Automatic driving test method and system based on data twinning

Abstract

The invention discloses an automatic driving test method and system based on data twinning, and the method comprises the steps: forming a simulation traffic environment through a digital twinning simulation platform, and a simulation traffic participant and a to-be-tested simulation vehicle which are located in the simulation traffic environment, detecting the simulated traffic environment and the to-be-detected simulated vehicle by a sensor simulating the to-be-detected simulated vehicle to obtain detection data; an automatic driving instruction is sent to the to-be-tested simulation vehicle through the automatic driving system based on the detection data, and the to-be-tested simulation vehicle is controlled to run in the simulation traffic environment; under the condition that the to-be-tested simulation vehicle has a collision accident, a collision intensity parameter of the collision accident is determined based on the impulse of the to-be-tested simulation vehicle, and the collision intensity parameter is used for representing the severity of loss caused by the collision accident; and obtaining a test result based on the collision intensity parameter. The test result can reflect the driving performance of the automatic driving system more objectively and truly.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and particularly to an autonomous driving test method and system based on digital twin. Background Art

[0002] With the application of digital simulation technology in the field of autonomous driving, it has become increasingly common to use a simulation platform to test an autonomous driving system. Compared with road tests in real scenarios, simulation tests have lower costs, lower safety risks, and higher flexibility. They can be used to test specific scenarios or diverse traffic scenarios.

[0003] The penalty score for collisions in a conventional simulation platform is determined based on the number of collisions and the route completion rate. In real scenarios, a minor scrape usually only affects the appearance of the vehicle and usually causes only a small amount of economic loss. If two vehicles collide at a very high relative speed, there is a high probability of life-threatening danger. If the evaluation method based on the number of collisions and the route completion rate in a conventional simulation platform is adopted, both types of accidents will only be recorded as "one collision", and the impact on the final score is exactly the same. However, the consequences of these two types of accidents are vastly different, and it is obviously unreasonable to give the same penalty score. Summary of the Invention

[0004] In view of the above problems existing in the prior art, this application provides an autonomous driving test method based on digital twin, an autonomous driving test system based on digital twin, and an electronic device. The technical solutions adopted in the embodiments of this application are as follows.

[0005] The first aspect of this application provides an autonomous driving test method based on digital twin, which is used to test an autonomous driving system by using a digital twin simulation platform; the method includes:

[0006] Form a simulated traffic environment, as well as simulated traffic participants and a to-be-tested simulated vehicle located in the simulated traffic environment through the digital twin simulation platform, and simulate the sensors of the to-be-tested simulated vehicle to detect the simulated traffic environment and the to-be-tested simulated vehicle, and obtain detection data;

[0007] Based on the detection data, send an autonomous driving instruction to the to-be-tested simulated vehicle through the autonomous driving system, and control the to-be-tested simulated vehicle to drive in the simulated traffic environment;

[0008] In the case where a collision accident occurs to the to-be-tested simulated vehicle, based on the impulse of the to-be-tested simulated vehicle, determine the collision intensity parameter of the collision accident, and the collision intensity parameter is used to characterize the severity of the loss caused by the collision accident;

[0009] Obtain a test result for characterizing the driving performance of the autonomous driving system based on the collision intensity parameter.

[0010] In some embodiments, when a collision accident occurs to the simulation vehicle to be tested, determining the collision intensity parameter of the collision accident based on the impulse of the simulation vehicle to be tested includes:

[0011] When a collision accident occurs to the simulation vehicle to be tested, determine the amount of change in speed of the simulation vehicle to be tested;

[0012] Based on the amount of change in speed, determine the impulse of the simulation vehicle to be tested;

[0013] Based on the impulse of the simulation vehicle to be tested, determine the collision intensity parameter of the collision accident.

[0014] In some embodiments, determining the collision intensity parameter of the collision accident based on the impulse of the simulation vehicle to be tested includes:

[0015] Based on the impulse, determine the impulse equivalent speed of the simulation vehicle to be tested;

[0016] Based on the impulse equivalent speed, determine the collision intensity parameter of the collision accident.

[0017] In some embodiments, determining the impulse equivalent speed of the simulation vehicle to be tested based on the impulse includes:

[0018] Determine the impulse equivalent speed through the following formula:

[0019] v = 60I / 40000

[0020] Wherein, I represents the impulse; v represents the impulse equivalent speed.

[0021] In some embodiments, determining the collision intensity parameter of the collision accident based on the impulse equivalent speed includes:

[0022] Determine the type of traffic participant involved in the collision accident with the simulation vehicle to be tested;

[0023] Based on the impulse equivalent speed and the type of traffic participant, determine the collision intensity parameter of the collision accident.

[0024] In some embodiments, determining the collision intensity parameter of the collision accident based on the impulse equivalent speed and the type of traffic participant includes:

[0025] When the traffic participant involved in the collision accident with the simulation vehicle to be tested is a vehicle, determine the collision intensity parameter through the following formula:

[0026]

[0027] Among them, Collision intensity represents the collision intensity parameter, and v represents the impulse equivalent velocity.

[0028] In some embodiments, determining the collision intensity parameter of the collision accident based on the impulse equivalent velocity and the type of participating object includes:

[0029] In the case where the traffic participant in the collision accident with the to-be-tested simulation vehicle is a pedestrian, the collision intensity parameter is determined by the following formula:

[0030]

[0031] Among them, Collision intensity represents the collision intensity parameter, and v represents the impulse equivalent velocity.

[0032] In some embodiments, obtaining the test result for characterizing the driving performance of the autonomous driving system based on the collision intensity parameter includes:

[0033] Determine the test score that can characterize the driving performance of the autonomous driving system through the following formula:

[0034] Driving_Score

[0035] =completion_rate×0.8 collision_times

[0036] ×Π(1 - collision_intensity)

[0037] Among them, Driving_Score represents the test score; completion_rate represents the completion degree of the autonomous driving route; collision_times represents the number of collisions; collision_intensity represents the collision intensity parameter.

[0038] The second aspect of this application provides an autonomous driving test system based on digital twin, including a digital twin simulation platform and an autonomous driving system;

[0039] The digital twin simulation platform is configured to: form a simulation traffic environment, as well as simulation traffic participants and a to-be-tested simulation vehicle located in the simulation traffic environment, simulate the sensors of the to-be-tested simulation vehicle to detect the simulation traffic environment and the to-be-tested simulation vehicle, and obtain detection data;

[0040] The autonomous driving system is configured to: based on the detection data, send an autonomous driving instruction to the to-be-tested simulation vehicle, and control the to-be-tested simulation vehicle to travel in the simulation traffic environment;

[0041] The digital twin simulation platform is further configured to: in the case of a collision accident of the to-be-tested simulation vehicle, based on the impulse of the to-be-tested simulation vehicle, determine a collision intensity parameter of the collision accident, where the collision intensity parameter is used to characterize the severity of the loss caused by the collision accident; based on the collision intensity parameter, obtain a test result for characterizing the driving performance of the autonomous driving system.

[0042] A third aspect of this application provides an electronic device, which includes at least a memory and a processor. A program is stored on the memory, and when the processor executes the program on the memory, the method described above is implemented.

[0043] The digital-twin-based autonomous driving test method of the embodiments of this application uses a digital twin simulation platform to test an autonomous driving system. In the case of a collision accident of the to-be-tested simulation vehicle, based on the impulse of the to-be-tested simulation vehicle, a collision intensity parameter of the collision accident is determined. The collision intensity parameter is used to characterize the severity of the loss caused by the collision accident; based on the collision intensity parameter, a test result is determined, and this test result can more objectively and truly reflect the driving performance of the autonomous driving system. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a system architecture diagram of the digital-twin-based autonomous driving test system of the embodiments of this application.

[0045] Figure 2 It is a flowchart of the digital-twin-based autonomous driving test method of the embodiments of this application.

[0046] Figure 3 It is a structural block diagram of the electronic device of the embodiments of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] Reference is made herein to the various schemes and features of this application with reference to the drawings.

[0048] It should be understood that various modifications can be made to the embodiments applied herein. Therefore, the above specification should not be regarded as a limitation, but only as an example of the embodiments. Those skilled in the art will think of other modifications within the scope and spirit of this application.

[0049] The drawings included in the specification and constituting a part of the specification illustrate the embodiments of this application, and together with the general description of this application given above and the detailed description of the embodiments given below, are used to explain the principles of this application.

[0050] These and other features of the present application will become apparent from the following description of the preferred forms of the embodiments given by way of non - limiting examples with reference to the accompanying drawings.

[0051] It should also be understood that although the present application has been described with reference to some specific examples, those skilled in the art can surely realize that many other equivalent forms of the present application should be regarded as being within the scope of protection defined by the present application.

[0052] When combined with the accompanying drawings, the above and other aspects, features, and advantages of the present application will become more apparent in view of the following detailed description.

[0053] Specific embodiments of the present application will be described hereinafter with reference to the accompanying drawings; however, it should be understood that the claimed embodiments are merely examples of the present application and can be implemented in various ways. Well - known and / or repetitive functions and structures are not described in detail to avoid obscuring the present application with unnecessary or redundant details. Therefore, the specific structural and functional details claimed herein are not intended to be limiting, but rather are merely a basis and representative basis for the claims to teach those skilled in the art to use the present application in substantially any suitable detailed structure in a variety of ways.

[0054] This specification may use the phrases "in one embodiment", "in another embodiment", "in yet another embodiment", or "in other embodiments", which may each refer to one or more of the same or different embodiments according to the present application.

[0055] An embodiment of the present application provides an autonomous driving test system based on digital twin. Figure 1 For the system architecture diagram of the autonomous driving test system based on digital twin in the embodiment of the present application, see Figure 1 As shown, the autonomous driving test system based on digital twin in the embodiment of the present application may include a digital twin simulation platform 110 and an autonomous driving system 120.

[0056] The digital twin simulation platform 110 is configured to: form a simulation traffic environment 111, as well as simulation traffic participants 113 and a to - be - tested simulation vehicle 112 located in the simulation traffic environment 111, simulate the sensors of the to - be - tested simulation vehicle 112 to detect the simulation traffic environment 111 and the to - be - tested simulation vehicle 112, and obtain detection data.

[0057] The autonomous driving system 120 is configured to: based on the detection data, send an autonomous driving instruction to the to - be - tested simulation vehicle 112, and control the to - be - tested simulation vehicle 112 to travel in the simulation traffic environment 111.

[0058] The digital twin simulation platform 110 is further configured to: in the case of a collision accident occurring to the to-be-tested simulation vehicle 112, determine a collision intensity parameter of the collision accident based on the impulse of the to-be-tested simulation vehicle 112, where the collision intensity parameter is used to characterize the severity of the losses caused by the collision accident; and obtain a test result for characterizing the driving performance of the autonomous driving system 120 based on the collision intensity parameter.

[0059] Optionally, the digital twin simulation platform 110 may include software modules. By running the software modules, the simulation traffic environment 111, the simulation traffic participants 113, and the to-be-tested simulation vehicle 112 can be formed. The digital twin simulation platform 110 may also include an electronic device for supporting the operation of the software modules. Similarly, the autonomous driving system 120 may also include software modules. Through the software modules, autonomous driving instructions can be sent to the to-be-tested simulation vehicle 112 based on detection data to control the driving of the to-be-tested simulation vehicle 112. The autonomous driving system 120 may also include an electronic device for supporting the operation of the software modules. The above-mentioned electronic devices include but are not limited to servers, workstations, desktop computers, laptop computers, tablet computers, and the like.

[0060] Optionally, the digital twin simulation platform 110 and the autonomous driving system 120 may run on the same electronic device, and the digital twin simulation platform 110 and the autonomous driving system 120 may transmit detection data and autonomous driving instructions based on inter-process communication or inter-system communication. The digital twin simulation platform 110 and the autonomous driving system 120 may also run on different electronic devices. At this time, the digital twin simulation platform 110 and the autonomous driving system 120 may use a wired communication network or a wireless communication network between the electronic devices to transmit detection data and autonomous driving instructions.

[0061] Optionally, an actual urban layout map can be pre-selected, and buildings, roads, traffic signs, etc. in the city can be reproduced based on digital twin technology to form a simulated traffic environment 111. Optionally, traffic routes that are relatively common and prone to traffic accidents can be selected from urban roads. For example, plane intersections, complex lanes, highway sections, overpasses, etc. Plane intersections are one of the most common forms of traffic diversion in the city, mainly three-way and four-way intersections, and generally traffic lights are set to ensure smooth traffic. In order to test the driving performance of the autonomous driving system 120 at different vehicle speeds, a highway and ordinary roads can be introduced into the simulated traffic environment 111, so that the simulated traffic environment 111 can test the driving performance of the autonomous driving system 120 in both high-speed scenarios and low-speed scenarios. Regarding the highway, the auxiliary roads, entrance ramps, and exit ramps of the highway can also be reproduced to be as close as possible to the real traffic environment. For cities with high population density and vehicle density, overpasses are important traffic hubs for quickly diverting traffic by utilizing vertical space. When autonomous vehicles drive in the city, they will inevitably need to pass on overpasses. Therefore, overpasses can also be reproduced in the simulated traffic environment 111. In addition, in order to be closer to the real traffic environment, green belts, bare ground, etc. on both sides of the road can also be reproduced.

[0062] Optionally, the simulated traffic participants 113 may include various objects that may appear in a real traffic environment, such as vehicles, pedestrians, animals, guardrails, traffic cones, etc. The simulated vehicle under test 112 may include, but is not limited to, sedans, SUVs, MPVs, buses, trucks, and so on.

[0063] Optionally, the sensors may include various sensors that can be applied to vehicles and can detect the traffic environment or the position and operating state of the vehicle itself. For example, the sensors may include, but are not limited to, Global Navigation Satellite System (GNSS), Inertial Measurement Unit (IMU), Millimeter Wave Radar (RADAR), Light Detection and Ranging (LiDAR), Camera, and so on. Correspondingly, the detection data may include the position information and motion state information of the simulated vehicle under test 112, as well as the point cloud data and image data of the simulated traffic environment 111, and so on.

[0064] After the autonomous driving system 120 obtains the detection data, it can plan the driving strategy of the to-be-tested simulation vehicle 112 in the simulation traffic environment 111 based on the detection data, and generate an autonomous driving instruction. Based on the communication path between the autonomous driving system 120 and the digital twin simulation platform 110, the autonomous driving instruction is sent to the digital twin simulation platform 110. The digital twin simulation platform 110 controls the to-be-tested simulation vehicle 112 to drive in the simulation environment based on the autonomous driving instruction.

[0065] In the case where a collision accident occurs to the to-be-tested simulation vehicle 112, the digital twin simulation platform 110 can obtain collision information related to the collision accident, such as the mass of the to-be-tested simulation vehicle 112, the change in speed, and the duration of the collision accident. The impulse of the to-be-tested simulation vehicle 112 is determined based on the collision information using the impulse algorithm. Based on the impulse of the to-be-tested simulation vehicle 112, a collision intensity parameter that can characterize the severity of the loss caused by the collision accident is determined. Subsequently, using a pre-selected evaluation algorithm for evaluating the driving performance of the autonomous driving system 120, the test result is determined based on the collision intensity parameter, and this test result can more objectively and truly reflect the driving performance of the autonomous driving system 120.

[0066] In some embodiments, the digital twin simulation platform 110 can be specifically configured to: determine the impulse equivalent speed of the to-be-tested simulation vehicle 112 based on the impulse; and determine the collision intensity parameter of the collision accident based on the impulse equivalent speed.

[0067] When a collision accident occurs, if the to-be-tested simulation vehicle 112 is impacted by the same impulse but has different vehicle models, the losses may not be the same. Simply relying on the impulse is not conducive to unifying the collision losses of vehicles with different models. Therefore, in the case of obtaining the impulse, the impulse equivalent speed of the to-be-tested simulation vehicle 112 can be determined based on the impulse, and the collision intensity parameter of the collision accident can be determined based on the impulse equivalent speed. In this way, the collision losses when vehicles with different models have a collision accident can be unified, making the evaluation of the driving performance of the autonomous driving system 120 more accurate, true, and objective.

[0068] In some embodiments, the impulse equivalent speed can be determined based on the following formula:

[0069] v = 60I / 40000 (1)

[0070] Where, I represents the impulse; v represents the impulse equivalent speed, and the unit is km / h.

[0071] Optionally, a target simulated vehicle can be pre-selected and subjected to a wall collision test at a speed of 60 km / h in a simulated traffic environment 111. By recording the vehicle speed before and after the collision, the speed change of the target simulated vehicle during the collision is obtained. Combined with the weight and momentum theorem of the target simulated vehicle, it is determined that the impulse received by the target simulated vehicle when it hits the wall is approximately 40,000 N·s. When the simulated vehicle 112 to be tested is subjected to an impulse of I during actual driving, we equate the damage received from the collision to hitting the wall at a speed of v=60I / 40,000 (km / h). In this way, the impulses of vehicles of different models can be equivalent to the speed of the target simulated vehicle, and the collision losses of vehicles of different models when a collision accident occurs can be unified.

[0072] In some embodiments, the digital twin simulation platform 110 can be specifically configured to: determine the type of traffic participant that has the collision accident with the simulated vehicle 112 to be tested; and determine the collision severity parameters of the collision accident based on the impulse equivalent velocity and the type of participant.

[0073] When a collision occurs, the same speed or the same impulse, but different types of traffic participants that collide with the simulated vehicle 112, may cause different losses. For example, when the simulated vehicle 112 collides with a person or a vehicle, even if the speed or impulse is the same, the losses and accident mortality rates are different.

[0074] To this end, in the case of a collision accident with the simulated vehicle 112 to be tested, the object type of the traffic object that has a collision accident with the simulated vehicle 112 to be tested can be determined. The object type may include vehicles, humans, animals, fixed objects in the traffic environment, etc. Based on the impulse equivalent velocity and the object type, the collision severity parameter of the collision accident can be determined, in order to more accurately evaluate the severity of the loss caused by the collision accident.

[0075] In some embodiments, the digital twin simulation platform 110 may be specifically configured as follows: when the traffic participant that has the collision accident with the simulated vehicle to be tested 112 is a vehicle, the collision severity parameter is determined by the following formula:

[0076]

[0077] Among them, Collision intensity represents the collision intensity parameter, and v represents the impulse equivalent velocity.

[0078] Optionally, formula (2) may be determined in advance based on the relationship between the speed difference before and after the collision between the vehicles and the accident mortality rate. If the impulse equivalent speed is less than 100 km / h, then based on The formula calculates the collision intensity parameter. According to statistical data, the probability of a fatality is close to 100%. Therefore, if the impulse equivalent speed is greater than or equal to 100 km / h, the collision intensity parameter can be set to 1. In this way, the collision intensity parameter is positively correlated with the probability of a fatality in a collision between vehicles, enabling the collision intensity parameter to truly reflect the severity of the collision accident.

[0079] In some embodiments, the digital twin simulation platform 110 may be specifically configured to: when the traffic participant in the collision accident with the to-be-tested simulation vehicle 112 is a pedestrian, determine the collision intensity parameter through the following formula:

[0080]

[0081] where Collision intensity represents the collision intensity parameter and v represents the impulse equivalent speed.

[0082] According to statistical data, when a vehicle collides with a pedestrian, if the vehicle speed is less than 32 km / h, the probability of a fatality is very small. When the vehicle speed is between 32 km / h and 70 km / h, as the vehicle speed increases, the probability of a fatality increases significantly. When the vehicle speed is greater than 70 km / h, the probability of a fatality is close to 100%. Therefore, when it is determined that the impulse equivalent speed is less than 32 km / h, the collision intensity parameter can be determined based on the formula. If the impulse equivalent speed is greater than or equal to 32 km / h and less than 70 km / h, then the collision intensity parameter can be determined based on the formula. If the impulse equivalent speed is greater than or equal to 70 km / h, the collision intensity parameter can be set to 1. In this way, the collision intensity parameter is positively correlated with the probability of a fatality in a collision between a vehicle and a pedestrian, enabling the collision intensity parameter to truly reflect the severity of the collision accident.

[0083] In some embodiments, the digital twin simulation platform 110 may be specifically configured to: determine the test score that can characterize the driving performance of the autonomous driving system 120 through the following formula:

[0084] Driving_Score=completion_rate×0.8 c1;lision_times ×∏(1 - collision_intensity) (4)

[0085] where Driving_Score represents the test score; completion_rate represents the completion degree of the autonomous driving route; collision_times represents the number of collisions; collision_intensity represents the collision intensity parameter.

[0086] As can be seen from the above formula, in the case where the to-be-tested simulation vehicle 112 has a collision accident, not only can the collision intensity parameter be determined, but also the completion degree of the autonomous driving route and the number of collisions can be determined. Based on the completion degree of the autonomous driving route, the number of collisions, and the collision intensity parameter, the driving performance of the autonomous driving system 120 is comprehensively evaluated by using formula (4), and a test smoothness that can characterize the autonomous driving performance of the autonomous driving system 120 is obtained. In this way, the driving performance of the autonomous driving system 120 can be accurately, objectively, and close to the real traffic scenario.

[0087] The embodiment of the present application also provides a digital-twin-based autonomous driving test method for testing an autonomous driving system on a digital-twin simulation platform. Figure 2 For the flowchart of the digital-twin-based autonomous driving test method of the embodiment of the present application, see Figure 2 As shown, the digital-twin-based autonomous driving test method of the embodiment of the present application may specifically include the following steps.

[0088] S210, form a simulation traffic environment, as well as simulation traffic participants and a to-be-tested simulation vehicle located in the simulation traffic environment through the digital-twin simulation platform, simulate the sensors of the to-be-tested simulation vehicle to detect the simulation traffic environment and the to-be-tested simulation vehicle, and obtain detection data.

[0089] S220, based on the detection data through the autonomous driving system, send an autonomous driving instruction to the to-be-tested simulation vehicle, and control the to-be-tested simulation vehicle to drive in the simulation traffic environment.

[0090] S230, in the case where the to-be-tested simulation vehicle has a collision accident, based on the impulse of the to-be-tested simulation vehicle, determine the collision intensity parameter of the collision accident, and the collision intensity parameter is used to characterize the severity of the loss caused by the collision accident.

[0091] S240, based on the collision intensity parameter, obtain a test result for characterizing the driving performance of the autonomous driving system.

[0092] In some embodiments, in the case where the to-be-tested simulation vehicle has a collision accident, determining the collision intensity parameter of the collision accident based on the impulse of the to-be-tested simulation vehicle includes:

[0093] In the case where the to-be-tested simulation vehicle has a collision accident, determine the speed change amount of the to-be-tested simulation vehicle;

[0094] Based on the speed change amount, determine the impulse of the to-be-tested simulation vehicle;

[0095] Determine the collision intensity parameter of the collision accident based on the impulse of the to-be-tested simulation vehicle.

[0096] In some embodiments, determining the collision intensity parameter of the collision accident based on the impulse of the to-be-tested simulation vehicle includes:

[0097] Based on the impulse, determine the impulse equivalent velocity of the to-be-tested simulation vehicle;

[0098] Based on the impulse equivalent velocity, determine the collision intensity parameter of the collision accident.

[0099] In some embodiments, determining the impulse equivalent velocity of the to-be-tested simulation vehicle based on the impulse includes:

[0100] Determine the impulse equivalent velocity through the following formula:

[0101] v = 60I / 40000

[0102] where I represents the impulse; v represents the impulse equivalent velocity.

[0103] In some embodiments, the determining the collision intensity parameter of the collision accident based on the impulse equivalent velocity includes:

[0104] Determine the type of traffic participant involved in the collision accident with the to-be-tested simulation vehicle;

[0105] Based on the impulse equivalent velocity and the type of traffic participant, determine the collision intensity parameter of the collision accident.

[0106] In some embodiments, the determining the collision intensity parameter of the collision accident based on the impulse equivalent velocity and the type of traffic participant includes:

[0107] In the case where the traffic participant involved in the collision accident with the to-be-tested simulation vehicle is a vehicle, determine the collision intensity parameter through the following formula:

[0108]

[0109] where Collision intensity represents the collision intensity parameter, and v represents the impulse equivalent velocity.

[0110] In some embodiments, the determining the collision intensity parameter of the collision accident based on the impulse equivalent velocity and the type of traffic participant includes:

[0111] In the case where the traffic participant involved in the collision accident with the to-be-tested simulation vehicle is a pedestrian, determine the collision intensity parameter through the following formula:

[0112]

[0113] Among them, Collision intensity represents the collision intensity parameter, and v represents the impulse equivalent velocity.

[0114] In some embodiments, obtaining a test result for characterizing the driving performance of the autonomous driving system based on the collision intensity parameter includes:

[0115] Determining a test score that can characterize the driving performance of the autonomous driving system through the following formula:

[0116] Driving_Score

[0117] = completion_rate × 0.8 collision_times × Π(1 - collision_intensity)

[0118] Among them, Driving_Score represents the test score; completion_rate represents the completion degree of the autonomous driving route; collision_times represents the number of collisions; collision_intensity represents the collision intensity parameter.

[0119] See Figure 3 As shown, an embodiment of the present application also provides an electronic device, including at least a memory 301 and a processor 302. A program is stored on the memory 301, and when the processor 302 executes the program on the memory 301, the method described in any one or more of the above embodiments is implemented.

[0120] An embodiment of the present application also provides a computer-readable storage medium. Computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions in the computer-readable storage medium are executed, the method described in any one or more of the above embodiments is implemented.

[0121] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, an electronic device, a computer-readable storage medium, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. When implemented by software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium.

[0122] The above-mentioned processor may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The above-mentioned PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0123] The above-mentioned memory may include non-permanent memory in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0124] The above-mentioned readable storage medium may be a magnetic disk, an optical disk, a DVD, a USB, a read-only memory (ROM), a random access memory (RAM), etc. The present application does not limit the specific form of the storage medium.

[0125] The above embodiments are only exemplary embodiments of the present application and are not used to limit the present application. The protection scope of the present application is defined by the claims. Those skilled in the art can make various modifications or equivalent replacements within the essence and protection scope of the present application, and such modifications or equivalent replacements should also be regarded as falling within the protection scope of the present application.

Claims

1. A digital-twin-based autonomous driving test method, characterized in that For testing an autonomous driving system using a digital twin simulation platform; the method includes: Forming a simulated traffic environment through the digital twin simulation platform, as well as simulated traffic participants and a to-be-tested simulated vehicle located in the simulated traffic environment, simulating the sensors of the to-be-tested simulated vehicle to detect the simulated traffic environment and the to-be-tested simulated vehicle, and obtaining detection data; Based on the detection data, sending an autonomous driving instruction to the to-be-tested simulated vehicle through the autonomous driving system, and controlling the to-be-tested simulated vehicle to drive in the simulated traffic environment; In the case where a collision accident occurs to the to-be-tested simulated vehicle, determining a collision intensity parameter of the collision accident based on the impulse of the to-be-tested simulated vehicle, where the collision intensity parameter is used to characterize the severity of the loss caused by the collision accident; Based on the collision intensity parameter, obtaining a test result for characterizing the driving performance of the autonomous driving system.

2. The method according to claim 1, wherein In the case where a collision accident occurs to the to-be-tested simulated vehicle, determining a collision intensity parameter of the collision accident based on the impulse of the to-be-tested simulated vehicle, includes: In the case where a collision accident occurs to the to-be-tested simulated vehicle, determining a speed change amount of the to-be-tested simulated vehicle; Based on the speed change amount, determining the impulse of the to-be-tested simulated vehicle; Based on the impulse of the to-be-tested simulated vehicle, determining the collision intensity parameter of the collision accident.

3. The method according to claim 1, wherein Based on the impulse of the to-be-tested simulated vehicle, determining a collision intensity parameter of the collision accident, includes: Based on the impulse, determining an impulse equivalent speed of the to-be-tested simulated vehicle; Based on the impulse equivalent speed, determining the collision intensity parameter of the collision accident.

4. The method according to claim 3, wherein Based on the impulse, determining an impulse equivalent speed of the to-be-tested simulated vehicle, includes: Determining the impulse equivalent speed through the following formula: v = 60I / 40000 Where, I represents impulse; v represents impulse equivalent speed.

5. The method according to claim 3, wherein Based on the impulse equivalent speed, determining a collision intensity parameter of the collision accident, includes: Determining the type of the traffic participant that has the collision accident with the to-be-tested simulated vehicle; Based on the impulse equivalent speed and the type of the traffic participant, determining the collision intensity parameter of the collision accident.

6. The method according to claim 5, wherein Based on the impulse equivalent speed and the type of the traffic participant, determining a collision intensity parameter of the collision accident, includes: In the case where the traffic participant that has the collision accident with the to-be-tested simulated vehicle is a vehicle, determining the collision intensity parameter through the following formula: Where, Collision intensity represents the collision intensity parameter, and v represents the impulse equivalent speed.

7. The method according to claim 5, characterized in that Based on the impulse equivalent speed and the type of the traffic participant, determining a collision intensity parameter of the collision accident, includes: In the case where the traffic participant that has the collision accident with the to-be-tested simulated vehicle is a pedestrian, determining the collision intensity parameter through the following formula: Where, Collision intensity represents the collision intensity parameter, and v represents the impulse equivalent speed.

8. The method according to claim 1, wherein Based on the collision intensity parameter, obtaining a test result for characterizing the driving performance of the autonomous driving system, includes: Determine the test score that can characterize the driving performance of the autonomous driving system through the following formula: Driving_Score =completion_rate×0.8 collision_times ×Π(1 - collision_intensity) where Driving_Score represents the test score; completion_rate represents the completion degree of the autonomous driving route; collision_times represents the number of collisions; and collision_intensity represents the collision intensity parameter.

9. An autonomous driving test system based on digital twin, characterized in that, It includes a digital twin simulation platform and an autonomous driving system; The digital twin simulation platform is configured to: form a simulated traffic environment, as well as simulated traffic participants and a to-be-tested simulated vehicle located in the simulated traffic environment, simulate the sensors of the to-be-tested simulated vehicle to detect the simulated traffic environment and the to-be-tested simulated vehicle, and obtain detection data; The autonomous driving system is configured to: based on the detection data, send autonomous driving instructions to the to-be-tested simulated vehicle, and control the to-be-tested simulated vehicle to drive in the simulated traffic environment; The digital twin simulation platform is further configured to: in the case where a collision accident occurs to the to-be-tested simulated vehicle, determine the collision intensity parameter of the collision accident based on the impulse of the to-be-tested simulated vehicle, and the collision intensity parameter is used to characterize the severity of the loss caused by the collision accident; Based on the collision intensity parameter, obtain a test result for characterizing the driving performance of the autonomous driving system.

10. An electronic device, at least including a memory and a processor, wherein a program is stored on the memory, and is characterized in that The processor implements the method according to any one of claims 1-8 when executing the program on the memory.

Images