Method, device and electronic equipment for processing autonomous driving simulation data

Abstract

The present disclosure provides a kind of automatic driving simulation data processing method, device and electronic equipment, especially related to artificial intelligence technical field such as automatic driving, intelligent traffic.The specific scheme is: the message type between simulation system and automatic driving system is determined to be transmitted;According to the message type, the data acquisition mode is determined;Based on the data acquisition mode, the data flow transmitted between the simulation system and the automatic driving system is acquired;According to the data flow, the performance of the automatic driving system is determined.Thereby, by processing the data acquired from simulation system and automatic driving system and transmitted between simulation system and automatic driving system, the performance of the automatic driving system can be accurately determined, thereby providing a basis for improving the performance of the automatic driving system, and further providing a reliable basis for actual road test.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, specifically to the field of artificial intelligence technology such as autonomous driving and intelligent transportation, and in particular to a method, apparatus and electronic device for processing autonomous driving simulation data. Background Technology

[0002] With the rapid development of computer technology, fields such as autonomous driving and intelligent transportation have also seen rapid advancements in artificial intelligence. In the safety testing of autonomous driving systems, simulation testing serves as a crucial supplement to actual road testing, and the processing of simulation data is of paramount importance. Summary of the Invention

[0003] This disclosure provides a method, apparatus, and electronic device for processing autonomous driving simulation data.

[0004] This disclosure provides a method for processing autonomous driving simulation data, including:

[0005] Determine the types of messages transmitted between the simulation system and the autonomous driving system;

[0006] Determine the data acquisition mode based on the message type;

[0007] Based on the data acquisition mode, the data stream transmitted between the simulation system and the autonomous driving system is acquired;

[0008] The performance of the autonomous driving system is determined based on the data stream.

[0009] Another aspect of this disclosure provides an apparatus for processing autonomous driving simulation data, comprising:

[0010] The first determining module is used to determine the message type transmitted between the simulation system and the autonomous driving system;

[0011] The second determining module is used to determine the data acquisition mode based on the message type;

[0012] The acquisition module is used to acquire the data stream transmitted between the simulation system and the autonomous driving system based on the data acquisition mode.

[0013] The third determining module is used to determine the performance of the autonomous driving system based on the data stream.

[0014] In another aspect of this disclosure, an electronic device is provided, comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the autonomous driving simulation data processing method described in one aspect of the above embodiment.

[0018] In another aspect of this disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, on which a computer program is stored, the computer instructions being used to cause the computer to execute the method for processing autonomous driving simulation data as described in one aspect of the above-described embodiment.

[0019] In another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method for processing autonomous driving simulation data as described in one aspect of the above-described embodiment.

[0020] The autonomous driving simulation data processing method, apparatus, and electronic equipment disclosed herein can first determine the message type transmitted between the simulation system and the autonomous driving system, then determine the data acquisition mode based on the message type, and then acquire the data stream transmitted between the simulation system and the autonomous driving system based on the data acquisition mode. Finally, the performance of the autonomous driving system can be determined based on the data stream. Therefore, by processing the data acquired from the simulation system and the autonomous driving system and transmitted between them, the performance of the autonomous driving system can be accurately determined, thus providing a basis for improving the performance of the autonomous driving system and, consequently, a reliable basis for actual road testing.

[0021] 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

[0022] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0023] Figure 1 This is a flowchart illustrating a method for processing autonomous driving simulation data according to an embodiment of the present disclosure.

[0024] Figure 2 A flowchart illustrating a method for processing autonomous driving simulation data according to another embodiment of this disclosure;

[0025] Figure 3A A flowchart illustrating a method for processing autonomous driving simulation data, provided as another embodiment of this disclosure;

[0026] Figure 3BA schematic diagram of an autonomous driving system and a simulation system provided in an embodiment of this disclosure;

[0027] Figure 4 A schematic diagram of the structure of an autonomous driving simulation data processing device provided in another embodiment of this disclosure;

[0028] Figure 5 This is a block diagram of an electronic device used to implement the method for processing autonomous driving simulation data according to embodiments of the present disclosure. Detailed Implementation

[0029] 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.

[0030] Data processing encompasses the acquisition, storage, retrieval, processing, transformation, and transmission of data. Depending on the structure and operation of the processing equipment, as well as the temporal and spatial distribution of the data, different data processing methods exist. Different processing methods require different hardware and software support. Each processing method has its own characteristics, and the appropriate method should be selected based on the actual environment of the application problem.

[0031] Artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It involves both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies mainly include computer vision, speech recognition, natural language processing, as well as machine learning, deep learning, big data processing, and knowledge graph technologies.

[0032] Autonomous driving refers to a driver assistance system that can assist the driver in steering and staying on the road, and perform a series of operations such as following other vehicles, braking and changing lanes. The driver can control the vehicle at any time, and the system will remind the driver to intervene in certain situations.

[0033] Intelligent transportation is a comprehensive transportation management system that effectively integrates advanced information technology, data communication and transmission technology, electronic sensing technology, control technology and computer technology into the entire ground traffic management system. It is a system that plays a role on a large scale and in all aspects, providing real-time, accurate and efficient transportation management. It consists of two parts: a traffic information service system and a traffic management system.

[0034] The following description, with reference to the accompanying drawings, outlines a method, apparatus, and electronic device for processing autonomous driving simulation data according to embodiments of the present disclosure.

[0035] The method for processing autonomous driving simulation data according to the present disclosure can be executed by the autonomous driving simulation data processing device provided in the present disclosure, which can be configured in an electronic device.

[0036] Figure 1 This is a flowchart illustrating a method for processing autonomous driving simulation data provided in an embodiment of this disclosure.

[0037] like Figure 1 As shown, the method for processing the autonomous driving simulation data may include the following steps:

[0038] Step 101: Determine the message type transmitted between the simulation system and the autonomous driving system.

[0039] In safety testing of autonomous driving systems, simulation testing is typically an important supplement to actual road testing. Through simulation testing, important scenarios, common traffic conditions, and various sensor data can be simulated on a virtual simulation system.

[0040] In practical implementation, simulation data can be acquired first, then processed to determine the performance of the autonomous driving system, such as identifying vulnerabilities or defects related to safety and reliability. The autonomous driving system can then be repaired to improve its performance. Only when the system's performance meets certain conditions can actual road testing be conducted. Therefore, the acquisition and processing of simulation data is crucial for improving the accuracy and reliability of actual road testing. In this embodiment, considering the diversity of simulation and autonomous driving systems, the message types transmitted between them can be determined first, and then the data transmitted between them can be acquired based on these message types.

[0041] It is understood that there can be multiple message types transmitted between the simulation system and the ADS (auto driving system), such as message type 1, message type 2, and message type 3, etc. This disclosure does not limit them.

[0042] Optionally, the message type transmitted between the simulation system and the autonomous driving system can be determined based on the message format transmitted between them.

[0043] The message formats transmitted between the simulation system and the autonomous driving system can be of various types. Different message formats may correspond to the same or different message types, and this disclosure does not limit this.

[0044] For example, if the message format is format 1, the corresponding message type can be message type 1; or if the message format is format 2, the corresponding message type can be message type 2, and so on. This disclosure does not limit this.

[0045] Optionally, the type of messages transmitted between the simulation system and the autonomous driving system can be determined based on the type of simulation system.

[0046] Different types of simulation systems may support the same or different message types, and this disclosure does not limit this.

[0047] For example, if the simulation system is simulation type 1, and it supports message types 1 and 2, then the message types transmitted between the simulation system and the autonomous driving system can be message type 1 and message type 2.

[0048] It should be noted that the above examples are merely illustrative and should not be construed as limiting the type of simulation system, the message types supported by the simulation system, or the message types transmitted between the simulation system and the autonomous driving system in the embodiments of this disclosure.

[0049] Optionally, the type of messages transmitted between the simulation system and the autonomous driving system can be determined based on the type of autonomous driving system.

[0050] It is understood that different types of autonomous driving systems may support the same or different message types. Therefore, in this embodiment of the disclosure, the supported message types can be determined according to the type of the autonomous driving system, thereby determining the message types transmitted between the simulation system and the autonomous driving system.

[0051] For example, if the autonomous driving system is type 1 and the message type it supports is message type 2, then it can be determined that the message type transmitted between the autonomous driving system and the simulation system is message type 2, etc. This disclosure does not limit this.

[0052] Optionally, the message type transmitted between the simulation system and the autonomous driving system can be determined based on the type of the simulation system and the autonomous driving system.

[0053] It is understood that different types of simulation systems may support the same or different message types; similarly, different types of autonomous driving systems may support the same or different message types. Therefore, in this embodiment of the disclosure, the message types supported by the simulation system and the autonomous driving system can be determined based on their respective types, thereby determining the message types transmitted between the simulation system and the autonomous driving system.

[0054] For example, if the simulation system is of type 1 and supports message types 1, 2, and 3, and the autonomous driving system is ADS 1 and supports message types 2 and 3, then it can be determined that the message types transmitted between the simulation system and the autonomous driving system can be message types 2 and 3, etc., and this disclosure does not limit this.

[0055] Step 102: Determine the data acquisition mode based on the message type.

[0056] Different message types may have the same or different data acquisition modes, and this disclosure does not limit this.

[0057] It is understandable that the correspondence between message type and data acquisition mode can be pre-agreed or pre-configured, and this disclosure does not limit this.

[0058] For example, if the message type is message type 1, its corresponding data acquisition mode can be mode 1; if the message type is message type 2, its corresponding data acquisition mode can be mode 3, and so on. This disclosure does not limit this.

[0059] Step 103: Based on the data acquisition mode, acquire the data stream transmitted between the simulation system and the autonomous driving system.

[0060] There may be one or more data acquisition modes, and this disclosure does not limit them.

[0061] In addition, a data stream can be an ordered sequence of bytes with a start and an end, which is not limited in this disclosure.

[0062] For example, data acquisition mode 1: acquire data once every 10 seconds; data acquisition mode 2: acquire data once every 30 seconds. If it is determined that the current data acquisition mode is 1, then the data stream transmitted between the simulation system and the autonomous driving system can be acquired once every 10 seconds, etc., and this disclosure does not limit this.

[0063] It is understood that the data stream transmitted between the simulation system and the autonomous driving system may include simulation data generated by the simulation system, as well as autonomous driving data generated by the autonomous driving system, etc. This disclosure does not limit this.

[0064] Step 104: Determine the performance of the autonomous driving system based on the data stream.

[0065] It is understandable that by parsing and integrating the data information in the data streams transmitted between the simulation system and the autonomous driving system, a sequence of data structures expressing the state and behavior during driving can be reconstructed. By analyzing this sequence of data structures, the safety and reliability of the autonomous driving system can be determined.

[0066] Optionally, after determining the safety and reliability of the autonomous driving system, adjustments can be made to the system to improve its safety and reliability, thereby providing a reliable basis for actual road testing and improving the accuracy and reliability of the actual road testing.

[0067] For example, by analyzing the driving speed data in the data stream and determining that the data is normal, it can be concluded that the performance of the autonomous driving system meets the requirements. Alternatively, by analyzing the driving speed data in the data stream and determining that there is abnormal data, it can be concluded that the performance of the autonomous driving system needs improvement, and adjustments can be made to the autonomous driving system based on the driving speed data.

[0068] In this embodiment, the message type transmitted between the simulation system and the autonomous driving system can be determined first. Then, based on the message type, a data acquisition mode can be determined. Next, based on the data acquisition mode, the data stream transmitted between the simulation system and the autonomous driving system can be acquired. Finally, the performance of the autonomous driving system can be determined based on the data stream. Therefore, by processing the data transmitted between the simulation system and the autonomous driving system, the performance of the autonomous driving system can be accurately determined, providing a basis for improving the performance of the autonomous driving system and, consequently, a reliable basis for actual road testing.

[0069] Understandably, in actual implementation, there can be multiple scenarios when acquiring the data stream transmitted between the simulation system and the autonomous driving system. The following will combine these scenarios with... Figure 2 The above process will be further explained.

[0070] Figure 2 This is a flowchart illustrating a method for processing autonomous driving simulation data provided in an embodiment of this disclosure, as shown below. Figure 2 As shown, the method for processing the autonomous driving simulation data may include the following steps:

[0071] Step 201: Determine the message type transmitted between the simulation system and the autonomous driving system.

[0072] Step 202: Determine the data acquisition mode based on the message type.

[0073] It should be noted that the specific content and implementation of steps 201 and 202 can be found in the descriptions of other embodiments of this disclosure, and will not be repeated here.

[0074] Step 203: Based on the data acquisition mode, obtain the data stream transmitted between the simulation system and the autonomous driving system from the bridging system, wherein the bridging system is connected to both the simulation system and the autonomous driving system.

[0075] The bridging system can support multiple message types, which can be matched with the types of simulation systems and autonomous driving systems.

[0076] For example, the simulation system supports message type 1 and message type 2, the autonomous driving system supports message type 1, message type 2 and message type 3, and the bridging system can be any bridging system or bridging component that supports message type 1, message type 2 and message type 3, etc., and this disclosure does not limit it.

[0077] It is understood that the bridging system can interact bidirectionally with both the simulation system and the autonomous driving system; that is, data can be transmitted between the simulation system and the autonomous driving system through the bridging system. For example, simulation data generated by the simulation system can be transmitted to the autonomous driving system through the bridging system, and autonomous driving data generated by the autonomous driving system can be transmitted to the simulation system through the bridging system, etc. This disclosure does not limit this.

[0078] Therefore, in this embodiment of the present disclosure, in order to ensure the integrity and reliability of the data transmitted between the simulation system and the autonomous driving system, the data stream transmitted between the simulation system and the autonomous driving system can be obtained from the bridging system, thereby making the obtained data more fundamental and as complete and accurate as possible.

[0079] Optionally, the data streams transmitted between the simulation system and the autonomous driving system can be obtained separately from the simulation system and the autonomous driving system.

[0080] Understandably, data generated during the simulation process can be stored in the simulation system, and data generated during the autonomous driving process can be stored in the autonomous driving system. Therefore, the data streams transmitted between the simulation system and the autonomous driving system can be obtained from both systems.

[0081] For example, after data transmission occurs between the simulation system and the autonomous driving system, the data stream transmitted between them can be obtained from both systems. Alternatively, the data stream transmitted between them can be obtained periodically, and so on. This disclosure does not limit this to any particular method.

[0082] Optionally, the data stream corresponding to a preset topic can be obtained based on the topic corresponding to each data stream transmitted between the simulation system and the autonomous driving system.

[0083] Different data streams may correspond to the same or different themes, and this disclosure does not limit this.

[0084] In addition, the preset theme can be the default theme, or it can be determined in other ways; this disclosure does not limit this.

[0085] For example, the predetermined topic is "driving speed". If the topic of data stream 1 transmitted between the simulation system and the autonomous driving system is "driving direction" and the topic of data stream 2 is "driving speed", then data stream 2 with the topic "driving speed" can be obtained. This disclosure does not limit this.

[0086] It is understandable that there can be one preset theme or multiple preset themes. For example, if there are multiple preset themes, then data streams corresponding to each preset theme can be obtained.

[0087] Optionally, before acquiring the data stream corresponding to the preset topic, the preset topic can be determined based on the autonomous driving performance to be tested.

[0088] The autonomous driving performance to be tested can be pre-set or can be adjusted as needed; this disclosure does not limit this.

[0089] It is understood that different autonomous driving performances to be tested may have the same or different preset themes, and this disclosure does not limit this.

[0090] For example, if the autonomous driving performance to be tested is whether the driving state is correct, then the corresponding preset topic could be "driving state". Or, if the autonomous driving performance to be tested is whether the driving speed exceeds the range, then the corresponding preset topic could be "driving speed", and so on. This disclosure does not limit this.

[0091] Optionally, a preset theme can be determined based on the obtained configuration instructions.

[0092] For example, if the configuration instruction is "Get driving speed data", then the preset topic can be determined to be "driving speed". If the topic of data stream 1 transmitted between the simulation system and the autonomous driving system is "driving speed" and the topic of data stream 2 is "driving status", then data stream 1 with the topic "driving speed" can be obtained. This disclosure does not limit this.

[0093] Step 204: Determine the performance of the autonomous driving system based on the data stream.

[0094] It should be noted that the specific content and implementation method of step 204 can be referred to the descriptions of other embodiments of this disclosure, and will not be repeated here.

[0095] In this embodiment, the message type transmitted between the simulation system and the autonomous driving system can be determined first. Then, based on the message type, a data acquisition mode can be determined. Next, based on the data acquisition mode, the data stream transmitted between the simulation system and the autonomous driving system can be obtained from the bridging system. Based on the data stream, the performance of the autonomous driving system can be determined. Therefore, by processing the data transmitted between the simulation system and the autonomous driving system, the performance of the autonomous driving system can be accurately determined, providing a basis for improving the performance of the autonomous driving system and, consequently, a reliable basis for actual road testing.

[0096] Understandably, in practical implementation, the data stream can include data sequences and timestamps corresponding to each data point. Therefore, the data sequences can be fused based on the timestamps of each data point in the data stream to determine the environmental and autonomous driving data corresponding to each timestamp. Then, the performance of the autonomous driving system can be determined. The following section will combine... Figure 3A The above process will be further explained.

[0097] Figure 3A This is a flowchart illustrating a method for processing autonomous driving simulation data provided in an embodiment of this disclosure.

[0098] like Figure 3A As shown, the method for processing the autonomous driving simulation data may include the following steps:

[0099] Step 301: Determine the message type transmitted between the simulation system and the autonomous driving system.

[0100] Step 302: Determine the data acquisition mode based on the message type.

[0101] Step 303: Based on the data acquisition mode, acquire the data stream transmitted between the simulation system and the autonomous driving system.

[0102] It should be noted that the specific content and implementation of steps 301 to 303 can be referred to the descriptions of other embodiments of this disclosure, and will not be repeated here.

[0103] Step 304: Based on the timestamp corresponding to each data in each data stream, merge the data sequences in multiple data streams to determine the environmental data and autonomous driving data corresponding to each timestamp.

[0104] The environmental data may include sensor data generated by the simulation system and observable data generated by the autonomous driving system, such as lanes, pedestrians, etc. This disclosure does not limit the scope of the data.

[0105] In addition, autonomous driving data can be any data generated by the autonomous driving system during the autonomous driving process, and this disclosure does not limit it.

[0106] This method allows for the fusion of multiple data sequences corresponding to the same timestamp from multiple data streams, thereby obtaining environmental data and autonomous driving data corresponding to each timestamp.

[0107] Step 305: Obtain the reference driving data corresponding to each timestamp based on the environmental data corresponding to each timestamp.

[0108] There are several ways to determine the reference driving data.

[0109] For example, it can be obtained through a reference model. For instance, environmental data can be input into the reference model as an event, thereby generating the model state corresponding to that environmental data, which in turn outputs the reference driving data corresponding to that environmental data.

[0110] The reference model can be any pre-trained model. By inputting environmental data into it, the corresponding reference driving data can be output. This disclosure does not limit this.

[0111] Alternatively, it can be determined based on the actual driving data and actual driving behavior collected. For example, the simulation system performs simulations based on the collected actual driving data, and the resulting data is the corresponding environmental data, while the actual collected normal driving behavior is the reference driving data.

[0112] It should be noted that the above examples are merely illustrative and should not be construed as limiting the methods for determining reference driving data in the embodiments of this disclosure.

[0113] Step 306: Determine the performance of the autonomous driving system based on the matching degree between the autonomous driving data corresponding to each timestamp and the reference driving data.

[0114] Understandably, a higher degree of matching between autonomous driving data and reference driving data indicates a more complete performance of the autonomous driving system, while a lower degree of matching indicates a worse performance of the autonomous driving system.

[0115] There are several ways to determine the matching degree between the autonomous driving data and the reference driving data corresponding to each timestamp.

[0116] For example, the driving speed, direction, and acceleration data from the same timestamp in autonomous driving data can be compared with the corresponding driving speed, direction, and acceleration data in reference driving data to determine the matching degree for each. Then, the matching degrees of each data point can be merged to determine the overall matching degree between the autonomous driving data and the reference driving data at the same timestamp. Based on this determined matching degree, the performance of the autonomous driving system can be assessed, and targeted adjustments can be made to improve the system.

[0117] Alternatively, the weights of each driving data point in the driving data can be configured in advance. Then, the matching degree between the autonomous driving data and each driving data point in the reference driving data corresponding to the same timestamp can be determined separately, and weighted fusion can be performed to determine the matching degree between the autonomous driving data and the reference driving data corresponding to the same timestamp.

[0118] It should be noted that the above examples are merely illustrative and should not be construed as limiting the methods for determining the matching degree between the autonomous driving data and the reference driving data corresponding to each timestamp in the embodiments of this disclosure.

[0119] Optionally, the autonomous driving system can be adjusted based on the matching degree between the autonomous driving data corresponding to each timestamp and the reference driving data to improve autonomous driving performance.

[0120] For example, if the "driving speed" matching degree between autonomous driving data and reference driving data is low, the parameters related to "driving speed" in the autonomous driving system can be adjusted, but this disclosure does not limit this.

[0121] In this embodiment of the disclosure, when determining the performance of the autonomous driving system, the timestamp corresponding to each data in the data stream is fully considered. The performance of the autonomous driving system is determined based on the matching degree between the autonomous driving data corresponding to each timestamp and the reference driving data. This makes the performance determination of the autonomous driving system more accurate and reliable. Subsequently, by analyzing the determined performance of the autonomous driving system, targeted adjustments can be made to the autonomous driving system to improve its performance. This provides a reliable basis for subsequent actual road testing, thereby improving the accuracy and reliability of actual road testing.

[0122] It is understood that the method for processing autonomous driving simulation data provided in this disclosure can be applied to any autonomous driving scenario, and this disclosure does not limit it.

[0123] The following is based on Figure 3B Taking the autonomous driving system and simulation system shown as examples, the method for processing autonomous driving simulation data provided in this disclosure is explained.

[0124] like Figure 3B As shown, the left side can be any simulation system, such as simulation system 1, simulation system 2, and simulation system 3, etc. This disclosure does not limit this.

[0125] The right side can be any ADS, such as an open source system or a closed source system. It can be any autonomous driving system that matches the message types supported by the simulation system, such as ADS1, ADS2, ADS3, etc. This disclosure does not limit it.

[0126] In addition, the bridging system can interact bidirectionally with the simulation system on the left and the autonomous driving system on the right. It can be any system or component that supports the message types of the simulation system and the autonomous driving system, and this disclosure does not limit it.

[0127] In addition, the sniffing component can be any component or system that can sniff autonomous driving data. It can automatically switch the sniffing function and connect to the corresponding port according to the message type supported by the bridging system in order to obtain the data stream transmitted between the simulation system and the autonomous driving system.

[0128] The sniffing component's configuration options can be set via configuration files or command-line arguments. Configuration options may include: the bridging system and port, the URI (uniform resource identifier) ​​corresponding to the data stream of the preset topic, the number of sniffing threads, etc. Alternatively, if no configuration file or command-line arguments are provided, the system can default to a preset topic and sniff data streams corresponding to preset topics on all ports in the current bridging system, etc.

[0129] Understandably, in Figure 3BIn the diagram, the simulation system sends its generated sensor data to the autonomous driving system via a bridging system. The autonomous driving system then returns its driving decisions and driving states to the simulation system via the bridging system. The sniffing component can obtain the data streams transmitted between the simulation system and the autonomous driving system from the bridging system. Then, based on the timestamps corresponding to each data point in each acquired data stream, the data sequences from multiple data streams are fused to determine the environmental and autonomous driving data corresponding to each timestamp. The environmental data corresponding to each timestamp can then be input into a reference model to obtain the corresponding reference driving data. Finally, the reference driving data and the autonomous driving data can be matched, and the performance of the autonomous driving system can be determined based on the degree of matching between the two.

[0130] It should be noted that the above examples are merely illustrative and should not be construed as limiting the simulation system, the autonomous driving system, and the data transmission method between them in the embodiments of this disclosure.

[0131] In this embodiment, the message type transmitted between the simulation system and the autonomous driving system can be determined first. Then, based on the message type, a data acquisition mode can be determined. Next, based on the data acquisition mode, the data stream transmitted between the simulation system and the autonomous driving system can be acquired. Then, based on the timestamp corresponding to each data point in each data stream, the data sequences in multiple data streams can be fused to determine the environmental data and autonomous driving data corresponding to each timestamp. Then, based on the environmental data corresponding to each timestamp, reference driving data corresponding to each timestamp can be acquired. Finally, the performance of the autonomous driving system can be determined based on the matching degree between the autonomous driving data and the reference driving data corresponding to each timestamp. Therefore, by processing the data transmitted between the simulation system and the autonomous driving system, the performance of the autonomous driving system can be accurately determined, providing a basis for improving the performance of the autonomous driving system and, consequently, a reliable basis for actual road testing.

[0132] To implement the above embodiments, this disclosure also proposes an apparatus for processing autonomous driving simulation data.

[0133] Figure 4 This is a schematic diagram of the structure of an autonomous driving simulation data processing device provided in an embodiment of the present disclosure.

[0134] like Figure 4 As shown, the autonomous driving simulation data processing device 400 includes: a first determining module 410, a second determining module 420, an acquisition module 430, and a third determining module 440.

[0135] The first determining module 410 is used to determine the message type transmitted between the simulation system and the autonomous driving system.

[0136] The second determining module 420 is used to determine the data acquisition mode based on the message type.

[0137] The acquisition module 430 is used to acquire the data stream transmitted between the simulation system and the autonomous driving system based on the data acquisition mode.

[0138] The third determining module 440 is used to determine the performance of the autonomous driving system based on the data stream.

[0139] Optionally, the acquisition module 430 is specifically used for:

[0140] The data stream transmitted between the simulation system and the autonomous driving system is obtained from the bridging system, wherein the bridging system is connected to both the simulation system and the autonomous driving system.

[0141] or,

[0142] The data streams transmitted between the simulation system and the autonomous driving system are obtained from the simulation system and the autonomous driving system, respectively.

[0143] Optionally, the first determining module 410 is specifically used for:

[0144] Based on the message format transmitted between the simulation system and the autonomous driving system, determine the message type transmitted between the simulation system and the autonomous driving system;

[0145] or,

[0146] The message type transmitted between the simulation system and the autonomous driving system is determined based on the type of the simulation system and / or the autonomous driving system.

[0147] Optionally, the acquisition module 430 is further specifically used for:

[0148] Based on the topic corresponding to each data stream transmitted between the simulation system and the autonomous driving system, obtain the data stream corresponding to the preset topic.

[0149] Optionally, the first determining module 410 is further configured to:

[0150] The preset theme is determined based on the autonomous driving performance to be tested;

[0151] or,

[0152] The preset theme is determined based on the obtained configuration instructions.

[0153] Optionally, the data stream includes a data sequence and a timestamp corresponding to each data point, and the third determining module 440 is specifically used for:

[0154] Based on the timestamp corresponding to each data in each data stream, the data sequences in multiple data streams are fused to determine the environmental data and autonomous driving data corresponding to each timestamp;

[0155] Based on the environmental data corresponding to each timestamp, obtain the reference driving data corresponding to each timestamp;

[0156] The performance of the autonomous driving system is determined based on the degree of matching between the autonomous driving data corresponding to each timestamp and the reference driving data.

[0157] The functions and specific implementation principles of the modules described in this embodiment can be found in the above method embodiments, and will not be repeated here.

[0158] The autonomous driving simulation data processing apparatus of this disclosure can first determine the message type transmitted between the simulation system and the autonomous driving system, then determine the data acquisition mode based on the message type, and then acquire the data stream transmitted between the simulation system and the autonomous driving system based on the data acquisition mode. Finally, the performance of the autonomous driving system can be determined based on the data stream. Therefore, by processing the data transmitted between the simulation system and the autonomous driving system, the performance of the autonomous driving system can be accurately determined, providing a basis for improving the performance of the autonomous driving system and, consequently, a reliable basis for actual road testing.

[0159] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0160] Figure 5 A schematic block diagram of an example electronic device 500 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.

[0161] like Figure 5As shown, device 500 includes a computing unit 501, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 502 or a computer program loaded from storage unit 508 into random access memory (RAM) 503. RAM 503 may also store various programs and data required for the operation of device 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. Input / output (I / O) interface 505 is also connected to bus 504.

[0162] Multiple components in device 500 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of monitors, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0163] The computing unit 501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 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 501 performs the various methods and processes described above, such as the method for processing autonomous driving simulation data. For example, in some embodiments, the method for processing autonomous driving simulation data can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed on device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of the method for processing autonomous driving simulation data described above can be performed. Alternatively, in other embodiments, the computing unit 501 can be configured to perform the method for processing autonomous driving simulation data by any other suitable means (e.g., by means of firmware).

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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).

[0168] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations 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., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

[0169] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem, addressing the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0170] The technical solution disclosed herein can first determine the message type transmitted between the simulation system and the autonomous driving system, then determine the data acquisition mode based on the message type, and then acquire the data stream transmitted between the simulation system and the autonomous driving system based on the data acquisition mode. Finally, the performance of the autonomous driving system can be determined based on the data stream. Therefore, by processing the data transmitted between the simulation system and the autonomous driving system, the performance of the autonomous driving system can be accurately determined, thus providing a basis for improving the performance of the autonomous driving system and, consequently, a reliable basis for actual road testing.

[0171] 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 provided in this disclosure can be achieved, and this is not limited herein.

[0172] 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 processing autonomous driving simulation data, comprising: Determine the types of messages transmitted between the simulation system and the autonomous driving system; Determine the data acquisition mode based on the message type; Based on the data acquisition mode, the data stream transmitted between the simulation system and the autonomous driving system is acquired; The performance of the autonomous driving system is determined based on the data stream; The step of acquiring the data stream transmitted between the simulation system and the autonomous driving system based on the data acquisition mode includes: After data transmission occurs between the simulation system and the autonomous driving system, the data stream transmitted between the two systems is obtained from both the simulation system and the autonomous driving system. or, The data stream transmitted between the simulation system and the autonomous driving system is periodically acquired. Each data stream includes a data sequence and a timestamp for each data item. Determining the performance of the autonomous driving system based on the data stream includes: Based on the timestamp of each data in each data stream, multiple data sequences corresponding to the same timestamp from multiple data streams are fused to determine the environmental data and autonomous driving data for each timestamp; Based on the environmental data at each timestamp, obtain the reference driving data for each timestamp; The performance of the autonomous driving system is determined based on the matching degree between the autonomous driving data at each timestamp and the reference driving data; The acquisition of the data stream transmitted between the simulation system and the autonomous driving system includes: Based on the topic corresponding to each data stream transmitted between the simulation system and the autonomous driving system, obtain the data stream corresponding to the preset topic; Before obtaining the data stream corresponding to the preset topic, the method further includes: The preset theme is determined based on the autonomous driving performance to be tested; or, The preset theme is determined according to the configuration instructions.

2. The method as described in claim 1, wherein, The step of acquiring the data stream transmitted between the simulation system and the autonomous driving system based on the data acquisition mode includes: The data stream transmitted between the simulation system and the autonomous driving system is obtained from the bridging system, wherein the bridging system is connected to both the simulation system and the autonomous driving system. or, The data streams transmitted between the simulation system and the autonomous driving system are obtained from the simulation system and the autonomous driving system, respectively.

3. The method as described in claim 1, wherein, The determination of the message types transmitted between the simulation system and the autonomous driving system includes: Based on the message format transmitted between the simulation system and the autonomous driving system, determine the message type transmitted between the simulation system and the autonomous driving system; or, The message type transmitted between the simulation system and the autonomous driving system is determined based on the type of the simulation system and / or the autonomous driving system.

4. A device for processing autonomous driving simulation data, comprising: The first determining module is used to determine the message type transmitted between the simulation system and the autonomous driving system; The second determining module is used to determine the data acquisition mode based on the message type; The acquisition module is used to acquire the data stream transmitted between the simulation system and the autonomous driving system based on the data acquisition mode. The acquisition module is specifically used to acquire the data stream transmitted between the simulation system and the autonomous driving system after data transmission is generated between the simulation system and the autonomous driving system. or, The data stream transmitted between the simulation system and the autonomous driving system is periodically acquired. The third determining module is used to determine the performance of the autonomous driving system based on the data stream; Each data stream includes a data sequence and a timestamp for each data item. The third determining module is specifically used for: Based on the timestamp of each data in each data stream, multiple data sequences corresponding to the same timestamp from multiple data streams are fused to determine the environmental data and autonomous driving data for each timestamp; Based on the environmental data at each timestamp, obtain the reference driving data for each timestamp; The performance of the autonomous driving system is determined based on the matching degree between the autonomous driving data at each timestamp and the reference driving data; The acquisition module is also specifically used for: Based on the topic corresponding to each data stream transmitted between the simulation system and the autonomous driving system, obtain the data stream corresponding to the preset topic; The first determining module is further configured to: The preset theme is determined based on the autonomous driving performance to be tested; or, The preset theme is determined according to the configuration instructions.

5. The apparatus of claim 4, wherein, The acquisition module is specifically used for: The data stream transmitted between the simulation system and the autonomous driving system is obtained from the bridging system, wherein the bridging system is connected to both the simulation system and the autonomous driving system. or, The data streams transmitted between the simulation system and the autonomous driving system are obtained from the simulation system and the autonomous driving system, respectively.

6. The apparatus of claim 4, wherein, The first determining module is specifically used for: Based on the message format transmitted between the simulation system and the autonomous driving system, determine the message type transmitted between the simulation system and the autonomous driving system; or, The message type transmitted between the simulation system and the autonomous driving system is determined based on the type of the simulation system and / or the autonomous driving system.

7. 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 1-3.

8. 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 1-3.

9. A computer program product comprising a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-3.

Images