Evaluation method, electronic equipment and readable storage medium

The method uses drive test data and point cloud maps to accurately evaluate lane priority, addressing the challenge of dynamic lane priority assessment in map-free autonomous driving, thereby improving lane change decisions.

CN119085682APending Publication Date: 2024-12-06SHENZHEN DEEPROUTE AI CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411250823.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-06
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

Accurate evaluation of dynamic lane priority is crucial for navigation routes in map-free autonomous driving, particularly with lightweight maps that lack detailed road information, to ensure safe and efficient lane changes.

Method used

A method involving obtaining drive test data, processing it with a target planning algorithm to determine lane priority, and using point cloud maps to evaluate lane types, ensuring accurate lane priority assessment through manual or deep learning-based annotation.

Benefits of technology

Enables precise evaluation of lane priority by integrating drive test data with point cloud maps, enhancing the accuracy of lane change decisions in autonomous vehicles.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119085682A_ABST
    Figure CN119085682A_ABST
Patent Text Reader

Abstract

The invention discloses an evaluation method, electronic equipment and a readable storage medium. The method comprises the following steps: acquiring drive test data; obtaining a planning result based on the road test data and a target planning algorithm, wherein the planning result comprises the target lane and the lane priority of the target lane; obtaining a corresponding point cloud map based on the drive test data; obtaining the lane type of the target lane according to the point cloud map; and evaluating the lane priority in the planning result by using the lane type of the target lane. In this way, the lane priority can be accurately evaluated.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of autonomous driving, and in particular to an evaluation method, an electronic device, and a readable storage medium. Background Art

[0002] In recent years, the map-free mode has attracted widespread attention. It is a mode that emphasizes perception over map, that is, a mode without high-precision maps. For example, a lightweight standard map (SD Map) is used. It does not have the rich road information of a high-precision map, but it has a fast update frequency and relatively low cost, and does not require a professional map collection vehicle. In the static mode combined with the navigation route, the static lane driving priority of local routing and other road information obtained by perception jointly output a dynamic lane priority to ultimately determine the decision of the vehicle to keep or change lanes. Therefore, for a navigation route or a specific scenario of a navigation route, accurate evaluation of dynamic lane priority is particularly important. Summary of the invention

[0003] The main purpose of this application is to provide an evaluation method, an electronic device and a readable storage medium that can accurately evaluate lane priority.

[0004] In order to solve the above technical problems, the first technical solution adopted by the present application is to provide a lane priority evaluation method. The method includes obtaining drive test data; obtaining a planning result based on the drive test data and a target planning algorithm, wherein the planning result includes a target lane and a lane priority of the target lane; obtaining a corresponding point cloud map based on the drive test data; obtaining a lane type of the target lane according to the point cloud map; and evaluating the lane priority in the planning result using the lane type of the target lane.

[0005] In order to solve the above technical problems, the second technical solution adopted by the present application is: to provide an algorithm evaluation method. The method includes obtaining a target planning algorithm; using the lane priority evaluation method in the first technical solution to evaluate the lane priority obtained based on the target planning algorithm to obtain an evaluation result; and evaluating the target planning algorithm according to the evaluation result.

[0006] To solve the above technical problems, the third technical solution adopted by the present application is to provide an electronic device. The electronic device includes a memory and a processor, the memory is used to store program data, and the program data can be executed by the processor to implement the method described in the first technical solution and / or the second technical solution.

[0007] To solve the above technical problems, the fourth technical solution adopted by the present application is to provide a computer-readable storage medium. The computer-readable storage medium stores program data and can be executed by a processor to implement the method described in the first technical solution and / or the second technical solution.

[0008] The beneficial effects of the present application include at least: obtaining the road test data, processing the road test data using the target planning algorithm to obtain the planning result, and the planning result includes the target lane and the corresponding lane priority. Further, the corresponding point cloud map is obtained based on the road test data, and the point cloud map is processed to obtain the lane type of the target lane. Finally, the lane priority of the planning result is accurately evaluated according to the lane type and lane priority of the target lane. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 It is a flowchart of the first embodiment of the lane priority evaluation method of the present application;

[0011] Figure 2 It is a flowchart of the second embodiment of the lane priority evaluation method of the present application;

[0012] Figure 3 is a schematic diagram of a target navigation area;

[0013] Figure 4 is a schematic diagram of a non-target navigation area;

[0014] Figure 5 is a schematic diagram of yet another target navigation area;

[0015] Figure 6 It is a flowchart of the third embodiment of the lane priority evaluation method of the present application;

[0016] Figure 7 It is a flowchart of the first embodiment of the algorithm evaluation method of the present application;

[0017] Figure 8 It is a flowchart of the second embodiment of the algorithm evaluation method of the present application;

[0018] Fig. 9 It is a structural schematic diagram of an embodiment of the electronic device of the present application;

[0019] Fig.10It is a structural diagram of an embodiment of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0021] The terms "first", "second", etc. in this application are used to distinguish different objects, rather than to describe a specific order. 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 that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0022] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0023] For a navigation route, or a specific scene of a navigation route, it is particularly important to evaluate the accuracy of dynamic lane priority. Based on this, this application chooses to generate a true value data set for real-time comparison and evaluation. It can be specifically implemented through the technical solution described in the following embodiments. It should be noted that if there are substantially the same results, the method of this application is not limited to the process sequence shown.

[0024] Reference Figure 1 , Figure 1 This is a flow chart of the first embodiment of the lane priority evaluation method of the present application. The execution subject of the method may be a vehicle-mounted device with computing function. It includes but is not limited to the following steps.

[0025] S11: Obtaining drive test data.

[0026] The road test data may be navigation data acquired during autonomous driving. The road test data may include raw sensor data. The raw sensor data may include BEV image data, lidar point cloud data, RTK GPS (Real-time kinematic Global Positioning System) pose data, IMU (Inertial Measurement Unit) data, timestamp data, fused pose data, and the like.

[0027] S12: Obtaining a planning result based on the road test data and the target planning algorithm, where the planning result includes a target lane and a lane priority of the target lane.

[0028] The target planning algorithm can obtain each target lane in the data and the lane priority corresponding to the target lane based on the road test data. The target planning algorithm can further include a perception algorithm and a lane planning algorithm. The perception algorithm is used to perceive each target lane based on the road test data, and the lane planning algorithm can determine the lane priority corresponding to the lane based on each target lane. For example, the lane priority can be represented by P0, P1...Pn, where P0 priority is greater than P1 priority, and P1 priority is greater than Pn priority. When the vehicle is driving, it will give priority to the lane with the highest priority, that is, it will drive limitedly in the lane corresponding to P0.

[0029] Optionally, the target planning algorithm in the present application can be an algorithm for planning based on a non-high-precision map (such as a standard map). Taking a standard map as an example, in a standard map, it only contains part of the road information, including the number of lanes, speed limit, traffic lights, road level, etc., and a broken line (local polyline) is used in the navigation map to represent a road segment (SDlink). There is topological information of the road network between the road segments, and the topological information includes the topological relationship between each lane segment. The topological relationship can be understood as that during driving, when the current lane segment can reach the next lane segment according to its own lane driving direction, it is considered that there is a topological relationship between the current lane segment and the next lane segment. Each road segment (SD link) contains attributes, such as the number of lanes, speed limit, whether there is a traffic light ahead, road level, lane turn arrow, etc.

[0030] S13: Obtain a corresponding point cloud map based on the drive test data.

[0031] S14: Obtain the lane type of the target lane according to the point cloud map.

[0032] S15: Evaluate the lane priority of the target lane in the planning result using the lane type of the target lane.

[0033] A point cloud map of the area corresponding to the drive test data is obtained based on the drive test data. Furthermore, the lane type corresponding to the target lane is obtained based on the point cloud map. The lane type is used as the true value data set in the lane evaluation process, and the lane priority in the planning result is evaluated using the lane type, so as to obtain an accurate evaluation result.

[0034] In this embodiment, the drive test data is obtained and processed by the target planning algorithm to obtain the planning result, which includes the target lane and the corresponding lane priority. The corresponding point cloud map is further obtained based on the drive test data, and the point cloud map is processed to obtain the lane type of the target lane. Finally, the lane priority of the planning result is accurately evaluated according to the lane type and lane priority of the target lane.

[0035] In one embodiment, the drive test data includes posture information and environmental point cloud information, and obtaining the corresponding point cloud map based on the drive test data includes fusing the environmental point cloud information according to the posture order of the posture information to obtain the point cloud map.

[0036] Environmental point cloud information is the point cloud information of the surrounding environment of the target vehicle obtained in a certain posture. In the road test data, each frame of road test data has its corresponding posture information and environmental point cloud information. The order in which the posture information is obtained is the posture order of the posture information. By fusing the corresponding environmental point cloud information according to the posture order, a point cloud map corresponding to the area corresponding to the road test data can be obtained.

[0037] In one embodiment, in order to ensure the accuracy of the generated point cloud map, the pose information is subjected to pose optimization processing before being fused according to the pose order.

[0038] The pose optimization process may include global optimization and local optimization. The pose optimization process is to optimize the pose by comprehensively utilizing historical perception data (which may be environmental point cloud information), thereby eliminating the pose errors accumulated during the motion process.

[0039] In one embodiment, obtaining the lane type of the target lane according to the point cloud map includes sending the point cloud map to a manual processing module to obtain the lane type of the target lane. After the point cloud map is obtained, it can be sent to the manual processing module. In the manual processing module, the point cloud map can be manually annotated to mark each lane and the lane type corresponding to each lane. The lane type can include a passable lane, a non-motorized lane, an emergency lane, etc. Each lane type can have its corresponding lane priority requirement.

[0040] In one embodiment, obtaining the lane type of the target lane according to the point cloud map includes sending the point cloud map to a lane detection module to obtain the lane type of the target lane. After obtaining the point cloud map, the lane and lane type can also be annotated through a deep learning network.

[0041] In one embodiment, when evaluating the lane priority of the drive test data, the drive test data may be divided into multiple frames of drive test data, and the lane priority of the planning result of each frame of the drive test data is evaluated respectively.

[0042] Reference Figure 2 , Figure 2 This is a flow chart of the second embodiment of the lane priority evaluation method of the present application. When the lane type is obtained using the lane detection module, this method is a further extension of the method of processing the point cloud map using the lane detection module, which includes but is not limited to the following steps.

[0043] S21: Identify and detect the point cloud map to obtain the topological relationship between target lanes and the target navigation area.

[0044] By identifying the point cloud map, each target lane and the lane driving direction of the target lane can be determined. According to the lane driving direction of the target lane, the topological relationship between the target lanes can be determined. And according to the topological relationship, the target navigation area can be determined. In the target navigation area, in the current driving direction, there is a lane entering the target navigation area and a lane exiting the target navigation area that does not have a topological relationship. The lack of a topological relationship can be understood as the inability to reach the exit lane by driving along the entry lane. The target navigation area can be a lane change area, such as a lane merging in or out. The target navigation area can also be a lane disconnection area, such as an intersection.

[0045] The target navigation area is described in more detail with reference to specific embodiments below.

[0046] Reference Figure 3 , Figure 3 is a schematic diagram of a target navigation area. Figure 3 In the illustrated area A, the current driving direction is from left to right. There are three entry lanes for entering the area according to the driving direction, and there is one exit lane for exiting the area according to the driving direction. If there is only one entry lane with an exit lane that has a topological relationship, that is, the bottom entry lane has a topological relationship with the exit lane, and the other two entry lanes have no topological relationship with the exit lane, then the area A can be used as the target navigation area.

[0047] Reference Figure 4 , Figure 4 is a schematic diagram of a non-target navigation area. Figure 4In the illustrated area B, the current driving direction is from left to right. There are three entry lanes for entering the area according to the driving direction, and there are three exit lanes for exiting the area according to the driving direction. There is a topological relationship between the entry lanes and the exit lanes, so the area B is not used as the target navigation area.

[0048] S22: Determine a lane type of a target lane entering the target navigation area based on a topological relationship between target lanes.

[0049] According to the topological relationship, the lane type of the target lane entering the target navigation area in the current driving direction is determined. The lane type may include a passable lane, an emergency lane, a non-motorized vehicle lane, etc. In the target navigation area, in the current driving direction, the entry lanes having a topological relationship with the exit lanes are determined, and the lane types of these entry lanes are determined as passable lanes.

[0050] Reference Figure 3 ,exist Figure 3 In the target navigation area A, the current driving direction is from left to right. In the current driving direction, only the bottommost driving lane of the three driving lanes has a topological relationship with the driving lane, so the lane type of the bottommost driving lane is determined as a passable lane.

[0051] Reference Figure 5 , Figure 5 This is a schematic diagram of another target navigation area. Figure 5 In the area C shown, the current driving direction is from left to right. In the current driving direction, there are three entry lanes entering the area and three exit lanes exiting the area. However, only two entry lanes have a topological relationship with the exit lanes. The bottom entry lane exits downward and does not reach the exit lane in the current driving direction, that is, the bottom entry lane has no topological relationship with the exit lane, so the lane type of the top and middle entry lanes is a passable lane.

[0052] According to the topological relationship between lanes, it can be determined which lanes are passable lanes.

[0053] The lane type of the passable lane determined based on a certain target navigation area only corresponds to the lanes in the lane area between the target navigation area and the previous target navigation area. That is, if there are three consecutive target navigation areas D, E, and F in a navigation section, the lane type determined based on the F target navigation area only applies to the lanes in the lane area between E and F, and the lane type determined based on the E target navigation area only applies to the lanes in the lane area between D and E.

[0054] Reference Figure 6 , Figure 6This is a flow chart of the third embodiment of the lane priority evaluation method of the present application. This method is a further extension of step S15, which includes but is not limited to the following steps.

[0055] S31: Obtaining a preset lane priority condition corresponding to the lane type.

[0056] S32: In response to the lane priority in the planning result not satisfying the corresponding preset lane priority condition, the evaluation result of the lane priority in the planning result is abnormal; in response to the lane priority in the planning result satisfying the corresponding preset lane priority condition, the evaluation result of the lane priority in the planning result is normal.

[0057] Whether the lane priority obtained by the target planning algorithm is accurate is judged based on whether the lane priority obtained in the planning result meets the corresponding preset lane priority conditions.

[0058] The preset lane priority condition may be set for a lane type. For example, for a passable lane, the preset lane priority condition is that the lane priority of the passable lane is the highest lane priority.

[0059] Optionally, corresponding lane priority conditions may be set for different lane types.

[0060] In one embodiment, in response to the lane type of the target lane being a passable lane, the passable lane has a preset lane priority condition. If, as described in the above embodiment, the lane priorities include P0, P1...Pn, then the preset lane priority condition of the passable lane may be the highest priority lane priority P0.

[0061] Furthermore, a lane comparison range can be set for the target lane. The preset lane priority condition can be set based on the lane comparison type range. For example, in a certain road test data frame, the lane types of the target lane obtained include passable lanes, emergency lanes, non-motorized lanes, auxiliary roads, etc. A lane comparison range is set according to the lane type, which includes passable lanes, emergency lanes and non-motorized lanes. The preset lane priority condition can be set based on the lane comparison range. For example, if the preset lane priority condition of the passable lane is to be set, the passable lane can be set to have the highest priority among all lanes in the range. If the lane priority result obtained by planning is passable lane P0, emergency lane P2, non-motorized lane P3, and auxiliary road P1. Then among all passable lanes, emergency lanes and non-motorized lanes, the lane priority of the passable lane is the highest, and the lane priority of the passable lane type meets the preset lane priority condition. If the lane priority result obtained by planning is passable lane P1, emergency lane P2, non-motorized lane P3, and auxiliary road P0. Among all passable lanes, emergency lanes and non-motorized vehicle lanes, the lane priority of the passable lane is still the highest, and the lane priority of the passable lane type also meets the preset lane priority conditions.

[0062] When the lane priority of a lane whose lane type is a passable lane in the planning result is not P0, it is determined that the lane priority in the planning result does not meet the preset lane priority condition, and the evaluation result of the lane priority in the planning result is determined to be abnormal. If the lane priority in the planning result is also P0, it is determined that the lane priority in the planning result meets the preset lane priority condition, and the evaluation result of the lane priority in the planning result is determined to be normal.

[0063] In one embodiment, in response to the target lane being a non-motorized vehicle lane or an emergency lane, its preset lane priority condition is not P0, that is, it is not the highest lane priority. If the lane priority of the target lane in the planning result is P0, it is considered that the lane priority in the planning result does not meet the preset lane priority condition, and the evaluation result is abnormal. If it is not P0, the evaluation result is normal.

[0064] If the acquired drive test data is divided into multiple frames of data for evaluation, the determined evaluation result is the evaluation result of the lane priority of the corresponding drive test data frame.

[0065] In each frame of data, the lane priorities obtained by planning all target lanes must be evaluated as normal, and then the lane priority evaluation result of the frame of data can be evaluated as normal.

[0066] Reference Figure 7 , Figure 7 This is a flow chart of the first embodiment of the algorithm evaluation method of this application, which includes but is not limited to the following steps.

[0067] S41: Obtain a target planning algorithm.

[0068] The target planning algorithm, i.e., the planning algorithm to be evaluated, may include multiple algorithms of corresponding functions, such as a perception algorithm and a lane planning algorithm.

[0069] S42: Evaluate the lane priority obtained based on the target planning algorithm to obtain an evaluation result.

[0070] S43: Evaluate the target planning algorithm according to the evaluation result.

[0071] After obtaining the target planning algorithm, the road test data is obtained, and the lane priority obtained by the target planning algorithm is evaluated using the lane priority evaluation method described above, thereby evaluating the performance of the planning algorithm based on the obtained lane priority evaluation result.

[0072] Reference Figure 8 , Figure 8 This is a flow chart of the second embodiment of the algorithm evaluation method of the present application. This method is a further extension of step S43, which includes but is not limited to the following steps.

[0073] S51: Determine a data frame of the drive test data with an abnormal evaluation result as a lane error frame.

[0074] S52: Determine a reliability index according to the number of lane error frames and the total number of frames of the drive test data.

[0075] S53: Use reliability indicators to evaluate the goal planning algorithm.

[0076] In this embodiment, the drive test data can be divided into multiple frames of drive test data to evaluate the lane priorities obtained by planning. According to the above lane priority evaluation algorithm, the drive test data frame with an abnormal evaluation result is determined as a lane error frame, and the reliability index is calculated based on the number of lane error frames and all data frames. The reliability index may include MTBF (Mean Time Between Failures), MDBF (Mean Distance Between Failures), etc. The performance of the target planning algorithm is evaluated and determined according to these reliability indicators.

[0077] In one embodiment, lane types may also include non-motorized lanes and emergency lanes, etc. In order to further distinguish lane error frames for more detailed evaluation and judgment, lane error frames may be further distinguished. For example, if the preset lane priority conditions of non-motorized lanes and emergency lanes are not P0, the road test data frames with lane priority of P0 for non-motorized lanes in the planning results are determined as non-motorized lane error frames, and the road test data frames with lane priority of P0 for emergency lanes in the planning results are determined as emergency lane error frames. The remaining lane error frames are passable lane error frames. The performance of the target planning algorithm is judged more accurately based on the number of different lane error frames.

[0078] like Fig. 9 As shown, Fig. 9 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application.

[0079] The electronic device includes a processor 110 and a memory 120 .

[0080] The processor 110 controls the operation of the electronic device, and the processor 110 may also be referred to as a CPU (Central Processing Unit). The processor 110 may be an integrated circuit chip having the ability to process a signal sequence. The processor 110 may also be a general-purpose processor, a digital signal sequence processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0081] The memory 120 stores instructions and program data required for the processor 110 to operate.

[0082] The processor 110 is used to execute instructions to implement the method provided by any embodiment and possible combination of the lane priority evaluation method and / or algorithm evaluation method described above in the present application.

[0083] like Fig.10 As shown, Fig.10 This is a schematic diagram of the structure of the first embodiment of the computer-readable storage medium of the present application.

[0084] An embodiment of a readable storage medium of the present application includes a memory 210, and the memory 210 stores program data. When the program data is executed, the method provided by any embodiment and possible combination of the lane steepness assessment method and / or algorithm assessment method of the present application is implemented.

[0085] The memory 210 may include a medium that can store program instructions, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or it may be a server that stores the program instructions. The server may send the stored program instructions to other devices for execution, or it may execute the stored program instructions itself.

[0086] In summary, by acquiring the road test data and processing the road test data using the target planning algorithm, the planning result is obtained, which includes the target lane and the corresponding lane priority. Further, the corresponding point cloud map is obtained based on the road test data, and the point cloud map is processed to obtain the lane type of the target lane. Finally, the lane priority of the planning result is accurately evaluated according to the lane type and lane priority of the target lane.

[0087] In the several embodiments provided in this application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only illustrative, for example, the division of the modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0088] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0089] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0090] If the integrated units in the above other embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), disk or optical disk and other media that can store program codes.

[0091] The above descriptions are merely embodiments of the present application and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A lane priority assessment method, characterized in that: The method comprises: Obtaining drive test data; Obtaining a planning result based on the drive test data and the target planning algorithm, the planning result including a target lane and a lane priority of the target lane; Obtaining a corresponding point cloud map based on the drive test data; Obtaining a lane type of the target lane according to the point cloud map; The lane priority of the target lane in the planning result is evaluated using the lane type of the target lane.

2. The method according to claim 1, characterized in that In response to the drive test data including the position information and the environment point cloud information, obtaining the corresponding point cloud map based on the drive test data includes: The environmental point cloud information is fused according to the posture order of the posture information to obtain the point cloud map.

3. The method according to claim 2, characterized in that Before fusing the environment point cloud information according to the posture order of the posture information to obtain the point cloud map, the method includes: Performing posture optimization processing on the posture information.

4. The method according to claim 1, characterized in that: The obtaining the lane type of the target lane according to the point cloud map includes: The point cloud map is sent to a manual processing module or a lane detection module to obtain the lane type of the target lane.

5. The method according to claim 4, characterized in that In response to sending the point cloud map to a lane detection module to obtain a lane type of the target lane, a method for processing the point cloud map using the lane detection module includes: Identify and detect the point cloud map to obtain the topological relationship between the target lanes and the target navigation area; wherein, in the target navigation area, in the current driving direction, there is a lane entering the target navigation area and a lane exiting the target navigation area that has no topological relationship; The lane type of the target lane entering the target navigation area is determined based on the topological relationship between the target lanes.

6. The method according to claim 1, characterized in that The evaluating the lane priority of the target lane in the planning result by using the lane type of the target lane includes: Obtaining a preset lane priority condition corresponding to the lane type; In response to the lane priority of the target lane in the planning result not satisfying the corresponding preset lane priority condition, the evaluation result of the lane priority in the planning result is abnormal; in response to the lane priority of the target lane in the planning result satisfying the corresponding preset lane priority condition, the evaluation result of the lane priority in the planning result is normal.

7. An algorithm evaluation method, characterized in that: The method comprises: Get the goal planning algorithm; Using the lane priority evaluation method according to any one of claims 1 to 7 to evaluate the lane priority obtained based on the target planning algorithm to obtain an evaluation result; The goal planning algorithm is evaluated according to the evaluation result.

8. The method according to claim 7, characterized in that The step of evaluating the target programming algorithm according to the evaluation result includes: Determine a data frame of the drive test data with an evaluation result of abnormality as a lane error frame; Determine a reliability index according to the number of frames of the lane error frame and the total number of frames of the drive test data; The goal programming algorithm is evaluated using the reliability index.

9. An electronic device, characterized in that: The invention comprises a memory and a processor, wherein the memory is used to store program data, and the program data can be executed by the processor to implement the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: Program data is stored and can be executed by a processor to implement the method according to any one of claims 1 to 8.