Method for improving utilization rate of automatic driving closed test site

Abstract

The invention discloses a method for improving the utilization rate of an automatic driving closed test site, and the method comprises the steps: carrying out the road section digitalization of a road network of the closed test site, and enabling the status bit of each road section to be 1 or 0; when the status bit of the road section is 0, allowing the test, determining an occupied space sequence of the test vehicle according to the status bit of each road section, and setting the status bits of all the occupied road sections from 0 to 1; constructing a time dictionary, and recording the to-be-occupied road section duration of the test vehicle on each tested road section; the test platform obtains the vehicle position and matches the vehicle position to the nearest road section; and when the test vehicle travels to a road section, countdown is performed on the road section duration occupied by the road section, and after countdown is finished, the status bit of the road section is reset from 1 to 0. According to the method, real-time and automatic distribution of each road section of the test site can be realized, multi-vehicle cooperative test is realized, the vacancy time of the site can be reduced, and the utilization rate of the test site is improved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving test technology. More specifically, the present invention relates to a method for improving the utilization rate of an autonomous driving closed test site. Background Art

[0002] In the process of developing autonomous driving technology, testing in closed venues is an indispensable and important key link. The rational use and management of closed venues are crucial to the development of technology. However, the current mainstream closed test site management and use methods have many drawbacks, which seriously restrict the test efficiency and the effective use of site resources.

[0003] At present, the use planning of closed test sites is relatively extensive. Most sites adopt a simple area division method, using cone barrels for isolation to define different test areas. This division method lacks precision and it is difficult to improve the space utilization rate of the site. From the perspective of space utilization, the division according to large areas does not take into account the actual available space of each part of the site, resulting in many areas that could have accommodated more vehicles for simultaneous testing being idle. For example, in some large closed test sites, some edge areas or transition zones between adjacent test areas have not been effectively utilized because they are simply used as isolation spaces or are not fully planned, resulting in a waste of space resources.

[0004] In terms of site information sharing, communication mainly relies on radios or WeChat groups. This method has serious information transmission defects. On the one hand, the information description is not precise enough, and the description of the use area and time period is often vague. The description of the use area may be too general to accurately define the specific test scope, and the time period information may be exaggerated, inaccurate, or change untimely. On the other hand, communication is unstable, and radios are easily affected by factors such as signal interference and equipment aging, resulting in poor information transmission or loss. Although WeChat groups can expand the scope of information dissemination to a certain extent, members may miss important information, resulting in untimely and inaccurate information reception. For example, when a test group informs other groups through a radio that a certain area has been occupied, but due to radio signal problems, other test groups do not receive the information, mistakenly thinking that the venue is idle and entering the test, it is very easy to cause test conflicts.

[0005] The WeChat applet site reservation system, which is widely used at present, has standardized the time arrangement of site use to a certain extent, but it still has obvious shortcomings. In terms of time dimension, the method of booking according to fixed time periods cannot flexibly adapt to complex testing needs such as debugging code of enterprise vehicles. During the debugging process of the code, the vehicle does not use the site continuously, and there will be a large number of idle periods. However, these periods cannot be effectively used by other test groups, resulting in the site being vacant during these time periods, wasting precious site resources. Most importantly, these problems lead to serious safety hazards. Due to inaccurate information, poor communication and unreasonable site planning, test conflicts often occur. In the autonomous driving test, the vehicle travels at a high speed, and some test vehicles can reach a speed of 140Km / h. Once a vehicle collision occurs, it will cause serious casualties and equipment damage. A more efficient, accurate and safe closed test site management and use method is urgently needed to improve site utilization and ensure the smooth progress of the test. Summary of the invention

[0006] The present invention provides a method for improving the utilization rate of a closed test site for autonomous driving, which can not only realize the real-time and automatic allocation of various sections of the test site and realize multi-vehicle collaborative testing, but also reduce the vacancy time of the site, improve the utilization rate of the test site, and at the same time improve the safety of the test.

[0007] In order to achieve these objectives and other advantages of the present invention, the present invention provides a method for improving the utilization rate of a closed autonomous driving test site, comprising: The road network of the closed test site is digitized into sections. Each section includes: ID, section longitude and latitude information, direction and two end nodes. The status bit of each section is: 1 or 0, where 1 means busy and 0 means idle; When the status bit of the road section is 0, the test is allowed, and the occupied space sequence of the test vehicle is determined according to the status bits of each road section, and the status bits of all occupied road sections are set from 0 to 1, wherein the occupied space sequence is composed of the road section ID of the driving trajectory of the test vehicle; Construct a time dictionary to record the length of time the test vehicle will occupy on each road section during its test; The test vehicle is tested according to the sequence of occupied space. The test platform obtains the position of the vehicle based on the GPS device of the test vehicle, and matches it to the nearest section based on the distance between the vehicle's position and each section. When the test vehicle travels to a section, the length of time occupied on the section is counted down at the same time. When the countdown ends, the status bit of the section is reset from 1 to 0.

[0008] Preferably, the method further includes a safety warning step: If the countdown ends according to the time dictionary, but the test vehicle's GPS device determines that the test vehicle has not completed the test of the road section, that is, the status bit of the road section has been reset to 0, but the road section is still occupied, a level 1 alarm is issued and the authority is exceeded, prohibiting the road section status bit from being 0; If the test vehicle does not drive according to the occupied space sequence of the test scenario, but drives to an irrelevant section of road, an alarm will be issued and the status bit of the irrelevant section will be set to 1; if the status bit of the irrelevant section is already 1, a secondary alarm will be issued to prompt the tester to stop the test.

[0009] Preferably, a target vehicle is also included, which is a vehicle that conflicts with the test vehicle, and the target vehicle is also provided with a vehicle-side GPS device, and the target vehicle is also provided with its own occupied space sequence and occupied road section duration; The test vehicle includes a plurality of test groups, each of which includes a plurality of test vehicles; the target vehicle also includes a plurality of target vehicle groups, each of which includes a plurality of target vehicles.

[0010] Preferably, the time dictionary is constructed to record the duration of each test vehicle to be occupied on each road section tested, and the duration of the occupied road section is calculated as follows: Section duration = section length / preset speed measurement + buffer time, The preset speed measurement is the expected driving speed of the test vehicle on the road section, and the buffer time is used to cover delays or abnormal situations that may occur during the test.

[0011] Preferably, the space occupied sequence of the test vehicle is determined according to the status bit of each road section, specifically: The test tasks are sorted according to the task priority. The test tasks with high task priority are assigned to the road sections first. The task priority is determined according to the urgency, complexity and importance of the test task. For each test task, traverse each road segment in the occupied space sequence to be used for its test, and check the status bit of each road segment; If the status bit of each road section is 0, it is assigned to the test task and the status bit of each road section is set to 1; If at least one of the road segments in the status bit of each road segment is 1, the available time of the road segment is calculated according to the countdown information in the time dictionary, and it is decided whether to wait or choose an alternative road segment; If multiple test tasks compete for the same road section, conflicts are resolved based on task priority. High-priority tasks take up the road section first, while low-priority tasks wait or re-plan the road section.

[0012] Preferably, the duration of each test vehicle occupying a road section recorded in the time dictionary is a dynamic time dictionary, specifically: The speed and acceleration of the test vehicle are acquired in real time by using the speed sensor and acceleration sensor installed on the test vehicle, and the acquired speed and acceleration data are transmitted to the test platform in real time; The cameras and road condition sensors deployed at the test site collect road condition information in real time; Construct a training model for predicting road section duration; Inputting the acquired real-time speed, acceleration and road condition information into the predicted section duration training model to obtain the predicted section duration; If the difference between the predicted section duration and the preset section duration in the time dictionary is greater than a threshold, the test platform updates the section duration in the time dictionary.

[0013] Preferably, the construction of the predicted road section duration training model is specifically as follows: Collect historical data information of the test vehicle, including driving speed, acceleration, road condition information and actual road duration on different road sections; The collected historical data information is used to extract road section type features, weather condition features, and time period features. The road section types are divided into: curves, straight roads, uphill and downhill; the weather conditions are divided into: sunny, rainy, snowy, and cloudy; and the time periods are divided into morning, afternoon, and evening. The long short-term memory network model is used to predict the road section duration.

[0014] Preferably, the determination of the task priority includes: calculating the priority score of each test task by a weighted algorithm, wherein the urgency, complexity and importance are respectively assigned different weights; sorting the test tasks according to the priority scores, and giving priority to assigning road sections to tasks with high priority scores.

[0015] Preferably, the first-level alarm is carried out and the authority is exceeded, and the road section status position is prohibited to be 0, specifically: after the first-level alarm is triggered, the test platform automatically exceeds the authority and forces the road section status bit to be kept at 1. The road section can be reallocated only after the vehicle status is manually confirmed and unlocked, and the unauthorized operation is recorded in the test platform; wherein, the first-level alarm includes: prohibiting the road section status position to be 0, forcibly maintaining the status bit at 1; sending an alarm message to the tester, including the current position of the vehicle and abnormal road section occupancy information, the test platform locks the road section, and prohibits other test tasks from allocating the road section; The secondary alarm includes: sending emergency alarm information to the tester, including conflicting road section information and the current location of the vehicle; suggesting that the tester stop the test immediately and check the vehicle status; the test platform automatically suspends all related test tasks.

[0016] Preferably, it also includes: after the digitization of the road section is completed, the test platform generates a road network topology map for visually displaying the connection relationship and status position of each road section; the road network topology map is updated in real time to reflect the current status of each road section.

[0017] The present invention has at least the following beneficial effects: First, through the digital management of road sections, the real-time status (busy or idle) of each road section can be accurately grasped, so that the driving route of the test vehicle can be reasonably planned to reduce the idleness or overuse of the road section. When determining the occupied space sequence of the test vehicle, it is allocated according to the road section status bit to ensure that each available road section can be fully utilized, avoiding the waste of resources caused by unclear information under the traditional management method, and greatly improving the utilization rate of the site space. The construction of the time dictionary and the countdown mechanism can accurately control the occupation time of the vehicle in each road section. The countdown is performed according to the preset road section duration, and the road section status is reset in time after the countdown ends, so that other test vehicles can use the road section as soon as possible, which improves the utilization rate of the closed test site in the time dimension and reduces the vacancy time of the closed test site. Therefore, through digitalization and status bit management, the automatic and real-time allocation of road section resources is realized, which significantly improves the utilization rate of the test site.

[0018] Second, the first-level alarm mechanism in the safety warning step, when the countdown ends but the test vehicle has not completed the test, the road section status bit is reset to 0 to prevent other test vehicles or target vehicles from mistakenly entering the still occupied road section, effectively preventing the occurrence of vehicle collision accidents. When the test vehicle deviates from the scheduled driving route and enters an irrelevant road section, the test personnel are prompted and the test is stopped, which can timely detect and stop abnormal driving behavior, reduce the risk of conflict between different test vehicles, and ensure the safety of the test process.

[0019] Third, consider the existence of the target vehicle and set up a management method similar to that of the test vehicle, namely, the vehicle-side GPS device, the sequence of occupied space, and the length of time the road section is occupied, so that in complex scenarios where multiple vehicles are tested at the same time, the driving routes and time arrangements between different vehicles can be better coordinated. Grouping test vehicles and target vehicles for management will help to uniformly dispatch and monitor vehicles in different groups. Through centralized management of vehicles in each group, site resources can be better allocated, the test process can be optimized, and the utilization rate and test efficiency of the site can be further improved. Therefore, through the management of target vehicle groups and multiple test groups, multi-vehicle collaborative testing in complex scenarios is achieved, further improving the utilization rate of the test site.

[0020] Other advantages, objectives and features of the present invention will be embodied in part through the following description, and in part will be understood by those skilled in the art through study and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A flow chart of a method for improving the utilization rate of a closed autonomous driving test site according to the present invention. DETAILED DESCRIPTION

[0022] The present invention is further described in detail below in conjunction with the accompanying drawings so that those skilled in the art can implement the invention with reference to the description.

[0023] It should be understood that the terms such as “having”, “including” and “comprising” used herein do not exclude the existence or addition of one or more other elements or combinations thereof.

[0024] like Figure 1 As shown, an embodiment of the present invention provides a method for improving the utilization rate of a closed test site for autonomous driving, including: S10, digitizing the road network of the closed test site into sections, each section including: ID, section latitude and longitude information, direction and two end nodes, and the status bit of each section is: 1 or 0, where 1 indicates busy and 0 indicates idle; S20, when the status bit of the road section is 0, the test is allowed, and the occupied space sequence of the test vehicle is determined according to the status bits of each road section, and the status bits of all occupied road sections are set from 0 to 1, wherein the occupied space sequence is composed of the road section ID of the driving trajectory of the test vehicle; S30, constructing a time dictionary to record the length of time that the test vehicle will occupy each road section during its test; S40. Test the test vehicle according to the sequence of occupied spaces; S401. The test platform obtains the position of the vehicle according to the GPS device of the test vehicle, and matches it to the nearest road section according to the distance between the position of the vehicle and each road section; S402. When the test vehicle travels to a road section, the length of time occupied on the road section is counted down at the same time; S403. When the countdown ends, the status bit of the road section is reset from 1 to 0.

[0025] In the above embodiment, the closed test site may contain a variety of different types of roads, such as straight roads, curves, uphill and downhill sections, etc. When the road network of the closed test site is digitized, a unique ID is assigned to each section. For example, the site is divided into multiple areas such as A, B, and C using the coding method of area code-section number, and the first section ID of area A is set to A-001. The longitude and latitude information of the section is recorded in detail, accurate to six decimal places, such as the longitude and latitude of section A-001 is (30.123456 north latitude, 118.654321 east longitude). The direction of the section is clarified, such as north-south, east-west, etc., as well as the nodes at both ends, which are marked as node A1, node B1, etc., and the initial state bits of all sections are set to 0, indicating idle. For example, a test vehicle (numbered V001) submits a test application, and the test platform obtains the current status bits of each road section and finds that the status bits of A-001, A-002, and A-003 are 0 (idle). According to the preset driving trajectory planning of the test vehicle, the occupied space sequence is determined to be [A-001, A-002, A-003]. The test platform automatically sets the status bits of these three sections from 0 to 1, indicating that these sections have been occupied by the V001 test vehicle.

[0026] According to the test plan and vehicle performance, the estimated driving speed of the V001 test vehicle on the A-001 section is 30km / h (about 8.33m / s). The length of the section is 500 meters. Considering the possible start-up acceleration and temporary deceleration, the buffer time is set to 10 seconds. According to the formula: Section duration = Section length / preset speed measurement + buffer time, the occupancy time of the A-001 section is 500÷8.33+10≈70 seconds; similarly, the occupancy time of the A-002 section is calculated to be 80 seconds, and the occupancy time of the A-003 section is calculated to be 90 seconds. The test platform constructs a time dictionary and records it as: [A-001:70, A-002:80, A-003:90]. For example, the test starts at 9:00, the V001 test vehicle enters the site, and the test platform obtains the vehicle location information in real time at a frequency of 10 times per second through the high-precision GPS device installed on the test vehicle. When the test vehicle starts and approaches the A-001 section, the test platform matches it to the A-001 section based on the distance between the vehicle's position and each section. At this time, the test platform counts down the 70-second occupation time of the A-001 section. During the countdown, the test platform continuously monitors the vehicle's position to ensure that the vehicle is driving normally on the A-001 section. When the countdown ends, if the vehicle has left the A-001 section, the test platform automatically resets the status bit of the A-001 section from 1 to 0. The vehicle continues to drive to the A-002 section, and the test platform counts down the 80-second occupation time of the A-002 section, completing the entire test according to this process.

[0027] In one specific implementation, a safety warning step is also included: If the countdown ends according to the time dictionary, but the test vehicle's GPS device determines that the test vehicle has not completed the test of the road section, that is, the status bit of the road section has been reset to 0, but the road section is still occupied, a level 1 alarm is issued and the authority is exceeded, prohibiting the road section status bit from being 0; If the test vehicle does not drive according to the occupied space sequence of the test scenario, but drives to an irrelevant section of road, an alarm will be issued and the status bit of the irrelevant section will be set to 1; if the status bit of the irrelevant section is already 1, a secondary alarm will be issued to prompt the tester to stop the test.

[0028] Specifically, the first-level alarm is issued and the authority is exceeded, and the section status position is prohibited to be 0. Specifically, after the first-level alarm is triggered, the test platform automatically exceeds the authority and forces the section status bit to be kept at 1. The vehicle status needs to be manually confirmed and unlocked before the section can be reallocated. The unauthorized operation is recorded in the test platform; wherein, the first-level alarm includes: prohibiting the section status position to be 0, and forcibly maintaining the status bit at 1; sending an alarm message to the tester, including the current position of the vehicle and abnormal section occupancy information, the test platform locks the section, and prohibits other test tasks from allocating the section; the second-level alarm includes: sending an emergency alarm message to the tester, including conflicting section information and the current position of the vehicle; suggesting that the tester stop the test immediately and check the vehicle status; the test platform automatically suspends all related test tasks.

[0029] In the above-mentioned implementation, in the management of the closed test site for autonomous driving, adding a safety warning step can significantly improve safety. The first-level alarm can effectively prevent vehicle collision accidents. When the countdown ends but the test vehicle has not completed the test, the prohibited road section status bit is reset to 0 to prevent other test vehicles or target vehicles from mistakenly entering the occupied road section. In the case where the autonomous driving test vehicle is traveling at a high speed, this alarm method can greatly reduce the risk of vehicle collision and ensure the life safety of the test personnel and the safety of the test equipment. In the case that the test vehicle deviates from the predetermined driving route and enters an irrelevant road section, the test platform will promptly alarm and take different measures according to the status bit of the irrelevant road section. If the status bit is 0, it is set to 1. If it is already 1, a second-level alarm is issued and the test personnel are prompted to stop the test. This processing method can timely detect and stop abnormal driving behavior, avoid conflicts in driving routes between different test vehicles, and ensure the orderliness and safety of vehicle driving in the entire test site. Therefore, the safety warning step adds abnormal handling capabilities to the entire closed test site test platform for autonomous driving, and enhances the stability and reliability of the test platform. When emergencies such as vehicle test timeout or driving abnormalities occur, the test platform can automatically respond and take corresponding measures to reduce the cost of manual intervention and ensure the smooth progress of the test.

[0030] For example, there are multiple test groups conducting tests at the same time, namely test group A and test group B. In test group A, there is a test vehicle numbered A-01, and the occupied space sequence of its test task plan is [R-001, R-002, R-003]; in test group B, there is a test vehicle numbered B-01, and its occupied space sequence is [R-004, R-005, R-006]. Test vehicle A-01 starts the test. When entering the R-001 section, the test platform starts the countdown according to the time dictionary, and it is expected that A-01 will occupy the R-001 section for 60 seconds. When the countdown ends, according to the normal process, the status bit of the R-001 section should be reset from 1 (busy) to 0 (idle). However, at this time, the test platform finds through A-01's GPS device that the vehicle is still in the R-001 section and has not completed the test of the section. This results in an abnormality in which the section status bit does not match the actual occupancy situation. The test platform immediately triggered a level one alarm and automatically overrode its authority: on the one hand, it forced the status bit of the R-001 section to remain at 1, prohibiting other test vehicles from occupying the section; on the other hand, it sent an alarm message to all testers in test group A, including the current location of the A-01 vehicle and abnormal occupancy information of the R-001 section.

[0031] After completing the test on the R-001 section, the test vehicle A-01 should have entered the R-002 section according to the occupied space sequence. However, due to an abnormality in the vehicle's automatic driving system, A-01 did not drive to the R-002 section, but drove to the R-007 section, which was not related to this test task. The test platform detected that A-01's driving trajectory had deviated and immediately issued an alarm. At the same time, the status bit of the R-007 section was set from 0 to 1, indicating that the section was abnormally occupied. If the status bit of the R07 section was originally 1 at this time, that is, it had been occupied by other test vehicles, the test platform would further issue a secondary alarm. The secondary alarm sends an emergency alarm message to the test personnel of test group A, including the conflicting section information (R-007 section) and the current location of the A-01 vehicle (precise latitude and longitude), and recommends that the test personnel stop the test immediately and check the status of the A-01 vehicle. In addition, the test platform automatically suspends all related test tasks in test group A to avoid more serious safety issues and test conflicts caused by the abnormal driving of A-01. After receiving the second-level alarm, the testers responded quickly, troubleshooting and handling the A-01 vehicle. After the problem was resolved, they replanned the test tasks and driving routes and resumed the test while ensuring safety.

[0032] In one specific embodiment, it also includes a target vehicle, which is a vehicle that causes a conflict with the test vehicle. The target vehicle is also provided with a vehicle-side GPS device, and the target vehicle is also provided with its own occupied space sequence and occupied road section duration; wherein, the test vehicle includes a plurality of test groups, each test group includes a plurality of test vehicles; the target vehicle also includes a plurality of target vehicle groups, each target vehicle group includes a plurality of target vehicles.

[0033] In the above-mentioned implementation, in the management of the closed test site for autonomous driving, the introduction of target vehicle-related settings and the grouping management of the test vehicles and target vehicles can effectively improve the test safety, optimize the utilization of site resources and improve the test efficiency. The target vehicle is equipped with a vehicle-side GPS device, an occupied space sequence and a road section occupied duration, so that the test platform can monitor the driving trajectory and time arrangement of the target vehicle and the test vehicle in real time. The grouping management of the test vehicles and the target vehicles can enable the test platform to uniformly dispatch and monitor vehicles of different groups. Through the centralized management of the vehicles in each group, the site road resources can be more reasonably allocated according to the test requirements and driving plans of each vehicle. The setting of multiple test groups and multiple target vehicle groups can adapt to complex test scenarios. Vehicles of different groups can be tested in the site in an orderly manner under the unified coordination of the test platform to achieve collaborative operations between multiple vehicles. The test platform can reasonably arrange the test sequence and time interval according to the occupied space sequence and road section occupied duration of each vehicle. For test tasks that may cause conflicts, adjustments are made in advance to avoid waiting or avoiding each other between vehicles and reduce delays during the test process.

[0034] In one specific implementation, the time dictionary is constructed to record the duration of each test vehicle to be occupied on each road section tested, and the duration of the occupied road section is calculated as follows: Section duration = section length / preset speed measurement + buffer time, The preset speed measurement is the expected driving speed of the test vehicle on the road section, and the buffer time is used to cover delays or abnormal situations that may occur during the test.

[0035] In the above implementation, the occupancy time of each road section is accurately calculated, and the stay time of the test vehicle on each road section is reasonably planned. The countdown method can ensure that the road section can be released in time after the vehicle is used, and other vehicles can use it as soon as possible, reducing the overall vacancy time of the site and improving the utilization rate of the site in the time dimension. The setting of the buffer time takes into account the uncertainty in the test process, such as vehicle startup acceleration, temporary deceleration, equipment response delay, etc. It reserves time for these potential delay factors to avoid the actual stay time of the vehicle on the road section exceeding expectations due to unexpected circumstances, thereby ensuring that the test is carried out as planned and reducing confusion and conflicts caused by insufficient time estimation.

[0036] In one specific implementation, the space occupied sequence of the test vehicle is determined according to the status bit of each road section, specifically: The test tasks are sorted according to the task priority. The test tasks with high task priority are assigned to the road sections first. The task priority is determined according to the urgency, complexity and importance of the test task. For each test task, traverse each road segment in the occupied space sequence to be used for its test, and check the status bit of each road segment; If the status bit of each road section is 0, it is assigned to the test task and the status bit of each road section is set to 1; If at least one of the road segments in the status bit of each road segment is 1, the available time of the road segment is calculated according to the countdown information in the time dictionary, and it is decided whether to wait or choose an alternative road segment; If multiple test tasks compete for the same road section, conflicts are resolved based on task priority. High-priority tasks take up the road section first, while low-priority tasks wait or re-plan the road section.

[0037] Among them, the determination of the task priority includes: calculating the priority score of each test task through a weighted algorithm, wherein the urgency, complexity and importance are respectively assigned different weights; sorting the test tasks according to the priority scores, and giving priority to assigning sections to tasks with high priority scores.

[0038] In the above implementation, the task priority is determined according to the urgency, complexity and importance of the test task, so that the key test tasks can be carried out with priority. For tasks involving new technology verification and emergency safety problem testing, they can obtain road section resources first because of their high priority, avoiding delays of important tests due to insufficient resources and improving the rationality of resource utilization. When allocating road sections, the road section status bits are traversed and checked. If the road section is idle, it is directly allocated to reduce waiting time. When the road section is occupied, the available time is calculated according to the time dictionary, which helps the test task to reasonably plan the waiting time or choose an alternative road section, avoid wasting time due to blind waiting, make the test process more compact and efficient, and speed up the overall test progress. When multiple tasks compete for the same road section, they are allocated according to priority, high-priority tasks are occupied first, and low-priority tasks choose to wait or re-plan, which avoids low-priority tasks occupying road section resources for a long time. Exemplarily, the test task can be a functional test, such as verifying the accuracy, reliability and stability of various sensors under different environmental conditions; verifying the path planning algorithm and control algorithm of the autonomous driving vehicle, including simulating different traffic scenarios, such as crossing, driving around the island, overtaking, etc., to verify whether the algorithm can accurately analyze the road conditions, plan a reasonable driving path and stably control the vehicle driving, etc. The test task can also be a safety test, a compatibility test, etc. For the determination of priority, for example: there are three test tasks, namely test task A, test task B and test task C. Test task A: The urgency score is 9 points (out of 10 points), the complexity score is 8 points, and the importance score is 9 points, then the priority score = 9×0.5 + 8×0.3 + 9×0.2 = 4.5 + 2.4 + 1.8 = 8.7 points. Test task B: The urgency score is 3 points, the complexity score is 4 points, and the importance score is 5 points. Priority score = 3×0.5 + 4×0.3 + 5×0.2 = 1.5 + 1.2 + 1 = 3.7 points. Test Task C: The urgency score is 4 points, the complexity score is 8 points, and the importance score is 8 points. Priority score = 4×0.5 + 8×0.3 + 8×0.2 = 2 + 2.4 +1.6 = 6 points. The order of priority scores is: Test Task A> Test Task C> Test Task B. For the determination of the occupied space sequence and the allocation of sections, for example: Test Task A: Its occupied space sequence is planned as [A-001, A-003, A-005]. The test platform traverses these sections and finds that the status bits of A-001, A-002, and A-003 are all 0, so these sections are allocated to Test Task A, and the status bits of A-001, A-002, and A-003 are set from 0 to 1. The test vehicle of Test Task A begins to enter the field test. Test task B: The occupied space sequence is planned to be [A-002, A-004].The test platform checks that the status bits of A-002 and A-004 are both 0, and assigns these two sections to test task B. The status bits are also set from 0 to 1, and the test vehicle of test task B starts the test. Test task C: The occupied space sequence is planned as [A-003, A-004]. When checking, the test platform finds that the status bit of A-003 is 1 (occupied by test task A), and the status bit of A-004 is also 1 (occupied by test task B). Based on the countdown information of test task A in A-003 in the time dictionary, the test platform calculates that A-003 is available for 5 minutes, and test task C decides to wait. At the same time, for A-004, test task C calculates that it will take 10 minutes for test task B to complete the test, and the waiting time is too long, so it chooses an alternative section and re-plans the occupied space sequence to [A-003, A-006] (assuming that the status bit of A-006 is 0). When test task A completes the test of section A-003 and the status bit of A-003 changes to 0, the test vehicle of test task C enters A-003 for testing.

[0039] In one specific implementation, the duration of each test vehicle occupying a road section recorded in the time dictionary is a dynamic time dictionary, specifically: S301. The speed and acceleration of the test vehicle are acquired in real time by using a speed sensor and an acceleration sensor mounted on the test vehicle, and the acquired speed and acceleration data are simultaneously transmitted to the test platform in real time.

[0040] S302. Collect road condition information in real time through cameras and road condition sensors deployed at the test site.

[0041] S303: Construct a training model for predicting road section duration.

[0042] The construction of the predicted road section duration training model is specifically as follows: A. Collect historical data information of the test vehicle, including driving speed, acceleration, road condition information and actual road duration on different road sections; B. Extract the road section type feature, weather condition feature and time period feature from the collected historical data information. The road section type is divided into: curve, straight road, uphill and downhill; the weather condition is divided into: sunny, rainy, snowy and cloudy; the time period is divided into morning, afternoon and evening; C. Use the long short-term memory network model to predict road section duration.

[0043] S304, inputting the acquired real-time speed, acceleration and road condition information into the predicted section duration training model to obtain the predicted section duration; S305: If the difference between the predicted segment duration and the segment duration preset in the time dictionary is greater than a threshold, the test platform updates the segment duration in the time dictionary. The threshold can be specifically set according to actual conditions, and for example, the threshold can be 10 seconds.

[0044] In the above implementation, the vehicle speed, acceleration and road condition information are obtained in real time, and the predicted road section duration training model is used for analysis. When the predicted duration differs greatly from the preset duration, the time dictionary is updated in time, so that the test personnel can know the possible changes in the test progress in advance, adjust the test plan in advance, avoid waiting or delays caused by inaccurate time estimation, and improve the overall test efficiency. The dynamic update of the time dictionary enables the test platform to have a more accurate grasp of the vehicle's occupation time in each road section. The test platform can arrange the routes and times of other test vehicles more reasonably according to the real-time situation, reduce the idleness and waste of site resources, and improve the utilization rate of the site in time and space dimensions. Considering the influence of various factors such as road section type, weather conditions and time period on the vehicle driving time, through the feature extraction of historical data and the prediction of the long short-term memory network model, the vehicle's road section driving time under different conditions can be more accurately estimated, providing a more accurate time reference for the test, making the test results more reliable and scientific. The dynamic time dictionary can adapt to various changes in the test process, such as vehicle performance fluctuations, temporary changes in road conditions, etc. Timely updating of the time dictionary ensures that the system is always managed and scheduled based on the latest information, enhancing the adaptability and flexibility of the entire test management system.

[0045] Specifically, the test platform collected a large amount of driving data of past test vehicles on different sections of the site, including different weather conditions, time periods and section types. For example, on a sunny morning, a test vehicle drove at a speed of 30m / s on a straight road, with acceleration stable at 0, and the actual section length was 60 seconds; on a rainy afternoon, another test vehicle drove at a speed of 15m / s on a curve, with acceleration fluctuating, and the actual section length was 80 seconds, etc. Feature extraction was performed on the collected historical data. For the section type, the sections were divided into curves, straight roads, uphill and downhill; weather conditions were divided into sunny days, rainy days, snowy days, and cloudy days; time periods were divided into morning, afternoon, and evening. For example, for the data of driving on a straight road on a sunny morning, the section type feature was straight road, the weather condition feature was sunny, and the time period feature was morning. The long short-term memory network model (LSTM) was used to predict the section length. The extracted feature data and the corresponding actual section length were used as training data to train the LSTM model so that it could learn the relationship between different factors and section length. The current real-time speed (25m / s), acceleration (0.5m / s²) of the test vehicle V001 and the collected road condition information (water on the road surface) are input into the trained prediction section duration training model. After calculation, the model predicts that the driving time of V001 on the current section is 70 seconds. In the time dictionary, the original preset driving time of V001 on this section is 60 seconds. Since the difference between the predicted section duration of 71 seconds and the preset duration of 60 seconds is greater than the set threshold (assuming the threshold is 10 seconds), the test platform determines that the section duration in the time dictionary needs to be updated. Therefore, the test platform updates the duration of V001 on this section in the time dictionary to 71 seconds.

[0046] In one specific implementation, it also includes: after the digitization of the road section is completed, the test platform generates a road network topology map for visually displaying the connection relationship and status position of each road section; the road network topology map is updated in real time to reflect the current status of each road section.

[0047] In the above implementation, the road network topology map can display the connection relationship and status of each road section in an intuitive graphical form, so that the test site manager can clearly understand the usage of the entire site. By observing the road network topology map, the manager can quickly determine which road sections are idle and which are in use, and then reasonably plan new test tasks and optimize site resource allocation.

[0048] The number of devices and processing scales described here are used to simplify the description of the present invention. Applications, modifications and variations of the present invention will be obvious to those skilled in the art.

[0049] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and the implementation modes, and they can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and the illustrations shown and described herein.

Claims

1. A method for improving the utilization rate of a closed test site for autonomous driving, characterized in that: include: The road network of the closed test site is digitized into sections. Each section includes: ID, section longitude and latitude information, direction and two end nodes. The status bit of each section is: 1 or 0, where 1 means busy and 0 means idle; When the status bit of the road section is 0, the test is allowed, and the occupied space sequence of the test vehicle is determined according to the status bits of each road section, and the status bits of all occupied road sections are set from 0 to 1, wherein the occupied space sequence is composed of the road section ID of the driving trajectory of the test vehicle; Construct a time dictionary to record the length of time that the test vehicle will occupy on each road section during its test; The test vehicle is tested according to the sequence of occupied space. The test platform obtains the position of the vehicle based on the GPS device of the test vehicle, and matches it to the nearest section based on the distance between the vehicle's position and each section. When the test vehicle travels to a section, the length of time occupied on the section is counted down at the same time. When the countdown ends, the status bit of the section is reset from 1 to 0.

2. The method for improving the utilization rate of the closed test site for autonomous driving according to claim 1, characterized in that: Also includes safety warning steps: If the countdown ends according to the time dictionary, but the test vehicle's GPS device determines that the test vehicle has not completed the test of the road section, that is, the status bit of the road section has been reset to 0, but the road section is still occupied, a level 1 alarm is issued and the authority is exceeded, prohibiting the road section status bit from being 0; If the test vehicle does not drive according to the occupied space sequence of the test scenario, but drives to an irrelevant section of road, an alarm will be issued and the status bit of the irrelevant section will be set to 1; if the status bit of the irrelevant section is already 1, a secondary alarm will be issued to prompt the tester to stop the test.

3. The method for improving the utilization rate of the closed test site for autonomous driving according to claim 2, characterized in that: Also included is a target vehicle, which is a vehicle that conflicts with the test vehicle, the target vehicle is also provided with a vehicle-side GPS device, and the target vehicle is also provided with its own occupied space sequence and occupied road section duration; The test vehicle includes a plurality of test groups, each of which includes a plurality of test vehicles; the target vehicle also includes a plurality of target vehicle groups, each of which includes a plurality of target vehicles.

4. The method for improving the utilization rate of the closed test site for autonomous driving according to claim 1, characterized in that: The time dictionary is constructed to record the duration of each test vehicle's occupancy on each road section tested. The duration of the road section occupied is calculated as follows: Section duration = section length / preset speed measurement + buffer time, The preset speed measurement is the expected driving speed of the test vehicle on the road section, and the buffer time is used to cover delays or abnormal situations that may occur during the test.

5. The method for improving the utilization rate of the closed test site for autonomous driving according to claim 3, characterized in that: The space occupied sequence of the test vehicle is determined according to the status bit of each road section, specifically: The test tasks are sorted according to the task priority. The test tasks with high task priority are assigned to the road sections first. The task priority is determined according to the urgency, complexity and importance of the test task. For each test task, traverse each road segment in the occupied space sequence to be used for its test, and check the status bit of each road segment; If the status bit of each road section is 0, it is assigned to the test task and the status bit of each road section is set to 1; If at least one of the road segments in the status bit of each road segment is 1, the available time of the road segment is calculated according to the countdown information in the time dictionary, and it is decided whether to wait or choose an alternative road segment; If multiple test tasks compete for the same road section, conflicts are resolved based on task priority. High-priority tasks take up the road section first, while low-priority tasks wait or re-plan the road section.

6. The method for improving the utilization rate of a closed autonomous driving test site according to claim 4, characterized in that: The duration of each test vehicle occupying the road section recorded in the time dictionary is a dynamic time dictionary, specifically: The speed and acceleration of the test vehicle are acquired in real time by using the speed sensor and acceleration sensor installed on the test vehicle, and the acquired speed and acceleration data are transmitted to the test platform in real time; The cameras and road condition sensors deployed at the test site collect road condition information in real time; Construct a training model for predicting road section duration; Inputting the acquired real-time speed, acceleration and road condition information into the predicted section duration training model to obtain the predicted section duration; If the difference between the predicted section duration and the preset section duration in the time dictionary is greater than a threshold, the test platform updates the section duration in the time dictionary.

7. The method for improving the utilization rate of the closed test site for autonomous driving according to claim 6, characterized in that: The construction of the predicted road section duration training model is specifically as follows: Collect historical data information of the test vehicle, including driving speed, acceleration, road condition information and actual road duration on different road sections; The collected historical data information is used to extract road section type features, weather condition features, and time period features. The road section types are divided into: curves, straight roads, uphill and downhill; the weather conditions are divided into: sunny, rainy, snowy, and cloudy; and the time periods are divided into morning, afternoon, and evening. The long short-term memory network model is used to predict the road section duration.

8. The method for improving the utilization rate of a closed autonomous driving test site according to claim 5, characterized in that: The determination of the task priority includes: calculating the priority score of each test task through a weighted algorithm, wherein the urgency, complexity and importance are respectively assigned different weights; sorting the test tasks according to the priority scores, and assigning road sections first to tasks with high priority scores.

9. The method for improving the utilization rate of the closed test site for autonomous driving according to claim 2, characterized in that: The first-level alarm is carried out and the authority is exceeded, and the road section status position is prohibited to be 0. Specifically, after the first-level alarm is triggered, the test platform automatically exceeds the authority and forces the road section status bit to be kept at 1. The road section can be reallocated only after the vehicle status is manually confirmed and unlocked. The unauthorized operation is recorded in the test platform; wherein, the first-level alarm includes: prohibiting the road section status position to be 0, forcibly keeping the status bit at 1; sending an alarm message to the tester, including the current position of the vehicle and abnormal road section occupancy information, the test platform locks the road section, and prohibits other test tasks from allocating the road section; The secondary alarm includes: sending emergency alarm information to the tester, including conflicting road section information and the current location of the vehicle; suggesting that the tester stop the test immediately and check the vehicle status; the test platform automatically suspends all related test tasks.

10. The method for improving the utilization rate of a closed autonomous driving test site according to claim 1, characterized in that: Also includes: After the digitization of the road section is completed, the test platform generates a road network topology map to visualize the connection relationship and status of each road section; The road network topology map is updated in real time to reflect the current status of each road section.

Images