a preset time range, the relative position relationships between the historical matching vehicles and the historical perception vehicles are obtained;

[0032] Based on each relative position relationship, when it is determined that there is an adjacent vehicle among each historical perception vehicle whose relative position relationship with the historical matching vehicle meets the preset conditions, the predicted physical position of the target vehicle at the target time is obtained based on the relative position relationship between the adjacent vehicle and the historical matching vehicle, and the environmental position of the adjacent vehicle at the target time.

[0033] Optionally, the preset conditions include: the driving direction of the historical matching vehicle and the historical perception vehicle is the same, and the straight-line distance between the historical matching vehicle and the historical perception vehicle is less than a distance threshold.

[0034] Optionally, the matching module is used to obtain a target matching vehicle that matches the target vehicle from each target sensing vehicle at the target time based on the predicted physical position, specifically for:

[0035] Based on the predicted physical position, a target perception vehicle whose error between the environmental position and the predicted physical position is less than a second threshold is obtained from each target perception vehicle at the target moment; and the target perception vehicle is used as the target matching vehicle.

[0036] In a third aspect, the present application provides an electronic device comprising a processor and a memory, wherein the memory stores program code, and when the program code is executed by the processor, the processor implements the steps of any one of the above-mentioned methods for matching a target vehicle.

[0037] In a fourth aspect, the present application also provides a computer-readable storage medium, which includes a program code. When the program code is run on an electronic device, the program code is used to enable the electronic device to execute the steps of any one of the methods for matching a target vehicle.

[0038] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of any of the above-mentioned methods for matching a target vehicle when executed by a processor.

[0039] The beneficial effects of this application are as follows:

[0040] An embodiment of the present application provides a method, apparatus, device and storage medium for matching a target vehicle, the method comprising: by continuously acquiring environmental perception data of the environment in which the target vehicle is located, and self-positioning data including the physical position of the target vehicle, the target vehicle can effectively and in real time generate a twin view with the target vehicle as the first perspective based on these data; and when the acquired self-positioning data cannot indicate the physical position of the target vehicle, the target vehicle can determine the historical matching vehicle based on various historical data acquired within a preset time range before the target moment, and then acquire the target matching vehicle at the current moment based on the historical matching vehicle and the continuously acquired environmental perception data. In this way, the target matching vehicle corresponding to the target moment is determined based on the historical data, thereby ensuring the continuity of the generated twin view with the target vehicle as the first perspective, and avoiding the problem of being unable to determine the matching vehicle due to the inability to acquire the position information of the target vehicle, thereby causing the twin view generation to be interrupted.

[0041] Furthermore, when determining the target matching vehicle based on historical data, three different solutions are adopted for three different situations, which effectively improves the flexibility and applicability of the implementation of the present application.

[0042] Specifically, when there is a target perceived vehicle with the same vehicle identification as a historical matching vehicle, the vehicle is directly selected as the target matching vehicle. By utilizing the continuity of the perception data, the goal of quickly matching the target vehicle is achieved, and the efficiency of twin view regeneration is effectively improved. Moreover, the implementation of this method is simple and efficient, and the computational cost is low. It can ensure that the twin view is regenerated without the user's awareness, thereby improving the user experience.

[0043] When faced with a perceived vehicle that does not have the same vehicle identification but has an adjacent vehicle, the relative position relationship between the target vehicle and the adjacent vehicle is used to predict the physical position of the target vehicle, and then the target vehicle is matched. This method makes full use of the influence of environmental factors, reduces the computational cost of predicting the physical position, and has a high accuracy rate, effectively ensuring the rapid and reliable implementation of this solution.

[0044] When there is neither a perceived vehicle with the same vehicle identification nor an adjacent vehicle, the target vehicle's own historical physical position and driving information are used to predict the position, ensuring that a twin view can be generated in any case, improving the reliability of the implementation of this solution. In addition, during the prediction process, the position of the road center is taken as part of the considerations in the generated predicted physical position, effectively avoiding the problem of inaccurate predicted position and deviation from the road due to prediction based solely on the historical physical position of the target vehicle, improving the accuracy of the predicted physical position and the reliability of the implementation of this solution.

[0045] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A schematic diagram of the twin view under vehicle-road collaboration with the target vehicle as the first-person perspective;

[0047] Figure 2 A schematic diagram of a possible application scenario provided for an embodiment of the present application;

[0048] Figure 3 A flowchart of a method for matching a target vehicle provided in an embodiment of the present application;

[0049] Figure 4A A schematic diagram of a twin view provided in an embodiment of the present application;

[0050] Figure 4B A schematic diagram of a twin view with a target vehicle as a first perspective provided in an embodiment of the present application;

[0051] Figure 5 A flowchart of a method for obtaining a target matching vehicle that matches a target vehicle provided in an embodiment of the present application;

[0052] Figure 6 A schematic diagram of matching a target vehicle based on a predicted physical position provided in an embodiment of the present application;

[0053] Figure 7 A flowchart of a method for determining whether an adjacent vehicle exists provided in an embodiment of the present application;

[0054] Figure 8 A schematic diagram of the relative position relationship of vehicles provided in an embodiment of the present application;

[0055] Fig. 9 A schematic diagram of the relative position relationship between an adjacent vehicle and a target vehicle provided in an embodiment of the present application;

[0056] Fig.10 A flowchart of a method for obtaining a predicted physical location provided in an embodiment of the present application;

[0057] Fig.11 A flowchart of a method for matching a target vehicle provided in an embodiment of the present application;

[0058] Fig.12 A logic diagram for matching a target vehicle provided in an embodiment of the present application;

[0059] Fig.13 A schematic diagram of the structure of a device for matching a target vehicle provided in an embodiment of the present application;

[0060] Fig.14 A schematic diagram of a hardware structure of an electronic device in an embodiment of the present application;

[0061] Fig.15 A schematic diagram of the hardware composition structure of another electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described below in conjunction with the drawings in the embodiment of the present application. Obviously, the described embodiment is only a part of the embodiment of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application. In the absence of conflict, the embodiments in the present application and the features in the embodiments can be arbitrarily combined with each other. In addition, although the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in an order different from that here.

[0063] It is understandable that in the following specific implementations of the present application, sample images and other related data are involved. When the various embodiments of the present application are applied to specific products or technologies, relevant licenses or consents need to be obtained, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions. For example, when it is necessary to obtain relevant data, relevant volunteers can be recruited and relevant agreements for volunteer authorization data can be signed, and then the data of these volunteers can be used for implementation; or, by implementing within the scope of the authorized organization, the following implementation method is implemented by using the data of internal members of the organization to identify internal members; or, the relevant data used in the specific implementation are all simulated data, such as simulated data generated in a virtual scene.

[0064] To facilitate understanding of the technical solutions provided in the embodiments of the present application, some key terms used in the embodiments of the present application are explained here:

[0065] Digital Twin (DT), also known as digital mapping and digital mirroring, is a process that makes full use of data such as physical models, sensor updates, and operation history, integrates multi-disciplinary, multi-physical quantities, multi-scale, and multi-probability simulations, and completes mapping in virtual space, thereby reflecting the entire life cycle of the corresponding physical equipment. In short, a digital twin is to create a digital version of a "clone" based on a device or system. This "clone", also known as a "digital twin", is created on an information platform and is virtual. Moreover, in the actual application process, compared to design drawings, the biggest feature of a digital twin is that it is a dynamic simulation of a physical object, that is, the real-time state of the physical object, as well as the external environmental conditions, will be reproduced on the "twin". In the embodiment of the present application, the digital twin of the target vehicle is the real-time reproduction of the environment in which the target vehicle is located in the virtual digital world.

[0066] Twin view: Twin view is a virtual view in the application, which is a mapping of people, objects, and events in the real scene.

[0067] Target vehicle: In the embodiment of the present application, the target vehicle is the vehicle that needs to be digitally twinned, and the digital twin view obtained by the vehicle is as follows: Figure 1 As shown, this is a view with the target vehicle as the main perspective.

[0068] Perceived vehicle: In the embodiment of the present application, the perceived vehicle is a vehicle in the environment where the target vehicle is located, obtained through environmental perception data acquired by some sensors or cameras and other devices, and these perceived vehicles include the target vehicle itself. Therefore, the target vehicle generally needs to use a positioning module to determine which perceived vehicle among these perceived vehicles is a matching vehicle for itself, the target vehicle.

[0069] Matching vehicle: Among all the perceived vehicles perceived by the target vehicle, the vehicle that is actually the target vehicle itself.

[0070] Euclidean distance formula: In a mathematical rectangular coordinate system, let the coordinates of points A and B be A(x1, y1) and B(x2, y2) respectively. To find the distance between points A and B, the Euclidean distance formula is generally used:

[0071] Azimuth angle: also known as the horizontal longitude (Azimuth angle, Az), is one of the methods of measuring the angular difference between objects on a plane. Specifically, it is the horizontal angle between the north direction line of a certain point and the target direction line in a clockwise direction.

[0072] The following is a brief introduction to the design concept of the embodiment of the present application:

[0073] With the rapid development of Internet technology and sensor technology, the mapping of target environment in virtual space through digital twin technology has been applied in many different fields. One of the more common applications is in the field of vehicle driving, which uses real-time digital twin technology to completely map the road conditions during vehicle driving in virtual space, so that people in the vehicle can understand the current conditions of vehicles, people, road signs, etc. on the road through the twin view of the road conditions on the display screen, thereby reducing the possibility of dangerous situations.

[0074] However, such technology is highly dependent on the positioning function of the target vehicle using the technology. Because in the digital twin process, the data obtained by the perception module that can perceive the road conditions includes various objects on the road including the target vehicle (such as vehicles, road signs, pedestrians, etc.). In this case, in order to obtain a real-time twin view with the target vehicle as the first perspective, the computing device that generates the view needs to clearly identify which perception vehicle is the target vehicle itself among all the perception vehicles. This process of finding a perception vehicle that matches the target vehicle can be called the main vehicle matching process.

[0075] However, in the actual vehicle driving process, due to the complex and changeable road conditions, the positioning module of the target vehicle often cannot always play the role of accurate positioning. For example, near densely built places in the city, the positioning signal that the target vehicle can receive during driving may be very weak, resulting in the target vehicle being unable to accurately locate its own position. For another example, in an underground passage or a mountain tunnel, the target vehicle may not be able to receive the positioning signal at all, resulting in the complete inability to locate the location of the target vehicle.

[0076] In this case, since the location information of the target vehicle cannot be obtained, the computing device cannot determine a matching vehicle that matches the target vehicle from the perceived vehicles, which results in the computing device ultimately being unable to generate a twin view with the target vehicle itself as the first perspective.

[0077] In view of this, the embodiments of the present application provide a method, device, equipment and computer storage medium for matching a target vehicle. When the target vehicle cannot obtain its own positioning information, the target matching vehicle that matches the target vehicle is obtained from each perception vehicle in the current moment's environmental perception data through its previously acquired environmental perception data and historical matching results. Specifically, the method is applied to the target vehicle, and the target vehicle needs to continuously obtain the environmental perception data of its environment and its own self-positioning data, wherein the environmental perception data at least includes: the environmental position of each perception vehicle in the environment where the target vehicle is located, and the self-positioning data includes the target vehicle's own physical position obtained based on the positioning network. In this way, when the self-positioning data obtained by the target vehicle can indicate the physical position of the target vehicle, the target vehicle can compare its acquired physical position with the environmental position of each perception vehicle, and use the vehicle whose error between the physical position and the environmental position is less than the first threshold as the matching vehicle corresponding to the target vehicle.

[0078] When the target vehicle determines that the self-positioning data acquired at the target time cannot indicate the physical location of the target vehicle, the target vehicle needs to screen out at least one historical matching vehicle from each historical perception vehicle based on the historical environmental positions of each historical perception vehicle and the historical physical positions of the target vehicle acquired within a preset time range before the target time.

[0079] Then, based on the at least one historical matching vehicle and the continuously acquired environmental perception data, a target matching vehicle that matches the target vehicle is obtained from the target perception vehicles corresponding to the target moment. Specifically, when the target vehicle cannot obtain the physical position of the target vehicle itself, in order to determine the target matching vehicle from the perception vehicles, it is first necessary to clarify the current situation of the target vehicle. For this reason, the embodiment of the present application presets three possible situations: First, the vehicle identification of the historical matching vehicle is the same as the vehicle identification of a target perception vehicle in the environmental perception data acquired at the target moment. In this way, the target vehicle can directly use the target perception vehicle with the same vehicle identification as the historical matching vehicle as the target matching vehicle corresponding to the target moment; second, there is no vehicle with the same vehicle identification as the historical matching vehicle among the target perception vehicles corresponding to the target moment, but there is a vehicle with the same vehicle identification as the historical matching vehicle before the target moment. The target vehicle can predict the physical position of the target vehicle at the target time according to the relative position relationship between the adjacent vehicle and the historical matching vehicle and the environmental position of the adjacent vehicle at the target time, so that the target vehicle can obtain the corresponding target matching vehicle from each target perception vehicle according to the predicted physical position; thirdly, when there is neither a perception vehicle with the same vehicle identification as the historical matching vehicle nor an adjacent vehicle that meets the preset conditions, the target vehicle can directly predict its physical position at the target time according to its historical physical position and its own driving information, so as to obtain the corresponding target matching vehicle from each target perception vehicle according to the physical position.

[0080] In this way, the embodiment of the present application provides a method for successfully completing the matching of the target vehicle in various situations where the positioning function fails.

[0081] In an embodiment of the present application, the part of predicting the physical position of the target vehicle at the target time involves artificial intelligence (AI) and machine learning technology, and is designed based on the position prediction technology in artificial intelligence and machine learning (ML).

[0082] Artificial intelligence is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence.

[0083] Artificial intelligence is the study of the design principles and implementation methods of various intelligent machines, so that the machines have the functions of perception, reasoning and decision-making. Artificial intelligence technology mainly includes computer vision technology, natural language processing technology, and machine learning / deep learning. With the research and progress of artificial intelligence technology, artificial intelligence has been studied and applied in many fields, such as common smart homes, smart customer service, virtual assistants, smart speakers, smart marketing, unmanned driving, automatic driving, robots, smart medical care, etc. It is believed that with the development of technology, artificial intelligence will be applied in more fields and play an increasingly important role.

[0084] Machine learning is a multi-disciplinary subject that involves probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Compared with data mining, which seeks mutual characteristics between big data, machine learning focuses more on algorithm design, allowing computers to automatically "learn" rules from data and use the rules to predict unknown data.

[0085] Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are spread across all areas of artificial intelligence. Machine learning and deep learning usually include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning and other technologies. Reinforcement learning (RL), also known as reinforcement learning, evaluation learning or enhanced learning, is one of the paradigms and methodologies of machine learning. It is used to describe and solve the problem of how an agent can maximize its rewards or achieve specific goals through learning strategies during its interaction with the environment.

[0086] The following briefly introduces the application scenarios to which the technical solutions of the embodiments of the present application can be applied. It should be noted that the application scenarios introduced below are only used to illustrate the embodiments of the present application and are not limited. In the specific implementation process, the technical solutions provided by the embodiments of the present application can be flexibly applied according to actual needs.

[0087] The solution provided in the embodiments of the present application can be applied to most scenarios for matching target vehicles, such as scenarios where vehicles in mountain tunnels cannot receive positioning signals, and scenarios where the accurate physical location cannot be provided due to weak positioning signals in densely populated urban areas.

[0088] See also Figure 2 , is a schematic diagram of a possible application scenario provided in an embodiment of the present application, in which a terminal device 201 and a server 202 may be included.

[0089] The terminal device 201 may be a mobile phone, a tablet computer (PAD), a personal computer (PC), a wearable device, a vehicle-mounted terminal, etc., or a camera, a video camera, a driving recorder, etc. The common feature of these devices is that they are in the same physical location as the target vehicle. The server 202 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0090] The server 202 may include one or more processors 2021, a memory 2022, and an I / O interface 2023 for interacting with the terminal. In addition, the server 202 may also be configured with a database 2024, which may be used to store environmental perception data about roads provided by the terminal device, historical matching vehicles of the target vehicle, and model parameters for predicting the physical location of the target vehicle. Among them, the memory 2022 of the server 202 may also store program instructions for the method for matching the target vehicle provided in the embodiment of the present application, which, when executed by the processor 2021, can be used to implement the steps of the method for matching the target vehicle provided in the embodiment of the present application to obtain the result of matching the target vehicle, and the generated twin view with the target vehicle as the first perspective can be displayed accordingly on the terminal device 201.

[0091] The terminal device 201 and the server 202 may be directly or indirectly connected to each other through one or more communication networks 203. The communication network 203 may be a wired network or a wireless network, for example, a mobile cellular network or a wireless fidelity (Wireless-Fidelity, WIFI) network, or other possible networks, which are not limited in the present application.

[0092] It should be noted that the method for matching the target vehicle in the embodiment of the present application can be executed by a computer device, which can be a terminal device 201 or a server 202, that is, the method can be executed by the terminal device 201 or the server 202 alone, or can be executed jointly by the terminal device 201 and the server 202.

[0093] For example, when the method is executed by the terminal device 201 alone, the terminal device 201 can directly obtain the target perception vehicle that matches the target vehicle among the perception vehicles corresponding to the target time through the environmental perception data obtained by the target vehicle and the historical matching data saved before the target time.

[0094] For another example, when the method is jointly executed by the terminal device 201 and the server 202, the terminal device 201 can continuously obtain environmental perception data of the target vehicle during its driving process, and then transmit these data to the server 202 that is communicatively connected to the terminal device 201 through the communication network 203. The target perception vehicle that matches the target vehicle is determined by the server 202, and then a twin view is directly generated in the server 202 and then transmitted to the terminal device 201, or the result of the target matching vehicle is directly sent to the terminal device 201, and the terminal device itself generates a corresponding twin view.

[0095] It should be noted that Figure 2 What is shown is just an example. In fact, the number and communication mode of terminal devices and servers are not limited and are not specifically limited in the embodiments of the present application.

[0096] The following describes the method for matching a target vehicle provided by an exemplary embodiment of the present application in combination with the application scenarios described above and with reference to the accompanying drawings. It should be noted that the above application scenarios are only shown to facilitate understanding of the spirit and principles of the present application, and the implementation methods of the present application are not limited in this regard.

[0097] During the driving process of the vehicle, the real-time twinning of the road conditions through digital twin technology can effectively improve the understanding of the road conditions by the personnel in the vehicle. However, such twin technology is very dependent on the positioning function of the vehicle, whether it is through the vehicle-mounted terminal device or the mobile terminal device of the personnel in the vehicle. Because only through correct and effective positioning signals can the vehicle determine which perceived vehicle is the vehicle it actually corresponds to from the perceived vehicles.

[0098] Therefore, in such a situation, once there is a problem with the vehicle positioning signal obtained and the vehicle itself cannot be accurately positioned, the process of real-time twinning of road conditions through digital twin technology will be forced to be interrupted.

[0099] To this end, the present application embodiment provides Figure 3A method for matching a target vehicle is shown, and the method is applied to the target vehicle. Specifically, it can be executed by a terminal device in the same physical location as the target vehicle, for example, a vehicle-mounted terminal device or a mobile terminal device such as a mobile phone or a tablet; it can also be executed by a server that is connected to the terminal device on the target vehicle, and this application does not limit it. For the sake of simplicity in the subsequent description, when introducing the method for matching a target vehicle provided in the embodiment of the present application, the execution subject will be taken as an example of a terminal device on the target vehicle.

[0100] See also Figure 3 , is a flow chart of a method for matching a target vehicle provided in an embodiment of the present application, and the specific operation steps of the method are as follows:

[0101] Step S301: Continuously acquire environmental perception data and self-positioning data of the target vehicle; wherein the environmental perception data at least includes: the environmental position of each perception vehicle in the environment where the target vehicle is located, and the self-positioning data includes: the physical position of the target vehicle obtained based on the positioning network.

[0102] It should be noted that the target vehicle can acquire environmental perception data and self-positioning data in a variety of different ways.

[0103] The first step is to obtain environmental perception data.

[0104] When the target vehicle acquires environmental perception data, it can acquire it through the terminal device owned by the target vehicle itself. For example, the image information of the road can be directly acquired through devices such as cameras, the distance information between various objects on the road can be acquired through the laser sensor of the target vehicle, and the information related to pedestrians on the road can be acquired through infrared probes. Alternatively, when the target vehicle acquires environmental perception data, it can also acquire the situation on the road by communicating with the devices on the road. For example, by exchanging data with the cameras on the road, the image information of entities such as vehicles and pedestrians on the road can be obtained; for another example, the relative position information of the target vehicle and the entities on the road can be acquired through sensors, chips, etc. on the road.

[0105] After obtaining the above information, the terminal device in the target vehicle that collects this data can obtain the environmental positions of various entities in the environment where the target vehicle is located based on the longitude and latitude data of the road section stored in itself and the environmental information of various physical objects on the road, including at least the environmental positions of each sensing vehicle, and may also include the environmental positions of pedestrians or road signs on the road. In an optional implementation, these environmental positions can be expressed in the form of longitude and latitude data.

[0106] The second is the acquisition of self-positioning data. For self-positioning data, the acquisition method is relatively simple. The target vehicle can directly obtain its own physical location through a device in the vehicle that communicates with the positioning network. For example, the target vehicle can obtain a global positioning system (GPS) signal through a terminal device in the vehicle, thereby directly locating its own physical location through the signal, or it can also locate its own physical location through other positioning networks (such as Beidou satellite navigation and positioning system, etc.), and this application does not limit it.

[0107] After obtaining environmental perception data and self-positioning data respectively in the above manner, if it is determined that the self-positioning data can indicate the physical position of the target vehicle at the corresponding moment, then the target vehicle can generate a corresponding twin view based on these two types of data.

[0108] For example, the target vehicle may first generate the current moment through environmental perception data. Figure 4A As shown, the twin view of the road section where the target vehicle is located includes the reproduction of all vehicles in the current road section in the virtual view, including the target vehicle. However, in the twin view at the current stage, it is not possible to determine which vehicle among all the vehicles should be used as the main perspective corresponding to the target vehicle. Therefore, the target vehicle also needs to obtain self-positioning data to determine its own physical position at the current moment, and then compare its own physical position with the environmental data of each perception vehicle in the environmental perception data, and select the perception vehicle whose error between the environmental position and the physical position of the target vehicle is less than the first threshold as the matching vehicle corresponding to the target vehicle. In this way, the target vehicle can generate the following according to the perspective of the matching vehicle. Figure 4B As shown, the twin view takes the target vehicle as the main perspective.

[0109] The above is a method for matching a target vehicle when the self-positioning data can accurately indicate the location of the target vehicle. However, since the target vehicle is not always able to receive the positioning signal, or the positioning signal is not always able to indicate the correct location of the target vehicle, when it is determined that the self-positioning data cannot indicate the physical location of the target vehicle, the target vehicle needs to perform the following operations to ensure that the expected effect of matching the target vehicle from the perceived vehicles can be achieved smoothly.

[0110] Step S302: When the self-positioning data obtained at the target time cannot indicate the physical position of the target vehicle, based on the historical environmental positions of each historically perceived vehicle and the historical physical positions of the target vehicle acquired within a preset time range before the target time, at least one historical matching vehicle is screened out from each historically perceived vehicle, and the error between the historical environmental position of the historical matching vehicle and the historical physical position of the target vehicle is less than a first threshold.

[0111] In this step, what the target vehicle needs to do is to obtain the historical matching vehicles of the target vehicle before the target time when it is found that the self-positioning data obtained at the target time cannot indicate the physical position of the target vehicle.

[0112] Optionally, the specific manifestation that the self-positioning data cannot indicate the physical position of the target vehicle at the target time can be in the following forms: one is that in the self-positioning data acquired by the target vehicle, the value of the data used to indicate the physical position of the target vehicle is 0, so that the target vehicle cannot acquire its own physical position through the self-positioning data; the other is that during the driving process of the target vehicle, in the self-positioning data acquired at the target time, the value of the data used to indicate the physical position of the target vehicle is the same as the value in the self-positioning data acquired last time, so that the target vehicle can determine that the currently acquired position information cannot accurately indicate the current physical position at the target time.

[0113] When it is determined that the acquired self-positioning data cannot indicate the physical position of the target vehicle at the target time, the target vehicle can directly determine the historical matching vehicles that match the target vehicle among the historical perception vehicles within the preset time range based on all environmental perception data and self-positioning data acquired within the preset time range before the target time; or, the target vehicle can also save the information about the matching vehicle each time the matching vehicle corresponding to the target vehicle is determined, so that when the target vehicle needs to obtain the information of the historical matching vehicle subsequently, the information of the historical matching vehicle can be directly obtained from the stored data.

[0114] Regardless of whether the historical matching vehicles are directly obtained by matching the historical environmental data with the historical physical position, or the information of the historical matching vehicles is directly obtained from the stored data, when the target vehicle is matched with the perceived vehicle, it is determined by the error between the environmental position of the perceived vehicle and the physical position of the target vehicle. When the error is less than the first threshold, it can be determined that the position of the target vehicle is close enough to the position of the perceived vehicle, and further it can be determined that the perceived vehicle in the environmental perception data is most likely the target vehicle itself. The specific value of the first threshold used in this determination method can be determined by direct pre-configuration by the developer, or it can be determined after obtaining a result that meets the convergence requirements through model training, and this application does not impose any restrictions on this.

[0115] After the historical matching vehicles are obtained, the target vehicle needs to perform the following operations:

[0116] Step S303: Based on at least one historical matching vehicle and the continuously acquired environmental perception data, a target matching vehicle that matches the target vehicle is obtained from each target perception vehicle corresponding to the target moment.

[0117] After determining that the physical location cannot be directly obtained through the self-positioning data obtained at the target time, the target vehicle can choose to obtain the corresponding target matching vehicle from each target perception vehicle through at least one historical matching vehicle and the continuously obtained environmental perception data.

[0118] Optionally, in the process of acquiring the target matching vehicle, the target vehicle may execute different methods of acquiring the target matching vehicle according to different situations of the historical matching vehicles and the historically perceived vehicles.

[0119] For details, see Figure 5 , which is a flow chart of a method for obtaining a target matching vehicle that matches a target vehicle provided in an embodiment of the present application, such as Figure 5 As shown, after obtaining the historical matching vehicle, the target vehicle can perform the following steps:

[0120] Step S501: Determine whether there is a target perception vehicle matching the vehicle identification of at least one historical matching vehicle among the target perception vehicles corresponding to the target moment; if so, execute step S502; if not, execute steps S503-S504.

[0121] Before the self-positioning data fails to indicate the physical location of the target vehicle, the target vehicle will try to ensure the continuity of the perceived object when perceiving the vehicle in the environment, that is, when the target vehicle perceives the vehicle in the environment, it will assign a unique vehicle ID to it to distinguish different perceived vehicles, and the ID of the same vehicle will be kept consistent as much as possible. In this way, by using this feature, when the self-positioning data fails to indicate the physical location of the target vehicle at the target time, the target vehicle can determine whether there is a target perceived vehicle with the same vehicle ID as at least one historical matching vehicle among all the target perceived vehicles corresponding to the target time.

[0122] If it exists, the target vehicle needs to perform the following operations:

[0123] Step S502: taking a target perception vehicle that matches the vehicle identification of at least one historical matching vehicle as a target matching vehicle that matches the target vehicle.

[0124] For example, after each successful completion of the target vehicle matching goal, the target vehicle can save the vehicle identification of the matched perception vehicle. Whenever the target vehicle determines that the self-positioning data cannot accurately indicate the physical location, the target vehicle can obtain the vehicle identification of the last saved historical matching vehicle before the target time, and then directly select the perception vehicle whose vehicle identification is the same as the vehicle identification of the last saved historical matching vehicle from the perception vehicles corresponding to the target time. If the perception vehicle can be successfully selected, the perception vehicle is used as the target matching vehicle corresponding to the target vehicle at the target time.

[0125] If it does not exist, the target vehicle needs to perform the following operations:

[0126] Step S503: Based on the physical position of at least one historical matching vehicle and the continuously acquired environmental perception data, the predicted physical position of the target vehicle at the target time is obtained.

[0127] Since there is no vehicle with the same vehicle identification as the historical matching vehicle among the target perception vehicles, when the target matching vehicle cannot be directly determined, the target vehicle can predict the physical position of the target vehicle at the target time based on the historical physical positions of the historical matching vehicles and the continuously acquired environmental perception data, thereby obtaining the corresponding predicted physical position.

[0128] Step S504: Based on the predicted physical position, a target matching vehicle that matches the target vehicle is obtained from each target perception vehicle at the target time.

[0129] After the predicted physical position is acquired, the target vehicle can acquire a target matching vehicle that matches the target vehicle from among the target sensing vehicles at the target time according to the predicted physical position.

[0130] Optionally, when the target vehicle obtains the target matching vehicle based on the predicted physical position, how to obtain the accurate target matching vehicle may be similar to the method of historical matching vehicles.

[0131] Specifically, the target vehicle can obtain a target perception vehicle whose error between the environmental position and the predicted physical position is less than a second threshold from the target perception vehicles at the target time based on the predicted physical position, and then use the target perception vehicle as the target matching vehicle corresponding to the target time. Figure 6 As shown in FIG. 1 , the position of the vehicle represented by the dotted line is the predicted physical position, and the vehicles represented by the other solid lines are the target sensing vehicles at the target time. Figure 6 In the scene shown, since the dashed vehicle is closest to vehicle 1 in the figure, vehicle 1 (perceived vehicle) can be used as the target matching vehicle.

[0132] For example, assuming that the predicted physical location is expressed in the form of longitude and latitude coordinates, the predicted physical location is recorded as (Lat cmp , Lng cmp ), and the environmental position of each target perception vehicle is (Lat j , Lng j ), where j is a positive integer, Lat represents longitude, and Lng represents latitude. In this way, when determining the error between the environmental position and the predicted physical position, the error between the predicted physical position and each environmental position can be determined by calculating the straight-line distance between the predicted physical position and each environmental position. Specifically, the formula for calculating the straight-line distance between the two is as follows:

[0133] d j =f dist (Lat cmp , Lng cmp , Lat j , Lng j ) (Formula 1)

[0134] Among them, d j It is used to indicate the straight-line distance corresponding to each target sensing vehicle, f dist Represents the distance formula between two points (i.e., the Euclidean distance formula).

[0135] After completing the d corresponding to each target perception vehicle j After calculation, from all d j Find the d that is less than the second threshold j The corresponding target perception vehicle takes the target perception vehicle as the target matching vehicle corresponding to the target vehicle at the target time.

[0136] It should be noted that, since in this method, the physical position of the target vehicle is obtained by predicting the target vehicle based on the historical physical position, the value of the second threshold for limiting the error between the predicted physical position and the environmental position may not be the same as the value of the first threshold, which is based on the judgment of the developer or the result obtained during model training. Therefore, this application does not limit whether the value of the second threshold is the same as the value of the first threshold.

[0137] In this solution, by continuously acquiring environmental perception data of the target vehicle's environment and self-positioning data including the target vehicle's physical position, the target vehicle can effectively and real-time generate a twin view with the target vehicle as the first perspective based on these data; and when the acquired self-positioning data cannot indicate the physical position of the target vehicle, the target vehicle can determine the historical matching vehicle based on various historical data acquired within a preset time range before the target moment, and then acquire the target matching vehicle at the current moment based on the historical matching vehicle and the continuously acquired environmental perception data. In this way, the target matching vehicle corresponding to the target moment is determined based on the historical data, thereby ensuring the continuity of the generated twin view with the target vehicle as the first perspective, and avoiding the problem of being unable to determine the matching vehicle due to the inability to obtain the target vehicle's position information, thereby interrupting the generation of the twin view.

[0138] Optionally, for the process of predicting the physical position of the target vehicle at the target time based on the historical physical position of the target vehicle in the above step S503, the embodiments of the present application provide the following two feasible implementation methods for different situations.

[0139] One is how the target vehicle predicts its physical position at the target time in the presence of adjacent vehicles.

[0140] Since the method proposed in the embodiment of the present application is applicable to the situation that the positioning signal provided by the positioning network cannot indicate the physical position of the target vehicle, and such a situation generally occurs because the target vehicle is in a crowded or confined environment. Therefore, for vehicles traveling in such an environment, frequent overtaking and frequent lane changes are usually less likely to occur. In other words, when the positioning signal fails to indicate the physical position, the relative position between the target vehicle and the vehicles around it will generally remain fixed to a certain extent.

[0141] By using the above characteristics, the target vehicle can predict its own physical position based on the relative position relationship between the surrounding vehicles and itself. If the target vehicle is expected to predict its physical position based on the relative position relationship between the surrounding vehicles and itself, then it is necessary that there are adjacent vehicles around it whose relative position relationship meets the preset requirements. To this end, the embodiment of the present application provides the following method for determining whether an adjacent vehicle exists.

[0142] See also Figure 7 , is a flow chart of a method for determining whether an adjacent vehicle exists provided in an embodiment of the present application. Figure 7 As shown, when determining whether an adjacent vehicle exists, the target vehicle can perform the following steps:

[0143] Step S701: Based on the historical positions of the historical matching vehicles and the historical environmental positions of the historical perception vehicles corresponding to each individual moment within a preset time range, the relative position relationships between the historical matching vehicles and the historical perception vehicles are obtained.

[0144] Among them, the preset time range is the preset time range in the above step S302. The specific length of the time range can be directly configured by the developer, or adjusted through the convergence process in the model training. This application does not impose any restrictions.

[0145] Furthermore, since the target vehicle continuously acquires environmental perception data and self-positioning data, the corresponding data of each perception vehicle is stored in batches in the terminal device of the target vehicle. For example, the target vehicle can store the environmental perception data continuously acquired over a period of time in the manner shown in Table 1 below.

[0146] Table 1

[0147] Time / Vehicle ID 001 002 003 004 005 007 18:11 <![CDATA[(x 11 ,and 11 )]]> <![CDATA[(x 21 ,and 21 )]]> <![CDATA[(x 31 ,and 31 )]]> <![CDATA[(x 41 ,and 41 )]]> <![CDATA[(x 51 ,and 51 )]]> <![CDATA[(x 71 ,and 71 )]]> 18:12 <![CDATA[(x 12 ,and 12 )]]> <![CDATA[(x 22 ,and 22 )]]> <![CDATA[(x 32 ,and 32 )]]> <![CDATA[(x 42 ,and 42 )]]> <![CDATA[(x 52 ,and 52 )]]> <![CDATA[(x 72 ,and 72 )]]> 18:13 <![CDATA[(x 13 ,and 13 )]]> <![CDATA[(x 23 ,and 23 )]]> <![CDATA[(x 33 ,and 33 )]]> <![CDATA[(x 43 ,and 43 )]]> <![CDATA[(x 53 ,and 53 )]]> <![CDATA[(x 73 ,and 73 )]]>

[0148] It should be understood that storing the environmental position corresponding to each sensing vehicle through the above Table 1 is only a possible storage method, which is shown to facilitate understanding of the spirit and principles of the present application, and the implementation methods of the present application are not limited in this regard.

[0149] It can be seen from the above Table 1 that the data of the corresponding environmental position of the sensing vehicle is continuously and intermittently acquired within a certain time range, wherein the time length of each interval is not necessarily fixed and can be specifically configured in actual use, and this application does not impose any restrictions on this.

[0150] Therefore, the method proposed in step S701: "Based on the historical positions of the historical matching vehicles corresponding to each individual moment within the preset time range and the historical environmental positions of each historically perceived vehicle", the relative position relationship is obtained, which is also performed for different perceived vehicles at different moments.

[0151] Among them, a more special point is that when the preset time range is configured to include only one environmental perception data, the environmental perception data and the corresponding historical matching vehicle data at this time are the last time before the target time that can be directly matched according to the self-positioning data, thereby obtaining the relevant data of the process of historical matching vehicles. In this way, the target vehicle needs to trace back less historical data, which reduces the amount of calculation required by the device. In this way, the efficiency of the device in obtaining the predicted physical location can be effectively improved, and the historical data is closest to the target time, so it is more referenceable, which can also improve the accuracy of the predicted physical location.

[0152] The acquisition of the relative positional relationships between the historical matching vehicles and the historical perception vehicles may be achieved in several different ways.

[0153] A relatively simple method is to directly use the straight-line distance between the historical matching vehicle and each historical perception vehicle as the relative position relationship between the two. This method is relatively simple and direct, and can quickly obtain the relative position relationship between the historical matching vehicle and different historical perception vehicles.

[0154] Another method is to obtain the direction angle between the historical matching vehicle and each historical perception vehicle while obtaining the straight-line distance between the historical matching vehicle and each historical perception vehicle, where the direction angle is the angle between the direction indicated by the front of the vehicle and the true north direction. Figure 8 , is a schematic diagram of a relative position relationship provided in an embodiment of the present application, in which Figure 8 In the scene shown, among the vehicles traveling in the opposite direction, one has an acute direction angle and the other has an obtuse direction angle. It can be seen that the relationship between the direction angles can be used to show whether the two vehicles are traveling in the same direction. In this way, by combining the two aspects of data, the relative position relationship between the historical matching vehicle and the historical perception vehicle can be expressed more accurately and comprehensively, thereby improving the reliability of the implementation of this method.

[0155] Step S702: Based on each relative position relationship, determine whether the relative position relationship between each historically perceived vehicle and the historically matched vehicle meets a preset condition; if yes, execute step S703; if no, execute step S704.

[0156] When judging whether the relative position relationship between each historically perceived vehicle and the historically matched vehicle satisfies a preset condition based on each relative position relationship, different preset conditions may be set based on the relative position relationship containing different data.

[0157] Exemplarily, when the relative positional relationship between the two vehicles is determined only based on the straight-line distance between the two vehicles, when it is determined that the straight-line distance between the two vehicles is less than a distance threshold, it can be determined that the preset condition is met between the two vehicles.

[0158] When the relative position relationship between the vehicles includes both the straight-line distance and the direction angle, determining whether the preset conditions are met between the two vehicles can be accomplished in the following manner.

[0159] Assuming that there is only one corresponding moment of environmental perception data and historical matching vehicle data within the preset time range, then let the direction angle of the historical matching vehicle be H last , the historical physical location is (Lat last , Lng last), and the direction angle of each historical perception vehicle corresponding to this moment is H j , the historical environment location is (Lat j , Lng j ).

[0160] Then, for each historical perception vehicle, whether the relative position relationship between it and the historical matching vehicle meets the preset requirements can be determined by the following two formulas:

[0161] |H last -H j |<H td (Formula 2)

[0162] f dist (Lat last , Lng last , Lat j , Lng j )<D td (Formula 3)

[0163] Among them, H td Used to indicate the direction angle threshold, D td Used to represent the distance threshold; Formula 2 is used to determine whether the historically perceived vehicle and the historically matched vehicle are in the same direction, and Formula 3 is used to determine whether the distance between the historically perceived vehicle and the historically matched vehicle is close enough.

[0164] In this way, when it is determined that the relative position relationship between a certain historically perceived vehicle and a historically matched vehicle satisfies the limitations of the above formula 2 and formula 3, it can be determined that the historically matched vehicle has a corresponding adjacent vehicle, and then the target vehicle can execute the subsequent step S703. When it is determined that there is no historically perceived vehicle whose relative position relationship with the historically matched vehicle satisfies the limitations of the above formula 2 and formula 3 among the historically perceived vehicles, the target vehicle needs to continue to execute step S704.

[0165] Step S703: The historically perceived vehicle whose relative position relationship with the historically matched vehicle meets a preset condition is regarded as an adjacent vehicle.

[0166] Optionally, when there are more than one historical perception vehicles and the relative position relationship between the historical matching vehicles meets a preset condition, the historical matching vehicle with the shortest straight-line distance to the historical matching vehicle is taken as the adjacent vehicle.

[0167] Step S704: Determine whether there is no adjacent vehicle among the historically sensed vehicles.

[0168] Through the above method, the target vehicle can determine whether there is a corresponding adjacent vehicle among the perceived vehicles acquired by the target vehicle.

[0169] When the target vehicle determines that there is an adjacent vehicle, and the environmental perception data obtained at the target time also contains a perceived vehicle with the same vehicle identification as the adjacent vehicle, the target vehicle can predict its physical position at the target time based on the relevant information of the adjacent vehicle.

[0170] Specifically, the target vehicle may obtain the predicted physical position of the target vehicle at the target time based on the relative position relationship between the adjacent vehicle and the historical matching vehicle, and the environmental position of the adjacent vehicle at the target time.

[0171] See also Fig. 9 , is a schematic diagram of the relative position relationship between an adjacent vehicle and a target vehicle provided in an embodiment of the present application. Fig. 9 As shown, the left half represents the positions of vehicles a and c traveling in the same direction on the road at time T-1, and the right half represents the positions of vehicles b and d traveling in the same direction on the road at time T; it should be noted that both vehicles c and d represent target vehicles, but due to the difference in time and position, in order to distinguish the vehicles at the two times and positions, vehicles c and d are used to represent the target vehicles respectively, and the same is true for vehicles a and b, except that both vehicles a and b represent the adjacent vehicles corresponding to the target vehicle.

[0172] So, in Fig. 9 In the scenario shown, when the target vehicle is unable to obtain the accurate physical position based on the self-positioning data at time T, and the vehicle identification of each target perception vehicle in the environmental perception data at time T does not exist in the vehicle identification of at least one historical matching vehicle, the target vehicle can predict the position of the target vehicle at time T based on the relative position relationship between the historical matching vehicle (vehicle c) and the adjacent vehicle (vehicle a) at time T-1.

[0173] Specifically, the basic principle of the prediction method is to use the properties of parallelograms: Figure 6 As shown, the four points of the parallelogram are vehicle a (adjacent vehicle) at time T-1, vehicle c (historical matching vehicle) at time T-1, vehicle b (adjacent vehicle) at time T, and vehicle d (target vehicle) at time T. The positions of the four vehicles a, b, c, and d can form a parallelogram, where ad and bc form a diagonal line and their midpoints coincide, ac is parallel to bd, and ab is parallel to cd. Therefore, when the positions of points a, b, and c are clear, the position of point d can be determined.

[0174] Assume that the position coordinates of adjacent vehicles at time T-1 and time T are: The position coordinates of the historical matching vehicle at time T-1 are: The predicted position coordinates of the target vehicle at time T are:

[0175] In this case, the target vehicle can determine the predicted physical position of the target vehicle at time T by using the following formulas 4 and 5:

[0176]

[0177]

[0178] The above describes how to predict the physical position of the target vehicle at the target time when there are adjacent vehicles.

[0179] As for predicting the physical position of the target vehicle at the target time, when there are no adjacent vehicles, it is also necessary to complete the prediction of the physical position. In this case, the target vehicle can also achieve the goal in the following way.

[0180] Optionally, when there is no corresponding adjacent vehicle to the target vehicle, the target vehicle can obtain the predicted physical position of the target vehicle at the target time based on the historical physical position of the historically matched vehicles and the driving information of the target vehicle within a preset time range.

[0181] Exemplarily, when obtaining the predicted physical position, the target vehicle first needs its own initial position information, compensation step s, and direction angle h.

[0182] Among them, the initial position information can be the historical physical position of the historical matching vehicle. Furthermore, in order to obtain a more accurate predicted physical position, the historical physical position corresponding to the initial position can be the historical physical position corresponding to the last time the physical position of the target vehicle could be accurately indicated before the target moment.

[0183] The compensation step length s may be calculated based on the target vehicle's driving information within a preset time range. In a possible implementation, the driving information includes at least one of the following: driving speed, driving time, and driving angle.

[0184] When calculating the compensation step length according to the above driving information, several different methods may be used.

[0185] For example, the target vehicle can first determine the time t between the time corresponding to the initial position information and the target time, and then calculate the average speed of the target vehicle during the driving process within this time range. Finally, based on the duration and average speed, the compensation step length within this time period is calculated

[0186] For another example, the target vehicle can count the time interval between each acquisition of environmental perception data, recorded as Δt, and the target vehicle can count the average reporting interval based on the most recent k reporting intervals, that is, Where i is a positive integer and k is a positive integer. The closest reporting interval of the target vehicle to the target time is denoted as Δt last , then the compensation interval corresponding to the compensation step is Δt last Next, the speed obtained at the time corresponding to the initial position information is taken as the initial speed and recorded as v last , then the compensation step length s = Δt can be calculated based on the compensation interval and initial speed last ×v last .

[0187] Regarding the acquisition of the direction angle, the target vehicle can determine the latitude and longitude information of the environment described by the target vehicle based on the pre-stored map information and the acquired environmental perception data, and then obtain the direction angle of the road where the target vehicle is located based on the latitude and longitude information. The value of the direction angle is also the value of the angle between the road extension direction and the true north direction.

[0188] In this way, after obtaining the initial position information, compensation step length s, direction angle h and other information, the physical position of the target vehicle at the target time can be predicted.

[0189] The above is a method for how the target vehicle obtains the predicted physical position when there are no adjacent vehicles.

[0190] Furthermore, in order to improve the accuracy of obtaining the predicted physical position, when the predicted physical position of the target vehicle at the target moment is obtained, information about the environment in which the target vehicle is located may also be added to the process of predicting the physical position of the target vehicle.

[0191] See also Fig.10 , is a flow chart of a method for obtaining a predicted physical location provided in an embodiment of the present application, and the specific implementation steps of the method are as follows:

[0192] Step S1001: Based on the historical physical position of the historically matched vehicle and the driving information of the target vehicle within a preset time range, the pending physical position of the target vehicle at the target time is obtained.

[0193] This process is the same as the process of obtaining the predicted physical location mentioned above. The specific acquisition process can be referred to the above introduction and will not be repeated here. In this step, the final obtained pending physical location can be recorded as (Lat pre ,Lng pre ).

[0194] Step S1002: Based on the environment perception data of the target vehicle at the target time, the road centerline position of the road centerline in the environment where the target vehicle is located is obtained.

[0195] Step S1003: weighting the pending physical position and the road centerline position to obtain the predicted physical position of the target vehicle at the target time.

[0196] During the driving process of the target vehicle, based on the acquired environmental perception data and the pre-saved map information, the target vehicle can obtain the coordinates of the nearest lane road center point (i.e., the road centerline position) according to the latitude and longitude information, which is recorded as (Lat lane ,Lng lane ).

[0197] Then, based on the obtained pending physical location (Lat pre ,Lng pre ) and the road centerline position (Lat lane ,Lng lane ) is weightedly calculated to obtain the final predicted physical location.

[0198] In this way, the problem of cumulative error that may occur when predicting the physical position of the target vehicle is overcome. For example, on a curved road, continuous prediction based on the tangential direction of the direction angle will cause the predicted physical position to gradually deviate from the driving road, which is reflected in the twin view as the target vehicle deviating further and further.

[0199] The above introduces the method provided by the embodiments of the present application and various possible implementation methods. In order to more clearly illustrate the implementation effect of the present solution, the present solution is introduced below through an embodiment in which the above-mentioned various possible implementation methods are combined.

[0200] See also Fig.11 , is a flow chart of a method for matching a target vehicle provided in an embodiment of the present application. Fig.11 As shown, the specific implementation steps of this method are as follows:

[0201] Step S1101: Continuously acquire environmental perception data and self-positioning data.

[0202] Step S1102: Determine whether the self-positioning data can indicate the physical position of the target vehicle at the target time; if yes, execute step S1103; if no, execute step S1104.

[0203] Step S1103: Based on the physical position of the target vehicle at the target time, obtain the target matching vehicle from each perceived vehicle, and continue to execute step S1101.

[0204] Step S1104: Determine whether there is a perceived vehicle with the same vehicle identification as the historical matching vehicle; if yes, execute step S1105; if no, execute step S1106.

[0205] Step S1105: Take the perceived vehicle having the same vehicle identification as the historical matching vehicle as the target matching vehicle, and continue to execute step S1101.

[0206] Step S1106: Determine whether there is an adjacent vehicle; if yes, execute step S1107; if no, execute step S1108.

[0207] Step S1107: Based on the relevant information of the adjacent vehicles, obtain the predicted physical position of the target vehicle at the target time, and continue to execute step S1110.

[0208] Step S1108: Based on the historical physical position of the historical matching vehicle and the driving information of the target vehicle, the physical position to be measured of the target vehicle at the target time is obtained.

[0209] Step S1109: Obtain the road centerline position of the road centerline in the environment where the target vehicle is located, and obtain the predicted physical position of the target vehicle at the target time based on the road centerline position and the physical position to be measured.

[0210] Step S1110: Based on the predicted physical position and the environmental position of each perceived vehicle, determine the target matching vehicle corresponding to the target vehicle, and continue to execute step S1101.

[0211] In this way, the target vehicle can continuously complete the process of matching the target vehicle while driving until a stop command is received.

[0212] Correspondingly, see Fig.12 , is a logic diagram of matching a target vehicle provided in an embodiment of the present application, such as Fig.12 As shown, in implementing the above Fig.11 When the scheme shown is used, it can be divided into several different modules for execution. Assuming that after the target vehicle drives into the mountain tunnel, the target vehicle determines that the self-positioning data cannot indicate its physical position at the current moment (referred to as invalid self-positioning data), and then enters the matching module (corresponding to the above steps S1104-S1109), and the position of the target vehicle is determined through the three matching modes in the matching module. Specifically, the matching module includes a matching hold mode (corresponding to the above steps S1104-S1105), an adjacent bundling mode (corresponding to the above step S1107) and a prediction compensation mode (corresponding to the above steps S1108-S1109). After passing the matching module, the target vehicle can continue to pass through the verification module (corresponding to the above step S1110) to complete the matching of the target vehicle and the perception vehicle.

[0213] Based on the same inventive concept, the embodiment of the present application also provides a device for matching a target vehicle, see Fig.13 , which is a structural schematic diagram of a device for matching a target vehicle provided in an embodiment of the present application. The device may be a terminal on the above-mentioned target vehicle or a server that is communicatively connected to the terminal of the target vehicle or a chip or integrated circuit therein, etc. The device includes modules / units / technical means for executing the method executed by the terminal or server in the above-mentioned method embodiment.

[0214] Exemplarily, the device 1300 includes:

[0215] The acquisition module 1301 is used to continuously acquire the environmental perception data and self-positioning data of the target vehicle; wherein the environmental perception data at least includes: the environmental position of each perception vehicle in the environment where the target vehicle is located; the self-positioning data includes: the physical position of the target vehicle obtained based on the positioning network;

[0216] The processing module 1302 is used to select at least one historical matching vehicle from among the historical perception vehicles, when the self-positioning data obtained at the target time cannot indicate the physical position of the target vehicle, based on the historical environmental positions of the historical perception vehicles and the historical physical positions of the target vehicle obtained within a preset time range before the target time, and the error between the historical environmental position of the historical matching vehicle and the historical physical position of the target vehicle is less than a first threshold;

[0217] The matching module 1303 is used to obtain a target matching vehicle that matches the target vehicle from each target perception vehicle corresponding to the target time based on at least one historical matching vehicle and the continuously acquired environmental perception data.

[0218] Optionally, each perceived vehicle has a vehicle identification; then the matching module 1303 is used to obtain a target matching vehicle that matches the target vehicle from each target perceived vehicle corresponding to the target time based on at least one historical matching vehicle and the continuously acquired environmental perception data, specifically for:

[0219] If there is a target perception vehicle matching the vehicle identification of at least one historical matching vehicle among the target perception vehicles corresponding to the target time, the matching target perception vehicle is used as the target matching vehicle matching the target vehicle;

[0220] If there is no target perception vehicle that matches the vehicle identification of at least one historical matching vehicle among the target perception vehicles corresponding to the target moment, then based on the historical physical position of at least one historical matching vehicle and the continuously acquired environmental perception data, the predicted physical position of the target vehicle at the target moment is obtained, and based on the predicted physical position, a target matching vehicle that matches the target vehicle is obtained from the target perception vehicles at the target moment.

[0221] Optionally, the matching module 1303 is used to obtain the predicted physical position of the target vehicle at the target time based on the historical physical position of at least one historical matching vehicle and the continuously acquired environmental perception data, specifically for:

[0222] Based on the historical physical positions of the historical matching vehicles and the historical environmental positions of the historical perception vehicles corresponding to each individual moment within a preset time range, the relative position relationships between the historical matching vehicles and the historical perception vehicles are obtained;

[0223] When, based on each relative position relationship, it is determined that there is no adjacent vehicle among each historically perceived vehicle whose relative position relationship with the historically matched vehicle meets the preset conditions, the predicted physical position of the target vehicle at the target time is obtained based on the historical physical position of the historically matched vehicle and the driving information of the target vehicle within a preset time range.

[0224] Optionally, the driving information includes at least one of the following: driving speed, driving time, and driving angle.

[0225] Optionally, the matching module 1303 is used to obtain the predicted physical position of the target vehicle at the target time based on the historical physical position of the historical matching vehicle and the driving information of the target vehicle within a preset time range, specifically for:

[0226] Based on the historical physical location of the historical matching vehicle and the driving information of the target vehicle within a preset time range, the pending physical location of the target vehicle at the target time is obtained;

[0227] Based on the environmental perception data of the target vehicle at the target time, the road centerline position of the road centerline in the environment where the target vehicle is located is obtained;

[0228] The determined physical position and the road centerline position are weighted to obtain the predicted physical position of the target vehicle at the target time.

[0229] Optionally, the matching module 1303 is used to obtain the predicted physical position of the target vehicle at the target time based on the historical physical position of at least one historical matching vehicle and the continuously acquired environmental perception data, specifically for:

[0230] Based on the historical physical positions of the historical matching vehicles and the historical environmental positions of the historical perception vehicles corresponding to each individual moment within a preset time range, the relative position relationships between the historical matching vehicles and the historical perception vehicles are obtained;

[0231] Based on each relative position relationship, when it is determined that there is an adjacent vehicle among each historical perception vehicle whose relative position relationship with the historical matching vehicle meets the preset conditions, the predicted physical position of the target vehicle at the target time is obtained based on the relative position relationship between the adjacent vehicle and the historical matching vehicle, and the environmental position of the adjacent vehicle at the target time.

[0232] Optionally, the preset conditions include: the driving direction of the historical matching vehicle and the historical perception vehicle is the same, and the straight-line distance between the historical matching vehicle and the historical perception vehicle is less than a distance threshold.

[0233] Optionally, the matching module 1303 is used to obtain a target matching vehicle that matches the target vehicle from each target sensing vehicle at the target time based on the predicted physical position, specifically for:

[0234] Based on the predicted physical position, a target perception vehicle whose error between the environmental position and the predicted physical position is less than a second threshold is obtained from each target perception vehicle at the target moment; and the target perception vehicle is used as the target matching vehicle.

[0235] Based on the same inventive concept, the embodiment of the present application also provides an electronic device. In a possible implementation, the electronic device may be a server, such as Figure 2 In this embodiment, the structure of the electronic device 1400 is as follows: Fig.14 As shown, it may include at least a memory 1401 , a communication module 1403 , and at least one processor 1402 .

[0236] The memory 1401 is used to store computer programs executed by the processor 1402. The memory 1401 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and programs required for running the instant messaging function, etc.; the data storage area may store various instant messaging information and operation instruction sets, etc.

[0237] The memory 1401 may be a volatile memory, such as a random-access memory (RAM); the memory 1401 may also be a non-volatile memory, such as a read-only memory, a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); or the memory 1401 may be any other medium that can be used to carry or store a desired computer program in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 1401 may be a combination of the above memories.

[0238] The processor 1402 may include one or more central processing units (CPU) or a digital processing unit, etc. The processor 1402 is used to implement the above-mentioned method of matching the target vehicle when calling the computer program stored in the memory 1401 .

[0239] The communication module 1403 is used to communicate with terminal devices and other servers.

[0240] The specific connection medium between the memory 1401, the communication module 1403 and the processor 1402 is not limited in the embodiment of the present application. Fig.14 In the embodiment, the memory 1401 and the processor 1402 are connected via a bus 1404. Fig.14 The connections between the other components are only for illustration and are not intended to be limiting. The bus 1404 can be divided into an address bus, a data bus, a control bus, etc. For ease of description, Fig.14 The diagram shows that only one thick line is used, but this does not mean that there is only one bus or one type of bus.

[0241] The memory 1401 stores a computer storage medium, and the computer storage medium stores computer executable instructions, and the computer executable instructions are used to implement the method for matching a target vehicle in the embodiment of the present application. The processor 1402 is used to execute the above-mentioned method for matching a target vehicle.

[0242] In another embodiment, the electronic device may also be other electronic devices, such as Figure 2 The terminal device 201 is shown. In this embodiment, the structure of the electronic device can be as follows Fig.15As shown, it includes: a communication component 1510, a memory 1515, a display unit 1530, a camera 1540, a sensor 1550, an audio circuit 1560, a Bluetooth module 1570, a processor 1580 and other components.

[0243] The communication component 1510 is used to communicate with the server. In some embodiments, a wireless fidelity (WiFi) module may be included. The WiFi module belongs to a short-range wireless transmission technology. The electronic device can help the object to send and receive information through the WiFi module.

[0244] The memory 1515 can be used to store software programs and data. The processor 1580 executes various functions and data processing of the terminal device 201 by running the software programs or data stored in the memory 1515. The memory 1520 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. The memory 1520 stores an operating system that enables the terminal device 201 to run. In the present application, the memory 1520 can store an operating system and various application programs, and can also store a computer program for executing the method for matching a target vehicle in the embodiment of the present application.

[0245] The display unit 1530 can also be used to display information input by the object or information provided to the object and a graphical user interface (GUI) of various menus of the terminal device 201. Specifically, the display unit 1530 may include a display screen 1532 disposed on the front of the terminal device 201. The display screen 1532 may be configured in the form of a liquid crystal display, a light emitting diode, etc. The display unit 1530 may be used to display the defect detection interface, the model training interface, etc. in the embodiment of the present application.

[0246] The display unit 1530 can also be used to receive input digital or character information and generate signal input related to the object setting and function control of the terminal device 201. Specifically, the display unit 1530 may include a touch screen 1531 set on the front of the terminal device 201, which can collect touch operations of objects on or near it, such as clicking a button, dragging a scroll box, etc.

[0247] The touch screen 1531 can be covered on the display screen 1532, or the touch screen 1531 and the display screen 1532 can be integrated to realize the input and output functions of the physical terminal device 201. The integrated touch screen can be referred to as a touch display screen. In this application, the display unit 1530 can display the application and the corresponding operation steps.

[0248] The camera 1540 can be used to capture static images, and the object can publish the image taken by the camera 1540 through the application. The camera 1540 can be one or more. The object generates an optical image through the lens and projects it onto the photosensitive element. The photosensitive element can be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, and then passes the electrical signal to the processor 1580 to convert it into a digital image signal.

[0249] The physical terminal device may also include at least one sensor 1550, such as an acceleration sensor 1551, a distance sensor 1552, a fingerprint sensor 1553, and a temperature sensor 1554. The terminal device may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, a light sensor, and a motion sensor.

[0250] The audio circuit 1560, the speaker 1561, and the microphone 1562 can provide an audio interface between the object and the terminal device 201. The audio circuit 1560 can transmit the electrical signal converted from the received audio data to the speaker 1561, which is converted into a sound signal for output. The physical terminal device 201 can also be configured with a volume button for adjusting the volume of the sound signal. On the other hand, the microphone 1562 converts the collected sound signal into an electrical signal, which is received by the audio circuit 1560 and converted into audio data, and then the audio data is output to the communication component 1510 to be sent to, for example, another physical terminal device 201, or the audio data is output to the memory 1515 for further processing.

[0251] The Bluetooth module 1570 is used to exchange information with other Bluetooth devices having Bluetooth modules through the Bluetooth protocol. For example, the physical terminal device can establish a Bluetooth connection with a wearable electronic device (such as a smart watch) that also has a Bluetooth module through the Bluetooth module 1570 to exchange data.

[0252] The processor 1580 is the control center of the physical terminal device. It uses various interfaces and lines to connect various parts of the entire terminal. It executes various functions of the terminal device and processes data by running or executing software programs stored in the memory 1515 and calling data stored in the memory 1515. In some embodiments, the processor 1580 may include one or more processing units; the processor 1580 may also integrate an application processor and a baseband processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the baseband processor mainly processes wireless communications. It is understandable that the above-mentioned baseband processor may not be integrated into the processor 1580. In the present application, the processor 1580 can run the operating system, application programs, user interface display and touch response, as well as the method for matching the target vehicle in the embodiment of the present application. In addition, the processor 1580 is coupled to the display unit 1530.

[0253] In addition, it should be noted that in the specific implementation of this application, object data related to the predicted physical location model is involved. When the above embodiments of this application are applied to specific products or technologies, it is necessary to obtain the object's permission or consent, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0254] In some possible implementations, various aspects of the method for matching a target vehicle provided in the present application may also be implemented in the form of a program product, which includes a computer program. When the program product is run on an electronic device, the computer program is used to enable the electronic device to execute the steps of the method for matching a target vehicle according to various exemplary embodiments of the present application described above in this specification.

[0255] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0256] The program product of the embodiment of the present application may adopt a portable compact disk read-only memory (CD-ROM) and include a computer program, and can be run on an electronic device. However, the program product of the present application is not limited thereto, and in this document, a readable storage medium may be any tangible medium containing or storing a program, which can be used by or in combination with a command execution system, apparatus, or device.

[0257] A readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, wherein a readable computer program is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with a command execution system, apparatus, or device.

[0258] The computer program embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0259] The computer program for performing the operation of the present application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as "C" language or similar programming languages. The computer program can be executed entirely on the user electronic device, partially on the user electronic device, as a separate software package, partially on the user electronic device and partially on a remote electronic device, or entirely on the remote electronic device. In the case of a remote electronic device, the remote electronic device can be connected to the user electronic device through any type of network including a local area network (LAN) or a wide area network (WAN), or can be connected to an external electronic device (for example, using an Internet service provider to connect through the Internet).

[0260] It should be noted that, although several units or subunits of the device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided into multiple units to be embodied.

[0261] In addition, although the operations of the method of the present application are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0262] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0263] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0264] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0265] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0266] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for matching a target vehicle, characterized in that: Applied to a target vehicle, the method comprises: Continuously acquiring environmental perception data and self-positioning data of the target vehicle; wherein the environmental perception data at least includes: the environmental position of each perception vehicle in the environment where the target vehicle is located; the self-positioning data includes: the physical position of the target vehicle obtained based on the positioning network; When the self-positioning data obtained at the target time cannot indicate the physical position of the target vehicle, based on the historical environmental positions of the historically perceived vehicles and the historical physical positions of the target vehicle acquired within a preset time range before the target time, at least one historical matching vehicle is selected from the historically perceived vehicles, and the error between the historical environmental position of the historical matching vehicle and the historical physical position of the target vehicle is less than a first threshold; Based on the at least one historical matching vehicle and the continuously acquired environmental perception data, a target matching vehicle that matches the target vehicle is obtained from each target perception vehicle corresponding to the target moment.

2. The method according to claim 1, characterized in that Each of the perceived vehicles has a vehicle identification; then, based on the at least one historical matching vehicle and the continuously acquired environmental perception data, obtaining a target matching vehicle that matches the target vehicle from each of the target perceived vehicles corresponding to the target time, includes: If there is a target perception vehicle matching the vehicle identification of the at least one historical matching vehicle among the target perception vehicles corresponding to the target time, the matching target perception vehicle is used as the target matching vehicle matching the target vehicle; If there is no target perception vehicle that matches the vehicle identification of the at least one historical matching vehicle among the target perception vehicles corresponding to the target moment, then based on the historical physical position of the at least one historical matching vehicle and the continuously acquired environmental perception data, the predicted physical position of the target vehicle at the target moment is obtained, and based on the predicted physical position, a target matching vehicle that matches the target vehicle is obtained from the target perception vehicles at the target moment.

3. The method according to claim 2, characterized in that The obtaining, based on the historical physical position of the at least one historical matching vehicle and the continuously acquired environmental perception data, of the predicted physical position of the target vehicle at the target time comprises: Based on the historical physical positions of the historical matching vehicles and the historical environmental positions of the historically perceived vehicles corresponding to the individual moments within the preset time range, the relative positional relationships between the historical matching vehicles and the historically perceived vehicles are obtained; When, based on the relative position relationships, it is determined that there is no adjacent vehicle among the historically perceived vehicles whose relative position relationship with the historically matched vehicle satisfies the preset conditions, the predicted physical position of the target vehicle at the target time is obtained based on the historical physical position of the historically matched vehicle and the driving information of the target vehicle within the preset time range.

4. The method according to claim 3, characterized in that The driving information includes at least one of the following: driving speed, driving time and driving angle.

5. The method according to claim 3, characterized in that The step of obtaining the predicted physical position of the target vehicle at the target time based on the historical physical position of the historical matching vehicle and the driving information of the target vehicle within the preset time range includes: Based on the historical physical position of the historical matching vehicle and the driving information of the target vehicle within the preset time range, obtaining the pending physical position of the target vehicle at the target time; Based on the environment perception data of the target vehicle at the target time, obtaining a road centerline position where a road centerline in the environment where the target vehicle is located is located; The pending physical position and the road centerline position are weighted to obtain the predicted physical position of the target vehicle at the target time.

6. The method according to claim 2, characterized in that The obtaining, based on the historical physical position of the at least one historical matching vehicle and the continuously acquired environmental perception data, of the predicted physical position of the target vehicle at the target time comprises: Based on the historical physical positions of the historical matching vehicles and the historical environmental positions of the historically perceived vehicles corresponding to the individual moments within the preset time range, the relative positional relationships between the historical matching vehicles and the historically perceived vehicles are obtained; Based on the relative position relationships, when it is determined that there is an adjacent vehicle among the historically perceived vehicles whose relative position relationship with the historically matched vehicle meets a preset condition, based on the relative position relationship between the adjacent vehicle and the historically matched vehicle, and the environmental position of the adjacent vehicle at the target moment, the predicted physical position of the target vehicle at the target moment is obtained.

7. The method according to claim 6, characterized in that The preset condition includes: the driving direction of the history matching vehicle is the same as that of the history perception vehicle, and the straight-line distance between the history matching vehicle and the history perception vehicle is less than a distance threshold.

8. The method according to claim 2, characterized in that The step of acquiring a target matching vehicle that matches the target vehicle from each target sensing vehicle at the target time based on the predicted physical position includes: Based on the predicted physical position, a target perception vehicle whose error between the environmental position and the predicted physical position is less than a second threshold is obtained from each target perception vehicle at the target moment; and the target perception vehicle is used as the target matching vehicle.

9. A device for matching a target vehicle, characterized in that: Applied to a target vehicle, the device comprises: An acquisition module, used to continuously acquire the environmental perception data and self-positioning data of the target vehicle; wherein the environmental perception data at least includes: the environmental position of each perception vehicle in the environment where the target vehicle is located; the self-positioning data includes: the physical position of the target vehicle obtained based on the positioning network; A processing module, configured to, when the self-positioning data obtained at the target time cannot indicate the physical position of the target vehicle, screen out at least one historical matching vehicle from among the historical perception vehicles based on the historical environmental positions of the historical perception vehicles and the historical physical positions of the target vehicle acquired within a preset time range before the target time, wherein the error between the historical environmental position of the historical matching vehicle and the historical physical position of the target vehicle is less than a first threshold; A matching module is used to obtain a target matching vehicle that matches the target vehicle from each target perception vehicle corresponding to the target moment based on the at least one historical matching vehicle and the continuously acquired environmental perception data.

10. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores program codes, and when the program codes are executed by the processor, the processor executes the steps of the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The method comprises a program code, and when the program code is run on a computing device, the program code is used to make the computing device execute the steps of the method according to any one of claims 1 to 8.

12. A computer program product, characterized in that The invention comprises a computer program, which implements the steps of the method according to any one of claims 1 to 8 when being executed by a processor.

Images