Autonomous vehicle road testing method and apparatus

Abstract

The application provides a kind of automatic driving vehicle road test method and device.The method comprises: in response to the end of the nth group of road test, the abnormal event that appears in the first n group of road test is obtained;Wherein, each group of road test includes at least one trip;Trip is the mileage of automatic driving vehicle from the starting point to the return terminal on the specified test route;According to whether the abnormal label corresponding to the abnormal event that appears in the first n group of road test covers the abnormal label in the first abnormal label set, and the distribution proportion of the number of abnormal events corresponding to each abnormal label in the second abnormal label set, it is determined whether the road test converges;In response to the convergence of road test, the total trip number of the first n group of road test is output.The method can accurately determine whether the road test converges, and then accurately realize the road test of automatic driving vehicle.

Description

Technical Field

[0001] This disclosure relates to a method and apparatus for road testing of autonomous vehicles. Background Technology

[0002] By collecting and acquiring data from autonomous vehicles (driverless cars) driving on test routes, and observing whether the fluctuations in the data tend to stabilize, it can be determined whether the road test has converged.

[0003] In related technologies, during the road testing of autonomous vehicles, the convergence of the road test is usually determined directly by the number of abnormal events or the mileage traveled.

[0004] The relevant technologies cannot accurately determine whether the road test has converged, and therefore cannot accurately realize the road test of autonomous vehicles. Summary of the Invention

[0005] In view of this, this application provides a method and apparatus for road testing of autonomous vehicles, which can accurately determine whether the road test has converged, thereby accurately realizing the road test of autonomous vehicles.

[0006] To solve the above-mentioned technical problems, the technical solution of this application is implemented as follows:

[0007] In one embodiment, a method for road testing of an autonomous vehicle is provided, the method comprising:

[0008] In response to the end of the nth group of road tests, acquire the abnormal events that occurred in the previous n groups of road tests; wherein, each group of road tests includes at least one trip; the trip is the distance from the starting point to the return point on the designated test route completed by the autonomous vehicle;

[0009] Whether the road test has converged is determined by whether the abnormal labels corresponding to the abnormal events that occurred in the first n sets of road tests cover the abnormal labels in the first set of abnormal labels, and by the distribution ratio of the number of abnormal events corresponding to each abnormal label in the second set of abnormal labels.

[0010] In response to convergence of the drive test, output the total number of trips for the first n groups of drive tests.

[0011] The method further includes:

[0012] In response to the failure of the road test to converge, the (n+1)th group of road tests is initiated.

[0013] The step of determining whether the road test has converged based on whether the anomaly labels corresponding to the anomaly events appearing in the first n sets of road tests cover the anomaly labels in the first set of anomaly labels, and the distribution ratio of the number of anomaly events corresponding to each anomaly label in the second set of anomaly labels, includes:

[0014] Based on the total set of abnormal labels, determine the abnormal labels corresponding to the abnormal events that occurred in the first n groups of road tests.

[0015] Determine the first distribution ratio of the number of abnormal events that occurred in the first n groups of road tests corresponding to each abnormal label in the second abnormal label set;

[0016] Determine the second distribution ratio of the number of abnormal events that occurred in the first n-1 groups of road tests corresponding to each abnormal label in the second abnormal label set;

[0017] If the identified anomaly label covers all anomaly labels in the first anomaly label set, and the absolute difference between the first distribution ratio and the second distribution ratio corresponding to each anomaly label in the second anomaly label set is less than a preset difference, then the drive test is determined to have converged; otherwise, the drive test is determined to have not converged.

[0018] in,

[0019] The determination of the first distribution ratio of the number of abnormal events occurring in the first n groups of road tests corresponding to each abnormal label in the second abnormal label set includes:

[0020] Determine the ratio of the number of abnormal events occurring in the first n groups of road tests to the total number of abnormal events occurring in the first n groups of road tests for each abnormal label in the second abnormal label set.

[0021] Determine the first distribution ratio corresponding to each anomaly label based on the ratio value corresponding to each anomaly label;

[0022] The determination of the second distribution ratio of the number of abnormal events occurring in the first n-1 groups of road tests corresponding to each abnormal label in the second abnormal label set includes:

[0023] Determine the ratio of the number of anomalous events in the first n-1 groups of road tests to the total number of anomalous events in the first n-1 groups of road tests for each anomalous label in the second annomalous label set.

[0024] The second distribution ratio corresponding to each of the anomaly labels is determined based on the ratio corresponding to each of the anomaly labels.

[0025] The acquisition of the first set of abnormal labels includes:

[0026] Before conducting a road test, a pre-road test is performed, and any abnormal events that occur during the pre-road test are collected; wherein, the pre-road test is a road test that includes multiple trips;

[0027] Determine the number of abnormal events that occurred in the pre-road test corresponding to each abnormal label in the total abnormal label set;

[0028] The exception tags in the total exception tag set are arranged from largest to smallest according to the number of corresponding exception events;

[0029] The number of abnormal events corresponding to the abnormal labels is accumulated according to the sorting order;

[0030] When the number of accumulated abnormal events exceeds a first preset value, the abnormal tags corresponding to the accumulated abnormal events are used to form a first abnormal tag set.

[0031] The acquisition of the second set of abnormal labels includes:

[0032] Determine the ratio of the number of abnormal events corresponding to each abnormal tag in the pre-road test to the total number of abnormal events in the pre-road test;

[0033] The anomaly labels in the total anomaly label set are arranged in descending order of their ratios.

[0034] The number of abnormal events corresponding to the abnormal labels is accumulated according to the sorting order;

[0035] When the number of accumulated abnormal events exceeds the second preset value, the abnormal tags corresponding to the accumulated abnormal events are used to form a second abnormal tag set.

[0036] In another embodiment, an autonomous vehicle road test device is provided, the device comprising: an acquisition unit, a determination unit, and an output unit;

[0037] The acquisition unit is used to acquire abnormal events that occurred in the previous n groups of road tests in response to the end of the nth group of road tests; wherein each group of road tests includes at least one trip; the trip is the mileage from the starting point to the return point on the designated test route completed by the autonomous vehicle.

[0038] The determining unit is used to determine whether the road test has converged based on whether the abnormal labels corresponding to the abnormal events that occurred in the first n groups of road tests cover the abnormal labels in the first abnormal label set, and the distribution ratio of the number of abnormal events corresponding to each abnormal label in the second abnormal label set.

[0039] The output unit is used to output the total number of trips for the first n groups of road tests in response to road test convergence.

[0040] In another embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the autonomous vehicle road test method.

[0041] In another embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps of the autonomous vehicle road test method.

[0042] In another embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the autonomous vehicle road test method.

[0043] As can be seen from the above technical solution, the above embodiments use the number of road test trips as the standard for judging whether the road test has converged; and the number of road test convergence trips is determined by the degree to which the abnormal labels corresponding to the abnormal events cover the abnormal labels in the first abnormal label set, and the stability of the distribution ratio of the number of abnormal events in the abnormal labels. This solution considers the number of abnormal events and the abnormal labels corresponding to the abnormal events, and conducts trip road tests. Therefore, it can accurately determine whether the road test has converged, and thus can accurately conduct road tests of autonomous vehicles. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a schematic diagram of the process for obtaining the abnormal tag set in an embodiment of this application;

[0046] Figure 2 This is a schematic diagram of the road test process for autonomous vehicles in the embodiments of this application;

[0047] Figure 3 This is a schematic diagram illustrating the specific implementation process of road testing for autonomous vehicles in this application embodiment;

[0048] Figure 4 This is a schematic diagram of the distribution of abnormal events corresponding to the number of trips in the embodiments of this application;

[0049] Figure 5 This is a schematic diagram of the road testing device for autonomous vehicles in the embodiments of this application;

[0050] Figure 6 This is a schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0051] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0052] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0053] The technical solution of the present invention will be described in detail below with reference to specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0054] In related technologies, the approach of directly determining whether a road test has converged by the number of abnormal events or the mileage traveled during autonomous vehicle road tests has the following problems:

[0055] The mileage of each test section varies considerably, making it difficult to judge intuitively;

[0056] Using mileage for determination makes it difficult to ensure the completeness of the trip during road testing, which may lead to the omission of road segments and abnormal events.

[0057] The implementation schemes in related technologies cannot accurately determine whether the road test has converged, and therefore cannot accurately conduct road tests of autonomous vehicles.

[0058] To address the aforementioned issues, this application provides a method for road testing of autonomous vehicles, using the number of road test trips as the criterion for determining whether the road test has converged. The convergence of the road test trips is determined by the degree to which the anomaly labels corresponding to the occurring abnormal events cover the anomaly labels in a first set of anomaly labels, and the stability of the distribution ratio of the number of abnormal events among the anomaly labels. This scheme considers the number of abnormal events and the anomaly labels corresponding to the abnormal events, and since it performs trip-based road testing, it can accurately determine whether the road test has converged, thereby enabling accurate road testing of autonomous vehicles.

[0059] First, here are the definitions of some terms:

[0060] Issue (abnormal event): A problem that occurs to an autonomous vehicle during road testing is called an issue;

[0061] Anomaly Labels: These are labels placed on abnormal events that occur during road testing of autonomous vehicles, such as sudden braking, sudden steering wheel turning, and slow acceleration.

[0062] During the autonomous vehicle's journey on the designated test route, the road test personnel will observe and record all abnormal events that occur. After collecting and summarizing these abnormal events, an abnormal event tag set, referred to as the total abnormal tag set, will be generated. This will provide a standardized and unified reference for tagging abnormal events when encountering corresponding problems during the road test. At the same time, the correspondence between abnormal events and abnormal tags will be recorded.

[0063] In this embodiment of the application, there are no restrictions on the acquisition of the abnormal tag set; the abnormal tag set corresponding to the corresponding drive test line can be used directly. At the same time, the correspondence between abnormal events and abnormal tags can be obtained.

[0064] A trip (circle) is defined as the distance an autonomous vehicle travels on a designated test route from the starting point to the return point.

[0065] Test route: refers to roads approved by the national government that permit public testing of autonomous vehicles.

[0066] Specifying a test route refers to the test route specified in the test route specification.

[0067] In this embodiment of the application, a pre-road test needs to be performed before the actual road test to determine the first set of abnormal labels and the second set of abnormal labels.

[0068] The pre-road test here can be a road test that includes multiple trips. The number of trips here is usually greater than the number of trips that the road test converges, so as to initialize the first and second anomaly label sets that are closest to the requirements.

[0069] The process of determining the first set of abnormal labels and the second set of abnormal labels is described in detail below with reference to the accompanying drawings.

[0070] See Figure 1 , Figure 1 This is a flowchart illustrating the process of obtaining the abnormal tag set in an embodiment of this application. The specific steps are as follows:

[0071] Step 101: Perform a pre-road test and obtain abnormal events that occur during the pre-road test.

[0072] During pre-road testing, multiple trips of road testing are performed.

[0073] Step 102: Determine the number of abnormal events that occurred in the pre-road test corresponding to each abnormal label in the total abnormal label set.

[0074] All acquired abnormal events are assigned corresponding abnormal labels in the total abnormal label set, which in turn allows us to determine the number of abnormal events corresponding to each abnormal label.

[0075] Assume the total set of exception labels includes 10 labels, from label 1 to label 10, and the total number of exception events is 1000. The number of exception events corresponding to label 1 is 500, label 2 is 0, label 3 is 100, label 4 is 150, label 5 is 50, label 6 is 5, label 7 is 10, label 8 is 15, label 9 is 140, and label 10 is 30.

[0076] After step 102, steps 103 and 106 are executed respectively.

[0077] Step 103: Sort the exception labels in the total exception label set from largest to smallest according to the number of corresponding exception events.

[0078] The exception labels are arranged from largest to smallest according to the number of corresponding exception events:

[0079] Tag 1 (500), Tag 4 (150), Tag 9 (140), Tag 3 (100), Tag 5 (50), Tag 10 (30), Tag 8 (15), Tag 7 (10), Tag 6 (5), Tag 2 (0).

[0080] Step 104: Accumulate the number of abnormal events corresponding to the abnormal labels in the order of arrangement.

[0081] The count starts from the number of exceptions corresponding to label 1. For example, when the count reaches label 1, the number of exception labels is 500. When the count reaches label 9, the number of exception labels is 790, and so on. The details will not be repeated.

[0082] Step 105: When the ratio of the accumulated number of abnormal events to the total number of abnormal events is greater than a first preset value, use the abnormal tags corresponding to the accumulated abnormal events to form a first abnormal tag set. End this process.

[0083] The first preset value here can be set according to the actual application scenario, such as 95%, but it is not limited to this in actual implementation. Therefore, the number of accumulated abnormal events should be greater than 950.

[0084] As in the example above, when the number of abnormal events is accumulated to label 10, the number of abnormal events is 980, which is greater than 950. Therefore, the first abnormal label set includes: label 1, label 4, label 9, label 3, label 5, and label 10.

[0085] Step 106: Determine the ratio of the number of abnormal events that occurred in the pre-road test corresponding to each abnormal label to the total number of abnormal events that occurred in the pre-road test.

[0086] The ratio corresponding to label 1 is 20%, label 4 is 15%, label 9 is 14%, label 3 is 10%, label 5 is 5%, label 10 is 3%, label 8 is 1.5%, label 7 is 1%, label 6 is 0.5%, and label 2 is 0%.

[0087] Step 107: Arrange the abnormal labels in the total abnormal label set in descending order of ratio.

[0088] The anomaly labels are arranged from largest to smallest according to the ratio:

[0089] Label 1 (20%, 500), Label 4 (15%, 150), Label 9 (14%, 140), Label 3 (10%, 100), Label 5 (5%, 50), Label 10 (3%, 30), Label 8 (1.5%, 15), Label 7 (1%, 10), Label 6 (0.5%, 5), Label 2 (0%, 0).

[0090] Step 108: Accumulate the number of abnormal events corresponding to the abnormal labels in the order of arrangement.

[0091] The count starts from the number of exceptions corresponding to label 1. For example, when the count reaches label 1, the number of exception labels is 500. When the count reaches label 9, the number of exception labels is 790, and so on. The details will not be repeated.

[0092] Step 109: When the ratio of the number of accumulated abnormal events to the total number of abnormal events is greater than the second preset value, the abnormal tags corresponding to the accumulated abnormal events are used to form a second abnormal tag set.

[0093] The second preset value here is usually set smaller than the first preset value, such as 80%, but it is not limited to this in actual implementation.

[0094] As in the example above, when the number of abnormal events is accumulated to label 3, it is 890, which is greater than 800. Therefore, the second abnormal label set includes: label 1, label 4, label 9, and label 3.

[0095] Such an implementation typically results in the second set of exception labels being a subset of the first set of exception labels.

[0096] At this point, the first and second sets of anomaly labels have been determined. Both the first and second sets of anomaly labels are subsets of the total set of anomaly labels.

[0097] The following detailed description, with reference to the accompanying drawings, illustrates the process of implementing road testing of autonomous vehicles in the embodiments of this application.

[0098] See Figure 2 , Figure 2 This is a schematic diagram of the road test process for an autonomous vehicle in this application. The specific steps are as follows:

[0099] Step 201: In response to the end of the nth group of road tests, obtain the abnormal events that occurred in the first n groups of road tests; wherein, each group of road tests includes at least one trip; the trip is the distance from the starting point to the return point on the specified test route completed by the autonomous vehicle.

[0100] Here, n is an integer greater than 1.

[0101] In the embodiments of this application, the number of trips included in each group of road tests can be the same, such as 5 trips as a group. That is, after testing 5 trips, it is determined whether the current road test has converged. In specific implementation, it is not limited to the implementation method of 5 trips as a group, nor is it limited to the case that the number of trips included in each group of road tests must be the same.

[0102] Using a set of trips to determine whether a road test has converged can save resources, avoid frequent checks, and make the results more reliable.

[0103] During the road test, abnormal events that occur during each trip will be recorded. When the nth trip is completed, the abnormal events that occurred during the previous n trips can be retrieved directly.

[0104] Step 202: Determine whether the road test has converged based on whether the abnormal labels corresponding to the abnormal events that occurred in the first n sets of road tests cover the abnormal labels in the first abnormal label set, and the distribution ratio of the number of abnormal events corresponding to each abnormal label in the second abnormal label set.

[0105] Does the abnormal label corresponding to the abnormal event that occurred in the first n groups of road tests cover the abnormal label in the first abnormal label set? In other words, does the abnormal label corresponding to the abnormal event that occurred in the first n groups of road tests cover the abnormal label in the first abnormal label set? In other words, do all the labels in the first abnormal label set have the abnormal label corresponding to the abnormal event that occurred in the first n groups of road tests?

[0106] The distribution ratio of the number of abnormal events corresponding to the abnormal labels in the second abnormal label set, that is, the proportion of the number of abnormal events corresponding to each abnormal label to the total number of abnormal events.

[0107] Step 203: In response to the convergence of the drive test, output the total number of trips for the first n groups of drive tests.

[0108] In response to road test convergence, the current road test ends, and the total number of trips of the first n road tests is output as the number of trips when road test convergence is achieved. The total number of trips of the first n road tests is the sum of the number of trips of all the road tests in the first n road tests.

[0109] In response to the failure of the road test to converge, the (n+1)th group of road tests is initiated.

[0110] After starting n+1 sets of road tests, perform the corresponding number of trips. After the n+1 sets of road tests are completed, use the same convergence judgment method used after the nth set of trips to determine convergence until the road tests converge.

[0111] In this embodiment, the number of road test trips is used as the criterion for determining whether the road test has converged. The convergence of the road test trips is determined by the degree to which the anomaly labels corresponding to the abnormal events cover the anomaly labels in the first set of anomaly labels, and the stability of the distribution ratio of the number of anomaly events among the anomaly labels. This scheme considers the number of anomaly events and the anomaly labels corresponding to the anomaly events, and since it performs trip-based road tests, it can accurately determine whether the road test has converged, thereby enabling accurate road testing of autonomous vehicles.

[0112] In some examples, step 201 determines whether the road test has converged based on whether the anomaly labels corresponding to the anomaly events in the first n sets of road tests cover the anomaly labels in the first set of anomaly labels, and the distribution ratio of the number of anomaly events corresponding to each anomaly label in the second set of anomaly labels. This includes:

[0113] Based on the total set of abnormal labels, determine the abnormal labels corresponding to the first n abnormal events that occurred in the road test.

[0114] Determine the first distribution ratio of the number of abnormal events that occurred in the first n groups of road tests corresponding to each abnormal label in the second abnormal label set;

[0115] Determine the second distribution ratio of the number of abnormal events that occurred in the first n-1 groups of road tests corresponding to each abnormal label in the second abnormal label set;

[0116] If the identified anomaly labels cover all anomaly labels in the first anomaly label set, and the absolute difference between the first distribution ratio and the second distribution ratio corresponding to each anomaly label in the second anomaly label set is less than a preset difference, then the drive test is determined to have converged; otherwise, the drive test is determined to have not converged.

[0117] in,

[0118] Determine the first distribution ratio of the number of abnormal events occurring in the first n groups of road tests corresponding to each abnormal label in the second abnormal label set, including:

[0119] Determine the ratio of the number of abnormal events occurring in the first n groups of road tests to the total number of abnormal events occurring in the first n groups of road tests for each abnormal label in the second abnormal label set.

[0120] The first distribution ratio corresponding to each anomaly label is determined based on the ratio corresponding to each anomaly label.

[0121] Determine the second distribution ratio of the number of abnormal events occurring in the first n-1 groups of road tests corresponding to each abnormal label in the second abnormal label set, including:

[0122] Determine the ratio of the number of anomalous events in the first n-1 groups of road tests to the total number of anomalous events in the first n-1 groups of road tests for each anomalous label in the second annomalous label set.

[0123] The second distribution ratio corresponding to each anomaly label is determined based on the ratio corresponding to each anomaly label.

[0124] All of the above-mentioned optional technical solutions can be combined in any way to form optional embodiments of this disclosure, and will not be described in detail here.

[0125] See Figure 3 , Figure 3 This is a schematic diagram illustrating the road test process for an autonomous vehicle as described in this embodiment. The specific steps are as follows:

[0126] Step 301: In response to the end of the nth group of road tests, obtain the abnormal events that occurred in the previous n groups of road tests; wherein, each road test includes at least one trip; the trip is the distance from the starting point to the return point on the specified test route completed by the autonomous vehicle.

[0127] In the embodiments of this application, the number of trips included in each group of road tests is the same, such as 5 trips as a group. That is, after testing 5 trips, it is determined whether the current road test has converged. In specific implementation, it is not limited to the implementation method of 5 trips as a group, nor is it limited to the case that the number of trips included in each group of road tests must be the same.

[0128] During the road test, abnormal events that occur during each trip will be recorded. When the nth trip is completed, the abnormal events that occurred during the previous n trips can be retrieved directly.

[0129] When obtaining abnormal events that occur in the first n groups of road tests, we can obtain the abnormal events that occur during the road test of each group of road tests, and then obtain the abnormal events that occur in the n groups of road tests.

[0130] You can also use the abnormal events that occurred during the first n-1 groups of road tests, then obtain the abnormal events that occurred during the nth group of road tests, and then obtain the abnormal events that occurred during the first n groups of road tests.

[0131] After step 301, steps 302 and 303 are executed respectively.

[0132] Step 302: Based on the total set of anomaly labels, determine the anomaly labels corresponding to the anomaly events occurring in the first n groups of road tests. Proceed to step 305.

[0133] The correspondence between abnormal events and abnormal labels is pre-set, which can determine the abnormal labels corresponding to all abnormal events that occur in the first n groups of road tests.

[0134] Step 303: Determine the first distribution ratio of the number of abnormal events that occurred in the first n groups of road tests corresponding to each abnormal label in the second abnormal label set.

[0135] In this step, the first distribution ratio of the number of abnormal events occurring in the first n groups of road tests corresponding to each abnormal label in the second abnormal label set is determined, including:

[0136] Determine the ratio of the number of abnormal events occurring in the first n groups of road tests to the total number of abnormal events occurring in the first n groups of road tests for each abnormal label in the second abnormal label set.

[0137] The first distribution ratio corresponding to each anomaly label is determined based on the ratio corresponding to each anomaly label.

[0138] Step 304: Determine the second distribution ratio of the number of abnormal events that occurred in the first n-1 groups of road tests corresponding to each abnormal label in the second abnormal label set.

[0139] In this step, the second distribution ratio of the number of abnormal events occurring in the first n-1 groups of road tests corresponding to each abnormal label in the second abnormal label set is determined, including:

[0140] Determine the ratio of the number of anomalous events in the first n-1 groups of road tests to the total number of anomalous events in the first n-1 groups of road tests for each anomalous label in the second annomalous label set.

[0141] The second distribution ratio corresponding to each anomaly label is determined based on the ratio corresponding to each anomaly label.

[0142] Steps 302 to 304 implement the process of determining whether the road test has converged based on whether the abnormal labels corresponding to the abnormal events that occurred in the first n groups of road tests cover the abnormal labels in the first abnormal label set, and the distribution ratio of the number of abnormal events corresponding to each abnormal label in the second abnormal label set.

[0143] Step 305: If the determined abnormal label covers all abnormal labels in the first abnormal label set, and the absolute difference between the first distribution ratio and the second distribution ratio corresponding to each abnormal label in the second abnormal label set is less than the preset difference, then the road test is determined to be converged, and the total number of trips of the first n groups of road tests is output; otherwise, the road test is determined to be unconverged, and the start of the (n+1)th group of road tests is triggered.

[0144] Once the road test converges, the current road test ends. The total number of trips for the first n road tests is output as the number of trips when the road test converges. The total number of trips for the first n road tests is the sum of the number of trips for all road tests in the first n road tests.

[0145] See Figure 4 , Figure 4 This is a schematic diagram of the distribution of abnormal events corresponding to the number of trips in the embodiments of this application. Figure 4 Taking the second set of abnormal labels, which includes 12 labels, as an example. Figure 2 The horizontal axis represents the number of trips, and the vertical axis represents the distribution ratio of each label in the second set of abnormal labels, that is, the percentage of the number of abnormal events corresponding to each label to the total number of abnormal events.

[0146] As can be observed from the above figure, when trip>n1, the above convergence conditions are basically met; when trip>n2, the distribution ratio of the anomaly labels is more stable. Therefore, the corresponding number of trips for converged road test is n2.

[0147] In specific implementation, for Figure 4 The number of trips included in the pre-road test of the corresponding road test route will be greater than n2.

[0148] If the road test fails to converge, start n+1 sets of road tests and perform the corresponding number of trips. After the n+1 sets of road tests are completed, use the same convergence judgment method used after the nth set of trips to determine convergence, until the road test converges.

[0149] In this embodiment, after the nth group of road tests is completed, abnormal events occurring during the first n and first n-1 groups of road tests are acquired. It is then determined whether the abnormal labels corresponding to the abnormal events in the first n groups of road tests cover the abnormal labels in the first abnormal label set, and the absolute difference between the first distribution ratio corresponding to the number of abnormal labels in the first n groups of road tests and the second distribution ratio corresponding to the number of abnormal events in the first n-1 groups of road tests is used to determine whether the current road test has converged. This scheme considers the number of abnormal events and the abnormal labels corresponding to the abnormal events, and since it performs trip road tests, it can accurately determine whether the road test has converged, thus enabling accurate road testing of autonomous vehicles.

[0150] All of the above-mentioned optional technical solutions can be combined in any way to form optional embodiments of this disclosure, and will not be described in detail here.

[0151] Based on the same inventive concept, this application also provides a road testing device for autonomous vehicles. See also Figure 5 , Figure 5 This is a schematic diagram of the structure of an autonomous vehicle road testing device in an embodiment of this application. The autonomous vehicle road testing device includes: an acquisition unit 501, a determination unit 502, and an output unit 503;

[0152] The acquisition unit 501 is used to acquire abnormal events that occurred in the previous n groups of road tests in response to the end of the nth group of road tests; wherein each group of road tests includes at least one trip; the trip is the mileage from the starting point to the return point on the designated test route completed by the autonomous vehicle.

[0153] The determining unit 502 is used to determine whether the road test has converged based on whether the abnormal labels corresponding to the abnormal events that occurred in the first n groups of road tests cover the abnormal labels in the first abnormal label set, and the distribution ratio of the number of abnormal events corresponding to each abnormal label in the second abnormal label set.

[0154] Output unit 503 is used to output the total number of trips for the first n groups of road tests in response to road test convergence.

[0155] In another embodiment, the automated driving road test device further includes: a triggering unit 504;

[0156] Trigger unit 504 is used to trigger the start of the (n+1)th group of road tests in response to the failure of the road test to converge.

[0157] In another embodiment,

[0158] The determining unit 502 is specifically used to determine, based on the total abnormal label set, the abnormal labels corresponding to the abnormal events appearing in the first n groups of road tests; determine a first distribution ratio of the number of abnormal events appearing in the first n groups of road tests corresponding to each abnormal label in the second abnormal label set; determine a second distribution ratio of the number of abnormal events appearing in the first n-1 groups of road tests corresponding to each abnormal label in the second abnormal label set; if the determined abnormal labels cover all abnormal labels in the first abnormal label set, and the absolute difference between the first distribution ratio and the second distribution ratio corresponding to each abnormal label in the second abnormal label set is less than a preset difference, then the road test is determined to have converged; otherwise, the road test is determined to have not converged.

[0159] In another embodiment,

[0160] The determining unit 502 is specifically used to determine the first distribution ratio of the number of abnormal events appearing in the first n groups of road tests corresponding to each abnormal label in the second abnormal label set, by respectively determining the ratio of the number of abnormal events appearing in the first n groups of road tests corresponding to each abnormal label in the second abnormal label set to the number of abnormal events appearing in the first n groups of road tests, and determining the first distribution ratio corresponding to each abnormal label based on the ratio corresponding to each abnormal label; and to determine the second distribution ratio of the number of abnormal events appearing in the first n-1 groups of road tests corresponding to each abnormal label in the second abnormal label set, by respectively determining the ratio of the number of abnormal events appearing in the first n-1 groups of road tests corresponding to each abnormal label in the second abnormal label set to the number of abnormal events appearing in the first n-1 groups of road tests, and determining the second distribution ratio corresponding to each abnormal label based on the ratio corresponding to each abnormal label.

[0161] In another embodiment,

[0162] The acquisition unit 501 is further configured to acquire the first abnormal tag set by: performing a pre-road test before conducting a road test, and acquiring abnormal events that occur in the pre-road test; wherein the pre-road test is a road test including multiple trips; determining the number of abnormal events that occur in the pre-road test corresponding to each abnormal tag in the total abnormal tag set; arranging the abnormal tags in the total abnormal tag set in descending order of the number of corresponding abnormal events; accumulating the number of abnormal events corresponding to the abnormal tags in the order of arrangement; and when the accumulated number of abnormal events is greater than a first preset value, using the abnormal tags corresponding to the accumulated abnormal events to form the first abnormal tag set.

[0163] In another embodiment,

[0164] The acquisition unit 501 is further configured to acquire the second abnormal tag set by: determining the ratio of the number of abnormal events corresponding to each abnormal tag in the pre-road test to the total number of abnormal events in the pre-road test; arranging the abnormal tags in the total abnormal tag set in descending order of the ratio; accumulating the number of abnormal events corresponding to the abnormal tags in the order of arrangement; and when the accumulated number of abnormal events is greater than a second preset value, using the abnormal tags corresponding to the accumulated abnormal events to form the second abnormal tag set.

[0165] The units in the above embodiments can be integrated into one unit or deployed separately; they can be merged into one unit or further divided into multiple sub-units.

[0166] In another embodiment, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of an autonomous vehicle road test method.

[0167] In another embodiment, a computer-readable storage medium is also provided, on which computer instructions are stored, which, when executed by a processor, can implement the steps in the autonomous vehicle road test method.

[0168] Figure 6 This is a schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention. Figure 6 As shown, the electronic device may include a processor 610, a communications interface 620, a memory 630, and a communication bus 640. The processor 610, communications interface 620, and memory 630 communicate with each other via the communication bus 640. The processor 610 can call logical instructions stored in the memory 630 to execute the following methods:

[0169] In response to the end of the nth group of road tests, acquire the abnormal events that occurred in the previous n groups of road tests; wherein, each group of road tests includes at least one trip; the trip is the distance from the starting point to the return point on the designated test route completed by the autonomous vehicle;

[0170] Whether the road test has converged is determined by whether the abnormal labels corresponding to the abnormal events that occurred in the first n sets of road tests cover the abnormal labels in the first set of abnormal labels, and by the distribution ratio of the number of abnormal events corresponding to each abnormal label in the second set of abnormal labels.

[0171] In response to convergence of the drive test, output the total number of trips for the first n groups of drive tests.

[0172] Furthermore, the logical instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0173] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0174] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0175] In another embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the autonomous vehicle road test method.

[0176] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments disclosed in this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those shown in the drawings. For example, two blocks shown connectedly may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0177] Those skilled in the art will understand that the features described in the various embodiments and / or claims disclosed in this application can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this application. In particular, without departing from the spirit and teachings of this application, the features described in the various embodiments and / or claims of this application can be combined and / or combined in various ways, and all such combinations and / or combinations fall within the scope of this application.

[0178] This document uses specific embodiments to illustrate the principles and implementation methods of the present invention. The descriptions of these embodiments are merely illustrative of the method and core concepts of the present invention and are not intended to limit this application. Those skilled in the art can make changes to the specific implementation methods and application scope based on the ideas, spirit, and principles of the present invention. Any modifications, equivalent substitutions, or improvements made should be included within the scope of protection of this application.

Claims

1. An automatic driving vehicle road test method, characterized by, The method comprises: in response to the end of the nth group of road tests, obtaining abnormal events occurring in the first n groups of road tests; wherein each group of road tests comprises at least one trip; the trip is the automatic driving vehicle completing the mileage from the starting point to the returning terminal point on the specified test route; determining whether the road test converges according to whether the target abnormal label corresponding to the abnormal event occurring in the first n groups of road tests covers the abnormal label in the first abnormal label set, and the distribution proportion of the number of the abnormal event corresponding to each abnormal label in the second abnormal label set; in response to the convergence of the road test, outputting the total number of trips of the first n groups of road tests; wherein, determining whether the road test converges according to whether the target abnormal label corresponding to the abnormal event occurring in the first n groups of road tests covers the abnormal label in the first abnormal label set, and the distribution proportion of the number of the abnormal event corresponding to each abnormal label in the second abnormal label set, comprises: determining the target abnormal label corresponding to the abnormal event occurring in the first n groups of road tests based on the total abnormal label set; determining the first distribution proportion of the number of the abnormal event occurring in the first n groups of road tests corresponding to each abnormal label in the second abnormal label set; determining the second distribution proportion of the number of the abnormal event occurring in the first n-1 groups of road tests corresponding to each abnormal label in the second abnormal label set; if it is determined that the target abnormal label covers all abnormal labels in the first abnormal label set, and the absolute difference between the first distribution proportion and the second distribution proportion corresponding to each abnormal label in the second abnormal label set is less than a preset difference value, it is determined that the road test converges; otherwise, it is determined that the road test does not converge.

2. The method of claim 1, wherein, The method further comprises: in response to the road test not converging, triggering the start of the nth+1 group of road tests.

3. The method of claim 1, wherein the determination of the first distribution proportion of the number of the abnormal event occurring in the first n groups of road tests corresponding to each abnormal label in the second abnormal label set comprises: respectively determining the ratio of the number of the abnormal event occurring in the first n groups of road tests corresponding to each abnormal label in the second abnormal label set to the number of the abnormal event occurring in the first n groups of road tests, determining the first distribution proportion corresponding to each abnormal label according to the ratio corresponding to each abnormal label; the determination of the second distribution proportion of the number of the abnormal event occurring in the first n-1 groups of road tests corresponding to each abnormal label in the second abnormal label set comprises: respectively determining the ratio of the number of the abnormal event occurring in the first n-1 groups of road tests corresponding to each abnormal label in the second abnormal label set to the number of the abnormal event occurring in the first n-1 groups of road tests, determining the second distribution proportion corresponding to each abnormal label according to the ratio corresponding to each abnormal label.

4. The method according to any one of claims 1 to 3, characterized in that, The acquisition of the first abnormal label set comprises: before the road test, performing a pre-road test, and acquiring abnormal events occurring in the pre-road test; wherein the pre-road test is a road test comprising a plurality of trips; determine a number of abnormal events corresponding to each abnormal label in the total abnormal label set in the pre-forecast; arrange the abnormal labels in the total abnormal label set in descending order according to the number of corresponding abnormal events; accumulate the number of abnormal events corresponding to the abnormal labels according to the arrangement order; when the accumulated number of abnormal events is greater than a first preset value, use the abnormal labels corresponding to the accumulated abnormal events to form a first abnormal label set.

5. The method of claim 4, wherein, The acquisition of the second abnormal label set comprises: determine a ratio of the number of abnormal events corresponding to each abnormal label to the total number of abnormal events in the pre-forecast; arrange the abnormal labels in the total abnormal label set in descending order according to the ratio; accumulate the number of abnormal events corresponding to the abnormal labels according to the arrangement order; when the accumulated number of abnormal events is greater than a second preset value, use the abnormal labels corresponding to the accumulated abnormal events to form a second abnormal label set.

6. An automatic driving vehicle road testing device, characterized by comprising: The device comprises an acquisition unit, a determination unit and an output unit; The acquisition unit is configured to acquire abnormal events occurring in the first n sets of road tests in response to the end of the nth set of road tests, wherein each set of road tests comprises at least one trip, and the trip refers to a distance covered by an autonomous vehicle from a starting point to an ending point on a specified test route. The determination unit is configured to determine whether the road tests converge according to whether the abnormal labels corresponding to the abnormal events occurring in the first n sets of road tests cover the abnormal labels in the first abnormal label set and the distribution proportion of the number of abnormal events corresponding to each abnormal label in the second abnormal label set. The output unit is configured to output the total number of trips in the first n sets of road tests in response to the road tests converging. The determination unit is further configured to: The determination unit is further configured to: determine a target abnormal label group corresponding to the abnormal events occurring in the first n sets of road tests based on the total abnormal label set; determine a first distribution proportion of the number of abnormal events corresponding to each abnormal label in the second abnormal label set in the first n sets of road tests; determine a second distribution proportion of the number of abnormal events corresponding to each abnormal label in the second abnormal label set in the first n-1 sets of road tests; if it is determined that the target abnormal label group covers all abnormal labels in the first abnormal label set and the absolute difference between the first distribution proportion and the second distribution proportion corresponding to each abnormal label in the second abnormal label set is less than a preset difference value, it is determined that the road tests converge; otherwise, it is determined that the road tests do not converge.

7. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to implement the method of any one of claims 1-5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the method of any one of claims 1-5.

9. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the method of any one of claims 1-5.

Images