Automatic driving simulation test method and device, vehicle and storage medium

Abstract

According to the automatic driving simulation test method and device, the vehicle and the storage medium provided by the embodiment of the invention, by receiving the reference coordinate point in the simulation driving path sent by the upper computer, the matched map data is determined in the high-precision map, and the target coordinate point based on the matched map data is obtained; the method comprises the following steps: acquiring a target coordinate point, performing vehicle simulation driving according to the target coordinate point, acquiring navigation guide information of matched map data, determining dynamic map feature point information according to the navigation guide information and the map data, and performing vehicle simulation control according to the matched map data, the target coordinate point and the dynamic map feature point information through an automatic driving algorithm. And determining the next target coordinate point in the high-precision map according to the control result of the vehicle simulation control. Through the mode, the simulation effect of lane level positioning can be achieved, the cost is low, and the test efficiency is high.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving algorithms, and particularly to an autonomous driving simulation test method, an autonomous driving simulation test device, a vehicle, and a storage medium. Background Art

[0002] With the continuous development of autonomous driving technology, especially the introduction of high-precision map data to make up for the lack of long-distance perception of the vehicle itself, intelligent assisted driving functions are continuously installed in the real vehicle environment and mass-produced. During the product development process, a large number of tests or real vehicle function verifications are often required. In the currently commonly used autonomous driving algorithm function test methods based on high-precision map data, one is to conduct large-scale real vehicle tests on open roads, and the other is to conduct large-scale simulation tests by building a simulation cloud platform. However, both of these two methods have certain limitations.

[0003] For the first method, due to the large amount of national map data and regional differences, real vehicle tests are time-consuming and laborious, with high costs and extremely low efficiency. For the second method, the simulation test development cost is relatively high, and a large number of scenario designs and constructions, as well as the construction of specific data, are required, with a large workload. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention are proposed to provide an autonomous driving simulation test method, an autonomous driving simulation test device, a vehicle, and a storage medium that overcome the above problems or at least partially solve the above problems.

[0005] To solve the above problems, an embodiment of the present invention discloses an autonomous driving simulation test method, which is applied to a vehicle. The vehicle communicates with a host computer, and a high-precision map is deployed on the vehicle. The method includes:

[0006] Receiving reference coordinate points in a simulated driving path sent by the host computer one by one, and determining map data matching the reference coordinate points in the high-precision map;

[0007] Obtaining target coordinate points based on the matching map data, and performing vehicle simulated driving according to the target coordinate points;

[0008] Obtaining navigation guidance information based on the matching map data; according to the matching map data and the navigation guidance information, determining dynamic map feature point information in the high-precision map, where the dynamic map feature point information includes: distance information and direction information of the dynamic map feature points relative to the vehicle position in the high-precision map;

[0009] Performing vehicle simulation control through an autonomous driving algorithm according to the matching map data, the target coordinate points, and the dynamic map feature point information.

[0010] Determine the next target coordinate point in the high-precision map according to the control result of the vehicle simulation control.

[0011] Optionally, the obtaining of the target coordinate point in the high-precision map includes:

[0012] When the reference coordinate point is the starting point of the simulated driving path, simulate taking a point in the matched map data according to the reference coordinate point to obtain the target coordinate point.

[0013] Optionally, the step of, when the reference coordinate point is the starting point of the simulated driving path, simulating taking a point in the matched map data according to the reference coordinate point to obtain the target coordinate point includes:

[0014] When the reference coordinate point is the starting point of the simulated driving path, determine the road information that matches the reference coordinate point in the road information of the matched map data;

[0015] In the lane information of the matched road information, determine the lane information that matches the reference coordinate point;

[0016] Judge whether the target lane corresponding to the matched lane information is a drivable lane;

[0017] If the target lane is a drivable lane, take the coordinate point on the center line of the target lane that is closest to the reference coordinate point as the target coordinate point;

[0018] If the target lane is not a drivable lane, determine all the drivable lanes of the road corresponding to the matched road information, and take the coordinate point on the center line of all the drivable lanes that is closest to the reference coordinate point as the target coordinate point.

[0019] Optionally, the vehicle is also equipped with a navigation map, and the obtaining of the navigation guidance information based on the matched map data includes:

[0020] Obtain the navigation path generated by the navigation map, where the starting point and the ending point of the navigation path respectively match the starting point and the ending point of the simulated driving path;

[0021] Perform path matching according to the navigation path and the matched map data to generate navigation guidance information.

[0022] Optionally, the step of performing vehicle simulation control by the automatic driving algorithm according to the matched map data, the target coordinate point, and the dynamic map feature point information includes:

[0023] Through the autonomous driving algorithm, a lateral control result is generated according to the dynamic map feature point information in the high-precision map and the matched map data; the lateral control result includes whether to perform a lane change operation and the lane change direction when it is determined to perform a lane change operation.

[0024] Through the autonomous driving algorithm, a longitudinal control result is generated according to the current vehicle speed during the simulated vehicle driving process and the matched map data; the longitudinal control result includes whether to adjust the vehicle speed and the target vehicle speed when it is determined to adjust the vehicle speed.

[0025] Vehicle simulation control is performed according to the lateral control result and the longitudinal control result.

[0026] Optionally, the generating of the lateral control result through the autonomous driving algorithm according to the dynamic map feature point information in the high-precision map and the matched map data includes:

[0027] Receiving a lateral lane change signal sent by the host computer;

[0028] Through the autonomous driving algorithm, a lateral control result is generated according to the dynamic map feature point information in the high-precision map, the matched map data, and the lateral lane change signal.

[0029] Optionally, the generating of the longitudinal control result through the autonomous driving algorithm according to the current vehicle speed during the simulated vehicle driving process and the matched map data includes:

[0030] Receiving a longitudinal speed adjustment signal sent by the host computer;

[0031] Through the autonomous driving algorithm, a longitudinal control result is generated according to the current vehicle speed during the simulated vehicle driving process, the matched map data, and the longitudinal speed adjustment signal.

[0032] Optionally, the method further includes:

[0033] Judging whether a preset condition is satisfied according to the reference coordinate point and the corresponding target coordinate point; the preset condition is that the distance between the reference coordinate point and the corresponding target coordinate point is less than a preset threshold and they are in the same lane;

[0034] The vehicle simulation driving according to the target coordinate point includes:

[0035] If the preset condition is satisfied, vehicle simulation driving is performed according to the target coordinate point.

[0036] Optionally, the method further includes:

[0037] If the preset condition is not satisfied, vehicle simulation driving is performed according to the reference coordinate point.

[0038] Optionally, the method further includes:

[0039] Sending the longitudinal control result to the host computer, so that the host computer adjusts the sampling interval of the reference coordinate points determined from the simulated driving path according to the longitudinal control result.

[0040] Correspondingly, an embodiment of the present invention discloses an autonomous driving simulation device, and the device includes:

[0041] A first determination module, configured to receive the reference coordinate points in the simulated driving path sent by the host computer one by one, and determine the map data matching the reference coordinate points in the high-precision map;

[0042] A first acquisition module, configured to acquire target coordinate points based on the matching map data, and perform vehicle simulation driving according to the target coordinate points;

[0043] A second acquisition module, configured to acquire navigation guidance information based on the matching map data; determine dynamic map feature point information in the high-precision map according to the matching map data and the navigation guidance information, where the dynamic map feature point information includes: distance information and direction information of the dynamic map feature points relative to the vehicle position in the high-precision map;

[0044] A control module, configured to perform vehicle simulation control according to the matching map data, the target coordinate points, and the dynamic map feature point information through an autonomous driving algorithm;

[0045] A second determination module, configured to determine the next target coordinate point in the high-precision map according to the control result of the vehicle simulation control.

[0046] Optionally, the first acquisition module includes:

[0047] A starting point sub-module, configured to, when the reference coordinate point is the starting point of the simulated driving path, simulate sampling in the matching map data according to the reference coordinate point to obtain target coordinate points.

[0048] Optionally, the starting point sub-module includes:

[0049] A road information determination sub-unit, configured to, when the reference coordinate point is the starting point of the simulated driving path, determine the road information matching the reference coordinate point in the road information of the matching map data;

[0050] A lane information determination sub-unit, configured to determine the lane information matching the reference coordinate point in the lane information of the matching road information;

[0051] A judgment subunit, configured to judge whether a target lane corresponding to the matched lane information is a drivable lane;

[0052] A drivable lane subunit, configured to, if the target lane is a drivable lane, take a coordinate point on the center line of the target lane that is the closest to the reference coordinate point as the target coordinate point;

[0053] A non-drivable lane subunit, configured to, if the target lane is a non-drivable lane, determine all drivable lanes of the road corresponding to the matched road information, and take a coordinate point on the center line of all the drivable lanes that is the closest to the reference coordinate point as the target coordinate point.

[0054] Optionally, the vehicle is further equipped with a navigation map, and the second acquisition module includes:

[0055] A navigation path sub-module, configured to acquire a navigation path generated by the navigation map, where the starting point and the ending point of the navigation path respectively match the starting point and the ending point of the simulated driving path;

[0056] A navigation path matching sub-module, configured to perform path matching according to the navigation path and the matched map data to generate navigation guidance information.

[0057] Optionally, the control module includes:

[0058] A lateral control sub-module, configured to generate a lateral control result through the automatic driving algorithm according to the dynamic map feature point information in the high-precision map and the matched map data; the lateral control result includes whether to perform a lane change operation and the lane change direction when it is determined to perform a lane change operation;

[0059] A longitudinal control sub-module, configured to generate a longitudinal control result through the automatic driving algorithm according to the current vehicle speed during the simulated vehicle driving process and the matched map data; the longitudinal control result includes whether to adjust the vehicle speed and the target vehicle speed when it is determined to adjust the vehicle speed;

[0060] A simulation control sub-module, configured to perform vehicle simulation control according to the lateral control result and the longitudinal control result.

[0061] Optionally, the lateral control sub-module includes:

[0062] A first receiving unit, configured to receive a lateral lane change signal sent by the host computer;

[0063] A first generating unit, configured to generate a lateral control result through the automatic driving algorithm according to the dynamic map feature point information in the high-precision map, the matched map data, and the lateral lane change signal.

[0064] Optionally, the longitudinal control sub-module includes:

[0065] A second receiving unit, configured to receive the longitudinal speed regulation signal sent by the host computer;

[0066] A second generating unit, configured to generate a longitudinal control result according to the current vehicle speed, the matched map data, and the longitudinal speed regulation signal during the simulated vehicle driving process through the automatic driving algorithm.

[0067] Optionally, a preset condition judging module is configured to judge whether a preset condition is satisfied according to a reference coordinate point and a corresponding target coordinate point; the preset condition is that the distance between the reference coordinate point and the corresponding target coordinate point is less than a preset threshold and they are in the same lane.

[0068] The simulation control sub-module further includes:

[0069] A satisfaction unit, configured to perform simulated vehicle driving according to the target coordinate point if the preset condition is satisfied.

[0070] A dissatisfaction unit, configured to perform simulated vehicle driving according to the reference coordinate point if the preset condition is not satisfied.

[0071] Optionally, the dissatisfaction unit further includes:

[0072] An adjustment interval sub-unit, configured to send the longitudinal control result to the host computer, so that the host computer adjusts the sampling interval of determining the reference coordinate point from the simulated driving path according to the longitudinal control result.

[0073] Correspondingly, an embodiment of the present invention discloses a vehicle, including: a processor, a memory, and a computer program stored on the memory and capable of running on the processor, where when the computer program is executed by the processor, each step of the embodiment of the above-mentioned automatic driving simulation test method is implemented.

[0074] Correspondingly, an embodiment of the present invention discloses a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, each step of the embodiment of the above-mentioned automatic driving simulation test method is implemented.

[0075] The embodiments of the present invention have the following advantages: An autonomous driving simulation test method provided by the embodiments of the present invention includes receiving reference coordinate points in a simulated driving path sent by a host computer one by one, determining map data matching the reference coordinate points in a high-precision map, obtaining target coordinate points based on the matching map data, and performing vehicle simulation driving according to the target coordinate points, obtaining navigation guidance information based on the matching map data, determining dynamic map feature point information in the high-precision map according to the matching map data and the navigation guidance information, where the dynamic map feature point information includes distance information and direction information of the dynamic map feature points relative to the vehicle position in the high-precision map, and through an autonomous driving algorithm, performing vehicle simulation control according to the matching map data, the target coordinate points, and the dynamic map feature point information, and determining the next target coordinate point in the high-precision map according to the control result of the vehicle simulation control. By the above method, by fitting the reference coordinate points on the simulated driving path and the high-precision map data, and selecting the target coordinate points for the simulated vehicle driving according to the navigation guidance information and the dynamic map feature point information, the effect of lane-level positioning is achieved, and the simulated driving on the high-precision map can be realized, which is more in line with the actual vehicle positioning scenario. The dynamic map feature point information can make up for the deficiency of the vehicle's own perception of long distances, thus providing better autonomous driving capabilities for the vehicle. This method does not require road vehicle testing or simulation testing, so the cost is low and the testing efficiency is high. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 is a flowchart of the steps of the autonomous driving algorithm test method based on high-precision map data in the embodiments of the present invention;

[0077] Figure 2A is a schematic diagram of simulated driving with point selection based on a high-precision map in the embodiments of the present invention;

[0078] Figure 2B is another schematic diagram of simulated driving with point selection based on a high-precision map in the embodiments of the present invention;

[0079] Figure 3 is a schematic diagram of the simulated driving path in the embodiments of the present invention;

[0080] Figure 4 is a schematic diagram of the road-level navigation path in the embodiments of the present invention;

[0081] Figure 5 is a schematic diagram of the matching between the road-level navigation path and the high-precision map in the embodiments of the present invention;

[0082] Figure 6 is a schematic diagram of the matching between the re-planned navigation path of the navigation map and the high-precision map in the embodiments of the present invention;

[0083] Figure 7It is a flowchart of the steps of an embodiment of the lateral control algorithm in an embodiment of the present invention;

[0084] Figure 8 It is a flowchart of the steps of an embodiment of the longitudinal control algorithm in an embodiment of the present invention;

[0085] Figure 9 It is a schematic diagram of a smooth lane change process in an embodiment of the present invention;

[0086] Figure 10 It is a structural block diagram of an embodiment of an automatic driving simulation device of the present invention. Detailed implementation manners

[0087] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific implementation manners.

[0088] One of the core concepts of the embodiment of the present invention is to receive the reference coordinate points in the simulated driving path sent by the host computer one by one, determine the map data matching the reference coordinate points in the high-precision map, obtain the target coordinate points based on the matching map data, and perform vehicle simulated driving according to the target coordinate points, obtain the navigation guidance information based on the matching map data, determine the dynamic map feature point information in the high-precision map according to the matching map data and the navigation guidance information, where the dynamic map feature point information includes the distance information and direction information of the dynamic map feature points relative to the vehicle position in the high-precision map, and through the automatic driving algorithm, according to the matching map data, the target coordinate points, and the dynamic map feature point information, perform vehicle simulated control, and determine the next target coordinate point in the high-precision map according to the control result of the vehicle simulated control. Through the above method, by fitting the reference coordinate points on the simulated driving path and the high-precision map data, and selecting the target coordinate points for the simulated vehicle driving according to the navigation guidance information and the dynamic map feature point information, the effect of lane-level positioning is achieved, and the simulated driving on the high-precision map can be realized, which is more in line with the actual vehicle positioning scenario. The dynamic map feature point information can make up for the deficiency of the vehicle's own perception of long distances, thus providing better automatic driving capabilities for the vehicle. This method does not require road vehicle testing or simulation testing, so the cost is low and the testing efficiency is high.

[0089] Referring to Figure 1 , it shows a flowchart of the steps of an embodiment of a method for testing an automatic driving algorithm based on high-precision map data of the present invention, which may specifically include the following steps:

[0090] Step 101, receive the reference coordinate points in the simulated driving path sent by the host computer one by one, and determine the map data matching the reference coordinate points in the high-precision map.

[0091] In practical applications, high-precision maps and navigation maps are deployed on the vehicle, and the vehicle communicates with the host computer. Among them, the host computer, the navigation map, and the high-precision map form a local area network to ensure that data can be transmitted between them through the Ethernet network. The high-precision map and the autonomous driving algorithm are deployed in the controller of the autonomous driving domain.

[0092] Specifically, the host computer can obtain road map data information through the open interface of the general-precision road map website of the mapping company. The host computer can set the starting point, the ending point, and one or more waypoints, and generate a simulated driving path based on the obtained road map data information. In practical applications, the starting point and the ending point of the simulated driving path can be set according to actual needs, and the embodiments of the present invention do not limit this.

[0093] The host computer selects reference coordinate points at preset distance intervals on the simulated driving path to obtain a set of reference coordinate points on the simulated driving path, and calculates information such as the heading angle of the simulated driving direction. And according to the set initial vehicle speed, the reference coordinate points are sent to the high-precision map one by one at a fixed sending frequency. Exemplarily, the preset distance interval can be 5 meters or 10 meters. The preset distance interval can be set according to actual needs in practical applications, and the embodiments of the present invention do not limit this. The fixed sending frequency can be once every 100 milliseconds or once every 200 milliseconds. The sending frequency can be set according to actual needs in practical applications, and the embodiments of the present invention do not limit this. The reference coordinate points on the simulated driving path are road-level simulated positioning points.

[0094] The high-precision map can receive the reference coordinate points in the simulated driving path sent by the host computer one by one. For each received reference coordinate point, the received reference coordinate point is matched with the high-precision map to obtain the high-precision map data matched by the reference coordinate point. Exemplarily, after the high-precision map mapping company SDK obtains the target reference point, it first determines whether the target reference point is near the coverage range of the high-precision map. If the target reference point is near the coverage range of the high-precision map, then the high-precision map data near the target reference point is output, including the high-precision map data within the range from a specific distance in front of the target reference point to a specific trailing distance behind the target reference point. The specific distance in front can be 2 kilometers, and the specific trailing distance behind can be 500 meters. Of course, the specific distance in front and the specific trailing distance behind can be set according to actual needs in practical applications, and the embodiments of the present invention do not limit this. When determining whether the target reference point is near the coverage range of the high-precision map, within the preset positioning range error, the high-precision map data can also be output. The preset positioning range error can be about 20 meters to 30 meters. Of course, the preset positioning range error can be set according to actual needs in practical applications, and the embodiments of the present invention do not limit this.

[0095] In practical applications, the coverage of high-precision maps is limited. For example, highways or urban expressways are within the coverage of high-precision maps, so there is high-precision map data for highways or urban expressways. Urban areas are not within the coverage of high-precision maps, so there is no high-precision map data for urban areas.

[0096] After the high-precision map obtains the high-precision map data of the reference coordinate point, the high-precision map data can also be processed and then stored in a structured manner. The processing includes converting the format of the matched high-precision map data into the format actually required. Among them, the high-precision map data matched by the reference coordinate point includes road segment information, lane information within the road segment, coordinates and attribute information of points within the lane, etc. The attribute information includes speed limit information of the road segment, solid or dashed information of the lane lines, etc.

[0097] Step 102: Obtain the target coordinate point based on the matched map data, and perform vehicle simulation driving according to the target coordinate point.

[0098] Referring to Figure 2, a schematic diagram of simulated point-taking driving based on a high-precision map in an embodiment of the present invention is shown. Figure 2A It is a schematic diagram of simulating vehicle driving on a high-precision map. Figure 2B After obtaining the target coordinate point on the high-precision map, drive forward from Figure 2A the position of the simulated vehicle. Obtain the target coordinate point based on the matched map data from the high-precision map, and perform vehicle simulation driving according to the target coordinate point. Vehicle simulation driving on the high-precision map needs to be carried out according to the target coordinate point.

[0099] In an embodiment of the present invention, obtaining the target coordinate point in the high-precision map may include the following sub-steps:

[0100] Sub-step S11: When the reference coordinate point is the starting point of the simulated driving path, simulate point-taking in the matched map data according to the reference coordinate point to obtain the target coordinate point.

[0101] Specifically, after the host computer obtains the starting point on the simulated driving path, it sends the starting point as the reference coordinate point to the high-precision map. After the high-precision map receives the reference coordinate point, it matches the reference coordinate point with the high-precision map to obtain the high-precision map data matched with the reference coordinate point, and performs simulated point-taking in the matched high-precision map data to obtain the target coordinate point. The target coordinate point is used as a road-level simulation positioning point for the simulated vehicle to drive on the high-precision map according to the target coordinate point.

[0102] In an embodiment of the present invention, when the reference coordinate point is the starting point of the simulated driving path, simulating a point in the matched map data according to the reference coordinate point to obtain a target coordinate point may further include the following sub-steps:

[0103] Sub-step S111, when the reference coordinate point is the starting point of the simulated driving path, determine the road information in the matched map data that matches the reference coordinate point;

[0104] Sub-step S112, in the lane information of the matched road information, determine the lane information that matches the reference coordinate point;

[0105] Sub-step S113, determine whether the target lane corresponding to the matched lane information is a drivable lane;

[0106] Sub-step S114, if the target lane is a drivable lane, take the coordinate point on the center line of the target lane that is closest to the reference coordinate point as the target coordinate point;

[0107] Sub-step S115, if the target lane is not a drivable lane, determine all the drivable lanes of the road corresponding to the matched road information, and take the coordinate point on the center line of all the drivable lanes that is closest to the reference coordinate point as the target coordinate point.

[0108] Specifically, when the reference coordinate point received by the high-precision map is the starting point of the simulated driving path sent by the host computer, the reference coordinate point is matched with the matched high-precision map data, and the road information in the matched high-precision map data that matches the reference coordinate point is determined, so as to determine the specific road where the reference coordinate point is located. Then, the lane information of the specific road where the reference coordinate point is located is determined, so as to determine the target lane where the reference coordinate point is located. According to the lane attribute information, it is judged whether the target lane where the reference coordinate point is located is a drivable lane. If the target lane is a drivable lane, then, take the point on the center line of the target lane that is closest to the reference coordinate point as the target coordinate point, and use this target coordinate point as the starting point for lane-level simulation positioning of vehicle simulation driving on the high-precision map; if the target lane is not a drivable lane, then traverse the points on the center lines of all lanes of the road where the target coordinate point is located, and take the point that is closest to the reference coordinate point as the target coordinate point, and use this target coordinate point as the starting point for lane-level simulation positioning of vehicle simulation driving on the high-precision map. Exemplarily, when the lane is an emergency lane, the lane is not a drivable lane.

[0109] The reference coordinate points on the simulated driving path sent by the host computer are road-level simulated positioning points with ordinary accuracy. The high-precision map obtains target coordinate points by simulating and taking points on the high-precision map according to the reference coordinate points. The target coordinate points are lane-level simulated positioning points, and their accuracy is higher than ordinary accuracy.

[0110] Step 103, obtain navigation guidance information based on the matched map data; according to the matched map data and the navigation guidance information, determine the dynamic map feature point information in the high-precision map, where the dynamic map feature point information includes: the distance information and direction information of the dynamic map feature point relative to the vehicle position in the high-precision map.

[0111] Specifically, the high-precision map obtains the navigation guidance information of the high-precision map data matched with the reference coordinate points, and then calculates the recommended lane, the curvature, slope, diversion point, confluence point, ramp, lane number change point, road type change point, construction area, tunnel, bridge, acceleration / deceleration lane, solid / dashed line change point, acceleration / deceleration lane, etc. of the dynamic map feature points relative to the real-time position of the simulated vehicle in the high-precision map according to the matched high-precision map data and the navigation guidance information. After determining the position of the target coordinate point in the high-precision map, traverse and deduce from the position of the target coordinate point in the driving direction. Since dynamic feature point information such as curvature, lane line type, ramp, construction area, bridge, etc. will be attached to the high-precision map data, it is necessary to determine the relative distance and direction between the current simulated vehicle position in the high-precision map and these dynamic feature points.

[0112] Exemplarily, calculate the curvature information at a fixed position ahead, such as calculating the road curvature at 300 meters ahead. Deduce forward from the current position of the simulated vehicle according to the road connection relationship, accumulate the distance, and take out the curvature of the point at 300m.

[0113] Exemplarily, calculate the distance to the construction area. Deduce from the current position of the simulated vehicle in the driving direction, continue to accumulate the distance while judging whether it is a construction area. When it is a construction area, output the accumulated distance value at this time as the distance to the entrance of the construction area, and then continue to deduce forward. When it is no longer a construction area, stop accumulating the distance and calculate the distance to the end of the construction area.

[0114] Exemplarily, calculate the recommended lane. First, deduce from the current position of the simulated vehicle in the driving direction, and according to the road connection relationship, find the road on the navigation path that has no successor. Then, backtrack from this road to the current position of the simulated vehicle according to the lane connection relationship, so as to mark the recommended lane.

[0115] The calculation method of the distance of other dynamic map feature points relative to the current simulated vehicle position is similar. The direction information can be calculated according to geometric methods. In practical applications, the calculation methods of the distance and direction of dynamic map feature points relative to the current simulated vehicle position can be set according to actual requirements, and the embodiments of the present invention do not limit this.

[0116] In the embodiments of the present invention, the vehicle is also deployed with a navigation map. The obtaining of the navigation guidance information based on the matched map data may include the following sub-steps:

[0117] Sub-step S21: Obtain the navigation path generated by the navigation map, where the start and end points of the navigation path match the start and end points of the simulated driving path;

[0118] Sub-step S22: Perform path matching according to the navigation path and the matched map data to generate navigation guidance information.

[0119] Specifically, the vehicle is also deployed with a navigation map, and the accuracy of the navigation map is ordinary accuracy. On the navigation map, according to the start point, waypoints, and end point of the simulated driving path, a road-level navigation path is set, and coordinate points are taken on the road-level navigation path and sent to the high-precision map. The sampling interval on the road-level navigation path can be appropriately larger. Exemplarily, the sampling interval can be 20 meters. Of course, the sampling interval can be adjusted according to actual requirements in practical applications, and the embodiments of the present invention do not limit this.

[0120] The high-precision map performs path matching between the road-level navigation path and the high-precision map matched with the reference coordinate points according to the received coordinate points, and generates navigation guidance information attached to the matched high-precision map. This navigation guidance information is lane-level navigation guidance information.

[0121] Step 104: Through the automatic driving algorithm, perform vehicle simulation control according to the matched map data, the target coordinate points, and the dynamic map feature point information.

[0122] Specifically, the automatic driving algorithm performs vehicle simulation control in the high-precision map according to the high-precision map data matched with the reference coordinate points, the target coordinate points determined in the matched high-precision map, and the dynamic map feature point information. In this way, only through the data opened by the map provider, and the high-precision map data and fitting based on the high-precision map data, the simulation effect of lane-level positioning is achieved, which is more in line with the actual driving effect of the vehicle in the high-precision map range in the real vehicle positioning scenario, without the need for large-scale real vehicle tests on open roads, nor the need to build a simulation cloud platform for large-scale simulation tests.

[0123] In an embodiment of the present invention, the vehicle simulation control performed by the autonomous driving algorithm according to the matched map data, the target coordinate points, and the dynamic map feature point information may include the following sub-steps:

[0124] Sub-step S31: Generate a lateral control result through the autonomous driving algorithm according to the dynamic map feature point information in the high-precision map and the matched map data; the lateral control result includes whether to perform a lane change operation and the lane change direction when it is determined to perform a lane change operation.

[0125] Sub-step S32: Generate a longitudinal control result through the autonomous driving algorithm according to the current vehicle speed during the simulated vehicle driving process and the matched map data; the longitudinal control result includes whether to adjust the vehicle speed and the target vehicle speed when it is determined to adjust the vehicle speed.

[0126] Sub-step S33: Perform vehicle simulation control according to the lateral control result and the longitudinal control result.

[0127] Specifically, the autonomous driving algorithm includes a lateral control algorithm and a longitudinal control algorithm. The lateral control algorithm comprehensively judges whether to perform a lane change operation on the current lane of the simulated vehicle according to the matched high-precision map data and dynamic map feature point information, and the lane change direction when it is determined to perform a lane change operation. If no lane change is required, continue to simulate driving on the current lane of the simulated vehicle; if a lane change is required, initiate a lane change request.

[0128] Exemplarily, when the successor lane of the current lane where the simulated vehicle is driving merges into other lanes, when the current lane where the simulated vehicle is driving is no longer a recommended lane, and when there are diversion points or confluence points ahead, the lateral control algorithm needs to consider performing a lane change. Moreover, when changing lanes, information such as whether there is a solid line on the road surface ahead, the distance and length of the solid line also needs to be considered.

[0129] The longitudinal control algorithm outputs a longitudinal control result by obtaining the current vehicle speed, lane speed limit information, road type, road curvature information ahead, etc. during the simulated vehicle driving process. Exemplarily, the current vehicle speed during the simulated vehicle driving process can be obtained by obtaining the set default cruise vehicle speed in the initialization configuration. After the longitudinal control algorithm obtains the set default cruise vehicle speed of the simulated vehicle, then obtains the lane speed limit information ahead, and then judges whether the current cruise vehicle speed is greater than the speed limit value ahead. If it is less, continue to drive at the set cruise vehicle speed. If it is greater, adjust the vehicle speed to the speed limit value ahead and adjust the vehicle speed according to the road curvature and other information in the dynamic feature point information.

[0130] Exemplarily, the vehicle is driving on a highway with a speed limit of 120 km / h, and the cruise speed is set to 100 km / h. The vehicle simulates driving at a speed of 100 km / h. If the speed limit value of the road ahead is reduced to 80 km / h, the longitudinal control algorithm will synchronously adjust the vehicle speed to 80 km / h. For another example, if entering a ramp ahead, the vehicle speed will be adjusted to the ramp speed limit, such as 40 km / h. If the curvature ahead is large and the bend is sharp, the vehicle speed will be further reduced.

[0131] In an embodiment of the present invention, it is determined whether a preset condition is satisfied according to a reference coordinate point and a corresponding target coordinate point; the preset condition is that the distance between the reference coordinate point and the corresponding target coordinate point is less than a preset threshold and they are in the same lane.

[0132] The vehicle simulation driving according to the target coordinate point includes:

[0133] If the preset condition is satisfied, vehicle simulation driving is performed according to the target coordinate point.

[0134] Specifically, the lane-level simulation positioning algorithm needs to determine whether the position difference between the reference coordinate point and the corresponding target coordinate point satisfies the preset condition. When the lateral distance between the target coordinate point and the reference coordinate point is less than the preset threshold and they are in the same lane, vehicle simulation driving is performed on the high-precision map according to the target coordinate point.

[0135] In an embodiment of the present invention, if the preset condition is not satisfied, vehicle simulation driving is performed according to the reference coordinate point.

[0136] Specifically, if the lateral distance between the target coordinate point and the reference coordinate point is greater than the preset threshold and they are in different lanes, vehicle simulation driving is performed on the high-precision map according to the reference coordinate point, and lane line fitting is performed again. Exemplarily, at an intersection involving road diversion, when the paths of the target coordinate point and the reference coordinate point diverge, the road-level navigation path needs to be used to reset the lane-level simulation positioning point and perform lane line fitting again. This scenario simulates the situation of manually taking over the steering wheel and not driving according to the navigation path at a fork in the road.

[0137] Refer to Figure 3 , which shows a schematic diagram of the simulated driving path in an embodiment of the present invention. The simulated driving path goes straight at the ramp intersection and does not need to get off the ramp. The host computer can obtain road map data information through the open interface of the general-precision road map website of the map provider. The host computer can set the starting point, the ending point, and one or more waypoints, and generate a simulated driving path based on the obtained road map data information.

[0138] Refer to Figure 4, showing a schematic diagram of the road-level navigation path in an embodiment of the present invention. A road-level navigation path is set on the navigation map. When simulating a situation where the road-level navigation path is different from the simulated driving path, the road-level navigation path directly exits the ramp at the ramp intersection.

[0139] Referring to Figure 5 , showing a schematic diagram of the matching of the road-level navigation path and the high-precision map in an embodiment of the present invention. The road-level navigation path set in Figure 5 is matched with the high-precision map. The path where points A and B are located is the Figure 5 obtained road-level navigation path, and the path where points A and C are located is the Figure 4 obtained simulated driving path. When simulating vehicle driving in the high-precision map, take points and drive along the navigation path matched on the high-precision map. When driving to the road divergence point A, the paths of the target coordinate point B and the reference coordinate point C diverge, and vehicle simulation driving is performed according to the reference coordinate point C on the high-precision map.

[0140] Referring to Figure 6 , showing a schematic diagram of the matching of the re-planned navigation path on the navigation map and the high-precision map in an embodiment of the present invention. Since the vehicle does not drive according to the navigation path, the navigation map will re-plan the path and match the re-planned navigation path with the high-precision map to obtain new navigation guidance information attached to the high-precision map.

[0141] In an embodiment of the present invention, the generating of the lateral control result according to the dynamic map feature point information in the high-precision map and the matched map data through the automatic driving algorithm may further include the following sub-steps:

[0142] Sub-step S311, receiving the lateral lane change signal sent by the host computer;

[0143] Sub-step S312, generating a lateral control result through the automatic driving algorithm according to the dynamic map feature point information in the high-precision map, the matched map data, and the lateral lane change signal.

[0144] Referring to Figure 7, which shows the schematic flow chart of the lateral control algorithm in the embodiment of the present invention. After determining the target coordinate point, that is, after inputting a lane and a simulated positioning point, the lateral control algorithm comprehensively judges whether the simulated vehicle needs to change lanes when driving in the current lane according to the matched high-precision map data and the dynamic map feature point information, and the lane-changing direction when it is determined to change lanes. If there is no need to change lanes, the vehicle continues to simulate driving in the current lane where the simulated vehicle is driving; if a lane change is required, a lane change request is initiated. The lateral control algorithm in the automatic driving algorithm can also receive the lateral lane change signal sent by the host computer, and then judge whether a lane change is needed and output the lateral control result according to the lateral lane change signal, the dynamic map feature point information and the matched high-precision map data. The judgment method is similar to that of the above embodiment and will not be elaborated here. After receiving the lateral lane change signal sent by the host computer, if it is confirmed that a lane change is possible, a lane change request is initiated, and then it is judged whether the road conditions at the current position of the simulated vehicle meet the lane change conditions. If they meet, a lane change is performed; if not, the lane change is inhibited, and the judgment of whether a lane change is needed is performed again. By receiving the lateral lane change signal input by manual intervention on the host computer, the lateral control result of this simulation is actively affected, simulating the manual lane change scenario in the actual process, which is more in line with the real vehicle environment and can achieve the purpose of testing the lateral control algorithm at the same time.

[0145] In the embodiment of the present invention, the step of generating a longitudinal control result by the automatic driving algorithm according to the current vehicle speed during the driving process of the simulated vehicle and the matched map data may further include the following sub-steps:

[0146] Sub-step S321, receiving the longitudinal speed regulation signal sent by the host computer;

[0147] Sub-step S322, generating a longitudinal control result by the automatic driving algorithm according to the current vehicle speed during the driving process of the simulated vehicle, the matched map data and the longitudinal speed regulation signal.

[0148] Refer to Figure 8, which shows the schematic flow chart of the longitudinal control algorithm in the embodiments of the present invention. The current vehicle speed during the simulated vehicle driving process is obtained. Specifically, it can be obtained by acquiring the set default cruise vehicle speed in the initialization configuration. After the longitudinal control algorithm acquires the set default cruise vehicle speed of the simulated vehicle, it then acquires the speed limit information of the front lane, and then determines whether the current cruise vehicle speed is greater than the front speed limit value. If it is less, it continues to drive at the set cruise vehicle speed. If it is greater, it adjusts the vehicle speed to the front speed limit value, and adjusts the vehicle speed according to the road curvature and other information in the dynamic feature point information. The longitudinal control algorithm in the automatic driving algorithm can also receive the longitudinal speed adjustment signal sent by the host computer, and then determine whether to adjust the speed and output the longitudinal control result according to the longitudinal speed adjustment signal, the current vehicle speed during the simulated vehicle driving process, and the matched high-precision map data. The judgment method is similar to that of the above embodiments and will not be elaborated here. By receiving the longitudinal speed adjustment signal input by manual intervention on the host computer, the longitudinal control result of this simulation is actively affected, simulating the scenario of manually adjusting the vehicle speed in the actual process, which is more in line with the real vehicle environment and can achieve the purpose of testing the longitudinal control algorithm at the same time.

[0149] In the embodiments of the present invention, it is necessary to send the longitudinal control result to the host computer so that the host computer adjusts the sampling interval of the reference coordinate points determined from the simulated driving path according to the longitudinal control result.

[0150] Specifically, the longitudinal control algorithm also needs to feedback the longitudinal control result to the host computer. The host computer synchronously adjusts the sampling interval of the reference coordinate points on the road-level simulated driving path according to the longitudinal control result, so that the vehicle speed of the host computer's simulated driving path is synchronized with the vehicle speed of the simulated vehicle driving in the high-precision map. Since the reference coordinate points are longitude and latitude points, the distance between two points can be confirmed by two longitude and latitude coordinate points, and the reference coordinate points are sent at a fixed frequency. Speed = distance / time. The time interval is fixed. Therefore, the greater the sampling interval distance of the reference coordinate points, the faster the vehicle speed.

[0151] Step 105, determine the next target coordinate point in the high-precision map according to the control result of the vehicle simulation control.

[0152] The lane-level simulation positioning algorithm confirms the next target coordinate point according to the control results of the lateral and longitudinal algorithms, referring to Figure 9, which shows a schematic diagram of the smooth lane change process in an embodiment of the present invention. The lane-level simulation positioning algorithm determines the target lane. When a lane change is required, according to parameters such as the time and distance of the lane change, the end point after the lane change is confirmed, that is, the next target coordinate point, and a smooth curve from the current position where the simulated vehicle travels to the next target coordinate point is generated as the lane change trajectory. This set of curve coordinates serves as the set of sampling points for the lane-level simulation positioning points during the lane change process, realizing the smooth lane change process.

[0153] Moreover, the high-precision map synchronously sends the next target coordinate point to the navigation map side, so that the position information of the navigation map and the high-precision map is kept synchronized.

[0154] In an embodiment of the present invention, when the simulated vehicle travels outside the range of the high-precision map, it is impossible to perform simulated driving based on the lane information of the high-precision map. Then, the road-level simulation positioning points sent by the host computer are directly used as the lane-level simulation positioning points until it re-enters the range of the high-precision map, and then lane line fitting is performed again to obtain new lane-level simulation positioning points.

[0155] The host computer can receive the process data sent by the high-precision map and synchronously display it in the visualization tool of the host computer.

[0156] Exemplarily, the host computer can record the intermediate process data generated during a certain simulation process through the data recording module, such as road-level positioning point coordinates, lane-level positioning point coordinates, high-precision map data, navigation paths, dynamic map feature point information, control signals output by the lateral and longitudinal control algorithms, host computer control signals, etc., and then replay the simulation scenario through the data playback module. During multiple simulation processes on the same road section, partial information of multiple data records can be synchronously read and presented to the visualization module, and intuitive comparative analysis can be performed through the visualization window.

[0157] It should be noted that for the method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the embodiments of the present invention are not limited by the described action sequences, because according to the embodiments of the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily essential for the embodiments of the present invention.

[0158] Referring to Figure 10 , which shows a structural block diagram of an embodiment of an automatic driving simulation device of the present invention, specifically including the following modules:

[0159] The first determination module 1001 is configured to receive the reference coordinate points in the simulated driving path sent by the host computer one by one, and determine the map data matching the reference coordinate points in the high-precision map;

[0160] The first acquisition module 1002 is configured to acquire the target coordinate points based on the matching map data, and perform vehicle simulation driving according to the target coordinate points;

[0161] The second acquisition module 1003 is configured to acquire the navigation guidance information based on the matching map data; according to the matching map data and the navigation guidance information, determine the dynamic map feature point information in the high-precision map, where the dynamic map feature point information includes: the distance information and direction information of the dynamic map feature point relative to the vehicle position in the high-precision map;

[0162] The control module 1004 is configured to perform vehicle simulation control according to the matching map data, the target coordinate points, and the dynamic map feature point information through an automatic driving algorithm;

[0163] The second determination module 1005 is configured to determine the next target coordinate point in the high-precision map according to the control result of the vehicle simulation control.

[0164] In an embodiment of the present invention, the first acquisition module includes:

[0165] The starting point sub-module is configured to, when the reference coordinate point is the starting point of the simulated driving path, simulate taking points in the matching map data according to the reference coordinate point to obtain target coordinate points.

[0166] In an embodiment of the present invention, the starting point sub-module includes:

[0167] The road information determination sub-unit is configured to, when the reference coordinate point is the starting point of the simulated driving path, determine the road information matching the reference coordinate point in the road information of the matching map data;

[0168] The lane information determination sub-unit is configured to determine the lane information matching the reference coordinate point in the lane information of the matching road information;

[0169] The judgment sub-unit is configured to judge whether the target lane corresponding to the matching lane information is a drivable lane;

[0170] The drivable lane sub-unit is configured to, if the target lane is a drivable lane, take the coordinate point closest to the reference coordinate point on the center line of the target lane as the target coordinate point;

[0171] A non-drivable lane sub-unit, configured to, if the target lane is a non-drivable lane, determine all drivable lanes of the road corresponding to the matched road information, and take the coordinate point on the center line of all the drivable lanes that is closest to the reference coordinate point as the target coordinate point.

[0172] In an embodiment of the present invention, the vehicle is further equipped with a navigation map, and the second acquisition module includes:

[0173] A navigation path sub-module, configured to acquire a navigation path generated by the navigation map, where the starting point and the ending point of the navigation path respectively match the starting point and the ending point of the simulated driving path;

[0174] A navigation path matching sub-module, configured to perform path matching according to the navigation path and the matched map data to generate navigation guidance information.

[0175] In an embodiment of the present invention, the control module includes:

[0176] A lateral control sub-module, configured to generate a lateral control result through the automatic driving algorithm according to the dynamic map feature point information in the high-precision map and the matched map data; the lateral control result includes whether to perform a lane change operation and the lane change direction when it is determined to perform a lane change operation;

[0177] A longitudinal control sub-module, configured to generate a longitudinal control result through the automatic driving algorithm according to the current vehicle speed during the simulated vehicle driving process and the matched map data; the longitudinal control result includes whether to adjust the vehicle speed and the target vehicle speed when it is determined to adjust the vehicle speed;

[0178] A simulation control sub-module, configured to perform vehicle simulation control according to the lateral control result and the longitudinal control result.

[0179] In an embodiment of the present invention, the lateral control sub-module includes:

[0180] A first receiving unit, configured to receive a lateral lane change signal sent by the host computer;

[0181] A first generating unit, configured to generate a lateral control result through the automatic driving algorithm according to the dynamic map feature point information in the high-precision map, the matched map data, and the lateral lane change signal.

[0182] In an embodiment of the present invention, the longitudinal control sub-module includes:

[0183] A second receiving unit, configured to receive a longitudinal speed regulation signal sent by the host computer;

[0184] A second generation unit, configured to generate a longitudinal control result according to the current vehicle speed, the matched map data, and the longitudinal speed regulation signal during the simulated vehicle driving process by using the automatic driving algorithm.

[0185] In an embodiment of the present invention, a determination module for meeting a preset condition is configured to determine whether a preset condition is met according to a reference coordinate point and a corresponding target coordinate point; the preset condition is that the distance between the reference coordinate point and the corresponding target coordinate point is less than a preset threshold and they are in the same lane.

[0186] The simulation control sub-module further includes:

[0187] A satisfaction unit, configured to perform simulated vehicle driving according to the target coordinate point if the preset condition is met.

[0188] A dissatisfaction unit, configured to perform simulated vehicle driving according to the reference coordinate point if the preset condition is not met.

[0189] In an embodiment of the present invention, the dissatisfaction unit further includes:

[0190] An adjustment interval sub-unit, configured to send the longitudinal control result to the host computer, so that the host computer adjusts the sampling interval of determining the reference coordinate point from the simulated driving path according to the longitudinal control result.

[0191] For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple. For related parts, please refer to the partial description of the method embodiment.

[0192] An embodiment of the present invention further provides a vehicle, including:

[0193] It includes a processor, a memory, and a computer program stored on the memory and capable of running on the processor. When the computer program is executed by the processor, it implements each process of the above-mentioned embodiment of the automatic driving simulation test method and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0194] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements each process of the above-mentioned embodiment of the automatic driving simulation test method and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0195] Each embodiment in this specification is described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the embodiments, please refer to each other.

[0196] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, an apparatus, or a computer program product. Therefore, the embodiments of the present invention can take the form of an all-hardware embodiment, an all-software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.

[0197] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing terminal devices generate a device for implementing the functions specified in Figure 1 one or more of the processes Figure 1 or blocks.

[0198] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the functions specified in Figure 1 one or more of the processes Figure 1 or blocks.

[0199] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, such that a series of operation steps are executed on the computer or other programmable terminal device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable terminal device provide steps for implementing the functions specified in Figure 1 one or more of the processes Figure 1 or blocks.

[0200] Although the preferred embodiments of the embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present invention.

[0201] Finally, it should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or terminal device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or terminal device comprising said element.

[0202] The above has introduced in detail an autonomous driving simulation test method, an autonomous driving simulation test device, a vehicle and a storage medium provided by the present invention. Specific examples are used in this text to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for autonomous driving simulation testing, characterized in that, Applied to a vehicle, the vehicle communicates with a host computer, and a high-precision map is deployed on the vehicle. The method includes: Receiving the reference coordinate points in the simulated driving path sent by the host computer one by one, and determining the map data matching the reference coordinate points in the high-precision map; Obtaining the target coordinate points based on the matched map data, and performing simulated driving of the vehicle according to the target coordinate points; Obtaining the navigation guidance information based on the matched map data; according to the matched map data and the navigation guidance information, determining the dynamic map feature point information in the high-precision map, where the dynamic map feature point information includes: the distance information and direction information of the dynamic map feature points relative to the vehicle position in the high-precision map; Performing simulated vehicle control through an automatic driving algorithm according to the matched map data, the target coordinate points, and the dynamic map feature point information; Determining the next target coordinate point in the high-precision map according to the control result of the simulated vehicle control.

2. The method according to claim 1, characterized in that, The obtaining of the target coordinate points in the high-precision map includes: When the reference coordinate point is the starting point of the simulated driving path, simulating to obtain a target coordinate point according to the reference coordinate point in the matched map data.

3. The method according to claim 2, characterized in that, The when the reference coordinate point is the starting point of the simulated driving path, simulating to obtain a target coordinate point according to the reference coordinate point in the matched map data includes: When the reference coordinate point is the starting point of the simulated driving path, determining the road information matching the reference coordinate point in the road information of the matched map data; Determining the lane information matching the reference coordinate point in the lane information of the matched road information; Judging whether the target lane corresponding to the matched lane information is a drivable lane; If the target lane is a drivable lane, taking the coordinate point closest to the reference coordinate point on the center line of the target lane as the target coordinate point; If the target lane is a non-drivable lane, determining all the drivable lanes of the road corresponding to the matched road information, and taking the coordinate point closest to the reference coordinate point on the center lines of all the drivable lanes as the target coordinate point.

4. The method according to claim 1, characterized in that, The vehicle is also deployed with a navigation map. The obtaining of the navigation guidance information based on the matched map data includes: Obtaining the navigation path generated by the navigation map, where the starting point and the ending point of the navigation path respectively match the starting point and the ending point of the simulated driving path; Performing path matching according to the navigation path and the matched map data to generate navigation guidance information.

5. The method according to claim 1, characterized in that, The performing of simulated vehicle control through an automatic driving algorithm according to the matched map data, the target coordinate points, and the dynamic map feature point information includes: Generating a lateral control result through the automatic driving algorithm according to the dynamic map feature point information in the high-precision map and the matched map data; the lateral control result includes whether to perform a lane change operation and the lane change direction when it is determined to perform a lane change operation; Through the autonomous driving algorithm, a longitudinal control result is generated according to the current vehicle speed during the simulated vehicle driving process and the matched map data; the longitudinal control result includes whether to adjust the vehicle speed and the target vehicle speed when it is determined to adjust the vehicle speed. According to the lateral control result and the longitudinal control result, vehicle simulation control is performed.

6. The method according to claim 5, characterized in that, The generating, by the autonomous driving algorithm, a lateral control result according to the dynamic map feature point information in the high-precision map and the matched map data includes: Receiving a lateral lane change signal sent by the host computer. Through the autonomous driving algorithm, a lateral control result is generated according to the dynamic map feature point information in the high-precision map, the matched map data, and the lateral lane change signal.

7. The method according to claim 5, characterized in that, The generating, by the autonomous driving algorithm, a longitudinal control result according to the current vehicle speed during the simulated vehicle driving process and the matched map data includes: Receiving a longitudinal speed adjustment signal sent by the host computer. Through the autonomous driving algorithm, a longitudinal control result is generated according to the current vehicle speed during the simulated vehicle driving process, the matched map data, and the longitudinal speed adjustment signal.

8. The method according to claim 5, characterized in that, The method further includes: Judging whether a preset condition is satisfied according to the reference coordinate point and the corresponding target coordinate point; the preset condition is that the distance between the reference coordinate point and the corresponding target coordinate point is less than a preset threshold and they are in the same lane. The performing vehicle simulation driving according to the target coordinate point includes: If the preset condition is satisfied, vehicle simulation driving is performed according to the target coordinate point.

9. The method according to claim 8, characterized in that,It further includes: If the preset condition is not satisfied, vehicle simulation driving is performed according to the reference coordinate point.

10. According to the method of claim 9, wherein, It further includes: Sending the longitudinal control result to the host computer so that the host computer adjusts the sampling interval of the reference coordinate points determined from the simulated driving path according to the longitudinal control result.

11. An automatic driving simulation device, wherein, The device includes: A first determination module, configured to receive the reference coordinate points in the simulated driving path sent by the host computer one by one and determine the map data matched with the reference coordinate points in the high-precision map. A first acquisition module, configured to acquire the target coordinate points based on the matched map data and perform vehicle simulation driving according to the target coordinate points. A second acquisition module, configured to acquire the navigation guidance information based on the matched map data; determine the dynamic map feature point information in the high-precision map according to the matched map data and the navigation guidance information, where the dynamic map feature point information includes: the distance information and direction information of the dynamic map feature points relative to the vehicle position in the high-precision map. A control module, configured to perform vehicle simulation control through the autonomous driving algorithm according to the matched map data, the target coordinate points, and the dynamic map feature point information. A second determination module, configured to determine the next target coordinate point in the high-precision map according to the control result of the vehicle simulation control.

12. A vehicle, wherein, It includes: A processor, a memory, and a computer program stored on the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the steps of the autonomous driving simulation test method according to any one of claims 1-10 are implemented.

13. A computer-readable storage medium, wherein, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the autonomous driving simulation test method according to any one of claims 1-10 are implemented.

Images