Splicing scene road rationality checking method and device, equipment and storage medium

Abstract

The application provides a splicing scene road rationality checking method and device, equipment and storage medium, and the method comprises the steps of rendering a to-be-tested scene in simulation software, controlling a vehicle to start automatic driving from a starting coordinate along a target path, wherein the to-be-tested scene is formed by splicing multiple scenes, and the target path completely covers the roads in the to-be-tested scene; monitoring the change of the vehicle coordinate before the vehicle reaches an ending coordinate; if the change of the vehicle coordinate is abnormal, recording the corresponding vehicle coordinate as an abnormal coordinate, moving the abnormal coordinate by a preset distance in the forward direction of the target path to obtain a connecting coordinate, and controlling the vehicle to start automatic driving from the connecting coordinate along the target path. Through the application, multiple road problems can be determined through one simulation test, thereby improving the efficiency of splicing scene road rationality checking.

Description

Technical Field

[0001] This application relates to the field of intelligent connected vehicle testing technology, specifically to a method, device, equipment, and storage medium for verifying the rationality of roads in spliced ​​scenarios. Background Technology

[0002] In the field of intelligent connected vehicle testing, simulation testing offers significant advantages: flexible test scenario configuration and high scenario coverage; safe testing process, and the ability to reproduce and retest "corner cases"; it enables automated testing and cloud-accelerated simulation testing, which improves testing efficiency and reduces testing costs. It is suitable for testing high-coverage scenarios based on ODC (operational design condition) evaluation requirements. Therefore, simulation testing is a necessary means to comprehensively, efficiently, and objectively evaluate ICVs (Intelligent Connected Vehicles). Scenario-based testing, by pre-setting scenarios, specifically verifies the ability of the vehicle under test to complete a specific goal and task. It systematically organizes safety verification activities in an efficient, objective, repeatable, and scalable manner, and can better handle large-scale, random, and high-risk testing. Therefore, scenario-based simulation testing is a common approach in the industry for using simulation as a pillar to conduct functional and safety verification of ICVs.

[0003] As the automation level of ICV products increases, fragmented scenarios can no longer meet verification needs; continuous regional scenarios are required to verify related autonomous driving functions. When building continuous regional scenarios, due to the parallel work of personnel or the real-time rendering and operation of computers, large amounts of raw data are generally cut into multiple segments. Each segment is built separately, and then the segments are stitched together to form a continuous, large-area regional scenario for product verification.

[0004] Continuous scenes spliced ​​from multiple segments pose a risk of inconsistencies at the splicing points. Common factors affecting testing include significant elevation differences before and after splicing, and the presence of gaps, which could cause the test vehicle to be unable to drive at the splicing point or "fall off" through the gap. Therefore, it is necessary to verify the reasonableness of the road conditions in the spliced ​​scenes.

[0005] The commonly used method is to set an autonomous driving target path along the centerline of the road in the simulation scene software, and configure an autonomous vehicle to drive along the set target path from the starting coordinates. When a problem occurs on the road, the simulation test is stopped, the problematic road is re-stitched, the scene is re-rendered, and after the rendering is complete, the vehicle is reset to the starting coordinates for the next test. This method can verify the rationality of the road, but it is inefficient. Summary of the Invention

[0006] This application provides a method, apparatus, device, and storage medium for verifying the rationality of roads in spliced ​​scenes, which can solve the technical problem of low efficiency in verifying the rationality of roads in spliced ​​scenes in the prior art.

[0007] In a first aspect, embodiments of this application provide a method for verifying the rationality of roads in a spliced ​​scene, the method comprising:

[0008] The test scene is rendered in simulation software, and the vehicle is controlled to perform autonomous driving from the starting coordinates along the target path. The test scene is formed by splicing together multiple scene segments, and the target path completely covers the roads in the test scene.

[0009] Monitor changes in vehicle coordinates before the vehicle reaches the destination coordinates;

[0010] If the vehicle coordinates change abnormally, the corresponding vehicle coordinates are recorded as abnormal coordinates. The abnormal coordinates are moved a preset distance along the direction of the target path to obtain the next coordinates. The vehicle is then controlled to start autonomous driving along the target path from the next coordinates.

[0011] Furthermore, in one embodiment, after the step of monitoring changes in vehicle coordinates before the vehicle reaches the destination coordinates, the method further includes:

[0012] After the vehicle reaches the destination coordinates, if there are abnormal coordinates, the test scene modified based on the abnormal coordinates is obtained, and the steps of rendering the test scene in the simulation software and controlling the vehicle to perform autonomous driving from the starting coordinates along the target path are re-executed. The vehicle speed in the next simulation test is the same as that in the current simulation test.

[0013] Furthermore, in one embodiment, after the step of monitoring changes in vehicle coordinates before the vehicle reaches the destination coordinates, the method further includes:

[0014] After the vehicle reaches the destination coordinates, if there are no abnormal coordinates and the speed of the autonomous driving system in this simulation test is greater than the preset speed, the steps of rendering the test scene in the simulation software and controlling the vehicle to perform autonomous driving along the target path from the starting coordinates will be executed again. In the next simulation test, the speed of the autonomous driving system will be less than the speed of the autonomous driving system in this simulation test.

[0015] Furthermore, in one embodiment, the step of monitoring changes in vehicle coordinates before the vehicle reaches the destination coordinates includes:

[0016] Before the vehicle reaches the destination coordinates, monitor the first distance the vehicle moves in the elevation direction within a preset time period;

[0017] If the first movement distance is greater than or equal to the first threshold, then the change in vehicle coordinates is determined to be abnormal.

[0018] Furthermore, in one embodiment, the step of monitoring changes in vehicle coordinates before the vehicle reaches the destination coordinates includes:

[0019] Before the vehicle reaches the destination coordinates, monitor the second distance the vehicle moves in three-dimensional space within a preset time period;

[0020] If the second movement distance is less than or equal to the second threshold, then the change in vehicle coordinates is determined to be abnormal.

[0021] Secondly, embodiments of this application also provide a device for verifying the rationality of roads in spliced ​​scenes, the device comprising:

[0022] The start control module is used to render the test scene in the simulation software and control the vehicle to perform autonomous driving from the starting coordinates along the target path. The test scene is formed by splicing multiple scene segments, and the target path completely covers the roads in the test scene.

[0023] The coordinate monitoring module is used to monitor changes in the vehicle's coordinates before the vehicle reaches the destination coordinates.

[0024] The anomaly handling module is used to record the corresponding vehicle coordinates as abnormal coordinates if the vehicle coordinates change abnormally. The abnormal coordinates are then moved a preset distance along the forward direction of the target path to obtain the next coordinates, and the vehicle is controlled to start autonomous driving along the target path from the next coordinates.

[0025] Furthermore, in one embodiment, the splicing scene road rationality verification device further includes:

[0026] The first verification module is used to obtain the test scene modified based on the abnormal coordinates after the vehicle reaches the destination coordinates, and re-execute the steps of rendering the test scene in the simulation software and controlling the vehicle to perform autonomous driving along the target path from the starting coordinates. The vehicle speed in the next simulation test is the same as that in the current simulation test.

[0027] Furthermore, in one embodiment, the splicing scene road rationality verification device further includes:

[0028] The second verification module is used to re-execute the steps of rendering the test scene in the simulation software and controlling the vehicle to perform autonomous driving from the starting coordinate along the target path after the vehicle reaches the destination coordinate. If there are no abnormal coordinates and the speed of the autonomous driving in this simulation test is greater than the preset speed, the module will re-execute the steps of rendering the test scene in the simulation software and controlling the vehicle to perform autonomous driving from the starting coordinate along the target path. In the next simulation test, the speed of the autonomous driving will be less than the speed of the autonomous driving in this simulation test.

[0029] Thirdly, this application embodiment also provides a splicing scene road rationality verification device, the splicing scene road rationality verification device includes a processor, a memory, and a splicing scene road rationality verification program stored in the memory and executable by the processor, wherein when the splicing scene road rationality verification program is executed by the processor, the steps of the above-mentioned splicing scene road rationality verification method are implemented.

[0030] Fourthly, this application embodiment also provides a storage medium storing a road rationality verification program for spliced ​​scenes, wherein when the road rationality verification program for spliced ​​scenes is executed by a processor, the steps of the above-mentioned road rationality verification method for spliced ​​scenes are implemented.

[0031] In this application, a test scenario is rendered in simulation software, and a vehicle is controlled to autonomously drive along a target path starting from the initial coordinates. The test scenario is formed by stitching together multiple scene segments, and the target path completely covers the roads within the test scenario. Before the vehicle reaches the endpoint coordinates, changes in the vehicle's coordinates are monitored. If the changes in the vehicle's coordinates are abnormal, the corresponding vehicle coordinates are recorded as abnormal coordinates. The abnormal coordinates are moved a preset distance along the forward direction of the target path to obtain the next coordinates, and the vehicle is controlled to autonomously drive along the target path starting from the next coordinates. Through this application, multiple road problems can be identified through a single simulation test, thereby improving the efficiency of verifying the rationality of roads in the stitched scenario. Attached Figure Description

[0032] Figure 1 This is a flowchart illustrating the method for verifying the rationality of roads in a spliced ​​scene according to one embodiment of this application;

[0033] Figure 2 This is a schematic diagram of the functional modules of the splicing scene road rationality verification device in one embodiment of this application;

[0034] Figure 3 This is a schematic diagram of the hardware structure of the road rationality verification device involved in the splicing scenario in the embodiments of this application. Detailed Implementation

[0035] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0036] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0037] Firstly, embodiments of this application provide a method for verifying the rationality of roads in spliced ​​scenarios.

[0038] Figure 1 A flowchart illustrating the method for verifying the rationality of roads in a spliced ​​scene according to an embodiment of this application is shown.

[0039] Reference Figure 1 In one embodiment, the method for verifying the rationality of roads in a spliced ​​scene includes the following steps:

[0040] S11. Render the scene to be tested in the simulation software and control the vehicle to perform autonomous driving from the starting coordinates along the target path. The scene to be tested is formed by splicing together multiple scene segments, and the target path completely covers the roads in the scene to be tested.

[0041] In this embodiment, the target path completely covers the roads in the scene to be tested, which is wider than the target path coverage in the prior art. It needs to be set not only on the center line of the road in the splicing scene, but also on the road edges.

[0042] Alternatively, the vehicle is an autonomous vehicle that comes with the simulation software.

[0043] S12. Monitor the changes in vehicle coordinates before the vehicle reaches the destination coordinates.

[0044] It is understandable that when there are no problems with the road in the test scenario, the coordinate changes of the vehicle during autonomous driving along the target path can be predicted. Conversely, when the changes in the vehicle's coordinates are abnormal, it indicates that there are problems with the road in the test scenario.

[0045] Optionally, the rules for determining anomalies in vehicle coordinates are preset based on potential road problems.

[0046] S13. If the vehicle coordinates change abnormally, the corresponding vehicle coordinates are recorded as abnormal coordinates. The abnormal coordinates are moved a preset distance along the forward direction of the target path to obtain the next coordinates. The vehicle is then controlled to start automatic driving along the target path from the next coordinates.

[0047] In this embodiment, when the vehicle coordinates change abnormally, the simulation test will not stop. Instead, the abnormal coordinates will be recorded, and the vehicle will be controlled to skip the path after the abnormal coordinates by a preset distance, i.e., the path between the abnormal coordinates and the successor coordinates, and continue to perform autonomous driving along the target path until the vehicle reaches the destination coordinates. The abnormal coordinates recorded in the simulation test are used for scene stitching modification.

[0048] For example, the preset distance is 5m.

[0049] Therefore, in this embodiment, the test scene is rendered in simulation software, and the vehicle is controlled to perform autonomous driving along the target path starting from the starting coordinates. The test scene is formed by stitching together multiple scene segments, and the target path completely covers the roads within the test scene. Before the vehicle reaches the destination coordinates, changes in the vehicle's coordinates are monitored. If the changes in the vehicle's coordinates are abnormal, the corresponding vehicle coordinates are recorded as abnormal coordinates. The abnormal coordinates are moved a preset distance along the direction of travel of the target path to obtain the next coordinates, and the vehicle is controlled to perform autonomous driving along the target path starting from the next coordinates. Through this embodiment, multiple road problems can be identified through a single simulation test, thereby improving the efficiency of verifying the rationality of roads in the stitched scene.

[0050] It's understandable that the higher the speed of an autonomous vehicle, the shorter the simulation test time, but the verification accuracy is also relatively low.

[0051] Furthermore, in one embodiment, after the step of monitoring changes in vehicle coordinates before the vehicle reaches the destination coordinates, the method further includes:

[0052] After the vehicle reaches the destination coordinates, if there are abnormal coordinates, the test scene modified based on the abnormal coordinates is obtained, and the steps of rendering the test scene in the simulation software and controlling the vehicle to perform autonomous driving from the starting coordinates along the target path are re-executed. The vehicle speed in the next simulation test is the same as that in the current simulation test.

[0053] In this embodiment, the presence of abnormal coordinates indicates that the scene under test has road problems under the verification accuracy corresponding to this simulation test. For the modified scene under test, the same autonomous driving speed is used in the two simulation tests before and after the modification to maintain consistent verification accuracy, so as to accurately determine whether the road problems detected in the previous test have been resolved.

[0054] Furthermore, in one embodiment, after the step of monitoring changes in vehicle coordinates before the vehicle reaches the destination coordinates, the method further includes:

[0055] After the vehicle reaches the destination coordinates, if there are no abnormal coordinates and the speed of the autonomous driving system in this simulation test is greater than the preset speed, the steps of rendering the test scene in the simulation software and controlling the vehicle to perform autonomous driving along the target path from the starting coordinates will be executed again. In the next simulation test, the speed of the autonomous driving system will be less than the speed of the autonomous driving system in this simulation test.

[0056] In this embodiment, the absence of abnormal coordinates indicates that the scene under test does not have road problems under the verification accuracy corresponding to this simulation test. The fact that the speed of the autonomous vehicle in this simulation test is greater than the preset speed indicates that the verification accuracy needs to be further improved. By reducing the speed of the autonomous vehicle used in the next simulation test, the verification accuracy can be improved, thereby enabling more precise detection of road problems.

[0057] For example, two sets of simulation tests are performed sequentially on the scenario to be tested. In the first set of simulation tests, the speed of the autonomous vehicle is 5 km / h, and in the second set of simulation tests, the speed of the autonomous vehicle is 1 km / h. The autonomous vehicle starts from the starting coordinate and drives along the target path to the destination coordinate, which is called a simulation test. There are no abnormal coordinates in the last simulation test of each set of simulation tests.

[0058] Furthermore, in one embodiment, the step of monitoring changes in vehicle coordinates before the vehicle reaches the destination coordinates includes:

[0059] Before the vehicle reaches the destination coordinates, monitor the first distance the vehicle moves in the elevation direction within a preset time period;

[0060] If the first movement distance is greater than or equal to the first threshold, then the change in vehicle coordinates is determined to be abnormal.

[0061] In this embodiment, if the first distance the vehicle moves in the elevation direction within a preset time period is greater than or equal to a first threshold, it indicates that the vehicle has "fallen" from the gap, which is used to detect whether there is a gap in the road.

[0062] For example, the vehicle coordinates adopt a spatial rectangular coordinate system. The coordinates of two vehicles collected at a preset time interval are (X1,Y1,Z1) and (X2,Y2,Z2), and the first movement distance is |Z1-Z2|.

[0063] Furthermore, in one embodiment, the step of monitoring changes in vehicle coordinates before the vehicle reaches the destination coordinates includes:

[0064] Before the vehicle reaches the destination coordinates, monitor the second distance the vehicle moves in three-dimensional space within a preset time period;

[0065] If the second movement distance is less than or equal to the second threshold, then the change in vehicle coordinates is determined to be abnormal.

[0066] In this embodiment, if the second movement distance of the vehicle in three-dimensional space within a preset time period is less than or equal to the second threshold, it indicates that the vehicle is abnormally stopped, which is used to detect whether there is an excessive elevation difference on the road.

[0067] For example, the vehicle coordinates use a spatial rectangular coordinate system. The coordinates of two vehicles collected at a preset time interval are (X1,Y1,Z1) and (X2,Y2,Z2), and the second movement distance is [(X1-X2)]. 2 +(Y1-Y2) 2 +(Z1-Z2) 2 ] 0.5 .

[0068] Secondly, this application also provides a device for verifying the rationality of roads in splicing scenarios.

[0069] Figure 2 A schematic diagram of the functional modules of the splicing scene road rationality verification device is shown in one embodiment of this application.

[0070] Reference Figure 2 In one embodiment, the device for verifying the rationality of roads in a spliced ​​scene includes:

[0071] The starting control module 10 is used to render the scene to be tested in the simulation software and control the vehicle to perform autonomous driving from the starting coordinates along the target path. The scene to be tested is formed by splicing multiple scene segments, and the target path completely covers the road in the scene to be tested.

[0072] The coordinate monitoring module 20 is used to monitor changes in the vehicle's coordinates before the vehicle reaches the destination coordinates.

[0073] The anomaly handling module 30 is used to record the corresponding vehicle coordinates as abnormal coordinates if the change in vehicle coordinates is abnormal, move the abnormal coordinates a preset distance along the forward direction of the target path to obtain the successor coordinates, and control the vehicle to start autonomous driving along the target path from the successor coordinates.

[0074] Furthermore, in one embodiment, the device for verifying the rationality of road alignment in a spliced ​​scene also includes:

[0075] The first verification module 40 is used to obtain the test scene modified based on the abnormal coordinates after the vehicle reaches the destination coordinates, and re-execute the steps of rendering the test scene in the simulation software and controlling the vehicle to perform autonomous driving along the target path from the starting coordinates. The vehicle speed in the next simulation test is the same as that in the current simulation test.

[0076] Furthermore, in one embodiment, the device for verifying the rationality of road alignment in a spliced ​​scene also includes:

[0077] The second verification module 50 is used to re-execute the steps of rendering the test scene in the simulation software and controlling the vehicle to perform autonomous driving from the starting coordinate along the target path after the vehicle reaches the destination coordinate. If there are no abnormal coordinates and the speed of the autonomous driving in this simulation test is greater than the preset speed, the next simulation test will have a lower speed of autonomous driving than the current simulation test.

[0078] Furthermore, in one embodiment, the coordinate monitoring module 20 is used for:

[0079] Before the vehicle reaches the destination coordinates, monitor the first distance the vehicle moves in the elevation direction within a preset time period;

[0080] If the first movement distance is greater than or equal to the first threshold, then the change in vehicle coordinates is determined to be abnormal.

[0081] Furthermore, in one embodiment, the coordinate monitoring module 20 is used for:

[0082] Before the vehicle reaches the destination coordinates, monitor the second distance the vehicle moves in three-dimensional space within a preset time period;

[0083] If the second movement distance is less than or equal to the second threshold, then the change in vehicle coordinates is determined to be abnormal.

[0084] The functions of each module in the above-mentioned splicing scene road rationality verification device correspond to the steps in the above-mentioned splicing scene road rationality verification method embodiment, and their functions and implementation processes will not be described in detail here.

[0085] Thirdly, this application provides a splicing scene road rationality verification device, which can be a personal computer (PC), laptop computer, server or other device with data processing function.

[0086] Figure 3 A schematic diagram of the hardware structure of the road rationality verification device for splicing scenarios involved in the embodiments of this application is shown.

[0087] Reference Figure 3 In this embodiment of the application, the device for verifying the rationality of road splicing scenes may include a processor, a memory, a communication interface, and a communication bus.

[0088] The communication bus can be of any type and is used to interconnect the processor, memory, and communication interface.

[0089] The communication interface includes input / output (I / O) interfaces, physical interfaces, and logical interfaces used for interconnecting internal components of the splicing scene road rationality verification equipment, as well as interfaces used for interconnecting the splicing scene road rationality verification equipment with other devices (such as other computing devices or user equipment). Physical interfaces can be Ethernet interfaces, fiber optic interfaces, ATM interfaces, etc.; user equipment can be displays, keyboards, etc.

[0090] Memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0091] The processor can be a general-purpose processor, which can call the splicing scene road rationality verification program stored in the memory and execute the splicing scene road rationality verification method provided in the embodiments of this application. For example, the general-purpose processor can be a central processing unit (CPU). The method executed when the splicing scene road rationality verification program is called can refer to the various embodiments of the splicing scene road rationality verification method of this application, and will not be repeated here.

[0092] Those skilled in the art will understand that Figure 3 The hardware structure shown does not constitute a limitation of this application and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0093] Fourthly, embodiments of this application also provide a storage medium.

[0094] The storage medium of this application stores a road rationality verification program for splicing scenes, wherein when the splicing scene road rationality verification program is executed by the processor, it implements the steps of the splicing scene road rationality verification method as described above.

[0095] The method implemented when the splicing scene road rationality verification procedure is executed can be referred to in the various embodiments of the splicing scene road rationality verification method of this application, and will not be repeated here.

[0096] It should be noted that the sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0097] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus. The terms "first," "second," and "third," etc., are used to distinguish different objects, etc., and do not indicate a sequence, nor do they limit "first," "second," and "third" to different types.

[0098] In the description of the embodiments of this application, terms such as "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a concrete manner.

[0099] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.

[0100] In some processes described in the embodiments of this application, multiple operations or steps are included in a specific order. However, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of this application, or they may be executed in parallel. The sequence number of the operation is only used to distinguish different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.

[0101] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, 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 is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of this application.

[0102] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for verifying the rationality of roads in spliced ​​scenes, characterized in that, The method for verifying the rationality of roads in the spliced ​​scene includes: The test scene is rendered in simulation software, and the vehicle is controlled to perform autonomous driving from the starting coordinates along the target path. The test scene is formed by splicing together multiple scene segments, and the target path completely covers the roads in the test scene. Monitor changes in vehicle coordinates before the vehicle reaches the destination coordinates; If the vehicle coordinates change abnormally, the corresponding vehicle coordinates are recorded as abnormal coordinates. The abnormal coordinates are moved a preset distance along the direction of the target path to obtain the next coordinates. The vehicle is then controlled to start autonomous driving along the target path from the next coordinates. After the vehicle reaches the destination coordinates, if there are no abnormal coordinates and the speed of the autonomous driving vehicle in this simulation test is greater than the preset speed, then the steps of rendering the test scene in the simulation software and controlling the vehicle to perform autonomous driving from the starting coordinates along the target path are executed again. In the next simulation test, the speed of the autonomous driving vehicle is less than the speed of the autonomous driving vehicle in this simulation test. The step of monitoring changes in vehicle coordinates before the vehicle reaches the destination coordinates includes: Before the vehicle reaches the destination coordinates, monitor the first distance the vehicle moves in the elevation direction within a preset time period; If the first movement distance is greater than or equal to the first threshold, then the change in vehicle coordinates is determined to be abnormal. Before the vehicle reaches the destination coordinates, monitor the second distance the vehicle moves in three-dimensional space within a preset time period; If the second movement distance is less than or equal to the second threshold, then the change in vehicle coordinates is determined to be abnormal.

2. The method for verifying the rationality of roads in spliced ​​scenes as described in claim 1, characterized in that, Following the step of monitoring changes in vehicle coordinates before the vehicle reaches the destination coordinates, the method further includes: After the vehicle reaches the destination coordinates, if there are abnormal coordinates, the test scene modified based on the abnormal coordinates is obtained, and the steps of rendering the test scene in the simulation software and controlling the vehicle to perform autonomous driving from the starting coordinates along the target path are re-executed. The vehicle speed in the next simulation test is the same as that in the current simulation test.

3. A device for verifying the rationality of roads in spliced ​​scenes, characterized in that, The splicing scene road rationality verification device includes: The start control module is used to render the test scene in the simulation software and control the vehicle to perform autonomous driving from the starting coordinates along the target path. The test scene is formed by splicing multiple scene segments, and the target path completely covers the roads in the test scene. The coordinate monitoring module is used to monitor changes in the vehicle's coordinates before the vehicle reaches the destination coordinates. The anomaly handling module is used to record the corresponding vehicle coordinates as abnormal coordinates if the changes in vehicle coordinates are abnormal. The abnormal coordinates are moved a preset distance along the forward direction of the target path to obtain the successor coordinates, and the vehicle is controlled to start autonomous driving along the target path from the successor coordinates. The second verification module is used to re-execute the steps of rendering the test scene in the simulation software and controlling the vehicle to perform autonomous driving from the starting coordinate along the target path after the vehicle reaches the destination coordinate. If there are no abnormal coordinates and the speed of the autonomous driving in this simulation test is greater than the preset speed, the next simulation test will be less than the speed of the autonomous driving in this simulation test. The coordinate monitoring module is specifically used for: Before the vehicle reaches the destination coordinates, monitor the first distance the vehicle moves in the elevation direction within a preset time period; If the first movement distance is greater than or equal to the first threshold, then the change in vehicle coordinates is determined to be abnormal. Before the vehicle reaches the destination coordinates, monitor the second distance the vehicle moves in three-dimensional space within a preset time period; If the second movement distance is less than or equal to the second threshold, then the change in vehicle coordinates is determined to be abnormal.

4. The splicing scene road rationality verification device as described in claim 3, characterized in that, The splicing scene road rationality verification device also includes: The first verification module is used to obtain the test scene modified based on the abnormal coordinates after the vehicle reaches the destination coordinates, and re-execute the steps of rendering the test scene in the simulation software and controlling the vehicle to perform autonomous driving along the target path from the starting coordinates. The vehicle speed in the next simulation test is the same as that in the current simulation test.

5. A device for verifying the rationality of roads in spliced ​​scenes, characterized in that, The splicing scene road rationality verification device includes a processor, a memory, and a splicing scene road rationality verification program stored in the memory and executable by the processor, wherein when the splicing scene road rationality verification program is executed by the processor, it implements the steps of the splicing scene road rationality verification method as described in claim 1 or 2.

6. A storage medium, characterized in that, The storage medium stores a road rationality verification program for spliced ​​scenes, wherein when the spliced ​​scene road rationality verification program is executed by the processor, it implements the steps of the spliced ​​scene road rationality verification method as described in claim 1 or 2.

Images