Method and device for matching a road section where a vehicle is located, storage medium, and electronic device

Abstract

The present application discloses a method and apparatus for matching a road section where a vehicle is located, a storage medium, and an electronic device. Among them, the above method includes: obtaining road section information of a group of road sections included in the map information received at the current vehicle position of the target vehicle; determining a reference road section area corresponding to the target vehicle according to the current vehicle position and the road section information of the group of road sections, where the reference road section area is an area used to determine the road section where the target vehicle is located; determining at least some of the road sections in the group of road sections that are located within the reference road section area as a group of road sections to be matched, and determining the target road section where the target vehicle is located from the group of road sections to be matched according to the position relationship between the target vehicle and each road section to be matched in the group of road sections to be matched.

Description

Technical Field

[0001] The present application relates to the field of vehicle wireless communication, and more particularly, to a method and apparatus for matching a road section where a vehicle is located, a storage medium, and an electronic device. Background Art

[0002] Currently, in V2X, the road section node information where a vehicle is located is usually determined by map matching. Due to the large amount of map data and the excessive number of road nodes, in order to reduce the redundant calculation amount, when matching the vehicle position, historical trajectories and historical matching results are generally considered first. When the vehicle performs map matching for the first time or the vehicle cannot match the road section of the previous matching result, a rectangular reference road section area within a determined range of the vehicle is generally constructed, and the road section to be matched is determined by the rectangular reference road section area.

[0003] However, the range size of the rectangular reference road section area directly affects the number of road sections to be matched. An overly large rectangular reference road section area increases the calculation amount and calculation time due to the excessive number of road sections to be matched, while an overly small rectangular reference road section area may not cover the actual road section where the vehicle is located, resulting in poor matching result efficiency.

[0004] It can be seen that the method for matching the road section where a vehicle is located in the related art has the problem of poor map matching efficiency due to the fixed range of the rectangular reference road section area. Summary of the Invention

[0005] Embodiments of the present application provide a method and apparatus for matching a road section where a vehicle is located, a storage medium, and an electronic device, so as to at least solve the problem of poor map matching efficiency in the method for matching the road section where a vehicle is located in the related art due to the fixed range of the rectangular reference road section area.

[0006] According to one aspect of the embodiments of the present application, a method for matching a road section where a vehicle is located is provided, including: obtaining road section information of a group of road sections included in map information received by a target vehicle at a current vehicle position of the target vehicle; determining a reference road section area corresponding to the target vehicle according to the current vehicle position and the road section information of the group of road sections, where the reference road section area is an area for determining the road section where the target vehicle is located; determining at least some of the road sections in the group of road sections that are located within the reference road section area as a group of road sections to be matched, and determining the target road section where the target vehicle is located from the group of road sections to be matched according to the position relationship between the target vehicle and each road section to be matched in the group of road sections to be matched.

[0007] According to another aspect of the embodiments of the present application, there is also provided a matching device for a road section where a vehicle is located, including: an acquisition unit configured to acquire road section information of a set of road sections included in map information received by a target vehicle at the current vehicle position of the target vehicle; a first determination unit configured to determine a reference road section area corresponding to the target vehicle according to the current vehicle position and the road section information of the set of road sections, where the reference road section area is an area for determining the road section where the target vehicle is located; a second determination unit configured to determine at least some of the road sections in the set of road sections that are located within the reference road section area as a set of road sections to be matched, and determine the target road section where the target vehicle is located from the set of road sections to be matched according to the position relationship between the target vehicle and each road section to be matched in the set of road sections to be matched.

[0008] According to still another aspect of the embodiments of the present application, there is also provided a computer-readable storage medium storing a computer program, where the computer program is configured to execute the above-mentioned method for matching the road section where a vehicle is located when running.

[0009] According to still another aspect of the embodiments of the present application, there is also provided an electronic device including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the above-mentioned processor executes the above-mentioned method for matching the road section where a vehicle is located through the computer program.

[0010] In the embodiments of the present application, by using the method of determining a reference road section area for determining the road section where a vehicle is located according to the road section information included in the map information received by the vehicle, the road section information of a set of road sections included in the map information received by the target vehicle at the current vehicle position of the target vehicle is acquired; a reference road section area corresponding to the target vehicle is determined according to the current vehicle position and the road section information of the set of road sections, where the reference road section area is an area for determining the road section where the target vehicle is located; at least some of the road sections in the set of road sections that are located within the reference road section area are determined as a set of road sections to be matched, and the target road section where the target vehicle is located is determined from the set of road sections to be matched according to the position relationship between the target vehicle and each road section to be matched in the set of road sections to be matched. Since the road section information near the vehicle can be different when the vehicle is at different positions, determining the size of the reference road section area according to the road section information near the vehicle can achieve the purpose of adaptively adjusting the range of the road section area for determining the road section where the vehicle is located, achieving the technical effect of improving the efficiency of map matching, and further solving the problem that the efficiency of the map matching method for the road section where a vehicle is located in the related art is poor due to the fixed range of the rectangular reference road section area. Description of the Drawings

[0011] The accompanying drawings here are incorporated into and constitute a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application.

[0012] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0013] Figure 1 It is a schematic diagram of the hardware environment of an optional method for matching the road section where a vehicle is located according to an embodiment of this application;

[0014] Figure 2 It is a schematic flowchart of an optional method for matching the road section where a vehicle is located according to an embodiment of this application;

[0015] Figure 3 It is a schematic diagram of an optional method for matching the road section where a vehicle is located according to an embodiment of this application;

[0016] Figure 4 It is a schematic flowchart of another optional method for matching the road section where a vehicle is located according to an embodiment of this application;

[0017] Figure 5 It is a schematic flowchart of yet another optional method for matching the road section where a vehicle is located according to an embodiment of this application;

[0018] Figure 6 It is a schematic flowchart of yet another optional method for matching the road section where a vehicle is located according to an embodiment of this application;

[0019] Figure 7 It is a schematic flowchart of yet another optional method for matching the road section where a vehicle is located according to an embodiment of this application;

[0020] Figure 8 It is a schematic diagram of another optional method for matching the road section where a vehicle is located according to an embodiment of this application;

[0021] Figure 9 It is a schematic flowchart of yet another optional method for matching the road section where a vehicle is located according to an embodiment of this application;

[0022] Figure 10 It is a schematic flowchart of yet another optional method for matching the road section where a vehicle is located according to an embodiment of this application;

[0023] Figure 11 It is a structural block diagram of an optional device for matching the road section where a vehicle is located according to an embodiment of this application;

[0024] Figure 12 It is a structural block diagram of an optional electronic device according to an embodiment of the present application. Detailed implementation manners

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order different from those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these process, method, product, or device.

[0027] According to one aspect of the embodiments of the present application, a method for matching a road section where a vehicle is located is provided. Optionally, in this embodiment, the above vehicle-to-vehicle communication method can be applied to, for example Figure 1 the hardware environment shown including the vehicle networking device 102 and the server 104. As Figure 1 shown, the server 104 is connected to the vehicle networking device 102 through a network. A database can be set on the server or independently of the server to provide data storage services for the server 104. Here, the vehicle networking device 102 can include an in-vehicle V2X device located on the vehicle.

[0028] The above network can include but is not limited to at least one of the following: a wired network, a wireless network. The above wired network can include but is not limited to at least one of the following: a wide area network, a metropolitan area network, a local area network. The above wireless network can include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth.

[0029] The matching method for the road section where the vehicle in the embodiment of the present application is located can be executed by the server 104, or can be executed by the vehicle networking device 102, or can also be jointly executed by the server 104 and the vehicle networking device 102. Taking the server 104 as an example to execute the matching method for the road section where the vehicle is located in this embodiment, Figure 2 It is a schematic flowchart of an optional matching method for the road section where the vehicle is located according to the embodiment of the present application. As Figure 2 shown, the process of this method can include the following steps:

[0030] Step S202, obtain the road section information of a group of road sections included in the map information received by the target vehicle at the current vehicle position of the target vehicle.

[0031] The matching method for the road section where the vehicle is located in this embodiment can be applied to the scenario of map matching according to the vehicle's location. Here, map matching refers to performing road section matching based on the vehicle's location information and map information to obtain the road section node information of the vehicle, which can be used as a basic support function for V2X (vehicle to everything, that is, vehicle's information exchange with the outside world). The vehicle's location information can be the vehicle's GPS (Global Positioning System) information.

[0032] The above map matching technology, that is, according to information such as longitude, latitude, heading angle, and speed in the GPS, and matching with information such as the upstream and downstream node relationships, node longitude, and node latitude of multiple nodes in the map information to obtain the unique matching road section technology.

[0033] In the prior art, due to the excessive amount of map data and the excessive number of road nodes, it will increase the time-consuming of the map matching calculation process, thus affecting the efficiency of map matching. When performing map matching on a vehicle, historical trajectories and historical matching results are usually given priority to reduce the redundant calculation amount. However, when the vehicle performs map matching for the first time or the vehicle cannot match the road section of the previous matching result, generally, an error area with a determined range of the vehicle needs to be constructed, and the road sections to be matched are determined by the error area. The range size of the error area directly affects the number of road sections to be matched. An overly large error area will increase the calculation time due to too many road sections to be matched, thus reducing the efficiency of map matching. A too small matching range may reduce the accuracy of map matching because it cannot cover the road section that the vehicle actually matches.

[0034] In order to at least solve some of the above problems, in this embodiment, the size and position of the error area can be determined according to the road section information of each road section near the vehicle's location, so as to realize the adaptive adjustment of the size of the error area and avoid the overly large or overly small error area affecting the efficiency or accuracy of map matching.

[0035] In this embodiment, before performing map matching, road segment information of a set of road segments included in the map information received at the current vehicle position of the target vehicle can be obtained. Here, the road segment information of the set of road segments may include information such as the road segment position, road segment length, and road segment width of each road segment in the set of road segments.

[0036] Optionally, the map information received by the target vehicle at the current vehicle position may be sent to the target vehicle by a roadside unit near the target vehicle by sending a V2X map message. It may be a map preset in the roadside unit and may include information such as road segments near the roadside unit. Correspondingly, the above set of road segments may be road segments within the communication coverage range of the roadside unit.

[0037] Optionally, when the map information is received, the data validity of the received map information can be verified first, and when it is verified that the map information is not empty, the process of obtaining the road segment information can be executed.

[0038] Step S204: Determine a reference road segment area corresponding to the target vehicle according to the current vehicle position and the road segment information of a set of road segments, where the reference road segment area is an area used to determine the road segment where the target vehicle is located.

[0039] After determining the road segment information of the set of road segments, a reference road segment area corresponding to the target vehicle can be determined according to the current vehicle position and the road segment information of the set of road segments. Here, the reference road segment area may be an area used to determine the road segment where the target vehicle is located, that is, the aforementioned error area. It may be a rectangular area or an area of other shapes. This embodiment does not make a limitation on this.

[0040] Optionally, the above current vehicle position may be determined according to the GPS positioning data of the target vehicle. When obtaining the GPS positioning data of the target vehicle, the validity of the obtained GPS positioning data can be verified first. When it is verified that the vehicle longitude and latitude and heading angle data in the GPS positioning data are not empty, the reference road segment area is determined.

[0041] Optionally, when determining the reference road segment area corresponding to the target vehicle, the center point position of the reference road segment area can be determined according to the current vehicle position, and the size of the reference road segment area can be determined according to the road segment information of the set of road segments.

[0042] Step S206: Determine at least some of the road segments in the set of road segments that are located within the reference road segment area as a set of road segments to be matched, and determine the target road segment where the target vehicle is located from the set of road segments to be matched according to the position relationship between the target vehicle and each road segment to be matched in the set of road segments to be matched.

[0043] In this embodiment, after determining the reference road section area, at least some of the road sections in a group of road sections that are located within the reference road section area can be determined as a group of road sections to be matched. Then, according to the positional relationship between the target vehicle and each road section to be matched in the group of road sections to be matched, the target road section where the target vehicle is located can be determined from the group of road sections to be matched. Here, the group of road sections to be matched can include at least one road section to be matched.

[0044] Optionally, the positional relationship between the target vehicle and each road section to be matched in the group of road sections to be matched can be determined according to the distance between the target vehicle and each road section to be matched. Here, the distance can be the perpendicular distance from the target vehicle to each road section to be matched, the projected distance of the target vehicle on each road section to be matched, or can also include both the perpendicular distance from the target vehicle to each road section to be matched and the projected distance of the target vehicle on each road section to be matched. In addition, the positional relationship between the target vehicle and each road section to be matched in the group of road sections to be matched can also be determined according to the distance between the target vehicle and each road section to be matched and the included angle between the driving direction of the target vehicle and the road section direction of each road section to be matched. This embodiment does not limit this.

[0045] Through the above steps S202 to S206, by obtaining the road section information of a group of road sections included in the map information received at the current vehicle position of the target vehicle; according to the current vehicle position and the road section information of the group of road sections, determining a reference road section area corresponding to the target vehicle, where the reference road section area is an area used to determine the road section where the target vehicle is located; determining at least some of the road sections in the group of road sections that are located within the reference road section area as a group of road sections to be matched, and according to the positional relationship between the target vehicle and each road section to be matched in the group of road sections to be matched, determining the target road section where the target vehicle is located from the group of road sections to be matched, the problem that the map matching efficiency is poor due to the fixed range of the reference road section area in the vehicle location matching method in the related art is solved, and the map matching efficiency is improved.

[0046] In an exemplary embodiment, determining a reference road section area corresponding to the target vehicle according to the current vehicle position and the road section information of a group of road sections includes:

[0047] S11. According to the road section information of a group of road sections, determining a distance parameter corresponding to the target vehicle, where the distance parameter is a parameter used to determine the area size of the reference road section area;

[0048] S12. Inputting the current vehicle position and the distance parameter into the trained reinforcement learning model to obtain an adaptive parameter corresponding to the target vehicle, where the adaptive parameter is a parameter used to determine the area size of the reference road section area;

[0049] S13, using the adaptive parameter to adjust the distance parameter to obtain an adaptive matching distance corresponding to the target vehicle, and determining a reference road section area corresponding to the target vehicle according to the adaptive matching distance.

[0050] When determining the reference section area corresponding to the target vehicle according to the current vehicle position and the section information of a group of sections, the distance parameter corresponding to the target vehicle can be determined according to the section information of the group of sections. Here, the distance parameter can be a parameter for determining the area size of the reference section area, that is, the maximum matching distance.

[0051] In order to improve the efficiency of map matching and ensure the accuracy of map matching results, the size of the reference road section area can be dynamically adjusted according to the current vehicle position to determine the road section to be matched. Considering the characteristics of "trial and error" and "delayed return" of reinforcement learning, after determining the distance parameter, the distance parameter and the current vehicle position can be input into the trained reinforcement learning model to obtain the adaptive parameter corresponding to the target vehicle. Here, the adaptive parameter can be a parameter used to determine the size of the reference road section area, which can be used to adjust the size of the distance parameter.

[0052] Alternatively, the basic process of the above reinforcement learning model can be as follows Figure 3 As shown, the experience value in reinforcement learning is defined as (s t ,a t ,r t ,s t+1 ), s t represents the algorithm input state at time t, a t represents the algorithm output at time t, r t Represents the reward given by the environment, s t+1 Represents the output state of the environment at time t+1. Reinforcement learning is learned through the interaction between the agent and the environment. The map matching process can be summarized as the environment, and the network that outputs adaptive parameters can be summarized as the agent. The agent is given the state s by the environment. t Output a decision action a t , and then react to the environment. The environment then responds to the agent’s decision action a t Output the new state s t+1 and the reward r corresponding to the action t , through continuous learning iteration, the training process can be Figure 4 As shown in , the output actions of the agent can be improved and the long-term rewards given by the environment can be increased. Through the reinforcement learning model, Figure 5 As shown, vehicle information and map information are input into the reinforcement learning network, and the network outputs the adaptive parameter a.

[0053] Optionally, a reinforcement learning network can be constructed and trained based on the Deep Deterministic Policy Gradient algorithm, or it can be constructed and trained based on other algorithms. Taking the construction and training of a reinforcement learning network based on the Deep Deterministic Policy Gradient algorithm as an example, the goal of reinforcement learning training is to maximize the long-term reward y i = r i + γQ'(s i+1 , μ'(s i+1 |θ μ' )|θ Q' ), where γ is the discount factor. Construct a current network that includes an actor action network μ(s|θ μ ) and a critic evaluation network Q(s, a|θ Q ), where the weight parameters are set as θ μ and θ Q . Then construct a target network that includes an actor action network μ' and a critic evaluation network Q', and the weight parameters are set as θ μ' and θ Q' . The current network is used to generate data, and the target network is used for model training. The actor network and the critic network are each set as a three-layer fully connected layer.

[0054] Correspondingly, the update target of the critic network can be to minimize the loss function, as shown in formula (1):

[0055]

[0056] The policy gradient update formula of the actor network is as shown in formula (2):

[0057]

[0058] The update of the target network is as shown in formula (3) and formula (4):

[0059] θ Q' = τθ Q + (1 - τ)θ Q' (3)

[0060] θ μ' = τθ Qμ + (1 - τ)θ μ' (4)

[0061] where τ is the learning rate.

[0062] In this embodiment, an adaptive parameter can be used to adjust the distance parameter to obtain an adaptive matching distance corresponding to the target vehicle, and a reference road section area corresponding to the target vehicle can be determined according to the adaptive matching distance.

[0063] Through this embodiment, an adaptive parameter for adjusting the distance parameter is determined by a reinforcement learning model to adjust the magnitude of the distance parameter, thereby achieving dynamic adjustment of the range of the reference road segment area according to the vehicle position, and enabling more flexible and efficient map matching based on the reference road segment area while ensuring the matching accuracy.

[0064] In an exemplary embodiment, determining a distance parameter corresponding to a target vehicle according to the road segment information of a set of road segments includes:

[0065] S21, determining the road segment length value and the road segment width value of the longest road segment in a set of road segments according to the road segment information of the set of road segments;

[0066] S22, determining a distance parameter corresponding to the target vehicle according to the road segment length value and the road segment width value.

[0067] To increase the possibility that the road segment where the target vehicle is located is included in the reference road segment area, the road segment information of the longest road segment in a set of road segments can be selected to determine the distance parameter. In this embodiment, the road segment length value and the road segment width value of the longest road segment in a set of road segments can be determined according to the road segment information of the set of road segments, and a distance parameter corresponding to the target vehicle can be determined according to the road segment length value and the road segment width value.

[0068] Optionally, the above road segment length value can be directly determined from the road segment information of each road segment in a set of road segments, or can be calculated and determined according to the endpoint information of each road segment in a set of road segments. This embodiment does not make a limitation on this.

[0069] Through this embodiment, the road segment length value and the road segment width value of the longest road segment in a set of road segments are selected to determine the distance parameter, thereby determining the reference road segment area, which can increase the possibility that the road segment where the target vehicle is located falls into the reference road segment area, and thus improve the accuracy of map matching.

[0070] In an exemplary embodiment, determining a distance parameter corresponding to a target vehicle according to the road segment length value and the road segment width value includes:

[0071] S31, using half of the road segment length value and the road segment width value as two right-angled sides and the distance parameter as the hypotenuse to determine the distance parameter.

[0072] In this embodiment, half of the road segment length value and the road segment width value can be used as two right-angled sides and the distance parameter as the hypotenuse, and the Pythagorean theorem can be used to assist in determining the distance parameter.

[0073] For example, taking the distance parameter as the maximum matching distance maxSearchLength, the calculation process of the maximum matching distance can be as shown in formula (5):

[0074]

[0075] Among them, the longest path maxPathLength represents the length of the longest road segment in the map, and the radius represents the action radius, which is the width of this longest road segment.

[0076] The method for determining the road segment to be matched can be as Figure 6 shown. Calculate the maximum matching distance maxSearchLength according to the longest path of the map and the action radius; then use the reinforcement learning method to train and output the adaptive parameters for constructing the rectangular error region, and represent the adaptive matching distance SearchLength of the map matching as the product of the adaptive parameters output by the reinforcement learning and the maximum matching distance maxSearchLength. Finally, screen the road segments to be matched according to the adaptive matching distance.

[0077] Through this embodiment, by using the Pythagorean theorem and taking the half of the road segment length value and the road segment width value as the right-angled sides to calculate the distance parameter, the efficiency of determining the distance parameter can be improved.

[0078] In an exemplary embodiment, input the current vehicle position and the distance parameter into the trained reinforcement learning model to obtain the adaptive parameters corresponding to the target vehicle, including:

[0079] S41. Input the coordinate information of the target vehicle and the distance parameter into the trained reinforcement learning model. Among them, the single-step reward information of the reinforcement learning model is determined according to the evaluation value of the matched road segment and the matching time for determining the matched road segment in the historical matching result;

[0080] S42. Determine the adaptive parameters corresponding to the target vehicle according to the output result of the trained reinforcement learning model.

[0081] In order to improve the correlation between the adaptive parameters and the current vehicle position of the target vehicle, and thus improve the efficiency and accuracy of map matching, when training the reinforcement learning model, the single-step reward information of the reinforcement learning model can be determined according to the evaluation value of the matched road segment and the matching time for determining the matched road segment in the historical matching result.

[0082] The evaluation value of the above-mentioned matched road segment can be the minimum evaluation value calculated according to the position relationship between the vehicle and each road segment to be matched during the historical matching process, and can be used to determine whether each road segment to be matched is the road segment where the vehicle is located.

[0083] Optionally, the single-step reward information can be determined after performing a normalization calculation on the evaluation value of each road segment unit of the matched road segment and the matching time for determining the matched road segment. The single-step reward design is shown in formula (6):

[0084] r = -(c1 * Evaluation + c2 * time) (6)

[0085] Where, Evaluation is the minimum evaluation value among the evaluation values of each section unit of the matching section, and time represents the time of map matching within the current adaptive matching range. c1 and c2 respectively represent the normalization coefficients of the evaluation value and the map matching time. Correspondingly, the output action of the reinforcement learning is a = (0, 1), and a will be used as the adaptive parameter of the matching distance.

[0086] Optionally, when training the reinforcement learning model, the state of the reinforcement learning can be set as the coordinate information of the target vehicle. The coordinate information of the target vehicle may include the abscissa and ordinate of the target vehicle, and the abscissa and ordinate of the target vehicle may be determined according to the Mercator projection of the target vehicle. Taking the distance parameter as the maximum matching distance as an example, the state s of the reinforcement learning is s = (X vehicle , Y vehicle , maxSearchLength), where X vehicle is the abscissa of the vehicle (Mercator projection), Y vehicle is the ordinate of the vehicle (Mercator projection), and maxSearchLength is the maximum matching distance calculated by the map.

[0087] In this embodiment, the coordinate information of the target vehicle and the distance parameter can be input into the trained reinforcement learning model, and then according to the output result of the trained reinforcement learning model, the adaptive parameter corresponding to the target vehicle is determined.

[0088] Through this embodiment, by setting the single-step reward of the reinforcement learning based on the evaluation value and the matching time of the matching section to train the reinforcement learning model, and using the vehicle position as the state of the reinforcement learning, the relevance between the adaptive parameter and the vehicle position and the nearby section can be improved, and then the relevance between the reference section area and the vehicle position and the nearby section can be improved, realizing the adaptive adjustment of the reference section area.

[0089] In an exemplary embodiment, using the adaptive parameter to adjust the distance parameter to obtain the adaptive matching distance corresponding to the target vehicle includes:

[0090] S51, determining the product of the distance parameter and the adaptive parameter as the adaptive matching distance of the target vehicle.

[0091] In this embodiment, when using the adaptive parameter to adjust the distance parameter, the product of the distance parameter and the adaptive parameter can be determined as the adaptive matching distance of the target vehicle. For example, taking the distance parameter as the maximum matching distance maxSearchLength, and the adaptive parameter a = (0, 1), the adaptive matching distance SearchLength can be expressed as the product of the adaptive parameter a output by reinforcement learning and the maximum matching distance maxSearchLength, as shown in formula (7):

[0092] SearchLength = a * maxSearchLength (7)

[0093] Through this embodiment, determining the product of the distance parameter and the adaptive parameter as the adaptive matching distance of the target vehicle can improve the relevance between the adaptive matching distance and the current position of the target vehicle while improving the efficiency of determining the adaptive matching distance.

[0094] In an exemplary embodiment, determining the reference road segment area corresponding to the target vehicle according to the adaptive matching distance includes:

[0095] S61, taking the current vehicle position as the center of the reference road segment area and taking half of the adaptive matching distance as half of the side length of the reference road segment area to determine the reference road segment area.

[0096] In this embodiment, the reference road segment area can be rectangular. When determining the reference road segment area corresponding to the target vehicle according to the adaptive matching distance, the current vehicle position can be taken as the center of the reference road segment area and half of the adaptive matching distance can be taken as half of the side length of the reference road segment area to determine the reference road segment area.

[0097] For example, taking the current vehicle position of the target vehicle as (X vehicle , Y vehicle ) as an example, where X vehicle is the abscissa of the vehicle (Mercator projection) and Y vehicle is the ordinate of the vehicle (Mercator projection), the reference road segment area can be a square centered on the target vehicle, and the determination process of the reference road segment area (i.e., the rectangular error area) can be as shown in formulas (8), (9), (10), (11):

[0098] X max = X vehicle + SearchLength (8)

[0099] X min = X vehicle - SearchLength (9)

[0100] Y max = Yvehicle +SearchLength (10)

[0101] Y min = Y vehicle -SearchLength (11)

[0102] wherein, X max is the maximum abscissa of the square, X min is the minimum abscissa of the square, Y max is the maximum ordinate of the square, Y min is the minimum ordinate of the square.

[0103] Through this embodiment, determining the center of the reference road segment area according to the current vehicle position can increase the possibility that the reference road segment area contains the road segment where the target vehicle is located, adaptively match the distance to determine the side length of the reference road segment area, achieve the purpose of dynamically adjusting the range size of the reference road segment area corresponding to the vehicle position, and further improve the flexibility and efficiency of map matching.

[0104] In an exemplary embodiment, the road segment information of a group of road segments includes the road segment endpoints and road segment directions of each road segment in the group of road segments. Determining the target road segment where the target vehicle is located from the group of road segments to be matched according to the positional relationship between the target vehicle and each road segment to be matched in the group of road segments to be matched includes:

[0105] S71, taking each road segment to be matched in the group of road segments to be matched as the current road segment to be matched, performing the following matching operations to obtain the evaluation value of each road segment to be matched: determining the target distance between the target vehicle and the current road segment to be matched according to the current vehicle position, and the projection distance of the target vehicle on each road segment unit of the current road segment to be matched; determining the included angle between the driving direction of the target vehicle and the road segment direction of each road segment unit of the current road segment to be matched according to the driving direction of the target vehicle; adding the product of the target distance and the first weight, the product of the projection distance and the second weight, and the product of the included angle and the third weight to obtain the evaluation value of each road segment unit of the current road segment to be matched; determining the minimum evaluation value among the evaluation values of each road segment unit of the current road segment to be matched as the evaluation value of the current road segment to be matched;

[0106] S72, in the case that the minimum evaluation value among the evaluation values of the group of road segments to be matched is less than or equal to the preset evaluation threshold, determining the road segment to be matched corresponding to the minimum evaluation value as the target road segment where the target vehicle is located.

[0107] To improve the accuracy of map matching, after determining a set of candidate segments based on the reference segment area, the evaluation value of each segment unit of each candidate segment in the set of candidate segments can be calculated respectively, and the minimum evaluation value can be selected as the evaluation value of each candidate segment to achieve quantitative analysis of each candidate segment. In this embodiment, the segment information of the foregoing set of segments may include the segment endpoints and segment directions of each segment in the set of segments. Each segment in the set of segments may include multiple segment units, and the length of the segment units into which each segment needs to be divided can be determined according to road conditions, traffic flow and other road traffic conditions, thereby obtaining multiple segment units.

[0108] At least one endpoint of the foregoing candidate segment may be located within the reference segment area. For example, taking the reference segment area as a rectangular error area, X max is the maximum abscissa of the rectangular error area, X min is the minimum abscissa of the rectangular error area, Y max is the maximum ordinate of the rectangular error area, Y min is the minimum ordinate of the rectangular error area. The coordinates of one of the endpoints A and B of the candidate segment may satisfy at least one of the formulas (12):

[0109]

[0110] When calculating the evaluation value, each candidate segment in the set of candidate segments can be used as the current candidate segment to perform the matching operation to obtain the evaluation value of each candidate segment. The matching operation may include determining the target distance between the target vehicle and each segment unit of the current candidate segment according to the current vehicle position, and the projection distance of the target vehicle on each segment unit of the current candidate segment; determining the angle between the driving direction of the target vehicle and the segment direction of each segment unit of the current candidate segment according to the driving direction of the target vehicle; adding the product of the target distance and the first weight, the product of the projection distance and the second weight, and the product of the angle and the third weight to obtain the evaluation value of each segment unit of the current candidate segment; and determining the minimum evaluation value among the evaluation values of each segment unit of the current candidate segment as the evaluation value of the current candidate segment. Here, the target distance may be the perpendicular distance from the target vehicle to each segment unit of the current candidate segment.

[0111] For example, as Figure 7 shown, the perpendicular distance, angle and projection distance between the vehicle and each segment unit of each candidate segment can be calculated in sequence. The perpendicular distance between the vehicle and each segment unit of each candidate segment can be as Figure 8 shown, P is the current position of the vehicle, Q is the historical position of the vehicle, is the driving direction of the vehicle. is a road segment unit, indicating the direction from A to B, indicating the direction from A to P. P’ is the projection of P on . t is the ratio of to i the vertical distance from vehicle P to the road segment unit . i is used to represent each road segment unit of the road segment to be matched. The calculation process is shown in formulas (13), (14), and (15):

[0112]

[0113] P' = A + (B - A) × t (14)

[0114] d i = |P - P'| (15)

[0115] When calculating the angle between the vehicle and each road segment unit of each road segment to be matched, the angle ∠AB (true azimuth angle) between the road segment unit and the due north direction can be calculated first, and the absolute value of the difference between the true azimuth angle of the road segment and the angle ∠heading between the vehicle's head and the due north direction is used as the angle A i between them. The calculation process can be shown in formulas (16) and (17):

[0116] A i = |∠AB - ∠heading| (16)

[0117]

[0118] where is the unit vector in the due north direction.

[0119] The projection distance R of the vehicle position on each road segment unit of each road segment to be matched i can be shown in formulas (18) and (19):

[0120]

[0121] R i = cos(∠BAP) * |PA| (19)

[0122] where cos(∠BAP) is the angle centered at A in the triangle formed by the two endpoints A, B of the road segment unit and the vehicle point P.

[0123] The evaluation value can be calculated as shown in formula (20). The distances, angles, and projection distances of each road segment unit of each road segment to be matched are multiplied by weights respectively to obtain the evaluation value of each road segment unit of each road segment to be matched:

[0124] Evaluation(i) = weightD * d i + weightA * A i + weightP * R i (20)

[0125] Wherein, weightD, weightA, and weightP respectively represent the coefficients of distance, angle, and projection distance.

[0126] Optionally, the smaller the evaluation value, the closer the target vehicle is to the road section to be matched.

[0127] To improve the accuracy of map matching and avoid the situation where the road sections to be matched within the reference road section area are actually far from the target vehicle due to incorrect selection of the reference road section area, etc., which may lead to matching errors. In this embodiment, an evaluation threshold can be preset in advance for verifying the road sections to be matched. When the minimum evaluation value among the evaluation values of a group of road sections to be matched is less than or equal to the preset evaluation threshold, the road section to be matched corresponding to the minimum evaluation value can be determined as the target road section where the target vehicle is located.

[0128] For example, as Figure 9 shown, after calculating the evaluation value of each road section to be matched, the evaluation values can be sorted, and the road section to be matched with the minimum evaluation value is used as the optimal matching road section. The calculation formula is as shown in formula (21), where Evaluation is the evaluation value:

[0129] i = argmin(Evaluation(i)) (21)

[0130] Sort the evaluation values, and select the evaluation value Evaluation that meets the range of Evaluation(i) < m. The road section that meets the conditions and has the minimum evaluation value is used as the matching result, and the forward and backward nodes of this road section are output. If there is no road section whose evaluation value meets the conditions, the map matching fails.

[0131] Through this embodiment, by determining the evaluation value of each road section to be matched based on the distance, projection distance, and angle between the target vehicle and the road section to be matched, the evaluation accuracy of the distance between the road section to be matched and the target vehicle can be improved, and thus the efficiency of map matching can be improved.

[0132] In an exemplary embodiment, before obtaining the road section information of a group of road sections included in the map information corresponding to the current vehicle position of the target vehicle, the above method further includes:

[0133] S81, determining whether there is a historical matching result corresponding to the current vehicle position of the target vehicle in the historical matching results of the target vehicle;

[0134] S82. When there is a historical matching result corresponding to the current vehicle position, determine the road section indicated by the historical matching result corresponding to the current vehicle position as the target road section where the target vehicle is located. Among them, obtaining the road section information of a group of road sections is executed when there is no historical matching result corresponding to the vehicle position of the target vehicle.

[0135] To improve the efficiency of map matching, before determining the reference road section area according to the foregoing method, it can be first determined whether there is a historical matching result corresponding to the current vehicle position of the target vehicle in the historical matching results of the target vehicle. When it is determined that there is no historical matching result corresponding to the vehicle position of the target vehicle, then obtain the road section information of a group of road sections, and then determine the road section where the target vehicle is located according to the reference road section area.

[0136] In this embodiment, when it is determined that there is a historical matching result corresponding to the current vehicle position, the road section indicated by the historical matching result corresponding to the current vehicle position can be directly determined as the target road section where the target vehicle is located.

[0137] Through this embodiment, determining the road section where the target vehicle is located according to the historical matching result can improve the efficiency of map matching.

[0138] In an exemplary embodiment, determining whether there is a historical matching result corresponding to the current vehicle position of the target vehicle in the historical matching results of the target vehicle includes:

[0139] S91. Determine the target road section to be matched as the matching road section corresponding to the matching result with the closest matching time in the historical matching results of the target vehicle;

[0140] S92. According to the target distance, projection distance and included angle between the target vehicle and each road section unit of the target road section to be matched, determine the evaluation value of each road section unit of the target road section to be matched, and determine the minimum evaluation value among the evaluation values of each road section unit of the target road section to be matched as the target evaluation value of the target road section to be matched with respect to the target vehicle;

[0141] S93. When the target evaluation value is less than or equal to the preset evaluation threshold, determine that there is a historical matching result corresponding to the vehicle position of the target vehicle;

[0142] S94. When the target evaluation value is greater than the preset evaluation threshold, determine that there is no historical matching result corresponding to the vehicle position of the target vehicle.

[0143] In order to improve the accuracy of determining the road section where the target vehicle is located based on historical matching results, in this embodiment, when determining whether there is a historical matching result corresponding to the current vehicle position of the target vehicle in the historical matching results of the target vehicle, the matching road section corresponding to the matching result with the closest matching time in the historical matching results of the target vehicle can be determined as the target road section to be matched. Here, the matching result with the closest matching time to the current refers to the matching result of the last map matching of the target vehicle.

[0144] After determining the target road section to be matched, the evaluation value of each road section unit of the target road section to be matched can be determined according to the target distance, projection distance, and included angle between the target vehicle and each road section unit of the target road section to be matched, and the minimum evaluation value among the evaluation values of each road section unit of the target road section to be matched can be determined as the target evaluation value of the target road section to be matched with respect to the target vehicle. Here, the method of determining the target evaluation value can be the same as the method of determining the evaluation value of the road section to be matched described above, and this embodiment will not elaborate here.

[0145] In the case where the target evaluation value is less than or equal to the preset evaluation threshold, it can be determined that there is a historical matching result corresponding to the vehicle position of the target vehicle. Correspondingly, the target road section to be matched can be determined as the current road section where the target vehicle is located. In the case where the target evaluation value is greater than the preset evaluation threshold, it can be determined that there is no historical matching result corresponding to the vehicle position of the target vehicle.

[0146] For example, taking the distance parameter as the maximum matching distance, the reference road section area as the rectangular error area, and the target road section to be matched as the last matching result road section, after obtaining the GPS positioning data and map message of the vehicle, the last matching result road section can be matched with the vehicle GPS positioning data to obtain the forward node ID and backward node ID of the last matching result road section, and the road section to be matched is set as this road section. Then, according to the distance, included angle, and projection distance between the vehicle and this road section, the evaluation value of this road section is determined and compared with the preset evaluation threshold. In the case where the evaluation value of this road section is less than or equal to the preset evaluation threshold, this road section is determined as the matching result of the vehicle; in the case where the evaluation value of this road section is greater than the preset evaluation threshold, the rectangular error area is determined using the reinforcement learning algorithm, and then the matching result is determined.

[0147] Optionally, when determining whether there is a historical matching result corresponding to the current vehicle position of the target vehicle in the historical matching results of the target vehicle, the last successfully matched road section can also be used as the road section to be matched, and the evaluation value of each road section unit of the road section to be matched is calculated respectively. In the case where the minimum evaluation value is less than or equal to the preset evaluation threshold, this road section to be matched is used as the optimal matching road section of the current vehicle position of the target vehicle.

[0148] Through this embodiment, by calculating the evaluation value of the matched road segments in the historical matching result to determine whether the road segment where the current target vehicle is located can be determined based on the historical matching result, the accuracy of map matching can be improved.

[0149] The matching method for the road segment where the vehicle is located in the embodiment of the present application will be explained below with reference to optional examples. In this optional example, the map information is map data, the distance parameter is the maximum matching distance, the reference road segment area is a rectangular error area, and the target road segment to be matched is the last matching result road segment.

[0150] This optional example provides a map matching method for adaptively screening road segments based on reinforcement learning. By using the reinforcement learning algorithm, adaptive parameters are output to dynamically adjust the size of the rectangular error area, and then the road segments to be matched are determined, which can make the map matching process more flexible and efficient.

[0151] The matching method for the road segment where the vehicle is located in this optional example can be as Figure 10 shown. The process of the matching method for the road segment where the vehicle is located may include the following steps:

[0152] Step 1001, query the GPS data of the vehicle.

[0153] Step 1002, query the map data.

[0154] Step 1003, determine whether the GPS data and the map data are valid. If they are valid, execute Step 1004; if they are invalid, execute Step 1008.

[0155] Step 1004, determine whether there is a previous map matching result. If there is, execute Step 1009; if there is no, execute Step 1005.

[0156] Step 1005, determine the road segments to be matched by the reinforcement learning method.

[0157] Step 1006, determine the optimal matching road segment according to the evaluation value of the road segment to be matched.

[0158] Step 1007, output the matching result.

[0159] Step 1008, determine whether the vehicle positioning and navigation is over. If it is determined that the vehicle positioning and navigation is over, the matching work ends; if it is determined that the vehicle positioning and navigation is not over, execute Step 1001.

[0160] Step 1009, use the previously successfully matched road segment as the road segment to be matched.

[0161] Step 1010, determine the evaluation value of each road segment unit of the road segment to be matched.

[0162] Step 1011: Determine whether the vehicle matches the previous matched road section according to the evaluation values of the road section units of the road section to be matched. If the match is successful, execute Step 1007; if the match is unsuccessful, execute Step 1005.

[0163] In this optional example, the reinforcement learning method is used to output adaptive parameters, dynamically adjust the adaptive matching distance, thereby dynamically adjusting the rectangular error area, and determining all road sections within the rectangular error area as the road sections to be matched, avoiding low matching efficiency caused by an overly large rectangular error area due to overly long roads in the map.

[0164] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0165] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM (Read-Only Memory), RAM (Random Access Memory), magnetic disk, optical disc), and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of the present application.

[0166] According to another aspect of the embodiments of the present application, there is also provided a matching device for the road section where the vehicle is located for implementing the above-mentioned matching method for the road section where the vehicle is located. Figure 11 is a structural block diagram of an optional matching device for the road section where the vehicle is located according to the embodiments of the present application, as Figure 11 shown. The device may include:

[0167] An acquisition unit 1102, configured to acquire road section information of a group of road sections included in the map information received at the current vehicle position of the target vehicle by the target vehicle;

[0168] The first determination unit 1104, connected to the acquisition unit 1102, is configured to determine a reference road section area corresponding to the target vehicle according to the current vehicle position and the road section information of a group of road sections, where the reference road section area is an area for determining the road section where the target vehicle is located;

[0169] The second determination unit 1106, connected to the first determination unit 1104, is configured to determine at least some of the road sections in the group of road sections that are located within the reference road section area as a group of road sections to be matched, and determine the target road section where the target vehicle is located from the group of road sections to be matched according to the position relationship between the target vehicle and each road section to be matched in the group of road sections to be matched.

[0170] It should be noted that the acquisition unit 1102 in this embodiment can be used to execute the above step S202, the first determination unit 1104 in this embodiment can be used to execute the above step S204, and the second determination unit 1106 in this embodiment can be used to execute the above step S206.

[0171] Through the above modules, by acquiring the road section information of a group of road sections included in the map information received at the current vehicle position of the target vehicle; determining a reference road section area corresponding to the target vehicle according to the current vehicle position and the road section information of the group of road sections, where the reference road section area is an area for determining the road section where the target vehicle is located; determining at least some of the road sections in the group of road sections that are located within the reference road section area as a group of road sections to be matched, and determining the target road section where the target vehicle is located from the group of road sections to be matched according to the position relationship between the target vehicle and each road section to be matched in the group of road sections to be matched, the problem that the map matching efficiency is poor due to the fixed range of the rectangular reference road section area in the vehicle location matching method in the related art is solved, and the map matching efficiency is improved.

[0172] In an exemplary embodiment, the first determination unit includes:

[0173] The first determination module is configured to determine a distance parameter corresponding to the target vehicle according to the road section information of a group of road sections, where the distance parameter is a parameter for determining the area size of the reference road section area;

[0174] The input module is configured to input the current vehicle position and the distance parameter into a trained reinforcement learning model to obtain an adaptive parameter corresponding to the target vehicle, where the adaptive parameter is a parameter for determining the area size of the reference road section area;

[0175] The first execution module is configured to adjust the distance parameter using the adaptive parameter to obtain an adaptive matching distance corresponding to the target vehicle, and determine a reference road section area corresponding to the target vehicle according to the adaptive matching distance.

[0176] In an exemplary embodiment, the first determination module includes:

[0177] A first determination sub-module, configured to determine the road segment length value and the road segment width value of the longest road segment in a set of road segments according to the road segment information of the set of road segments;

[0178] A second determination sub-module, configured to determine the distance parameter corresponding to the target vehicle according to the road segment length value and the road segment width value.

[0179] In an exemplary embodiment, the second determination sub-module includes:

[0180] A determination sub-unit, configured to determine the distance parameter with half of the road segment length value and the road segment width value as two right-angled sides and the distance parameter as the hypotenuse.

[0181] In an exemplary embodiment, the input module includes:

[0182] An input sub-module, configured to input the coordinate information and the distance parameter of the target vehicle into the trained reinforcement learning model, where the single-step reward information of the reinforcement learning model is determined according to the evaluation value of the matched road segment in the historical matching result and the matching time for determining the matched road segment;

[0183] A third determination sub-module, configured to determine the adaptive parameter corresponding to the target vehicle according to the output result of the trained reinforcement learning model.

[0184] In an exemplary embodiment, the first execution module includes:

[0185] A fourth determination sub-module, configured to determine the product of the distance parameter and the adaptive parameter as the adaptive matching distance of the target vehicle.

[0186] In an exemplary embodiment, the first execution module includes:

[0187] A fifth determination sub-module, configured to determine the reference road segment area with the current vehicle position as the center of the reference road segment area and half of the adaptive matching distance as the side length of the reference road segment area.

[0188] In an exemplary embodiment, the road segment information of a set of road segments includes the road segment endpoints and the road segment directions of each road segment in the set of road segments, and the second determination unit includes:

[0189] A second execution module, configured to use each to-be-matched road segment in a group of to-be-matched road segments as the current to-be-matched road segment, and perform the following matching operations to obtain an evaluation value for each to-be-matched road segment: Determine the target distance between the target vehicle and each road segment unit of the current to-be-matched road segment, and the projection distance of the target vehicle on each road segment unit of the current to-be-matched road segment according to the current vehicle position; Determine the included angle between the driving direction of the target vehicle and the road segment direction of each road segment unit of the current to-be-matched road segment according to the driving direction of the target vehicle; Add the product of the target distance and the first weight, the product of the projection distance and the second weight, and the product of the included angle and the third weight to obtain an evaluation value for each road segment unit of the current to-be-matched road segment; Determine the minimum evaluation value among the evaluation values of each road segment unit of the current to-be-matched road segment as the evaluation value of the current to-be-matched road segment;

[0190] A second determination module, configured to, when the minimum evaluation value among the evaluation values of a group of to-be-matched road segments is less than or equal to a preset evaluation threshold, determine the to-be-matched road segment corresponding to the minimum evaluation value as the target road segment where the target vehicle is located.

[0191] In an exemplary embodiment, the above device further includes:

[0192] A judgment unit, configured to, before obtaining the road segment information of a group of road segments included in the map information corresponding to the current vehicle position of the target vehicle, judge whether there is a historical matching result corresponding to the current vehicle position of the target vehicle in the historical matching results of the target vehicle;

[0193] A third determination unit, configured to, when there is a historical matching result corresponding to the current vehicle position, determine the road segment indicated by the historical matching result corresponding to the current vehicle position as the target road segment where the target vehicle is located, where obtaining the road segment information of a group of road segments is performed when there is no historical matching result corresponding to the vehicle position of the target vehicle.

[0194] In an exemplary embodiment, the judgment unit includes:

[0195] A third determination module, configured to determine the to-be-matched road segment corresponding to the matching result with the closest matching time in the historical matching results of the target vehicle as the target to-be-matched road segment;

[0196] A third execution module, configured to determine the evaluation value of each road segment unit of the target to-be-matched road segment according to the target distance, projection distance, and included angle between the target vehicle and each road segment unit of the target to-be-matched road segment, and determine the minimum evaluation value among the evaluation values of each road segment unit of the target to-be-matched road segment as the target evaluation value of the target to-be-matched road segment with respect to the target vehicle;

[0197] A fourth determination module, configured to determine that there is a historical matching result corresponding to the vehicle position of the target vehicle when the target evaluation value is less than or equal to a preset evaluation threshold;

[0198] A fifth determination module, configured to determine that there is no historical matching result corresponding to the vehicle position of the target vehicle when the target evaluation value is greater than the preset evaluation threshold.

[0199] It should be noted here that the examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules, as part of the device, can run in a hardware environment as shown in Figure 1 and can be implemented by software or by hardware. Among them, the hardware environment includes a network environment.

[0200] According to another aspect of the embodiments of the present application, there is also provided a storage medium. Optionally, in this embodiment, the above storage medium can be used to execute the program code of any one of the above methods for matching the road section where the vehicle is located in the embodiments of the present application.

[0201] Optionally, in this embodiment, the above storage medium can be located on at least one of multiple network devices in the network shown in the above embodiment.

[0202] Optionally, in this embodiment, the storage medium is set to store program code for executing the following steps:

[0203] S1. Obtain the road section information of a group of road sections included in the map information received by the target vehicle at the current vehicle position of the target vehicle;

[0204] S2. Determine a reference road section area corresponding to the target vehicle according to the current vehicle position and the road section information of a group of road sections, where the reference road section area is an area used to determine the road section where the target vehicle is located;

[0205] S3. Determine at least some of the road sections in the group of road sections that are located within the reference road section area as a group of road sections to be matched, and determine the target road section where the target vehicle is located from the group of road sections to be matched according to the position relationship between the target vehicle and each road section to be matched in the group of road sections to be matched.

[0206] Optionally, the specific examples in this embodiment can refer to the examples described in the above embodiments, and will not be elaborated herein.

[0207] Optionally, in this embodiment, the above storage medium may include, but is not limited to: various media such as USB flash drives, ROMs, RAMs, mobile hard disks, magnetic disks, or optical discs that can store program code.

[0208] According to another aspect of the embodiments of the present application, an electronic device for implementing the above-mentioned method for matching the road section where the vehicle is located is further provided. The electronic device may be a server, a terminal, or a combination thereof.

[0209] Figure 12 FIG. is a structural block diagram of an optional electronic device according to an embodiment of the present application. As Figure 12 shown, it includes a processor 1202, a communication interface 1204, a memory 1206, and a communication bus 1208. Among them, the processor 1202, the communication interface 1204, and the memory 1206 complete mutual communication through the communication bus 1208. Among them,

[0210] The memory 1206 is used to store a computer program;

[0211] When the processor 1202 is used to execute the computer program stored on the memory 1206, the following steps are implemented:

[0212] S1, obtaining the road section information of a group of road sections included in the map information received at the current vehicle position of the target vehicle;

[0213] S2, determining a reference road section area corresponding to the target vehicle according to the current vehicle position and the road section information of a group of road sections, where the reference road section area is an area used to determine the road section where the target vehicle is located;

[0214] S3, determining at least some of the road sections in the group of road sections that are located within the reference road section area as a group of road sections to be matched, and determining the target road section where the target vehicle is located from the group of road sections to be matched according to the position relationship between the target vehicle and each road section to be matched in the group of road sections to be matched.

[0215] Optionally, the communication bus may be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity of representation, Figure 12 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus. The communication interface is used for communication between the above-mentioned electronic device and other devices.

[0216] The memory may include a RAM, and may also include a non-volatile memory, for example, at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0217] As an example, the above-mentioned memory 1206 may but is not limited to include the acquisition unit 1102, the first determination unit 1104, and the second determination unit 1106 in the matching device for the road section where the vehicle is located. In addition, it may also include but is not limited to other module units in the matching device for the road section where the vehicle is located, which will not be elaborated in this example.

[0218] The above-mentioned processor may be a general-purpose processor, which may include but is not limited to: CPU (Central Processing Unit, central processing unit), NP (Network Processor, network processor), etc.; it may also be a DSP (Digital Signal Processing, digital signal processor), ASIC (Application Specific Integrated Circuit, application-specific integrated circuit), FPGA (Field-Programmable Gate Array, field-programmable gate array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0219] Optionally, the specific examples in this embodiment may refer to the examples described in the above-mentioned embodiment, and will not be elaborated here.

[0220] Those of ordinary skill in the art can understand that Figure 12 The structure shown is only schematic. The device for implementing the method for matching the road section where the vehicle is located may be a terminal device, and the terminal device may be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, and a mobile Internet device (Mobile Internet Devices, MID), a PAD and other terminal devices. Figure 12 It does not limit the structure of the above-mentioned electronic device. For example, the electronic device may further include more or fewer components (such as a network interface, a display device, etc.) than those shown Figure 12 in the figure, or have a different configuration from that shown Figure 12 in the figure.

[0221] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above-mentioned embodiments can be completed by instructing the relevant hardware of the terminal device through a program, and the program can be stored in a computer-readable storage medium. The storage medium may include: a flash drive, a ROM, a RAM, a magnetic disk or an optical disc, etc.

[0222] The serial numbers of the embodiments of the present application above are only for description and do not represent the advantages and disadvantages of the embodiments.

[0223] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage media. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing one or more computer devices (which can be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0224] In the above embodiments of this application, the descriptions of the various embodiments each have their own focuses. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0225] In the several embodiments provided by this application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the units or modules can be in electrical or other forms.

[0226] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution provided in this embodiment.

[0227] In addition, the functional units in the various embodiments of this application can be integrated in a processing unit, or each unit can exist physically alone, or at least two units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0228] The above are only the preferred embodiments of this application. It should be noted that for those of ordinary skill in the art, without departing from the principle of this application, several improvements and refinements can still be made, and these improvements and refinements should also be regarded as the protection scope of this application.

Claims

1. A method for matching a road section where a vehicle is located, characterized in that, Including: Obtaining road segment information of a set of road segments included in the map information received at the current vehicle position of the target vehicle; Determining a reference road segment area corresponding to the target vehicle according to the current vehicle position and the road segment information of the set of road segments, where the reference road segment area is an area used to determine the road segment where the target vehicle is located; Determining at least some of the road segments in the set of road segments that are located within the reference road segment area as a set of road segments to be matched, and determining the target road segment where the target vehicle is located from the set of road segments to be matched according to the position relationship between the target vehicle and each road segment to be matched in the set of road segments to be matched; Wherein, the determining a reference road segment area corresponding to the target vehicle according to the current vehicle position and the road segment information of the set of road segments includes: determining a distance parameter corresponding to the target vehicle according to the road segment information of the set of road segments, where the distance parameter is a parameter used to determine the area size of the reference road segment area; inputting the current vehicle position and the distance parameter into a trained reinforcement learning model to obtain an adaptive parameter corresponding to the target vehicle, where the adaptive parameter is a parameter used to determine the area size of the reference road segment area; adjusting the distance parameter using the adaptive parameter to obtain an adaptive matching distance corresponding to the target vehicle, and determining a reference road segment area corresponding to the target vehicle according to the adaptive matching distance.

2. The method according to claim 1, wherein The determining a distance parameter corresponding to the target vehicle according to the road segment information of the set of road segments includes: Determining the road segment length value and the road segment width value of the longest road segment in the set of road segments according to the road segment information of the set of road segments; Determining a distance parameter corresponding to the target vehicle according to the road segment length value and the road segment width value.

3. The method according to claim 2, wherein The determining a distance parameter corresponding to the target vehicle according to the road segment length value and the road segment width value includes: Using half of the road segment length value and the road segment width value as two right-angled sides, and the distance parameter as the hypotenuse, to determine the distance parameter.

4. The method according to claim 1, characterized in that, The inputting the current vehicle position and the distance parameter into a trained reinforcement learning model to obtain an adaptive parameter corresponding to the target vehicle includes: Inputting the coordinate information of the target vehicle and the distance parameter into the trained reinforcement learning model, where the single-step reward information of the reinforcement learning model is determined according to the evaluation value of the matched road segment and the matching time for determining the matched road segment in the historical matching result; Determining the adaptive parameter corresponding to the target vehicle according to the output result of the trained reinforcement learning model.

5. The method according to claim 1, characterized in that, The adjusting the distance parameter using the adaptive parameter to obtain an adaptive matching distance corresponding to the target vehicle includes: Determining the product of the distance parameter and the adaptive parameter as the adaptive matching distance of the target vehicle.

6. The method according to claim 1, characterized in that, The determining a reference road segment area corresponding to the target vehicle according to the adaptive matching distance includes: Taking the current vehicle position as the center of the reference road section area and the adaptive matching distance as half of the side length of the reference road section area, determine the reference road section area.

7. The method according to claim 1, characterized in that, The road section information of the set of road sections includes the road section endpoints and road section directions of each road section in the set of road sections. Determining the target road section where the target vehicle is located from the set of candidate road sections according to the positional relationship between the target vehicle and each candidate road section in the set of candidate road sections includes: Taking each candidate road section in the set of candidate road sections as the current candidate road section, performing the following matching operations to obtain the evaluation value of each candidate road section: According to the current vehicle position, determine the target distance between the target vehicle and each road section unit of the current candidate road section, and the projection distance of the target vehicle on each road section unit of the current candidate road section; According to the driving direction of the target vehicle, determine the included angle between the driving direction of the target vehicle and the road section direction of each road section unit of the current candidate road section; Add the product of the target distance and the first weight, the product of the projection distance and the second weight, and the product of the included angle and the third weight to obtain the evaluation value of each road section unit of the current candidate road section; Determine the minimum evaluation value among the evaluation values of each road section unit of the current candidate road section as the evaluation value of the current candidate road section; In the case where the minimum evaluation value among the evaluation values of the set of candidate road sections is less than or equal to a preset evaluation threshold, determine the candidate road section corresponding to the minimum evaluation value as the target road section where the target vehicle is located.

8. The method according to any one of claims 1 to 7, characterized in that Before obtaining the road section information of the set of road sections included in the map information corresponding to the current vehicle position of the target vehicle, the method further includes: Judging whether there is a historical matching result corresponding to the current vehicle position of the target vehicle in the historical matching results of the target vehicle; In the case where there is a historical matching result corresponding to the current vehicle position, determine the road section indicated by the historical matching result corresponding to the current vehicle position as the target road section where the target vehicle is located, where obtaining the road section information of the set of road sections is performed in the case where there is no historical matching result corresponding to the vehicle position of the target vehicle.

9. The method according to claim 8, wherein Judging whether there is a historical matching result corresponding to the current vehicle position of the target vehicle in the historical matching results of the target vehicle includes: Determine the candidate road section corresponding to the matching result with the closest matching time in the historical matching results of the target vehicle as the target candidate road section; According to the target distance, projection distance and included angle between the target vehicle and each road section unit of the target candidate road section, determine the evaluation value of each road section unit of the target candidate road section, and determine the minimum evaluation value among the evaluation values of each road section unit of the target candidate road section as the target evaluation value of the target candidate road section with respect to the target vehicle; When the target evaluation value is less than or equal to a preset evaluation threshold, it is determined that there is a historical matching result corresponding to the vehicle position of the target vehicle; When the target evaluation value is greater than the preset evaluation threshold, it is determined that there is no historical matching result corresponding to the vehicle position of the target vehicle.

10. A matching device for a section where a vehicle is located, characterized in that, It includes: An acquisition unit, configured to acquire the road segment information of a group of road segments included in the map information received by the target vehicle at the current vehicle position of the target vehicle; A first determination unit, configured to determine a reference road segment area corresponding to the target vehicle according to the current vehicle position and the road segment information of the group of road segments, where the reference road segment area is an area for determining the road segment where the target vehicle is located; A second determination unit, configured to determine at least some of the road segments in the group of road segments located within the reference road segment area as a group of road segments to be matched, and determine the target road segment where the target vehicle is located from the group of road segments to be matched according to the positional relationship between the target vehicle and each road segment to be matched in the group of road segments to be matched; Wherein, the first determination unit includes: A first determination module, configured to determine a distance parameter corresponding to the target vehicle according to the road segment information of the group of road segments, where the distance parameter is a parameter for determining the area size of the reference road segment area; An input module, configured to input the current vehicle position and the distance parameter into a trained reinforcement learning model to obtain an adaptive parameter corresponding to the target vehicle, where the adaptive parameter is a parameter for determining the area size of the reference road segment area; A first execution module, configured to adjust the distance parameter using the adaptive parameter to obtain an adaptive matching distance corresponding to the target vehicle, and determine a reference road segment area corresponding to the target vehicle according to the adaptive matching distance.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when running, executes the method according to any one of claims 1 to 9.

12. An electronic device, comprising a memory and a processor, characterized in that, A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 9 through the computer program.

Images