Vehicle planning control method and device, electronic equipment and vehicle

Abstract

The application provides a vehicle planning control method and device, electronic equipment and vehicle. The method comprises the following steps: acquiring at least one perceived lane line in front of a target road section of a vehicle and a corresponding map lane line of the target road section in a high-definition map, wherein the perceived lane line is generated by using perception data of the vehicle; determining a fusion matching state between the at least one perceived lane line and between the at least one perceived lane line and the map lane line respectively; determining a confidence degree of the high-definition map and a confidence degree of the perception data according to the fusion matching state; and determining a planning control strategy for the vehicle based on the confidence degree of the high-definition map and the confidence degree of the perception data. The application realizes automatic driving planning control, so as to improve positioning accuracy, avoid positioning jump and improve the safety of automatic driving.

Description

Technical Field

[0001] This invention relates to the field of vehicle planning and control, and more particularly to a vehicle planning and control method and apparatus, electronic equipment and vehicle. Background Technology

[0002] Currently, in autonomous driving localization, a multi-sensor fusion approach is typically used to fuse various data sources, including RTK (Real-time Kinematic) carrier phase differential technology, IMU (Inertial Measurement Unit), vector maps, and point cloud maps, to obtain the vehicle's localization data. However, the driving environment of autonomous vehicles is extremely complex, and different fusion schemes will inevitably encounter edge scenarios that cannot be handled.

[0003] However, multi-sensor data and high-precision map data often contain errors or significant inaccuracies due to varying environments. For example, in tunnel scenarios: positioning signals may have large errors; point cloud and map feature information is not readily apparent, making accurate positioning difficult through matching; estimations using IMU and wheel speed sensors may also suffer from sensor drift and vehicle parameter variations. Furthermore, the production cycle of high-precision maps means that autonomous vehicles using these maps may encounter issues such as untimely updates and map data errors.

[0004] Driving planning in autonomous driving relies on positioning data. However, depending on different environmental conditions, the sensor data or high-precision map data used for positioning often contains errors or large errors, which makes the positioning data unable to meet the requirements of high-precision positioning and prone to positioning jumps. These problems with positioning data can easily affect the safety of autonomous driving systems.

[0005] Therefore, how to achieve autonomous driving planning and control to improve positioning accuracy, avoid positioning jumps, and improve the safety of autonomous driving is a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0006] In order to overcome the deficiencies of the aforementioned related technologies, this invention provides a vehicle planning and control method and device, electronic equipment and vehicle, thereby realizing autonomous driving planning and control, improving positioning accuracy, avoiding positioning jumps, and improving the safety of autonomous driving.

[0007] According to one aspect of the present invention, a vehicle planning and control method is provided, comprising:

[0008] The vehicle acquires at least one perceived lane line for a target road segment ahead and the corresponding map lane line for the target road segment in a high-precision map. The perceived lane line is generated using the vehicle's perception data.

[0009] Determine the fusion matching status between the at least one sensed lane lines and between the at least one sensed lane line and the map lane lines respectively;

[0010] The confidence level of the high-precision map and the confidence level of the perceived data are determined based on the fusion matching status.

[0011] Based on the confidence level of the high-precision map and the confidence level of the perception data, a planning and control strategy for the vehicle is determined.

[0012] In some embodiments of this application, the fusion matching state includes a first matching degree between the at least one perceived lane line and a second matching degree between the at least one perceived lane line and the map lane line, respectively.

[0013] In some embodiments of this application, determining the confidence level of the high-precision map and the sensing data based on the fusion matching state includes:

[0014] If the first matching degree is determined to meet the first preset condition, the confidence level of the perceived data is determined to be greater than the first preset threshold.

[0015] And / or, if it is determined that the second matching degree meets the second preset condition, the confidence degree of the high-precision map is determined to be greater than the second preset threshold.

[0016] In some embodiments of this application, determining that the confidence level of the high-precision map is greater than a second preset threshold when the second matching degree satisfies a second preset condition includes:

[0017] If at least one of the second matching degrees is determined to be greater than a third preset threshold, the confidence level of the high-precision map is determined to be greater than the second preset threshold.

[0018] In some embodiments of this application, the at least one perceived lane line includes visual lane lines and laser point cloud lane lines, wherein the visual lane lines are generated using perception data acquired by a visual sensor, and the laser point cloud lane lines are generated using perception data acquired by a lidar. Correspondingly, determining that the confidence level of the high-precision map is greater than the second preset threshold when at least one of the second matching degrees is greater than the third preset threshold includes:

[0019] If the second matching degree between the visual lane line and the map lane line is determined to be greater than a third preset threshold, the confidence level of the high-precision map is determined to be the first confidence level.

[0020] If the second matching degree between the laser point cloud lane line and the map lane line is determined to be greater than the third preset threshold, the confidence level of the high-precision map is determined to be the second confidence level.

[0021] Both the first confidence level and the second confidence level are greater than the second preset threshold, and the first confidence level is set to be greater than the second confidence level.

[0022] In some embodiments of this application, determining the planning and control strategy for the vehicle based on the confidence level of the high-precision map and the perception data includes:

[0023] If the confidence level of the perceived data is greater than a first preset threshold and the confidence level of the high-precision map is less than or equal to a second preset threshold, a planning and control strategy for the vehicle is determined based on the perceived data.

[0024] In some embodiments of this application, determining the planning and control strategy for the vehicle based on the confidence level of the high-precision map and the perception data includes:

[0025] If the confidence level of the high-precision map is greater than a second preset threshold and the confidence level of the perception data is less than or equal to a first preset threshold, a planning and control strategy for the vehicle is determined based on the high-precision map.

[0026] According to another aspect of this application, a vehicle planning control is also provided, comprising:

[0027] The lane line acquisition module is configured to acquire at least one perceived lane line of a target road segment ahead of the vehicle and the map lane line corresponding to the target road segment in a high-precision map. The perceived lane line is generated using the vehicle's perception data.

[0028] The fusion matching state determination module is configured to determine the fusion matching state between the at least one perceived lane lines and between the at least one perceived lane line and the map lane lines, respectively.

[0029] The confidence determination module is configured to determine the confidence of the high-precision map and the confidence of the perceived data based on the fusion matching state.

[0030] The confidence levels of the high-precision map and the perception data are used to determine the planning and control strategy for the vehicle.

[0031] According to another aspect of this application, an electronic device is also provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to implement the above-described method when executing the instructions.

[0032] According to another aspect of this application, a vehicle is also provided, comprising:

[0033] Perception sensors, configured to acquire perception data from the vehicle;

[0034] The perception fusion module is configured as follows:

[0035] The vehicle acquires at least one perceived lane line for a target road segment ahead and the corresponding map lane line for the target road segment in a high-precision map. The perceived lane line is generated using the vehicle's perception data.

[0036] Determine the fusion matching status between the at least one sensed lane lines and between the at least one sensed lane line and the map lane lines respectively;

[0037] The confidence level of the high-precision map and the confidence level of the perceived data are determined based on the fusion matching status.

[0038] The planning and control module is configured to determine the planning and control strategy for the vehicle based on the confidence level of the high-precision map and the confidence level of the perception data.

[0039] Compared with the prior art, the advantages of this invention are:

[0040] The confidence levels of the high-precision map and the perception data are determined by the fusion and matching states between at least one perceived lane line and the map lane lines, respectively. Based on these confidence levels, a planning and control strategy for the vehicle is determined. This ensures that the vehicle's planning and control strategy can utilize high-confidence high-precision map data and / or perception data, avoiding positioning errors caused by data errors or inaccuracies in the high-precision map data or perception data, thereby improving the safety of autonomous driving planning. Attached Figure Description

[0041] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0042] Figure 1 A flowchart of a vehicle planning and control method according to an embodiment of the present invention is shown.

[0043] Figure 2 A block diagram of a vehicle planning and control device according to an embodiment of the present invention is shown.

[0044] Figure 3 A block diagram of a vehicle according to an embodiment of the present invention is shown.

[0045] Figure 4 The schematic diagram illustrates a computer-readable storage medium according to an exemplary embodiment of the present invention.

[0046] Figure 5 The schematic diagram illustrates an electronic device according to an exemplary embodiment of the present invention. Detailed Implementation

[0047] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that the invention will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0048] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0049] The flowchart shown in the attached diagram is merely an illustrative example and does not necessarily include all steps. For example, some steps may be broken down, while others may be combined or partially combined. Therefore, the actual execution order may change depending on the specific circumstances.

[0050] Figure 1 A flowchart of a vehicle planning and control method according to an embodiment of the present invention is shown. The vehicle planning and control method provided in this application includes the following steps:

[0051] Step S110: Obtain at least one perceived lane line of the target road segment ahead of the vehicle and the map lane line corresponding to the target road segment in the high-precision map. The perceived lane line is generated using the perceived data of the vehicle.

[0052] Step S120: Determine the fusion matching status between the at least one sensed lane lines and between the at least one sensed lane line and the map lane lines respectively.

[0053] Step S130: Determine the confidence level of the high-precision map and the confidence level of the sensing data based on the fusion matching status.

[0054] Step S140: Based on the confidence level of the high-precision map and the confidence level of the perception data, determine the planning and control strategy for the vehicle.

[0055] In the vehicle planning and control method provided in this application, the confidence level of the high-precision map and the confidence level of the perception data are determined by the fusion matching state between at least one perceived lane line and between at least one perceived lane line and the map lane line, respectively. Based on the confidence levels of the high-precision map and the perception data, a planning and control strategy for the vehicle is determined. This ensures that the planning and control strategy for the vehicle can use high-confidence high-precision map data and / or perception data, avoiding the problem of vehicle positioning errors due to data errors or inaccuracies in the high-precision map data and perception data, thereby improving the safety of autonomous driving planning.

[0056] Specifically, the perception data of the vehicle can include visual sensor data and radar sensor data, and other perception data are also within the scope of protection of this application. Perceived lane lines can be detected based on the perception data. For example, a visual sensor obtains visual sensor data, and lane line detection based on the visual sensor data can obtain visual lane lines. Specifically, lane line detection based on visual sensor data can be achieved through various artificial intelligence models or image processing algorithms, and this application is not limited thereto. For example, a lidar can obtain laser point cloud sensor data, and lane line detection based on the laser point cloud sensor data can obtain laser point cloud lane lines. Specifically, lane line detection based on laser point cloud sensor data can be achieved through feature extraction of the laser point cloud and matching with preset lane line features, and this application is not limited thereto. Of course, in other embodiments, perception data can also be obtained through perception sensors such as millimeter-wave radar, and perceived lane lines can be detected based on the perception data. For example, millimeter-wave radar can obtain measurement data such as echo intensity, distance, and angle, and visual lane lines can be detected based on the measurement data.

[0057] Specifically, the target road segment ahead of the vehicle can be set as needed to a road segment within a designated area ahead of the vehicle. For example, the target road segment ahead of the vehicle can be a road segment 0.5 meters to 5 meters ahead of the vehicle, but this application is not limited to this. Since the perception data is acquired based on perception sensors installed on the vehicle, the perceived lane lines of the target road segment ahead of the vehicle can be detected and obtained based on the distance between each feature in the perception data and the vehicle. In some embodiments, the vehicle's position in the high-precision map can be determined based on the vehicle's positioning signal, such as GPS (Global Positioning System) positioning signal, BeiDou positioning signal, etc., and then the map lane lines of the target road segment ahead of the vehicle in the high-precision map can be obtained based on the determined vehicle position. In other embodiments, the vehicle's position in the high-precision map can be determined based on inertial measurement unit and vehicle driving information, and then the map lane lines of the target road segment ahead of the vehicle in the high-precision map can be obtained based on the determined vehicle position. In still other embodiments, the map lane lines corresponding to the perceived lane lines can be determined based on feature matching between the perception data and the high-precision map. This application can achieve a variety of different methods for obtaining map lane lines, which will not be elaborated here.

[0058] Specifically, the fusion matching state may include one or more of the following: the matching degree between lane lines, the fusion weight between lane lines, and the lane line confidence provided by lane line detection.

[0059] The matching degree between lane lines can include the distance between them. For example, after detecting a lane line, a mathematical expression, such as a curve equation, can be determined using methods like curve fitting. Based on this, when determining the matching degree between two lane lines, the Euclidean distance between them can be calculated using the lane line's mathematical expression; the shorter the Euclidean distance, the higher the matching degree. Of course, in other embodiments, the matching degree can also be determined using curve matching algorithms such as the IterativeClosestPoint (ICP) method, and this application does not impose any limitations on this. Therefore, determining the fusion matching state based at least on the matching degree between lane lines has several advantages. First, it only requires data processing on the same target object obtained from different data sources (i.e., perception data and high-precision maps), without the need to compare a large amount of perception data and high-precision map data, thus improving data processing efficiency. Second, it can incorporate the data correlation (matching degree between lane lines) of different data sources (i.e., perception data and high-precision maps) into the determination of the confidence level of perception data and high-precision maps, as well as the determination of planning and control strategies, thereby improving the accuracy of the confidence level of the acquired perception data and high-precision maps and thus improving the safety of autonomous driving planning.

[0060] In autonomous driving, after obtaining perceived lane lines and map lane lines, the lane lines can be fused to enable vehicle autonomous driving control based on the fused lane lines. Therefore, in some embodiments, the fusion weight of the perceived lane lines and map lane lines during lane line fusion can be used as the fusion matching state. The fusion weight represents the importance of the perceived lane lines and map lane lines when fusion. Specifically, in the autonomous driving control process, lane line information (such as the position and shape of lane lines) is needed for autonomous driving operations such as lane line control and lane changing. Lane line information can be obtained based on a weighted fusion of perceived lane lines and map lane lines. For example, corresponding lane line feature points can be determined by fitting curves of perceived lane lines and map lane lines. The coordinates of the corresponding lane line feature points in the perceived lane lines and the corresponding lane line feature points in the map lines are then weighted and summed to obtain the coordinates of the corresponding feature points in the lane line information. Combinations of these feature points can obtain the required lane line information. The fusion weight can include the weights used when fusing the lane line feature points of the perceived lane lines and the map lane lines. The fusion weight of the perceived lane lines can be calculated based on the confidence level of the perceived lane lines. The confidence score of the perceived lane line is used to represent the degree of confidence of the obtained perceived lane line. In some specific implementations, the perceived lane line can be predicted based on an artificial intelligence model, such as a neural network model, which can output the perceived lane line and its probability. The probability output by the artificial intelligence model can be used as the confidence score of the perceived lane. The confidence score of the map lane line is used to represent the degree of confidence of the obtained map lane line. In some specific implementations, the confidence score of the map lane line can be calculated based on the confidence score of the vehicle's positioning signal (e.g., the confidence score of the vehicle's positioning signal can be used as the confidence score of the map lane line). The confidence score of the positioning signal can be provided by the positioning module itself, or it can be predicted by a trained artificial intelligence model based on the vehicle's location and environmental information. This application is not intended to be limiting.

[0061] Therefore, determining the fusion matching state based at least on the fusion weights between lane lines has several advantages. First, it only requires data processing on the same target object obtained from different data sources (i.e., perception data and high-precision maps), eliminating the need to compare large amounts of perception data and high-precision map data, thus improving data processing efficiency. Second, since autonomous driving involves a lane line fusion step, the fusion weights used during lane line fusion can be reused, eliminating the need to recalculate the fusion state, thus improving the efficiency of determining the confidence levels of perception data and high-precision maps. Third, it incorporates the importance of fusion between different data sources (i.e., perception data and high-precision maps) into the determination of the confidence levels of perception data and high-precision maps, as well as the determination of planning and control strategies, thereby improving the accuracy of the acquired confidence levels of perception data and high-precision maps and enhancing the safety of autonomous driving planning.

[0062] In other embodiments, some lane detection algorithms automatically provide the confidence level of the detected lane lines, allowing the confidence level provided by the detection algorithm to be directly used as the fusion matching state. The confidence level of the perceived lane lines represents the degree of confidence of the obtained perceived lane lines. In some specific implementations, the lane detection algorithm can be an artificial intelligence model, such as a neural network model. The perceived lane lines can be predicted based on the output of an artificial intelligence model, such as a neural network model, which can output the perceived lane lines and their probabilities; the probabilities output by the artificial intelligence model can be used as the confidence level of the perceived lane. The confidence level of the map lane lines represents the degree of confidence of the obtained map lane lines. In some specific implementations, the confidence level of the map lane lines can be calculated based on the confidence level of the vehicle's positioning signal (e.g., the confidence level of the vehicle's positioning signal can be used as the confidence level of the map lane lines). The confidence level of the positioning signal can be provided automatically by the positioning module or predicted by a trained artificial intelligence model based on the vehicle's location and environmental information.

[0063] Therefore, determining the fusion matching state based at least on the confidence level of lane lines has several advantages. First, it only requires data processing of the same target object obtained from different data sources (i.e., perception data and high-precision maps), without the need to compare a large amount of perception data and high-precision map data, thus improving data processing efficiency. Second, since the confidence level of lane lines can usually be directly output by relevant modules (such as the positioning module and the lane line detection module), there is no need to recalculate the fusion state, thus improving the efficiency of determining the confidence level of perception data and high-precision maps.

[0064] This application can achieve a variety of different fusion matching states, which will not be elaborated here.

[0065] In some embodiments, the fusion matching state may include a first matching degree between the at least one perceived lane line and a second matching degree between the at least one perceived lane line and the map lane lines respectively. The first matching degree between the perceived lane lines and the second matching degree between the at least one perceived lane line and the map lane lines can be used to determine the confidence level of the high-precision map and the perceived data. Specifically, the matching degree between lane lines can be calculated based on lane line position data, lane line shape data, etc. For example, the smaller the error in the lane line position data, the higher the matching degree. In some embodiments, the error in the lane line position data can be calculated based on the average Euclidean distance between corresponding points between lane lines. The smaller the average Euclidean distance between corresponding feature points between lane lines, the higher the matching degree between lane lines. For another example, the mathematical expression of the lane lines, such as the curve equation, can be determined using curve fitting, and the matching degree between lane lines can be determined using curve matching algorithms such as the nearest point search method. This application can implement various different matching degree calculation methods, which will not be elaborated here.

[0066] Therefore, the first matching degree between at least one perceived lane line and the second matching degree between the at least one perceived lane line and the map lane line respectively can incorporate the data association relationship (the matching degree between lane lines) between different data sources (i.e., between multiple perceived data, and between perceived data and high-precision maps) into the determination of the confidence of perceived data and high-precision maps and the determination of planning and control strategies. This can improve the accuracy of the confidence of the acquired perceived data and high-precision maps, thereby improving the safety of autonomous driving planning.

[0067] In some embodiments, step S130 may include: determining that the confidence level of the perceived data is greater than a first preset threshold when the first matching degree meets a first preset condition. In some embodiments, step S130 may include: determining that the confidence level of the high-precision map is greater than a second preset threshold when the second matching degree meets a second preset condition. In some embodiments, step S130 may include: determining that the confidence level of the perceived data is greater than a first preset threshold when the first matching degree meets a first preset condition; and determining that the confidence level of the high-precision map is greater than a second preset threshold when the second matching degree meets a second preset condition. Specifically, the first preset condition and the second preset condition can be set as needed. For example, the first preset condition may include: the first matching degree is greater than a preset threshold. Thus, by using the first preset condition, when the matching degree between each perceived lane line is high, the confidence level of the perceived data is high, thereby making the confidence level of the perceived data greater than the first preset threshold. In a specific implementation, assuming a preset threshold of 0.8 and a first preset threshold of 0.8, when the matching degree between the visual lane line and the laser point cloud lane line is 0.9, which is greater than the preset threshold, the confidence level of the perceived data can be greater than the first preset threshold of 0.8. For example, the confidence level of the perceived data can be 0.9. For example, a second preset condition may include: at least one of the second matching degrees is greater than a third preset threshold. Thus, through the second preset condition, when at least one perceived lane line has a high matching degree with the map lane line, the confidence level of the high-precision map is high, thereby making the confidence level of the high-precision map greater than the second preset threshold. In one specific implementation, assuming the third preset threshold is 0.8 and the second preset threshold is 0.8, when the matching degree between the visual lane line and the map lane line is 0.9, which is greater than the third preset threshold, the confidence level of the high-precision map can be greater than the second preset threshold of 0.8, for example, the confidence level of the high-precision map can be 0.9. Similarly, when the matching degree between the laser point cloud lane line and the map lane line is 0.9, which is greater than the third preset threshold, the confidence level of the high-precision map can also be greater than the second preset threshold of 0.8, for example, the confidence level of the high-precision map can be 0.9. Therefore, through the above different embodiments, this application can, on the one hand, realize the determination of the confidence level of the perception data and / or the confidence level of the high-precision map, thereby adapting to different autonomous driving planning and control situations; on the other hand, the calculation of the confidence level of the perception data and / or the confidence level of the high-precision map requires a small amount of data, and the calculation method is simple and efficient, making it more adaptable to the real-time nature of the autonomous vehicle's planning and control strategy.

[0068] Furthermore, the confidence levels of the perceived data and the high-precision map can be calculated based on a first matching degree and a second matching degree. For example, the confidence level of the perceived data can be positively correlated with the first matching degree between the perceived lane lines of the perceived data and the perceived lane lines of other perceived data, and / or the second matching degree between the perceived lane lines of the perceived data and the map lane lines. In other words, the higher the matching degree between the perceived lane lines of the perceived data and other perceived lane lines and / or map lane lines, the higher the confidence level of the perceived data.

[0069] In some specific implementations, the confidence level T of the perceived data from the visual sensor v = k1S1, where k1 is a positive correlation parameter, and S1 is the first matching degree between the visual lane line and the laser point cloud lane line. k1 can be determined based on experience, historical lane line data, or prediction by an artificial intelligence model. In an embodiment where k1 is determined based on historical lane line data, the confidence level of the perception data can be calculated using different positive correlation parameters based on historical lane line data. Based on the confidence level of the perception data, the planning and control strategy of the vehicle is determined, and the positive correlation parameter that maximizes the safety of the vehicle's planning and control strategy is obtained.

[0070] In some specific implementations, the confidence level T of the perceived data from the visual sensor v = k2S2, where k2 is the positive correlation parameter and S2 is the second matching degree between the visual lane line and the map lane line. The method for determining k2 can be similar to that for k1, and will not be elaborated here.

[0071] In some specific implementations, the confidence level T of the perceived data from the visual sensor v = k3(S1+S2) / 2, where k3 is the positive correlation parameter, S1 is the first matching degree between the visual lane line and the laser point cloud lane line, and S2 is the second matching degree between the visual lane line and the map lane line. The method for determining K3 can be similar to that for k1, and will not be elaborated here.

[0072] In some other specific implementations, it can be based on T v =k1S1;T v =k2S2;T v =k3(S1+S2) / 2 were tested in combination with historical lane line data. The method with the highest confidence in the safety of the vehicle's planning and control strategy was used as the method for calculating the confidence of the perception data.

[0073] The confidence level of radar sensor perception data can be calculated in a similar way to that of vision sensor perception data, and will not be elaborated here. This application is not intended to limit this.

[0074] For example, the confidence level of a high-definition map can be positively correlated with the second degree of matching between the map lane lines and at least one perceived lane line. In other words, the higher the second degree of matching between the map lane lines and the perceived lane lines, the higher the confidence level of the high-definition map.

[0075] In some specific implementations, the confidence level T of high-precision maps m = k4S2, where k4 is the positive correlation parameter, and S2 is the first matching degree between the visual lane line and the map lane line. k4 can be determined based on experience, historical lane line data, or prediction by an artificial intelligence model. In an embodiment where k4 is determined based on historical lane line data, the confidence level of the high-precision map can be calculated using different positive correlation parameters based on historical lane line data. Based on the confidence level of the high-precision map, the planning and control strategy of the vehicle is determined, and the positive correlation parameter that maximizes the safety of the vehicle's planning and control strategy is obtained.

[0076] In some specific implementations, the confidence level T of high-precision maps m = k5S4, where k5 is the positive correlation parameter and S4 is the second matching degree between the laser point cloud lane lines and the map lane lines. The method for determining k5 can be similar to that for k4, and will not be elaborated here.

[0077] In some specific implementations, the confidence level T of high-precision maps m = k6(S2+S4) / 2, where k6 is the positive correlation parameter, S2 is the second matching degree between the visual lane line and the map lane line, and S4 is the second matching degree between the laser point cloud lane line and the map lane line. The method for determining K6 can be similar to that for k4, and will not be elaborated here.

[0078] In some other specific implementations, it can be based on T m =k4S2;T m =k5S4;T m =k6(S2+S4) / 2 were tested in combination with historical lane line data. The confidence calculation method with the highest safety of the vehicle's planning and control strategy was used as the confidence calculation method for the high-precision map.

[0079] This application can also implement different methods for calculating matching degree and confidence degree, which will not be elaborated here.

[0080] In some specific embodiments, the at least one perceived lane line may include a visual lane line and a laser point cloud lane line. The visual lane line is generated using perception data acquired by a visual sensor, and the laser point cloud lane line is generated using perception data acquired by a lidar. Correspondingly, determining that the confidence level of the high-precision map is greater than the second preset threshold when at least one of the second matching degrees is greater than the third preset threshold may include the following steps: when the second matching degree between the visual lane line and the map lane line is determined to be greater than the third preset threshold, the confidence level of the high-precision map is determined to be a first confidence level; when the second matching degree between the laser point cloud lane line and the map lane line is determined to be greater than the third preset threshold, the confidence level of the high-precision map is determined to be a second confidence level. Both the first confidence level and the second confidence level are greater than the second preset threshold, and the first confidence level is set to be greater than the second confidence level.

[0081] In a specific implementation, assuming the second preset threshold is 0.8 and the third preset threshold is 0.7, when the matching degree between the visual lane line and the map lane line is 0.9, which is greater than the third preset threshold, the confidence level of the high-precision map can be determined to be 1; when the matching degree between the laser point cloud lane line and the map lane line is 0.9, which is greater than the third preset threshold, the confidence level of the high-precision map can also be 0.9.

[0082] Specifically, in this embodiment, the confidence level of the map lane lines is determined by the magnitude of the second matching degree between the map lane lines and different perceived lane lines. Specifically, since the high-precision map data is obtained through offline processing of laser point clouds scanned by a laser sensor, the perceived data obtained by the visual sensor differs more significantly from the perceived data of the laser point cloud compared to the high-precision map. Therefore, when the matching degree between the map lane lines and the visual lane lines is high, the confidence level of the map lane lines can be determined to be high.

[0083] The above embodiments are merely illustrative of one method for determining the confidence level of map lane lines in this application. This application is not intended to limit the scope of the application. Based on the first matching degree and the second matching degree, various different methods for determining the confidence level of map lane lines can be implemented. For example, when both the first and second matching degrees are greater than a third preset threshold, that is, when the map lane lines, visual lane lines, and map lane lines all match, the confidence level of the high-precision map can be determined to be greater than or equal to confidence level T1; when the second matching degree between the visual lane line and the map lane line is greater than the third preset threshold, and the second matching degree between the laser point cloud lane line and the map lane line, and the first matching degree between the visual lane line and the laser point cloud lane line are less than the third preset threshold, the confidence level of the high-precision map is determined to be T2; when the second matching degree between the laser point cloud lane line and the map lane line is greater than the third preset threshold, and the second matching degree between the visual lane line and the map lane line, and the first matching degree between the visual lane line and the laser point cloud lane line are less than the third preset threshold, the confidence level of the high-precision map is determined to be T3; when both the first and second matching degrees are less than the third preset threshold, that is, when the map lane lines, visual lane lines, and map lane lines do not match, the confidence level of the high-precision map can be determined to be greater than or equal to confidence level T4. The confidence levels T1 through T4 decrease sequentially. Similarly, the confidence level of the perceived lane line can also be determined based on the numerical range of the first and second matching scores. This application can implement many more variations, which will not be elaborated here.

[0084] In some embodiments, step S140 may include determining a planning and control strategy for the vehicle based on the perception data when the confidence level of the perceived data is greater than a first preset threshold and the confidence level of the high-precision map is less than or equal to a second preset threshold. The planning and control strategy includes, but is not limited to, vehicle positioning, prediction of the actions of objects around the vehicle, driving control strategies, and vehicle driving planning. Specifically, the driving control strategy may include different autonomous driving functions, such as fully autonomous driving and lane centering. Further, different driving control strategies can be selected according to different confidence levels of the perception data and the high-precision map. For example, when the confidence level of the high-precision map is higher, the fully autonomous driving function can be selected; when the confidence level of the perception data is higher, the lane centering function can be selected. For another example, when the confidence level of the high-precision map is a first confidence level, the fully autonomous driving function can be selected; when the confidence level of the high-precision map is a second confidence level, the lane centering function can be selected. This application can implement many more different variations, which will not be elaborated here. Therefore, in this embodiment, vehicle localization and the prediction of actions of objects around the vehicle can be performed based on perception data, and vehicle driving planning can be performed based on the vehicle localization, action prediction results, and driving control strategies derived from the perception data. Furthermore, by correlating the confidence levels of the perception data and / or the high-precision map with the driving control strategies, the efficiency of determining the driving control strategies can be improved, making it more adaptable to the real-time requirements of autonomous vehicle planning and control strategies. In addition, performing vehicle localization and the prediction of actions of objects around the vehicle solely based on perception data, and then performing vehicle driving planning based on the vehicle localization, action prediction results, and driving control strategies derived from the perception data, reduces the amount of data that needs to be processed, improving the real-time performance and safety of vehicle driving planning.

[0085] In some embodiments, step S140 may include determining a planning and control strategy for the vehicle based on the high-precision map when the confidence level of the high-precision map is greater than a second preset threshold and the confidence level of the perception data is less than or equal to a first preset threshold. Thus, in this embodiment, vehicle localization and motion prediction of objects around the vehicle can be performed based on the map data of the high-precision map, and vehicle driving planning can be performed based on the vehicle localization, motion prediction results, and driving control strategy from the perception data. Furthermore, by establishing a correlation between the confidence level of the perception data and / or the confidence level of the high-precision map and the driving control strategy, the efficiency of determining the driving control strategy can be improved, making it more adaptable to the real-time requirements of the planning and control strategy for autonomous vehicles. In addition, performing vehicle localization and motion prediction of objects around the vehicle based solely on the high-precision map, and performing vehicle driving planning based on the vehicle localization, motion prediction results, and driving control strategy from the high-precision map, can reduce the amount of data that needs to be processed, improving the real-time performance and safety of vehicle driving planning.

[0086] In other embodiments, step S140 may include determining a planning and control strategy for the vehicle based on the confidence levels of the perception data and the high-precision map, combined with the perception data and the high-precision map. Thus, in this embodiment, vehicle localization and motion prediction of objects around the vehicle can be performed based on the confidence levels of the perception data and the high-precision map, combined with the perception data and the high-precision map, and vehicle driving planning can be performed based on the vehicle localization, motion prediction results, and driving control strategy. Furthermore, by establishing a correlation between the confidence levels of the perception data and / or the high-precision map and the driving control strategy, the efficiency of determining the driving control strategy can be improved, making it more adaptable to the real-time requirements of the planning and control strategy for autonomous vehicles. In addition, performing vehicle localization and motion prediction of objects around the vehicle based on the confidence levels of the perception data and the high-precision map, and then performing vehicle driving planning based on the vehicle localization, motion prediction results, and driving control strategy, can improve the accuracy of localization and behavior prediction.

[0087] The above is merely an illustrative representation of the method for determining the planning and control strategy of this application. This application is not intended to limit the scope of the application, and many more different planning and control strategies for vehicles can be implemented.

[0088] The above are merely several specific implementations of the vehicle planning and control method of the present invention. Each implementation can be implemented independently or in combination, and the present invention is not intended to limit it. Furthermore, the flowchart of the present invention is merely illustrative, and the execution order between the steps is not limited thereto. The splitting, merging, sequential exchange, and other synchronous or asynchronous execution methods of the steps are all within the protection scope of the present invention.

[0089] See below. Figure 2 , Figure 2 A block diagram of a vehicle planning and control device according to an embodiment of the present invention is shown. The vehicle planning and control device 200 includes a lane line acquisition module 210, a fusion matching state determination module 220, and a confidence level determination module 230.

[0090] The lane line acquisition module 210 is configured to acquire at least one perceived lane line of a target road segment ahead of the vehicle and the map lane line corresponding to the target road segment in a high-precision map, wherein the perceived lane line is generated using the vehicle's perception data.

[0091] The fusion matching state determination module 220 is configured to determine the fusion matching state between the at least one perceived lane lines and between the at least one perceived lane line and the map lane lines, respectively.

[0092] The confidence determination module 230 is configured to determine the confidence of the high-precision map and the confidence of the perceived data based on the fusion matching state;

[0093] The confidence levels of the high-precision map and the perception data are used to determine the planning and control strategy for the vehicle.

[0094] In the vehicle planning and control device of an exemplary embodiment of the present invention, the confidence level of the high-precision map and the confidence level of the perception data are determined by the fusion matching state between at least one perceived lane line and between at least one perceived lane line and the map lane line, respectively. Based on the confidence level of the high-precision map and the confidence level of the perception data, a planning and control strategy for the vehicle is determined. This ensures that the planning and control strategy for the vehicle can use high-confidence high-precision map data and / or perception data, avoiding the problem of vehicle positioning errors due to data errors or data inaccuracies in the high-precision map data and perception data, thereby improving the safety of autonomous driving planning.

[0095] Figure 2 This illustration of the vehicle planning and control device 200 provided by the present invention is merely schematic. The splitting, merging, and addition of modules without departing from the inventive concept are all within the scope of protection of this invention. The vehicle planning and control device 200 provided by the present invention can be implemented by software, hardware, firmware, plug-ins, and any combination thereof, and the present invention is not limited thereto.

[0096] See below. Figure 3 , Figure 3 A block diagram of a vehicle according to an embodiment of the present invention is shown. The vehicle 300 includes a perception sensor 310, a perception fusion module 320, and a planning and control module.

[0097] The perception sensor 310 is configured to acquire perception data from the vehicle.

[0098] The perception fusion module 320 is configured to: acquire at least one perceived lane line of a target road segment ahead of the vehicle and the corresponding map lane line of the target road segment in a high-precision map, wherein the perceived lane line is generated using the vehicle's perception data; determine the fusion matching state between the at least one perceived lane line and between the at least one perceived lane line and the map lane line respectively; and determine the confidence level of the high-precision map and the confidence level of the perception data based on the fusion matching state.

[0099] The planning and control module may include, for example, a prediction module 350 and a planning module 360. The planning and control module is configured to determine a planning and control strategy for the vehicle based on the confidence level of the high-precision map and the confidence level of the perceived data.

[0100] In some embodiments, the sensing sensor 310 may include a camera 311, a lidar 312, and a millimeter-wave radar 313. This application is not limited thereto, and the sensing sensor 310 may also include other sensing sensors, which will not be elaborated here.

[0101] Specifically, the perception fusion module 320 can have the following characteristics: Figure 2 The diagram illustrates the modular structure of the vehicle planning and control device. The perception fusion module 320 can also fuse the perception data from the perception sensor 310 and the high-precision map data provided by the high-precision map module 330. The high-precision map module 330 can interact with the positioning module 340 to determine the vehicle's position on the high-precision map. The positioning module 340 can also transmit positioning information to the perception fusion module 320, allowing the perception fusion module 320 to determine the correspondence between the perception data and the high-precision map data.

[0102] Specifically, the prediction module 350 can predict the possible trajectories of various objects near the vehicle based on the confidence levels of the high-precision map provided by the perception fusion module 320 and the perception data, combined with the fusion results of the high-precision map and / or the perception fusion module 320. The planning module 360 ​​can plan the trajectory of the autonomous vehicle using the predicted trajectory, the high-precision map, vehicle positioning, and other information, based on the confidence levels of the high-precision map provided by the perception fusion module 320 and the perception data.

[0103] In the vehicle 300 of an exemplary embodiment of the present invention, the confidence level of the high-precision map and the confidence level of the perception data are determined by the fusion matching state between at least one perceived lane line and between at least one perceived lane line and the map lane line, respectively. Based on the confidence level of the high-precision map and the confidence level of the perception data, a planning and control strategy for the vehicle is determined. This ensures that the planning and control strategy for the vehicle can use high-confidence high-precision map data and / or perception data, avoiding the problem of incorrect vehicle positioning due to data errors or data inaccuracies in the high-precision map data and perception data, thereby improving the safety of autonomous driving planning.

[0104] In exemplary embodiments of the present invention, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by, for example, a processor, can implement the steps of the vehicle planning and control method described in any of the above embodiments. In some possible embodiments, various aspects of the present invention can also be implemented as a program product comprising program code that, when run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of the present invention described in the above-described vehicle planning and control method section of this specification.

[0105] refer to Figure 4 As shown, a program product 700 for implementing the above-described method according to an embodiment of the present invention is described. It may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0106] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0107] The computer-readable storage medium may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0108] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the tenant's computing device, partially on the tenant's device, as a standalone software package, partially on the tenant's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the tenant's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0109] In an exemplary embodiment of the present invention, an electronic device is also provided, which may include a processor and a memory for storing executable instructions of the processor. The processor is configured to perform the steps of the vehicle planning and control method described in any of the above embodiments by executing the executable instructions.

[0110] Those skilled in the art will understand that various aspects of the present invention can be implemented as systems, methods, or program products. Therefore, various aspects of the present invention can be specifically implemented in the following forms: entirely hardware implementations, entirely software implementations (including firmware, microcode, etc.), or implementations combining hardware and software aspects, collectively referred to herein as “circuits,” “modules,” or “systems.”

[0111] The following reference Figure 5 To describe an electronic device 500 according to this embodiment of the present invention. Figure 5 The electronic device 500 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0112] like Figure 5 As shown, the electronic device 500 is presented in the form of a general-purpose computing device. The components of the electronic device 500 may include, but are not limited to: at least one processing unit 510, at least one storage unit 520, a bus 530 connecting different system components (including storage unit 520 and processing unit 510), a display unit 540, etc.

[0113] The storage unit stores program code that can be executed by the processing unit 510, causing the processing unit 510 to perform the steps described in the above-described vehicle planning and control method section of this specification, according to various exemplary embodiments of the present invention. For example, the processing unit 510 can perform the steps of the vehicle planning and control method described in any of the above embodiments.

[0114] The storage unit 520 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 5201 and / or a cache storage unit 5202, and may further include a read-only memory unit (ROM) 5203.

[0115] The storage unit 520 may also include a program / utility 5204 having a set (at least one) program module 5205, such program module 5205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0116] Bus 530 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0117] Electronic device 500 can also communicate with one or more external devices 600 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable tenants to interact with electronic device 500, and / or with any device that enables electronic device 500 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 550. Furthermore, electronic device 500 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 560. Network adapter 560 can communicate with other modules of electronic device 500 via bus 530. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0118] The electronic device 500 may be a vehicle with autonomous driving capabilities, or other components with autonomous driving capabilities. The electronic device 500 includes, but is not limited to, an in-vehicle terminal, an in-vehicle controller, an in-vehicle module, an in-vehicle assembly, in-vehicle components, an in-vehicle chip, an in-vehicle unit, in-vehicle radar, or an in-vehicle camera, and other sensors. The vehicle can implement the methods provided in this application through the in-vehicle terminal, in-vehicle controller, in-vehicle module, in-vehicle assembly, in-vehicle components, in-vehicle chip, in-vehicle unit, in-vehicle radar, or camera.

[0119] The electronic device 500 can also be a smart terminal with autonomous driving capabilities other than a vehicle, or be installed in a smart terminal with autonomous driving capabilities other than a vehicle, or be installed in a component of the smart terminal. The smart terminal can be intelligent transportation equipment, smart home equipment, robots, or other terminal devices. The electronic device 500 includes, but is not limited to, the smart terminal or its controller, chip, radar or camera, other sensors, and other components.

[0120] The electronic device 500 can be a general-purpose device or a special-purpose device. In specific implementations, the device can also be a desktop computer, a laptop computer, a web server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, an embedded device, or other devices with processing capabilities. This application does not limit the type of the electronic device 500.

[0121] The electronic device 500 can also be a chip or processor with processing capabilities, and can include multiple processors. The processor can be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. The chip or processor with processing capabilities can be located within the sensor, or it can be located at the receiving end of the sensor's output signal.

[0122] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, portable hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, or network device, etc.) to execute the vehicle planning and control method described above according to the embodiments of the present invention.

[0123] Compared with the prior art, the advantages of this invention are:

[0124] The confidence levels of the high-precision map and the perception data are determined by the fusion and matching states between at least one perceived lane line and the map lane lines, respectively. Based on these confidence levels, a planning and control strategy for the vehicle is determined. This ensures that the vehicle's planning and control strategy can utilize high-confidence high-precision map data and / or perception data, avoiding positioning errors caused by data errors or inaccuracies in the high-precision map data or perception data, thereby improving the safety of autonomous driving planning.

[0125] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the appended claims.

Claims

1. A vehicle planning and control method, characterized in that, include: The vehicle acquires at least one perceived lane line for a target road segment ahead and the corresponding map lane line for the target road segment in a high-precision map. The perceived lane line is generated using the vehicle's perception data. Determine the fusion matching status between the at least one sensed lane lines and between the at least one sensed lane line and the map lane lines respectively; The confidence level of the high-precision map and the confidence level of the perceived data are determined based on the fusion matching status. Based on the confidence level of the high-precision map and the confidence level of the perception data, a planning and control strategy for the vehicle is determined.

2. The vehicle planning and control method as described in claim 1, characterized in that, The fusion matching state includes a first matching degree between the at least one perceived lane line and a second matching degree between the at least one perceived lane line and the map lane lines respectively.

3. The vehicle planning and control method as described in claim 2, characterized in that, Determining the confidence level of the high-precision map and the sensing data based on the fusion matching state includes: If the first matching degree is determined to meet the first preset condition, the confidence level of the perceived data is determined to be greater than the first preset threshold. And / or, if it is determined that the second matching degree meets the second preset condition, the confidence degree of the high-precision map is determined to be greater than the second preset threshold.

4. The vehicle planning and control method as described in claim 3, characterized in that, The step of determining that the confidence level of the high-precision map is greater than the second preset threshold when the second matching degree meets the second preset condition includes: If at least one of the second matching degrees is determined to be greater than a third preset threshold, the confidence level of the high-precision map is determined to be greater than the second preset threshold.

5. The vehicle planning and control method as described in claim 4, characterized in that, The at least one perceived lane line includes visual lane lines and laser point cloud lane lines, wherein the visual lane lines are generated using perception data acquired by a visual sensor, and the laser point cloud lane lines are generated using perception data acquired by a lidar. Correspondingly, determining that the confidence level of the high-precision map is greater than the second preset threshold when at least one of the second matching degrees is greater than the third preset threshold includes: If the second matching degree between the visual lane line and the map lane line is determined to be greater than a third preset threshold, the confidence level of the high-precision map is determined to be the first confidence level. If the second matching degree between the laser point cloud lane line and the map lane line is determined to be greater than the third preset threshold, the confidence level of the high-precision map is determined to be the second confidence level. Both the first confidence level and the second confidence level are greater than the second preset threshold, and the first confidence level is set to be greater than the second confidence level.

6. The vehicle planning and control method as described in claim 1, characterized in that, The step of determining the planning and control strategy for the vehicle based on the confidence level of the high-precision map and the perception data includes: If the confidence level of the perceived data is greater than a first preset threshold and the confidence level of the high-precision map is less than or equal to a second preset threshold, a planning and control strategy for the vehicle is determined based on the perceived data.

7. The vehicle planning and control method as described in claim 1, characterized in that, The step of determining the planning and control strategy for the vehicle based on the confidence level of the high-precision map and the perception data includes: If the confidence level of the high-precision map is greater than a second preset threshold and the confidence level of the perception data is less than or equal to a first preset threshold, a planning and control strategy for the vehicle is determined based on the high-precision map.

8. A vehicle planning and control device, characterized in that, include: The lane line acquisition module is configured to acquire at least one perceived lane line of a target road segment ahead of the vehicle and the map lane line corresponding to the target road segment in a high-precision map. The perceived lane line is generated using the vehicle's perception data. The fusion matching state determination module is configured to determine the fusion matching state between the at least one perceived lane lines and between the at least one perceived lane line and the map lane lines, respectively. The confidence determination module is configured to determine the confidence of the high-precision map and the confidence of the perceived data based on the fusion matching state. The confidence levels of the high-precision map and the perception data are used to determine the planning and control strategy for the vehicle.

9. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to implement the method of any one of claims 1-7 when executing the instructions.

10. A vehicle, characterized in that, include: Perception sensors, configured to acquire perception data from the vehicle; The perception fusion module is configured as follows: The vehicle acquires at least one perceived lane line for a target road segment ahead and the corresponding map lane line for the target road segment in a high-precision map. The perceived lane line is generated using the vehicle's perception data. Determine the fusion matching status between the at least one sensed lane lines and between the at least one sensed lane line and the map lane lines respectively; The confidence level of the high-precision map and the confidence level of the perceived data are determined based on the fusion matching status. The planning and control module is configured to determine the planning and control strategy for the vehicle based on the confidence level of the high-precision map and the confidence level of the perception data.

Images