Driving scene instance determination method and apparatus

Abstract

The present disclosure provides a driving scene instance determination method and device, electronic equipment, storage medium and an autonomous vehicle, relates to the technical field of autonomous driving, in particular to the technical field of autonomous driving scene. The specific implementation scheme is: determining a first driving scene segment in real road test data; performing logical combination based on the first driving scene segment to obtain a second driving scene segment; adjusting the time domain of the first driving scene segment and / or the second driving scene segment to determine a driving scene instance. Through the present disclosure, more abundant and comprehensive scene instances can be provided for algorithm model iteration and version gray test of autonomous driving.

Description

Technical Field

[0001] This disclosure relates to the field of autonomous driving technology, and more particularly to the field of autonomous driving scenario technology, specifically to a method, apparatus, electronic device, storage medium, and autonomous vehicle for determining driving scenario instances. Background Technology

[0002] Before being applied to autonomous vehicles, autonomous driving systems need to undergo simulation testing. This simulation testing can be a closed-loop simulation test of the algorithms for autonomous driving perception, decision-making, planning, and control, thereby meeting the requirements of autonomous driving testing.

[0003] Driving scenario libraries are the foundation of autonomous driving simulation testing; therefore, the autonomous driving scenarios constructed during the simulation testing process are particularly important. Summary of the Invention

[0004] This disclosure provides a method, apparatus, electronic device, storage medium, and autonomous vehicle for determining driving scenario instances.

[0005] According to a first aspect of this disclosure, a method for determining a driving scenario instance is provided, the method comprising:

[0006] Identify a first driving scenario segment from real road test data; logically combine the first driving scenario segment to obtain a second driving scenario segment; adjust the time domain of the first driving scenario segment and / or the second driving scenario segment to determine a driving scenario instance.

[0007] According to a second aspect of this disclosure, a driving scenario instance determination apparatus is provided, the apparatus comprising:

[0008] The determining module is used to determine a first driving scene segment in real road test data; the combining module is used to logically combine the first driving scene segment to obtain a second driving scene segment; the determining module is also used to adjust the time domain of the first driving scene segment and / or the second driving scene segment to determine a driving scene instance.

[0009] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0010] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the first aspect.

[0011] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method according to the first aspect.

[0012] According to a fifth aspect of this disclosure, a computer product is provided, including a computer program that, when executed by a processor, implements the method according to the first aspect.

[0013] According to a sixth aspect of this disclosure, an autonomous vehicle is provided, including electronic equipment as described in the third aspect.

[0014] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0015] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0016] Figure 1 This is a schematic diagram of the application environment according to the embodiments of this disclosure;

[0017] Figure 2 A flowchart illustrating a method for determining a driving scenario instance provided in an embodiment of this disclosure is shown.

[0018] Figure 3 A flowchart illustrating a method for obtaining driving scenario instances provided in an embodiment of this disclosure is shown.

[0019] Figure 4 A schematic diagram of a method for obtaining driving scenario instances provided in an embodiment of this disclosure is shown;

[0020] Figure 5 A flowchart illustrating a driving scenario combination method provided in an embodiment of this disclosure is shown;

[0021] Figure 6 A schematic diagram of a driving scenario combination provided by an embodiment of this disclosure is shown;

[0022] Figure 7 A flowchart illustrating a method for time-domain adjustment of a driving scene segment provided in an embodiment of this disclosure is shown.

[0023] Figure 8 A schematic diagram of an adjusted driving scene segment provided in an embodiment of this disclosure is shown;

[0024] Figure 9 This diagram illustrates a structural schematic of a driving scenario instance determination device provided in an embodiment of the present disclosure;

[0025] Figure 10 A schematic block diagram of an example electronic device 1000 that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0026] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0027] Before an autonomous driving system can be applied to an autonomous vehicle, it needs to undergo simulation testing. This simulation testing can be a closed-loop simulation test of algorithms for autonomous driving perception, decision-making, planning, and control, thereby meeting the requirements of autonomous driving testing.

[0028] The discovery of autonomous driving scenario instances is necessary during simulation testing. These instances are crucial for the iteration of autonomous driving algorithms and the execution of simulation tests.

[0029] In related technologies, autonomous driving simulation testing mainly involves constructing a virtual scenario library to simulate and test autonomous driving algorithms such as perception, decision-making, planning, and control, thereby meeting the requirements of autonomous driving testing. The scenario library is used to store instances of autonomous driving scenarios.

[0030] However, the construction of autonomous driving scenario sets in related technologies, besides enriching autonomous driving scenarios with dangerous driving and human intervention cases, mainly involves constructing virtual road test driving scenarios. Virtual road test driving scenarios cannot reflect real road structures and various complex traffic elements, and have few driving scenario instances, which is not conducive to the simulation testing of autonomous driving systems.

[0031] Based on this, this disclosure provides a method and apparatus for determining driving scenario instances, proposing to acquire driving scenarios based on real road test data, making the obtained driving scenario instances more realistic. Furthermore, it proposes that multiple existing driving scenarios can be combined logically to obtain more driving scenario instances. This solves the problems of scenario realism, scenario diversity, and scenario instance rationalization. Moreover, the method for determining road test driving scenarios based on autonomous driving road test data can provide richer and more comprehensive scenario instances for autonomous driving algorithm model iteration and version gray-scale testing.

[0032] The driving scenario instance determination method provided in this application can be applied to, for example... Figure 1In the application environment shown, terminal 101 communicates with server 102 via a network. Terminal 101 can be used to acquire real road test data, and server 102 is used to determine driving scenario instances. Terminal 101 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices, and server 102 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0033] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0034] Figure 2 A flowchart illustrating a method for determining driving scenario instances provided in an embodiment of this disclosure is shown, as follows: Figure 2 As shown, the method may include:

[0035] In step S201, the first driving scenario segment in the real road test data is determined.

[0036] In this embodiment of the disclosure, a portion of real-world road test data during vehicle operation can be acquired. This real-world road test data can be sensor-based data or video data. The vehicle can be either a non-autonomous vehicle or an autonomous vehicle.

[0037] From real roadside data, identify the required driving scenario segments. For example, driving scenario segments such as the main vehicle encountering an obstacle vehicle exiting the park, or encountering pedestrians crossing when turning left at an intersection.

[0038] For ease of distinction, this disclosure refers to the driving scenario segment obtained from real road test data as the first driving scenario segment.

[0039] In step S202, the second driving scene segment is obtained by logically combining the first driving scene segment.

[0040] In this embodiment of the disclosure, driving scene segments (i.e., the first driving scene segment) obtained from real road test data can be combined to obtain other required driving scene segments. It should be noted that this disclosure refers to the driving scene segment obtained by combining the first driving scene segment at least once as the second driving scene segment.

[0041] In step S203, the time domain of the first driving scene segment and / or the second driving scene segment is adjusted to determine the driving scene instance.

[0042] In this embodiment of the disclosure, the time domain of the first driving scene segment and / or the second driving scene segment can be adjusted to achieve the rationalization of the first driving scene segment and / or the second driving scene segment instance, so as to obtain the driving scene instance.

[0043] The driving scenario instance determination method provided in this disclosure, which acquires driving scenarios based on real road test data, can produce more realistic driving scenario instances, providing richer and more comprehensive driving scenario instances for autonomous driving algorithm model iteration and version gray-scale testing. By logically combining the first driving scenario fragments, more realistic driving scenario instances can be obtained, reducing the cost of acquiring driving scenario instances.

[0044] In this disclosure, first driving scenario segments can be obtained from real road test data based on the corresponding acquisition strategy.

[0045] Figure 3 This illustration shows a flowchart of a method for obtaining driving scenario instances provided in an embodiment of this disclosure, such as... Figure 3 As shown, the method may include:

[0046] In step S301, the required first driving scene segment is determined, and the strategy for acquiring the first driving scene is determined.

[0047] In step S302, based on the strategy, a first driving scenario segment is determined from real road test data.

[0048] In this embodiment of the disclosure, each first driving scenario segment corresponds to a strategy, and this acquisition can be customized. The corresponding driving scenario segment is acquired from real road test data using a determined strategy. In other words, the strategy for acquiring the driving scenario can be predetermined.

[0049] To reduce costs, the first driving scenario segment identified in this disclosure can be a key road section or a scenario where the main vehicle and obstacles have strong interaction.

[0050] In this disclosure, the process of determining the first driving scenario segment in real road test data can be achieved by using a road test data frame playback method and writing an acquisition strategy to recall the temporal information of the driving scenario segment.

[0051] For example, Figure 4 A schematic diagram of a method for obtaining driving scenario instances provided in an embodiment of this disclosure is shown. Figure 4As shown, the road test frame data is the same as the road test data frame in the above embodiment. Based on the road test frame data and the high-precision map data of the area, a driving scene mining manager is used to acquire a first driving scene fragment based on an acquisition strategy, and store it in the scene library. The first driving scene can also be called an atomic scene, and the acquisition strategy is the atomic scene strategy.

[0052] In this disclosure, the acquired first driving scene fragments can be combined to obtain more driving scene fragments.

[0053] Figure 5 A flowchart illustrating a driving scenario combination method provided in an embodiment of this disclosure is shown, as follows: Figure 5 As shown, the method may include:

[0054] In step S501, the first expression corresponding to the first driving scene segment is obtained.

[0055] In step S502, the first expression is subjected to at least one logical operation based on logical symbols until the desired second expression is obtained.

[0056] In step S503, a second driving scene segment is determined based on the second expression.

[0057] In this embodiment of the disclosure, a new driving scene segment can be determined by logically combining the first driving scene segment to obtain the corresponding driving scene instance.

[0058] In this disclosure, the first driving scene segment can be logically combined based on the first expression and logical symbols corresponding to the first driving scene segment.

[0059] The expression can be understood as a programming language used to describe segments of driving scenarios.

[0060] By logically combining the first expression, a combined expression can be obtained, thereby determining a new expression, and further determining the second driving scene segment corresponding to the new expression (i.e., the second expression).

[0061] In the embodiments of this disclosure, multiple first driving scene segments can be logically combined, or the first driving scene segments and the combined driving scene segments can be combined, or multiple combined driving scene segments can be combined. In other words, all driving scene segments in this disclosure can be combined with at least one other driving scene segment.

[0062] Figure 6 A schematic diagram of a driving scenario combination provided by an embodiment of this disclosure is shown, such as... Figure 6As shown, if the expression of the first driving scene segment includes expression A and expression B. * indicates returning the intersection interval of scene events, + indicates that the scenes have an intersection or are continuous in the time domain, returning the union interval of scene events, - indicates returning the difference interval of scene events, that is, returning the time interval where scene event A occurs and scene event B does not occur, @ indicates that scene event A occurs, and scene event B has an intersection with scene event A or is continuous in the time domain, returning the time interval of scene event A, otherwise returning empty, # indicates that scene event B is returned if scene event A does not occur, otherwise returning empty.

[0063] For example, expression A represents a driving scenario segment where a left turn is made at an intersection between 3 and 5 seconds, and expression B represents a driving scenario segment where a pedestrian crosses the road between 2 and 4 seconds. The expression obtained by A*B can represent a left turn at an intersection between 3 and 4 seconds where a pedestrian crosses the road.

[0064] In this embodiment of the disclosure, the first driving scene segment and the second driving scene segment are data structures. These data structures are used to represent data within a time interval. For example, junction:{start_time=0.1,end_time=5.1} indicates that the main vehicle passed through the intersection between 0.1s and 5.1s.

[0065] In this embodiment of the disclosure, the time domain of the determined first and second driving scenario segments can be adjusted to make the resulting driving scenario segments more accurately used for autonomous driving simulation testing. The time domain to be adjusted can be the start time, end time, and time of transition to the autonomous driving system of the driving scenario segment.

[0066] Figure 7 This illustration shows a flowchart of a driving scene segment temporal domain adjustment method provided in an embodiment of the present disclosure, as follows: Figure 7 As shown, the method may include:

[0067] In step S701, the first start time and the first end time of the first driving scene segment and / or the second driving scene are obtained.

[0068] In step S702, the first start time is adjusted based on the start time of the simulation test to obtain the second start time.

[0069] In step S703, the first end time is adjusted based on the end time of the simulation test to obtain the second end time.

[0070] In step S704, a driving scenario instance is determined based on the second start time and the second end time.

[0071] In this embodiment of the disclosure, it is necessary to obtain the first start time and the first end time of the first driving scenario segment and / or the second driving scenario. The start time includes the driving start reservation time and / or driving verification time. The end time includes the driving end reservation time.

[0072] In this embodiment of the disclosure, the start time of the first driving scenario segment and / or the second driving scenario is determined based on the actual situation, and a reasonableness verification time interval for the start time is determined. Based on the determined start time, the start time is determined by combining the cold start time of the autonomous driving system and the reasonableness verification time interval.

[0073] Specifically, the start time of the first driving scenario segment and / or the second driving scenario is determined based on actual conditions to avoid the main vehicle encountering complex traffic events at the very beginning of the simulation test. A reasonableness verification time interval is used to avoid factors such as collision risks. The end time is used to prevent dangerous and complex traffic events from occurring during the autonomous driving simulation test.

[0074] In this disclosure, the driving scenario instance is an automated driving scenario instance, and the driving scenario instance also includes the autonomous driving start time.

[0075] It should be noted that before the autonomous driving system begins operation, driving decisions can be controlled by human intervention or by previous real-world road test data. Once autonomous driving begins, the system is activated and makes driving decisions, including speed and direction.

[0076] By adjusting the start and end times of driving scene segments, the resulting driving scene instances are made more perfect, increasing the accuracy of testing autonomous driving systems and improving the efficiency of simulation testing for autonomous driving systems.

[0077] Further rationalization primarily involves selecting appropriate start and end points for driving scenario segments. This avoids the main vehicle encountering complex traffic events at the outset during simulation testing, allowing for a cold start process for the vehicle-side model (i.e., the autonomous driving system). Furthermore, the exit from the scenario should not involve any dangerous or complex traffic events, concentrating traffic scenario elements within the extracted time segments. In addition, to better address the vehicle-side cold start issue and obtain more reasonable scenario test results, it is necessary to select an appropriate transition point from manual driving decisions to autonomous driving system control decisions in the early stages of the driving scenario.

[0078] In one embodiment of this disclosure, for the selection of the start time of a driving scene segment, a pre-reserved time for the start of the scene can be defined according to the scene semantics, and a reasonable time point can be selected as the reasonable start time of the scene by comprehensively considering factors such as collision risk within this interval.

[0079] In another embodiment of this disclosure, the selection of the end time of a driving scenario segment can be based on the semantic definition of the scenario, which defines a reserved time after the scenario ends so that the main vehicle can safely exit the test scenario.

[0080] In another embodiment of this disclosure, for the timing of the control execution decision of the autonomous driving system, the open-loop to closed-loop rationality verification interval can be defined according to the scene semantics. Within this interval, factors such as collision risk are comprehensively considered, and a reasonable timing point is selected as the timing of the control execution decision of the autonomous driving system.

[0081] For example, Figure 8 The illustration shows a schematic diagram of an adjusted driving scene segment provided in an embodiment of this disclosure, such as... Figure 8 The diagram includes: a defined autonomous driving scenario segment, a pre-start time for the scenario, a pre-end time for the scenario, a scenario start rationality verification interval, a time interval for the autonomous driving system's control execution decision, a rationalized scenario start time, an open-loop to closed-loop transition time, and a rationalized scenario end time.

[0082] In this embodiment, after determining the driving scenario instance, corresponding tags can be added to the driving scenario instance based on its scenario semantics. The tagged driving scenario instance is then placed in a scenario instance library for use in autonomous driving simulation testing, improving the efficiency of autonomous driving simulation testing.

[0083] In this disclosure, adding corresponding tags to driving scenario instances may include at least one of the following:

[0084] Road structure;

[0085] Main vehicle behavior;

[0086] Road topology details;

[0087] Traffic light status;

[0088] Key obstacle categories;

[0089] Key obstacle behavior;

[0090] Location of key obstacles.

[0091] This disclosure improves the usability of the scenario instance library by adding tags to driving scenario instances.

[0092] Based on and Figure 2 The method shown follows the same principle. Figure 9 A schematic diagram of a driving scenario instance determination device provided in an embodiment of this disclosure is shown, such as... Figure 9 As shown, the driving scenario instance determination device 900 may include:

[0093] The determining module 901 is used to determine a first driving scene segment in real road test data; the combining module 902 is used to logically combine the first driving scene segment to obtain a second driving scene segment; the determining module 901 is also used to adjust the time domain of the first driving scene segment and / or the second driving scene segment to determine a driving scene instance.

[0094] In this embodiment of the disclosure, the determining module 901 is used to determine the required first driving scenario segment and determine the acquisition strategy, wherein the acquisition strategy is the acquisition strategy corresponding to the required first driving scenario segment; based on the acquisition strategy, the first driving scenario segment is determined in real road test data.

[0095] In this embodiment of the disclosure, the combination module 902 is used to obtain a first expression corresponding to the first driving scene segment; perform at least one logical operation on the first expression based on logical symbols until the desired second expression is obtained; and determine a second driving scene segment based on the second expression.

[0096] In this embodiment of the disclosure, the first driving scene segment and the second driving scene segment are data structures; the data structures are used to represent data within a time interval.

[0097] In this embodiment of the disclosure, the determining module 901 is further configured to acquire the first start time and the first end time of the first driving scenario segment and / or the second driving scenario; adjust the first start time based on the start time of the simulation test to obtain a second start time; adjust the first end time based on the end time of the simulation test to obtain a second end time; and determine a driving scenario instance based on the second start time and the second end time.

[0098] In this embodiment of the disclosure, the driving scenario instance is an automated driving scenario instance; the driving scenario instance also includes the autonomous driving start time.

[0099] In this embodiment of the disclosure, the start time includes the start driving reserved time and / or driving verification time; the end time includes the end driving reserved time.

[0100] In this embodiment of the disclosure, the determining module 901 is further configured to add corresponding tags to the driving scene instance based on the scene semantics of the driving scene instance.

[0101] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0102] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0103] Figure 10 A schematic block diagram of an example electronic device 1000 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0104] like Figure 10 As shown, device 1000 includes a computing unit 1001, which can perform various appropriate actions and processes according to a computer program stored in read-only memory (ROM) 1002 or a computer program loaded from storage unit 1008 into random access memory (RAM) 1003. The RAM 1003 may also store various programs and data required for the operation of device 1000. The computing unit 1001, ROM 1002, and RAM 1003 are interconnected via bus 1004. Input / output (I / O) interface 1005 is also connected to bus 1004.

[0105] Multiple components in device 1000 are connected to I / O interface 1005, including: input unit 1006, such as keyboard, mouse, etc.; output unit 1007, such as various types of monitors, speakers, etc.; storage unit 1008, such as disk, optical disk, etc.; and communication unit 1009, such as network card, modem, wireless transceiver, etc. Communication unit 1009 allows device 1000 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0106] The computing unit 1001 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1001 performs the various methods and processes described above, such as the driving scene instance determination method. For example, in some embodiments, the driving scene instance determination method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1008. In some embodiments, part or all of the computer program may be loaded and / or installed on device 1000 via ROM 1002 and / or communication unit 1009. When the computer program is loaded into RAM 1003 and executed by the computing unit 1001, one or more steps of the driving scene instance determination method described above may be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to perform a driving scenario instance determination method by any other suitable means (e.g., by means of firmware).

[0107] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0108] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0109] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0110] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0111] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0112] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0113] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0114] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for determining a driving scenario instance, the method comprising: Determine the required first driving scenario segment and determine the strategy for acquiring the first driving scenario segment, wherein the first driving scenario segment includes key road sections or scenarios involving the main vehicle and strong interaction with obstacles, and each first driving scenario segment corresponds to a strategy; Based on the aforementioned strategy, a first driving scenario segment is determined from real road test data; Based on the first expression and logical symbols corresponding to the first driving scene segment, the first driving scene segment is logically combined to obtain the second driving scene segment; Obtain the first start time and the first end time of the first driving scene segment and / or the second driving scene; The first start time is adjusted based on the cold start time of the autonomous driving system and the reasonableness verification time interval based on simulation test to obtain the second start time. The reasonableness verification time interval is the time interval to avoid collision risk. The first end time is adjusted based on the end driving allowance time from the simulation test to obtain the second end time; Based on the second start time and the second end time, a driving scenario instance is determined; The step of logically combining the first driving scene segment based on the first expression and logical symbols corresponding to the first driving scene segment to obtain the second driving scene segment includes: Obtain the first expression corresponding to the first driving scene segment, where the first expression refers to the programming language used to describe the first driving scene segment; Perform at least one logical operation on the first expression based on the logical symbols until the desired second expression is obtained; Based on the second expression, the second driving scenario segment is determined.

2. The method according to claim 1, wherein, The first driving scene segment and the second driving scene segment are data structures; The data structure is used to represent data within a time interval.

3. The method according to claim 1, wherein, The driving scenario example is an example of an automated driving scenario; The driving scenario examples also include the start time of autonomous driving.

4. The method according to claim 1, wherein, After determining the driving scenario instance, the method further includes: Based on the scene semantics of the driving scene instance, add corresponding tags to the driving scene instance.

5. A driving scenario instance determination device, the device comprising: The determination module is used to determine the required first driving scenario segment and determine the strategy for obtaining the first driving scenario segment. The first driving scenario segment includes key road sections or scenarios with strong interaction between the main vehicle and obstacles. Each first driving scenario segment corresponds to a strategy. Based on the strategy, the first driving scenario segment is determined in real road test data. A combination module is used to logically combine the first driving scene segment based on a first expression and logical symbols corresponding to the first driving scene segment to obtain a second driving scene segment. Specifically, the combination module is used to: obtain the first expression corresponding to the first driving scene segment, wherein the first expression refers to a programming language used to describe the first driving scene segment; perform at least one logical operation on the first expression based on the logical symbols until the required second expression is obtained; and determine the second driving scene segment based on the second expression. The determining module is further configured to acquire the first start time and the first end time of the first driving scenario segment and / or the second driving scenario; adjust the first start time based on the cold start time of the autonomous driving system in the simulation test and the reasonableness verification time interval to obtain a second start time, wherein the reasonableness verification time interval is the time interval for avoiding collision risks; adjust the first end time based on the end driving reservation time in the simulation test to obtain a second end time; and determine a driving scenario instance based on the second start time and the second end time.

6. The apparatus according to claim 5, wherein, The first driving scene segment and the second driving scene segment are data structures; The data structure is used to represent data within a time interval.

7. The apparatus according to claim 5, wherein, The driving scenario example is an example of an automated driving scenario; The driving scenario examples also include the start time of autonomous driving.

8. The apparatus according to claim 5, wherein, The determining module is further configured to: Based on the scene semantics of the driving scene instance, add corresponding tags to the driving scene instance.

9. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-4.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-4.

11. A computer product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-4.

12. An autonomous vehicle, including the electronic equipment as claimed in claim 9.

Images