Information generation, adjustment method, device, equipment, medium and autonomous driving vehicle

Abstract

The present disclosure provides an information generation and adjustment method, device, equipment, medium and autonomous driving vehicle, which relates to the field of artificial intelligence technology, and in particular to the field of autonomous driving technology. The specific implementation scheme is: obtaining the first distance of the first path and the second distance of the second path in the path pair; generating first characterization information characterizing the degree of detour of the path planned by the target path planning algorithm based on the first distance and the second distance; obtaining the first speed information of the autonomous driving vehicle based on the first path and the second speed information based on the second path; generating second characterization information characterizing the speed control effect of the target path planning algorithm based on the first speed information and the second speed information; generating third characterization information characterizing the planning effect of the target path planning algorithm based on the first characterization information and the second characterization information. Applying the scheme provided by the embodiment of the present disclosure, it is possible to generate information characterizing the planning effect of the path planning algorithm.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to the field of autonomous driving technology. Background Art

[0002] With the rapid development of the autonomous driving industry in recent years, research related to autonomous driving has received more and more attention. Among them, the path planning algorithm is crucial to autonomous driving vehicles, and is directly related to the driving path and driving efficiency of autonomous driving vehicles. Therefore, it is necessary to know the planning effect of the path planning algorithm so as to adjust the path planning algorithm when the planning effect is not good. Summary of the invention

[0003] The present disclosure provides an information generation and adjustment method, device, equipment, medium and autonomous driving vehicle.

[0004] According to one aspect of the present disclosure, there is provided an information generating method, comprising:

[0005] Obtaining a first distance of a first path and a second distance of a second path in a path pair, wherein the first path is a path planned using a target path planning algorithm, the second path is a path planned using a reference path planning algorithm, and the first path and the second path have the same starting point and destination;

[0006] Generating first characterization information characterizing a degree of detour of the path planned by the target path planning algorithm according to the first distance and the second distance;

[0007] Obtaining first speed information of the autonomous driving vehicle based on the first path and second speed information of the autonomous driving vehicle based on the second path;

[0008] Generating second characterization information characterizing a speed control effect of the target path planning algorithm according to the first speed information and the second speed information;

[0009] According to the first characterization information and the second characterization information, third characterization information characterizing the planning effect of the target path planning algorithm is generated.

[0010] According to another aspect of the present disclosure, there is provided an information adjustment method, comprising:

[0011] Obtaining third characterization information characterizing a planning effect of a target path planning algorithm, wherein the third characterization information is generated according to the above-mentioned information generation method;

[0012] When the third characterization information satisfies a preset adjustment condition, a difference between the first path and the corresponding second path is obtained, and the parameters of the target path planning algorithm are adjusted based on the obtained difference, wherein the first path is a path planned using the target path planning algorithm, and the second path is a path planned using the reference path planning algorithm, and the starting point and destination of the first path and the second path are the same.

[0013] According to another aspect of the present disclosure, there is provided an information generating device, comprising:

[0014] a distance obtaining module, configured to obtain a first distance of a first path and a second distance of a second path in a path pair, wherein the first path is a path planned using a target path planning algorithm, and the second path is a path planned using a reference path planning algorithm, and the starting point and the destination of the first path and the second path are the same;

[0015] A first information generating module, configured to generate first characterizing information characterizing a degree of detour of the path planned by the target path planning algorithm according to the first distance and the second distance;

[0016] A speed acquisition module, used to obtain first speed information of the autonomous driving vehicle based on the first path and second speed information of the autonomous driving vehicle based on the second path;

[0017] A second information generating module, configured to generate second characterizing information characterizing a speed control effect of the target path planning algorithm according to the first speed information and the second speed information;

[0018] The third information generating module is used to generate third characterization information characterizing the planning effect of the target path planning algorithm according to the first characterization information and the second characterization information.

[0019] According to another aspect of the present disclosure, there is provided an information adjustment device, comprising:

[0020] An information acquisition module, used to obtain third characterization information characterizing the planning effect of the target path planning algorithm, wherein the third characterization information is generated according to the above-mentioned information generation device;

[0021] A parameter adjustment module is used to obtain the difference between the first path and the corresponding second path when the third characterization information meets the preset adjustment conditions, and adjust the parameters of the target path planning algorithm based on the obtained difference, wherein the first path is a path planned using the target path planning algorithm, the second path is a path planned using the reference path planning algorithm, and the starting point and destination of the first path and the second path are the same.

[0022] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0023] at least one processor; and

[0024] a memory communicatively connected to the at least one processor; wherein,

[0025] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned information generation method or information adjustment method.

[0026] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the above-mentioned information generation method or information adjustment method.

[0027] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program implements the above-mentioned information generating method or information adjusting method when executed by a processor.

[0028] According to another aspect of the present disclosure, an autonomous driving vehicle is provided, comprising the electronic device as described above.

[0029] From the above, it can be seen that the solution provided in the embodiment of the present disclosure introduces a benchmark path planning algorithm, and refers to the first path planned using the target path planning algorithm and the second path planned using the benchmark path planning algorithm, so as to successfully generate information characterizing the planning effect of the path planning algorithm.

[0030] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0032] Figure 1 A schematic diagram of a flow chart of a first information generating method provided in an embodiment of the present disclosure;

[0033] Figure 2 A schematic diagram of a flow chart of a second information generating method provided in an embodiment of the present disclosure;

[0034] Figure 3 A flowchart of an information adjustment method provided by an embodiment of the present disclosure;

[0035] Figure 4 A schematic diagram of the structure of an information generating device provided in an embodiment of the present disclosure;

[0036] Figure 5 A schematic diagram of the structure of an information adjustment device provided in an embodiment of the present disclosure;

[0037] Figure 6 It is a block diagram of an electronic device used to implement the information generating method or information adjusting method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0038] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0039] The concepts involved in the embodiments of the present disclosure are first introduced below.

[0040] 1. Path pair

[0041] Each path pair includes two paths, a first path and a second path, and the first path and the second path have the same starting point and destination.

[0042] 2. The first path

[0043] The first path is a path planned using a target path planning algorithm.

[0044] The target path planning algorithm is an algorithm for generating information characterizing the path planning effect by applying the solution provided by the embodiment of the present disclosure, and may also be referred to as the path planning algorithm to be evaluated. The target path planning algorithm may be used to plan a path for an autonomous driving vehicle. The target path planning algorithm may be run in a data processing device installed in an autonomous driving vehicle, or in a server for providing path planning services for autonomous driving vehicles.

[0045] The target path planning algorithm may be an A* algorithm, a Dijkstra algorithm, a D*Lite algorithm, a Weighted A* algorithm, etc., and may also be an algorithm evolved based on the above algorithms.

[0046] In view of the above situation, the above-mentioned first path can be obtained by the data processing device in the autonomous driving vehicle running the target path planning algorithm, or it can be obtained by the above-mentioned server running the target path planning algorithm.

[0047] 3. Second Path

[0048] The second path is a path planned using a reference path planning algorithm.

[0049] The above-mentioned reference path planning algorithm may be a path planning algorithm used by existing map software.

[0050] Considering that the traffic conditions of various roads vary at different times of the day, in order to ensure that the obtained first path and second path can cover as many traffic conditions as possible, the first path and second path can be obtained in different time periods.

[0051] In addition, considering that the path planning algorithm is affected by various factors, the obtained path may contain noise data. Therefore, in one implementation, after obtaining the first path and the second path, the obtained path may be cleaned based on at least one of the following information. The above information includes:

[0052] The accuracy of the path planning task, the accuracy of the path planning time, the degree of safety officer intervention, etc.

[0053] For example, paths whose path planning task accuracy is lower than the first accuracy threshold are cleared, paths whose path planning time accuracy is lower than the second accuracy threshold are cleared, and paths whose safety officer intervention distance is higher than the total distance of the entire path are cleared.

[0054] The information generation method provided by the embodiment of the present disclosure is introduced in detail below.

[0055] See also Figure 1 , a flow chart of a first information generating method is provided, the method comprising the following steps S101-S105.

[0056] Step S101: obtaining a first distance of a first path and a second distance of a second path in a path pair.

[0057] For each path, a certain distance is covered along the path from the starting point to the destination. The above distance can be called the distance of the path. Since the distance of a path reflects the situation of the entire path, the distance of the path can be considered as the global information of the path, reflecting the global path planning ability of the path planning algorithm.

[0058] In view of the above situation, the first distance is the distance that will be traveled from the starting point to the destination along the first path. The second distance is the distance that will be traveled from the starting point to the destination along the second path.

[0059] The first distance and the second distance mentioned above may be 5 kilometers, 6.6 kilometers, etc.

[0060] Step S102: Generate first characterization information characterizing the degree of detour of the path planned by the target path planning algorithm according to the first distance and the second distance.

[0061] It is understandable that there may be multiple paths from the starting point to the destination. For example, one path is directly from the starting point to the destination along a straight road, and another path is from the starting point to the destination by bypassing two alleys.

[0062] In the embodiment of the present disclosure, the second path planned by the reference path planning algorithm is used as a reference to check the difference between the first path and the second path planned by the target path planning algorithm, so as to determine whether there is a detour in the first path relative to the second path.

[0063] Specifically, the above difference is determined according to the first distance and the second distance. If the above difference indicates that the first distance is shorter than the second distance, it means that the target path planning algorithm is better than the benchmark path planning algorithm in terms of global path planning capability, and the path planned by the target path planning algorithm does not have a detour relative to the path planned by the benchmark path planning algorithm; if the above difference indicates that the first distance is equal to the second distance, it means that the target path planning algorithm is consistent with the benchmark path planning algorithm in terms of global path planning capability, and the path planned by the target path planning algorithm does not have a detour relative to the path planned by the benchmark path planning algorithm; if the above difference indicates that the first distance is longer than the second distance, it means that the target path planning algorithm is inferior to the benchmark path planning algorithm in terms of global path planning capability, and the path planned by the target path planning algorithm has a detour relative to the path planned by the benchmark path planning algorithm.

[0064] The first representation information may be generated in different ways, as described in subsequent embodiments, which will not be described in detail here.

[0065] Step S103: Obtain first speed information of the autonomous driving vehicle based on the first path and second speed information of the autonomous driving vehicle based on the second path.

[0066] The first path used in this step and the first path used in the aforementioned step S101 may be planned by different devices. In one implementation, the first path used in this step may be planned by a data processing device installed on the autonomous driving vehicle, and the first path used in the aforementioned step S101 may be planned by the aforementioned server. In another implementation, the first path used in this step may be planned by the aforementioned server, and the first path used in the aforementioned step S101 may be planned by a data processing device installed on the autonomous driving vehicle.

[0067] The first path used in this step and the aforementioned step S101 may also be planned by the same device, for example, both are planned by the aforementioned server, or both are planned by a data processing device installed on the autonomous driving vehicle.

[0068] The first speed information and the second speed information are information related to the speed of the autonomous driving vehicle.

[0069] In one implementation, the first speed information is: the average speed of the autonomous driving vehicle based on the first path, and the second speed information is: the average speed of the autonomous driving vehicle based on the second path. In this way, the first speed information and the second speed information can respectively reflect the average speed of the autonomous driving vehicle on the first path and the second path, and can reflect the average control of the autonomous driving vehicle's driving speed by the target path planning algorithm and the reference path planning algorithm, respectively.

[0070] Specifically, a path can be divided into multiple path segments, and the length of each path segment and the driving time of the autonomous driving vehicle on each path segment are counted. Then, the driving speed of the autonomous driving vehicle on each path segment is calculated based on the above length and driving time. For example, the driving speed is obtained by calculating the ratio of the length of each segment to the driving time, and the average of the various driving speeds is determined as the average speed of the path.

[0071] Among them, the length and travel time corresponding to each path segment in the first path and the second path can be obtained in different ways. For example, the length and travel time corresponding to each path segment of the first path can be obtained by actual measurement of an autonomous driving vehicle, and the length and travel time corresponding to each path segment of the second path can be obtained by algorithm prediction. Of course, the length and travel time corresponding to each path segment in the first path and the second path can also be obtained in the same way. The embodiments of the present disclosure are not limited to this.

[0072] In another implementation, the first speed information may include at least one of the following information: the highest speed, the lowest speed, the speed variance, etc. of the autonomous driving vehicle based on the first path. Correspondingly, the second speed may include at least one of the following information: the highest speed, the lowest speed, the speed variance, etc. of the autonomous driving vehicle based on the second path. This can reflect the control capability of the path planning algorithm on the driving speed of the autonomous driving vehicle from different angles.

[0073] Step S104: Generate second characterization information characterizing the speed control effect of the target path planning algorithm according to the first speed information and the second speed information.

[0074] Different paths have different road conditions, which directly affect the driving speed of the autonomous vehicle. A better path planning algorithm is expected to plan a path that enables the autonomous vehicle to reach the destination quickly and efficiently from the starting point within the speed range.

[0075] In view of this, in the solution provided by the embodiment of the present disclosure, the second speed information of the autonomous driving vehicle based on the second path is used as a benchmark to check the difference between the first speed information and the second speed information, and then determine the speed control effect of the target path planning algorithm relative to the benchmark path planning algorithm.

[0076] The second representation information may be generated in different ways, as described in subsequent embodiments, which will not be described in detail here.

[0077] Step S105: generating third characterization information characterizing a planning effect of the target path planning algorithm according to the first characterization information and the second characterization information.

[0078] Specifically, the third representation information may be generated in different ways.

[0079] In one implementation, the product of the first characterization information and the second characterization information can be obtained as the third characterization information that characterizes the planning effect of the target path planning algorithm. This not only enables the third characterization information to reflect the degree of detour of the path planned by the target path planning algorithm relative to the path planned by the reference path planning algorithm, but also reflects the control effect of the target path planning algorithm in terms of speed relative to the reference path planning algorithm, and also makes the third characterization information more concise and intuitive.

[0080] In another implementation manner, the sum of the first representation information and the second representation information may be calculated, and then the sum may be determined as the third representation information.

[0081] In another implementation method, a first score characterizing the planning effect of the target path planning algorithm can be obtained based on the correspondence between the first characterization information and the score, and a second score characterizing the planning effect of the target path planning algorithm can be obtained based on the correspondence between the second characterization information and the score, and then the sum of the first score and the second score is determined as the above-mentioned third characterization information.

[0082] The embodiment of the present disclosure is merely described by taking the above as an example, and does not limit the manner of generating the third representation information according to the first representation information and the second representation information.

[0083] From the above, it can be seen that the solution provided in the embodiment of the present disclosure introduces a benchmark path planning algorithm, and refers to the first path planned using the target path planning algorithm and the second path planned using the benchmark path planning algorithm, so as to successfully generate information characterizing the planning effect of the path planning algorithm.

[0084] Specifically, on the one hand, from the perspective of the distance of the path, the first characterization information is generated according to the distance of the first path and the distance of the second path. Since the distance of the path reflects the length of the entire path, the first characterization information obtained according to the distances of the above two paths reflects the degree of detour of the path planned by the target path planning algorithm relative to the path planned by the reference path planning algorithm. That is to say, the first characterization information reflects the planning effect of the path planned by the target path planning algorithm relative to the path planned by the reference path planning algorithm from the global perspective of the entire path. On the other hand, from the perspective of driving speed, since the speed information reflects the actual speed of the autonomous driving vehicle under the control of the path planning algorithm, the second characterization information obtained according to the first speed information and the second speed information can reflect the control effect of the target path planning algorithm on the actual running speed of the autonomous driving vehicle relative to the reference path planning algorithm. Combining the above two aspects, the third characterization information obtained according to the first characterization information and the second characterization information can reflect the planning effect of the target path planning algorithm from the two perspectives of detour degree and speed control effect.

[0085] On the basis of the above, for different path planning algorithms, the solution provided by the embodiment of the present disclosure can be used to generate characterization information that characterizes the path planning effect, so that different path planning algorithms can be measured using the same standards, making it easy to compare the advantages and disadvantages of different path planning algorithms.

[0086] From the foregoing description, it can be seen that the present disclosure uses path pairs, each of which includes a first path and a second path, and the first path and the second path have the same starting point and destination. According to different ways of obtaining the path pairs, the path pairs can be divided into different categories.

[0087] In one embodiment of the present disclosure, the above-mentioned path pairs include: first-class path pairs and / or second-class path pairs, that is, the above-mentioned path pairs are divided into first-class path pairs and second-class path pairs, but in the application process, only the first-class path pairs, only the second-class path pairs, or both the first-class path pairs and the second-class path pairs may be used.

[0088] The first type of path pair is: a path pair for the same address pair in different time periods, where the address pair includes: a starting point and a destination. That is, the target path planning algorithm and the reference path planning algorithm are used in different time periods to plan the first path and the second path from the starting point to the destination in the same address pair.

[0089] The second type of path pairs are: path pairs for different address pairs in the same period, that is, the target path planning algorithm and the reference path planning algorithm are used at the same time to plan the first path and the second path from the starting point to the destination in different address pairs.

[0090] Since traffic conditions vary at different times of the day, by performing path planning for the same starting point and destination at different time periods, different paths planned by the path planning algorithm to cope with different traffic conditions can be obtained. In addition, even in the same time period, traffic conditions between different starting points and destinations are different. By performing path planning for different starting points and destinations, different paths planned by the path planning algorithm to cope with different traffic conditions can also be obtained. Therefore, it can be seen that the above two types of paths can make the investigation of the path planning algorithm more comprehensive, and the obtained paths are also more comprehensive, which is conducive to improving the accuracy of the various representation information generated.

[0091] The aforementioned step S102 can generate the first representation information in different ways, which are described below respectively.

[0092] In one embodiment of the present disclosure, when there are multiple path pairs, a first sum of the first distances of the first path in each path pair is calculated, and a second sum of the second distances of the second path in each path pair is calculated, and a ratio between the first sum and the second sum is obtained as first characterization information characterizing the degree of detour of the path planned by the target path planning algorithm.

[0093] Since there is a first path and a second path in each path pair, and each first path corresponds to a first distance, and each second path corresponds to a second distance, the solution provided in this embodiment takes into account multiple path pairs, that is, multiple first distances and multiple second distances, which can effectively avoid the problem of low accuracy of the first characterization information caused by errors in the distance of a single path, so that the final first characterization information has high accuracy. In addition, the ratio between the first sum and the second sum used in the solution provided in this embodiment is used as the first characterization information, so that the first characterization information can reflect the relative changes between the path planned by the target path planning algorithm and the path planned by the reference path planning algorithm.

[0094] In another embodiment of the present disclosure, after calculating the first sum and the second sum, the difference between the first sum and the second sum can be obtained first, and then the ratio between the difference and the second sum can be obtained, and the obtained ratio can be used as the first characterization information. In this way, not only can the first characterization information reflect the relative change between the path planned by the target path planning algorithm and the path planned by the reference path planning algorithm, but also the relative change amount can be clearly defined.

[0095] In another embodiment of the present disclosure, after calculating the first sum and the second sum, the difference between the first sum and the second sum can be obtained, and the difference is directly used as the first characterization information of the merchant. In this way, the first characterization information can reflect the absolute change between the path planned by the target path planning algorithm and the path planned by the reference path planning algorithm.

[0096] The aforementioned step S104 can generate the second representation information in different ways, which are described below respectively.

[0097] In one embodiment of the present disclosure, for each path pair, the difference between the first speed information corresponding to the first path in the path pair and the second speed information corresponding to the second path in the path pair can be calculated; and the average value of the obtained differences is obtained as the second characterization information characterizing the degree of influence of the target path planning algorithm on the speed.

[0098] As mentioned above, the solution provided in this embodiment takes into account multiple path pairs, that is, the speed information corresponding to multiple paths is taken into account, which can effectively avoid the problem of low accuracy of the second characterization information caused by errors in the speed information corresponding to a single path, so that the first characterization information finally obtained has high accuracy. In addition, the solution provided in this embodiment uses the difference between the first speed information and the second speed information to obtain the second characterization information, so that the second characterization information can reflect the absolute difference between the target path planning algorithm and the reference path planning algorithm in the actual driving speed control effect.

[0099] In another embodiment of the present disclosure, for each path pair, the ratio between the first speed information corresponding to the first path and the second speed information corresponding to the second path in the path pair can be calculated, and the average value of the obtained ratios can be obtained as the second characterization information. In this way, the second characterization information can reflect the relative difference between the target path planning algorithm and the reference path planning algorithm in the actual driving speed control effect.

[0100] In one embodiment of the present disclosure, see Figure 2 , a flow chart of a second information generation method is provided. In this embodiment, the path pairs include a first type of path pair and a second type of path pair. The method includes the following steps S201-S207.

[0101] Step S201: obtaining a first distance of a first path and a second distance of a second path in a path pair.

[0102] This step is similar to the previous Figure 1 Step S101 in the illustrated embodiment is the same and will not be described again here.

[0103] Step S202: Generate first sub-characterization information characterizing the degree of detour of the path planned by the target path planning algorithm according to the first distance of the first path and the second distance of the second path in the first type of path pair.

[0104] The method of generating the first sub-representation information is similar to the method of generating the first representation information described above, except that the path pair mentioned above is specifically the first type of path pair indicated in this step, and the generated representation information is referred to as the first sub-representation information in this step. In view of this, the specific method of generating the first sub-representation information is not described in detail here.

[0105] Step S203: generating second sub-characterization information characterizing the degree of detour of the path planned by the target path planning algorithm according to the first distance of the first path and the second distance of the second path in the second type of path pair.

[0106] The method of generating the second sub-representation information is similar to the method of generating the first representation information, except that the path pair mentioned above is specifically the second type of path pair indicated in this step, and the generated representation information is referred to as the second sub-representation information in this step. In view of this, the specific method of generating the second sub-representation information is not described in detail here.

[0107] Step S204: performing weighted calculation on the first sub-characterization information and the second sub-characterization information according to the weighted coefficients corresponding to the first sub-characterization information and the second sub-characterization information respectively, to obtain first characterization information characterizing the degree of detour of the path planned by the target path planning algorithm.

[0108] Since the first sub-characterization information is generated based on the first type of path pairs, and the first type of path pairs are path pairs for the same address pair in different time periods, introducing information related to the first type of path pairs when generating the first characterization information can be considered as introducing lateral information according to the time of path generation, and evaluating the target path planning algorithm from a lateral perspective of time.

[0109] Since the second sub-characterization information is generated based on the second type of path pairs, and the second type of path pairs are path pairs for different address pairs in the same time period, the introduction of information related to the second type of path pairs when generating the second characterization information can be considered as the introduction of longitudinal information according to the time of path generation, and the target path planning algorithm is evaluated from the longitudinal perspective of time.

[0110] The weighting system corresponding to the first sub-representation information and the weighting coefficient corresponding to the second sub-representation information can be set by the staff according to different attention levels in the horizontal direction and the vertical direction.

[0111] Step S205: Obtain first speed information of the autonomous driving vehicle based on the first path and second speed information of the autonomous driving vehicle based on the second path.

[0112] Step S206: Generate second characterization information characterizing the speed control effect of the target path planning algorithm according to the first speed information and the second speed information.

[0113] Step S207: generating third characterization information characterizing a planning effect of the target path planning algorithm according to the first characterization information and the second characterization information.

[0114] The above steps S205 to S207 are respectively the same as the above Figure 1 In the illustrated embodiment, steps S103 to S105 are the same and will not be described in detail here.

[0115] From the above, it can be seen that in the solution provided by this embodiment, when generating the first characterization information, sub-representation information is generated based on the paths obtained in different time dimensions. In this way, the first characterization information generated based on the above sub-representation information integrates the characteristics of the paths planned by the path planning algorithm under different time dimensions, so that the first characterization information finally generated is more accurate, which is beneficial to improve the accuracy of the path planning effect of the generated representation target path planning algorithm.

[0116] From the foregoing description, it can be seen that the solution provided by the embodiment of the present disclosure can generate characterization information that characterizes the path planning effect of the target path planning algorithm. In addition, in one embodiment of the present disclosure, it is also possible to select a first path corresponding to a first characterization information greater than a preset threshold value 1 from path M, and select a first path corresponding to a second characterization information greater than a preset threshold value 2 from path N, and then perform data analysis on the selected first path to derive the reasons for the poor planning effect of the first path. In this way, the evaluation results of the planning effect of the target path planning algorithm can have not only characterization information for reference, but also cause information for reference, thereby improving the reliability of the results.

[0117] Among them, path M is the first path used to generate the first representation information, and path N is the first path used to generate the second representation information.

[0118] Corresponding to the above-mentioned information generating method, the embodiment of the present disclosure provides an information adjusting method.

[0119] See also Figure 3 , a flow chart of an information adjustment method is provided, the method comprising the following steps S301-S302.

[0120] Step S301: Obtain third characterization information characterizing the planning effect of the target path planning algorithm.

[0121] The third representation information is generated according to the information generation method provided in the above embodiments, which will not be described in detail here.

[0122] Step S302: when the third characterization information satisfies a preset adjustment condition, a difference between the first path and the corresponding second path is obtained, and parameters of the target path planning algorithm are adjusted based on the obtained difference.

[0123] Among them, the first path is a path planned using a target path planning algorithm, and the second path is a path planned using a reference path planning algorithm. The starting point and destination of the first path and the second path are the same, that is, the second path corresponding to the first path has the same starting point and destination.

[0124] For example, the adjustment condition may be that the third characterization information is greater than a preset first threshold.

[0125] It can be seen from the previous description that the first path used to generate the third characterization information includes two parts, one part is the first path used to generate the first characterization information, for the convenience of expression, these first paths are called path M, and the other part is the first path used to generate the second characterization information, for the convenience of expression, these paths are called path N. Based on this, in one embodiment of the present disclosure, after the third characterization information meets the adjustment condition, the first path corresponding to the first characterization information greater than the preset second threshold can be selected from path M, and the first path corresponding to the second characterization information greater than the preset third threshold can be selected from path N, and then the selected first path is subjected to data analysis to obtain the difference between the selected first path and the corresponding second path, and the parameters of the target path planning algorithm are adjusted based on the obtained difference, so that the path planned by the adjusted target path planning algorithm is aligned with the path planned by the reference path planning algorithm.

[0126] Specifically, when adjusting the parameters of the target path planning algorithm based on the obtained differences, the parameters can be adjusted based on a pre-set strategy. For example, the above strategy can be that the difference values ​​in different ranges correspond to different parameters to be adjusted, parameter adjustment directions, parameter adjustment steps, etc.

[0127] Since the selected first path is the first path that has a large gap with the second path in terms of detour degree or speed control, the selected first paths can be considered as paths with a higher level of attention. Analyzing these first paths can more accurately locate the difference between the target path planning algorithm and the benchmark path planning algorithm, which is conducive to improving the reliability of parameter adjustment of the target planning algorithm.

[0128] From the above, it can be seen that in the solution provided by this embodiment, since the third characterization information can reflect the planning effect of the target path planning algorithm from two perspectives: the degree of detour and the effect of speed control, it can be known whether the parameters of the target path planning algorithm need to be adjusted based on the third characterization information. Moreover, since the difference in path planning between the target path planning algorithm and the benchmark path planning algorithm can be obtained based on the first path used to generate the third characterization information, the parameters of the target path planning algorithm can be effectively adjusted.

[0129] Corresponding to the above-mentioned information generating method, an embodiment of the present disclosure provides an information generating device.

[0130] See also Figure 4 , a schematic diagram of the structure of an information generating device is provided, including:

[0131] A distance obtaining module 401 is used to obtain a first distance of a first path and a second distance of a second path in a path pair, wherein the first path is a path planned using a target path planning algorithm, and the second path is a path planned using a reference path planning algorithm, and the starting point and the destination of the first path and the second path are the same;

[0132] A first information generating module 402, configured to generate first characterizing information characterizing a degree of detour of the path planned by the target path planning algorithm according to the first distance and the second distance;

[0133] The speed obtaining module 403 is used to obtain first speed information of the autonomous driving vehicle based on the first path and second speed information of the autonomous driving vehicle based on the second path;

[0134] A second information generating module 404 is used to generate second characterizing information characterizing the speed control effect of the target path planning algorithm according to the first speed information and the second speed information;

[0135] The third information generating module 405 is used to generate third characterization information representing the planning effect of the target path planning algorithm according to the first characterization information and the second characterization information.

[0136] From the above, it can be seen that the solution provided in the embodiment of the present disclosure introduces a benchmark path planning algorithm, and refers to the first path planned using the target path planning algorithm and the second path planned using the benchmark path planning algorithm, so as to successfully generate information characterizing the planning effect of the path planning algorithm.

[0137] Specifically, on the one hand, from the perspective of the distance of the path, the first characterization information is generated according to the distance of the first path and the distance of the second path. Since the distance of the path reflects the length of the entire path, the first characterization information obtained according to the distances of the above two paths reflects the degree of detour of the path planned by the target path planning algorithm relative to the path planned by the reference path planning algorithm. That is to say, the first characterization information reflects the planning effect of the path planned by the target path planning algorithm relative to the path planned by the reference path planning algorithm from the global perspective of the entire path. On the other hand, from the perspective of driving speed, since the speed information reflects the actual speed of the autonomous driving vehicle under the control of the path planning algorithm, the second characterization information obtained according to the first speed information and the second speed information can reflect the control effect of the target path planning algorithm on the actual running speed of the autonomous driving vehicle relative to the reference path planning algorithm. Combining the above two aspects, the third characterization information obtained according to the first characterization information and the second characterization information can reflect the planning effect of the target path planning algorithm from the two perspectives of detour degree and speed control effect.

[0138] On the basis of the above, for different path planning algorithms, the solution provided by the embodiment of the present disclosure can be used to generate characterization information that characterizes the path planning effect, so that different path planning algorithms can be measured using the same standards, making it easy to compare the advantages and disadvantages of different path planning algorithms.

[0139] In one embodiment of the present disclosure, the path pairs include: first-type path pairs and / or second-type path pairs;

[0140] The first type of path pair is: a path pair for the same address pair in different time periods, wherein the address pair includes: a starting point and a destination;

[0141] The second type of path pairs are path pairs for different address pairs in the same period.

[0142] Since traffic conditions vary at different times of the day, by performing path planning for the same starting point and destination at different time periods, different paths planned by the path planning algorithm to cope with different traffic conditions can be obtained. In addition, even in the same time period, traffic conditions between different starting points and destinations are different. By performing path planning for different starting points and destinations, different paths planned by the path planning algorithm to cope with different traffic conditions can also be obtained. Therefore, it can be seen that the above two types of paths can make the investigation of the path planning algorithm more comprehensive, and the obtained paths are also more comprehensive, which is conducive to improving the accuracy of the various representation information generated.

[0143] In one embodiment of the present disclosure, when the path pair includes a first type of path pair and a second type of path pair,

[0144] The first information generating module 402 is specifically used to generate first sub-characterization information characterizing the degree of detour of the path planned by the target path planning algorithm according to the first distance of the first path and the second distance of the second path in the first type of path pair; generate second sub-characterization information characterizing the degree of detour of the path planned by the target path planning algorithm according to the first distance of the first path and the second distance of the second path in the second type of path pair; and perform weighted calculation on the first sub-characterization information and the second sub-characterization information according to weighted coefficients corresponding to the first sub-characterization information and the second sub-characterization information respectively, to obtain first characterization information characterizing the degree of detour of the path planned by the target path planning algorithm.

[0145] From the above, it can be seen that in the solution provided by this embodiment, when generating the first characterization information, sub-representation information is generated based on the paths obtained in different time dimensions. In this way, the first characterization information generated based on the above sub-representation information integrates the characteristics of the paths planned by the path planning algorithm under different time dimensions, so that the first characterization information finally generated is more accurate, which is beneficial to improve the accuracy of the path planning effect of the generated representation target path planning algorithm.

[0146] In one embodiment of the present disclosure, when there are multiple path pairs,

[0147] The first information generating module 402 is specifically used to calculate the first sum of the first distances of the first path in each path pair, and calculate the second sum of the second distances of the second path in each path pair; obtain the ratio between the first sum and the second sum as the first characterization information characterizing the degree of detour of the path planned by the target path planning algorithm.

[0148] Since there is a first path and a second path in each path pair, and each first path corresponds to a first distance, and each second path corresponds to a second distance, the solution provided in this embodiment takes into account multiple path pairs, that is, multiple first distances and multiple second distances, which can effectively avoid the problem of low accuracy of the first characterization information caused by errors in the distance of a single path, so that the final first characterization information has high accuracy. In addition, the ratio between the first sum and the second sum used in the solution provided in this embodiment is used as the first characterization information, so that the first characterization information can reflect the relative changes between the path planned by the target path planning algorithm and the path planned by the reference path planning algorithm.

[0149] In one embodiment of the present disclosure, the second information generating module 404 is specifically used to calculate, for each path pair, the difference between the first speed information corresponding to the first path in the path pair and the second speed information corresponding to the second path in the path pair; and obtain the average value of the obtained difference as the second characterization information characterizing the degree of influence of the target path planning algorithm on the speed.

[0150] As mentioned above, the solution provided in this embodiment takes into account multiple path pairs, that is, the speed information corresponding to multiple paths is taken into account, which can effectively avoid the problem of low accuracy of the second characterization information caused by errors in the speed information corresponding to a single path, so that the first characterization information finally obtained has high accuracy. In addition, the solution provided in this embodiment uses the difference between the first speed information and the second speed information to obtain the second characterization information, so that the second characterization information can reflect the absolute difference between the target path planning algorithm and the reference path planning algorithm in the actual driving speed control effect.

[0151] In one embodiment of the present disclosure, the first speed information is: the average speed of the autonomous driving vehicle traveling on the first path; the second speed information is: the average speed of the autonomous driving vehicle traveling on the second path. In this way, the first speed information and the second speed information can respectively reflect the average speed of the autonomous driving vehicle traveling on the first path and the second path, and can reflect the average control of the autonomous driving vehicle's driving speed by the target path planning algorithm and the reference path planning algorithm, respectively.

[0152] In one embodiment of the present disclosure, the third information generation module 405 is specifically used to obtain the product of the first characterization information and the second characterization information as the third characterization information characterizing the planning effect of the target path planning algorithm. In this way, not only can the third characterization information reflect the degree of detour of the path planned by the target path planning algorithm relative to the path planned by the reference path planning algorithm, but also can reflect the control effect of the target path planning algorithm in terms of speed relative to the reference path planning algorithm, and can also make the third characterization information more concise and intuitive.

[0153] Corresponding to the above-mentioned information adjustment method, an embodiment of the present disclosure provides an information adjustment device.

[0154] See also Figure 5 , a structural diagram of an information adjustment device is provided, including:

[0155] The information acquisition module 501 is used to obtain third characterization information characterizing the planning effect of the target path planning algorithm, and the third characterization information is generated according to the information generation device provided by the above-mentioned embodiments.

[0156] The parameter adjustment module 502 is used to obtain the difference between the first path and the corresponding second path when the third characterization information meets the preset adjustment conditions, and adjust the parameters of the target path planning algorithm based on the obtained difference, wherein the first path is a path planned using the target path planning algorithm, and the second path is a path planned using the reference path planning algorithm, and the starting point and destination of the first path and the second path are the same.

[0157] From the above, it can be seen that in the solution provided by this embodiment, since the third characterization information can reflect the planning effect of the target path planning algorithm from two perspectives: the degree of detour and the effect of speed control, it can be known whether the parameters of the target path planning algorithm need to be adjusted based on the third characterization information. Moreover, since the difference in path planning between the target path planning algorithm and the benchmark path planning algorithm can be obtained based on the first path used to generate the third characterization information, the parameters of the target path planning algorithm can be effectively adjusted.

[0158] In one embodiment of the present disclosure, the parameter adjustment module 502 is specifically used to select, from the first path used to generate the first characterization information, a first path corresponding to the first characterization information greater than a preset second threshold value; from the first path used to generate the second characterization information, a first path corresponding to the second characterization information greater than a preset third threshold value; perform data analysis on the selected first path to obtain the difference between the selected first path and the corresponding second path, and adjust the parameters of the target path planning algorithm based on the obtained difference. By analyzing the first path, the difference between the target path planning algorithm and the reference path planning algorithm can be more accurately found, which is conducive to improving the accuracy of parameter adjustment of the target planning algorithm.

[0159] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, a computer program product and an autonomous driving vehicle.

[0160] In one embodiment of the present disclosure, an electronic device is provided, including:

[0161] at least one processor; and

[0162] a memory communicatively connected to the at least one processor; wherein,

[0163] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the information generation method or information adjustment method provided by the above-mentioned various method embodiments.

[0164] In one embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the information generation method or information adjustment method provided by the above-mentioned various method embodiments.

[0165] In one embodiment of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the computer program implements the information generating method or the information adjusting method provided by the above-mentioned various method embodiments.

[0166] In one embodiment of the present disclosure, an autonomous driving vehicle is provided, comprising the electronic device as described above.

[0167] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0168] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0169] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0170] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as information generation methods or information adjustment methods. For example, in some embodiments, the information generation method or the information adjustment method may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the information generation method or the information adjustment method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to execute the information generating method or the information adjusting method in any other appropriate manner (eg, by means of firmware).

[0171] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0172] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0173] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0174] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0175] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0176] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0177] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0178] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for generating information, comprising: Obtaining a first distance of a first path and a second distance of a second path in a path pair, wherein the first path is a path planned using a target path planning algorithm, the second path is a path planned using a reference path planning algorithm, and the first path and the second path have the same starting point and destination; Generating first characterization information characterizing a degree of detour of the path planned by the target path planning algorithm according to the first distance and the second distance; Obtaining first speed information of the autonomous driving vehicle based on the first path and second speed information of the autonomous driving vehicle based on the second path; Generating second characterization information characterizing a speed control effect of the target path planning algorithm according to the first speed information and the second speed information; Generating third characterization information characterizing a planning effect of the target path planning algorithm according to the first characterization information and the second characterization information; The generating, according to the first distance and the second distance, first characterization information characterizing the degree of detour of the path planned by the target path planning algorithm includes: In the case where there are multiple path pairs, a first sum of the first distances of the first path in each path pair is calculated, and a second sum of the second distances of the second path in each path pair is calculated; a ratio between the first sum and the second sum is obtained as first characterization information characterizing the degree of detour of the path planned by the target path planning algorithm; or obtaining a difference between the first sum and the second sum, obtaining a ratio between the difference and the second sum, and using the obtained ratio as the first characterization information; or Obtaining a difference between the first sum value and the second sum value as the first characterization information; The step of generating second characterization information characterizing a speed control effect of the target path planning algorithm according to the first speed information and the second speed information includes: For each path pair, calculating the difference between the first speed information corresponding to the first path and the second speed information corresponding to the second path in the path pair; obtaining an average value of the obtained differences as second characterization information characterizing the degree of influence of the target path planning algorithm on the speed; or For each path pair, a ratio between first speed information corresponding to the first path and second speed information corresponding to the second path in the path pair is calculated, and an average value of the obtained ratios is obtained as the second representation information.

2. The method according to claim 1, wherein: The path pairs include: first-category path pairs and / or second-category path pairs; The first type of path pair is: a path pair for the same address pair in different time periods, wherein the address pair includes: a starting point and a destination; The second type of path pairs are path pairs for different address pairs in the same period.

3. The method according to claim 2, wherein: In the case where the path pairs include a first type of path pair and a second type of path pair, The generating, according to the first distance and the second distance, first characterization information characterizing the degree of detour of the path planned by the target path planning algorithm includes: Generate first sub-characterization information characterizing the degree of detour of the path planned by the target path planning algorithm according to a first distance of the first path and a second distance of the second path in the first type of path pair; generating second sub-characterization information characterizing the degree of detour of the path planned by the target path planning algorithm according to a first distance of the first path and a second distance of the second path in the second type of path pair; The first sub-characterization information and the second sub-characterization information are weightedly calculated according to the weight coefficients respectively corresponding to the first sub-characterization information and the second sub-characterization information to obtain first characterization information characterizing the degree of detour of the path planned by the target path planning algorithm.

4. The method according to claim 1 or 2, wherein: The first speed information is: an average speed of the autonomous driving vehicle based on the first path; The second speed information is: the average speed of the autonomous driving vehicle based on the second path.

5. The method according to claim 1 or 2, wherein: The step of generating third characterization information characterizing a planning effect of the target path planning algorithm according to the first characterization information and the second characterization information includes: The product of the first characterization information and the second characterization information is obtained as third characterization information characterizing a planning effect of the target path planning algorithm.

6. An information adjustment method, comprising: Obtaining third characterization information characterizing a planning effect of a target path planning algorithm, wherein the third characterization information is generated according to the method of any one of claims 1 to 5; When the third characterization information satisfies a preset adjustment condition, a difference between the first path and the corresponding second path is obtained, and the parameters of the target path planning algorithm are adjusted based on the obtained difference, wherein the first path is a path planned using the target path planning algorithm, and the second path is a path planned using the reference path planning algorithm, and the starting point and destination of the first path and the second path are the same.

7. The method according to claim 6, wherein: The obtaining of the difference between the first path and the corresponding second path includes: Selecting, from the first paths used to generate the first characterization information, a first path corresponding to the first characterization information that is greater than a preset second threshold; Selecting, from the first paths used to generate the second characterization information, the first path corresponding to the second characterization information that is greater than a preset third threshold; Data analysis is performed on the selected first path to obtain a difference between the selected first path and the corresponding second path.

8. An information generating device, comprising: a distance obtaining module, configured to obtain a first distance of a first path and a second distance of a second path in a path pair, wherein the first path is a path planned using a target path planning algorithm, and the second path is a path planned using a reference path planning algorithm, and the starting point and the destination of the first path and the second path are the same; A first information generating module, configured to generate first characterizing information characterizing a degree of detour of the path planned by the target path planning algorithm according to the first distance and the second distance; A speed acquisition module, used to obtain first speed information of the autonomous driving vehicle based on the first path and second speed information of the autonomous driving vehicle based on the second path; A second information generating module, configured to generate second characterizing information characterizing a speed control effect of the target path planning algorithm according to the first speed information and the second speed information; A third information generating module, configured to generate third characterization information characterizing a planning effect of the target path planning algorithm according to the first characterization information and the second characterization information; The first information generating module is specifically used for: In the case where there are multiple path pairs, a first sum of the first distances of the first path in each path pair is calculated, and a second sum of the second distances of the second path in each path pair is calculated; Obtaining a ratio between the first sum value and the second sum value as first characterization information characterizing a degree of detour of the path planned by the target path planning algorithm; or obtaining a difference between the first sum and the second sum, obtaining a ratio between the difference and the second sum, and using the obtained ratio as the first characterization information; or Obtaining a difference between the first sum value and the second sum value as the first characterization information; The second information generating module is specifically used for: For each path pair, calculating the difference between the first speed information corresponding to the first path and the second speed information corresponding to the second path in the path pair; obtaining an average value of the obtained differences as second characterization information characterizing the degree of influence of the target path planning algorithm on the speed; or For each path pair, a ratio between first speed information corresponding to the first path and second speed information corresponding to the second path in the path pair is calculated, and an average value of the obtained ratios is obtained as the second representation information.

9. The device according to claim 8, wherein: The path pairs include: first-category path pairs and / or second-category path pairs; The first type of path pair is: a path pair for the same address pair in different time periods, wherein the address pair includes: a starting point and a destination; The second type of path pairs are path pairs for different address pairs in the same period.

10. The device according to claim 9, wherein: In the case where the path pairs include a first type of path pair and a second type of path pair, The first information generating module is specifically configured to generate first sub-characterization information characterizing a degree of detour of the path planned by the target path planning algorithm according to a first distance of the first path and a second distance of the second path in the first type of path pair; generating second sub-characterization information characterizing the degree of detour of the path planned by the target path planning algorithm according to a first distance of the first path and a second distance of the second path in the second type of path pair; The first sub-characterization information and the second sub-characterization information are weightedly calculated according to the weight coefficients respectively corresponding to the first sub-characterization information and the second sub-characterization information to obtain first characterization information characterizing the degree of detour of the path planned by the target path planning algorithm.

11. The device according to claim 8 or 9, wherein: The first speed information is: an average speed of the autonomous driving vehicle based on the first path; The second speed information is: the average speed of the autonomous driving vehicle based on the second path.

12. The device according to claim 8 or 9, wherein: The third information generating module is specifically used to obtain the product of the first characterization information and the second characterization information as the third characterization information characterizing the planning effect of the target path planning algorithm.

13. An information adjustment device, comprising: An information acquisition module, used to obtain third characterization information characterizing a planning effect of a target path planning algorithm, wherein the third characterization information is generated according to the device of any one of claims 8 to 12; A parameter adjustment module is used to obtain the difference between the first path and the corresponding second path when the third characterization information meets the preset adjustment conditions, and adjust the parameters of the target path planning algorithm based on the obtained difference, wherein the first path is a path planned using the target path planning algorithm, the second path is a path planned using the reference path planning algorithm, and the starting point and destination of the first path and the second path are the same.

14. The device according to claim 13, wherein: The parameter adjustment module is specifically used for: for selecting, from the first paths used to generate the first characterization information, a first path corresponding to the first characterization information that is greater than a preset second threshold value when the third characterization information satisfies a preset adjustment condition; From the first paths used to generate the second characterization information, select the first path corresponding to the second characterization information that is greater than a preset third threshold; perform data analysis on the selected first path to obtain the difference between the selected first path and the corresponding second path, and adjust the parameters of the target path planning algorithm based on the obtained difference.

15. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5 or 6-7.

16. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-5 or 6-7.

17. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1-5 or 6-7.

18. An autonomous driving vehicle comprising the electronic device as claimed in claim 15.

Images