Automatic driving simulation method and device, electronic equipment and storage medium
By reading messages from road test information, adjusting the generated message sequence and list, and determining the target message based on simulation time for simulation processing, the problem of difficulty in adjusting the message sequence and time in autonomous driving simulation test is solved, and the flexibility of simulation is improved Efficiency reduces link coupling.
Patent Information
- Application Number
- CN202311716076.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-13
- Publication Date
- 2024-11-22
AI Technical Summary
The existing autonomous driving simulation tests are difficult to flexibly adjust the packet message sequence and sending time, resulting in inefficient simulation processes and strong coupling dependence among various links, which cannot meet the user's adaptive needs.
By reading messages from the road test information, adjusting the generated message sequence and message list, determining the target message to be sent based on the simulation time for simulation processing, realizing adaptive playback and time interval adjustment, and reducing coupling dependency.
It improves the flexibility and efficiency of autonomous driving simulation, adapts to user needs, and reduces the coupling dependence between various links of the simulation system.
Smart Images

Figure CN119004746A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of autonomous driving technology, in particular to the field of artificial intelligence, data processing and simulation testing technology, and specifically to an autonomous driving simulation method, device, electronic device and storage medium. Background Art
[0002] Autonomous driving simulation testing is to digitally restore the application scenarios of autonomous driving through data modeling, establish a system model that is as close to the real world as possible, and conduct analysis and research through simulation testing to improve the safety of autonomous driving vehicle testing and save testing time and costs.
[0003] With the development of autonomous driving simulation, simulation is no longer limited to the reproduction of road test problems, and it is gradually necessary to adjust the message sequence or sending time of data packets. Therefore, simulation methods that can achieve adaptive playback of data are of great significance. Summary of the invention
[0004] The present invention provides a method, device, electronic device and storage medium for autonomous driving simulation.
[0005] According to one aspect of the present disclosure, there is provided an autonomous driving simulation method, comprising:
[0006] Obtain a drive test information set, and read N messages from the drive test information set, where N is a positive integer;
[0007] Adjusting the N messages to generate a message sequence;
[0008] Extracting key information from messages in the message sequence, and generating a message list based on the key information of the messages;
[0009] Determine a simulation time, and generate simulation indication information based on the simulation time and key information of the message in the message list;
[0010] According to the simulation indication information, a target message to be sent is determined from the message sequence, and simulation processing is performed on the target message.
[0011] According to another aspect of the present disclosure, there is provided an automatic driving simulation device, comprising:
[0012] A first acquisition module, configured to acquire a drive test information set and read N messages from the drive test information set, where N is a positive integer;
[0013] A second acquisition module, used to adjust the N messages to generate a message sequence;
[0014] A third acquisition module is used to extract key information from the messages in the message sequence and generate a message list based on the key information of the N messages;
[0015] A fourth acquisition module, used to determine the simulation time, and generate simulation indication information based on the simulation time and key information of the message in the message list;
[0016] The simulation module is used to determine the target message to be sent from the message sequence according to the simulation indication information, and perform simulation processing on the target message.
[0017] According to a third aspect of the present disclosure, an electronic device is provided, comprising: 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, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in the first aspect.
[0018] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method according to the first aspect.
[0019] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the steps of the method according to the first aspect.
[0020] In the disclosed embodiment, by reading messages from a road test data set and adjusting them to generate a message sequence and a message list, the target message is determined for simulation processing, which can adaptively meet the needs of users and improve the flexibility of autonomous driving simulation and the efficiency of simulation.
[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.
[0023] Figure 1 is a schematic diagram of an automatic driving simulation method provided by an embodiment of the present disclosure;
[0024] Figure 2 is a schematic diagram of another automatic driving simulation method provided by an embodiment of the present disclosure;
[0025] Figure 2AIt is a schematic diagram of sorting messages provided by an embodiment of the present disclosure;
[0026] Figure 3 is a schematic diagram of another automatic driving simulation method provided by an embodiment of the present disclosure;
[0027] Figure 4 is a schematic diagram of another automatic driving simulation method provided by an embodiment of the present disclosure;
[0028] Figure 4A is a schematic diagram of deleting a target message provided by an embodiment of the present disclosure;
[0029] Figure 5 is a schematic diagram of another automatic driving simulation method provided by an embodiment of the present disclosure;
[0030] Figure 6 is a structural schematic diagram of an automatic driving simulation device provided by an embodiment of the present disclosure;
[0031] Figure 7 is a structural schematic diagram of an automatic driving simulation system provided by an embodiment of the present disclosure;
[0032] Figure 8 It is a block diagram of an electronic device used to implement an autonomous driving simulation method according to an embodiment of the present disclosure. DETAILED DESCRIPTION
[0033] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.
[0034] Autonomous Driving relies on the collaboration of artificial intelligence, visual computing, radar, monitoring devices and global positioning systems to allow computers to automatically and safely operate motor vehicles without any active human operation. It uses modern communication methods and directly faces the train to achieve two-way data communication between the train and the ground, with fast transmission speed and large amount of information.
[0035] Artificial Intelligence (AI) is an information technology science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. It includes research in the fields of robotics, speech recognition, image recognition, natural language processing and expert systems. Artificial Intelligence can simulate the information process of human consciousness and thinking, with the aim of enabling machines to perform complex tasks that usually require human intelligence.
[0036] Data processing is the collection, storage, retrieval, processing, transformation and transmission of data. The basic purpose of data processing is to extract and derive valuable and meaningful data for certain specific people from a large amount of data that may be disorganized and difficult to understand.
[0037] Simulation Test refers to a test that simulates the actual usage environment of the software and configures the software to the actual usage state. It digitally restores the application scenario in the form of data modeling to establish a system model that is as close to the real world as possible.
[0038] Figure 1 Schematic diagram of an automatic driving simulation method provided by an embodiment of the present disclosure. Figure 1 As shown, the method comprises the following steps:
[0039] S101, obtaining a drive test information set, and reading N messages from the drive test information set.
[0040] Wherein, N is a positive integer.
[0041] In some implementations, the drive test information set includes multiple messages, and the number of messages in the drive test data set is greater than N.
[0042] In some implementations, each message may be data sampled and recorded by the vehicle during actual road running. Each message is data corresponding to a sampling, such as coordinates, driving parameters, or current decision data, for simulation testing of autonomous driving.
[0043] Furthermore, considering the processing situation of the simulation, N messages are read from the drive test information set, and subsequent simulation processing is performed on the N messages.
[0044] S102, adjust N messages to generate a message sequence.
[0045] Optionally, in order to ensure the simulation effect and meet user needs, the N messages may be adjusted.
[0046] In some implementations, the messages may be sorted in the order of collection time to obtain a message sequence; in other implementations, the messages may be sorted according to user requirements, for example, messages related to positioning information may be sorted first, and N messages may be sorted according to the actual needs of the user to obtain a sorted message sequence; in other implementations, the time intervals of the messages may be adjusted to change the relative relationship between the messages to generate a message sequence; in other implementations, the messages may be deleted or added according to the actual needs of the user, and the messages may be adaptively adjusted according to the needs of the user to obtain a message sequence.
[0047] S103, extracting key information from messages in the message sequence, and generating a message list based on the key information of the messages.
[0048] In some implementations, the key information may be information such as the time or name corresponding to the message that can uniquely identify the message.
[0049] Optionally, each message may be characterized by its key information to generate a message list; for example, the time and name of a message may be used as a data group, which may uniquely correspond to a message, so the time and name of all messages may be arranged in sequence to generate a message list.
[0050] Optionally, the message list may be obtained by arranging the messages in the message sequence according to their sorting order, that is, the order of the messages in the message list is consistent with the order of the messages in the message sequence.
[0051] S104, determining the simulation time, and generating simulation indication information based on the simulation time and key information of the message in the message list.
[0052] In some implementations, the simulation time may be time information preset during the simulation flow control process, and each simulation time corresponds to a different message.
[0053] In some implementations, the simulation indication information can be used to indicate the message that needs to be simulated. The message list includes the adjusted message, and the corresponding message under the simulation time of each simulation process control can be determined according to the simulation time and the time in the key information of the message in the message list, so as to generate the simulation indication information, and the simulation indication information indicates the message corresponding to the process control time; that is, the simulation indication information indicates the message corresponding to the simulation configuration information.
[0054] S105, determining a target message to be sent from the message sequence according to the simulation indication information, and performing simulation processing on the target message.
[0055] In some implementations, the simulation indication information indicates a corresponding message under the simulation configuration information, so the target message to be sent can be determined from the message list according to the simulation indication information.
[0056] It can be understood that the simulation indication information can indicate a corresponding message in the message list, and according to key information of the indicated message in the message list, a corresponding target message to be sent can be obtained in the message sequence.
[0057] Furthermore, the target message is sent to subsequent simulation computing nodes, and simulation processing is performed on the target message to improve the efficiency of the autonomous driving simulation process.
[0058] In the disclosed embodiment, by reading messages from a road test data set and adjusting them to generate a message sequence, it is possible to adaptively meet user needs and flexibly adjust the order and time intervals of messages; a message list is generated based on the key information of the message, and then the target message to be sent is determined based on the key information of the message in the message list and the simulation time, and the target message is processed, thereby reducing the coupling dependency between the various links in the autonomous driving simulation system and improving the flexibility of the autonomous driving simulation and the efficiency of the simulation.
[0059] Figure 2 Schematic diagram of an automatic driving simulation method provided by an embodiment of the present disclosure. Figure 2 As shown, the method comprises the following steps:
[0060] S201, obtaining a drive test information set, and reading N messages from the drive test information set.
[0061] In the embodiments of the present disclosure, the implementation method of step S201 can be implemented by any of the methods in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0062] S202, adjust N messages to generate a message sequence.
[0063] In some implementations, a message sorting rule may be obtained, and N messages may be sorted according to the message sorting rule to generate a message sequence.
[0064] Optionally, a playback window of a preset length may be obtained; according to the length of the playback window, N messages are read from the drive test data set and stored in the playback window, where N is not greater than the length of the playback window; in the playback window, the N messages are sorted to generate a message sequence. In other words, the playback window is set as an intermediate processing node, the N messages read from the drive test data set are stored in the playback window, the messages are adjusted in the playback window, and the corresponding message sequence is generated, which can ensure the integrity of the data in the message during the processing.
[0065] The message sorting rule is used to indicate the order in which messages are arranged. In some implementations, the message sorting rule can be determined by the message acquisition attributes. For example, the message sorting rule is determined according to the time of message collection, and N messages are arranged in sequence according to the order of message collection to obtain a message sequence. In some implementations, the message sorting rule can also be determined according to the actual needs of the user, such as arranging positioning-related messages in front, or arranging vehicle status-related messages in front, so that N messages can be arranged more flexibly according to the message sorting rule to generate a message sequence.
[0066] In some implementations, a time adjustment rule may also be obtained, wherein the time adjustment includes time delay, time advance and time adaptation; the time intervals of N messages are adjusted according to the time adjustment rule to generate a message sequence.
[0067] The time adjustment rule is used to adjust the time intervals between N messages. Time adjustment can include time delay, time advance and time adaptation, that is, increasing the time interval, decreasing the time interval or adaptively adjusting the time interval. The relative relationship between messages is changed according to the adjusted time interval, so that different message combinations can be obtained at different simulation times.
[0068] As an example, for message ABC, the corresponding time for message A is 0 seconds, the corresponding time for message B is 1 second, and the corresponding time for message C is 2 seconds. The time interval is adjusted to adjust the return time of message B to 1.5 seconds. Although the order of the messages is not changed, the time interval is greater than the interval between the messages in the road test data set, resulting in changes between the messages.
[0069] As an example, in the positioning simulation method (used to test the positioning accuracy of the autonomous driving positioning module), point cloud compensation is required in the simulation, and the driving module relies on tf messages (including timestamps, coordinate conversion and other data) for point cloud compensation. The tf message is calculated by the positioning module, and the positioning module relies on the point cloud message (Scan) of the previous frame to calculate the tf message. The two form a loop, and there is a deadlock phenomenon in the simulation flow control. Therefore, the playback order of the Scan message can be adjusted. When N messages are read out from the road test data set, whenever there is a Scan message, its playback time is increased by a delay time value dt. During the data playback process, the positioning module will first calculate the tf data, and then replay the current frame Scan after dt time, so that the driving module can calculate the point cloud data.
[0070] It is understandable that the value of the delay time dt needs to be controlled within a reasonable range. For example, the "delay time value adaptation" function is provided through adaptive playback. Taking Scan as an example, an empirical value dt0 is first provided. The adaptive playback module adjusts Scan to dt0 time and then plays it. If the operation fails (such as: point cloud compensation timeout), the dt value will be automatically adjusted up and down until the simulation task runs successfully and the point cloud can be calculated normally. At this time, a dt will be fed back to the user as a reference value.
[0071] As an example, in the asynchronous decompression playback of images, including compressed image messages such as the front view and rear view of the fisheye camera, the image decompression module decompresses the image during the simulation process. The positioning and perception modules need to obtain the decompressed image message before they can start the calculation. Since the simulation flow control defaults to single thread, after playing the compressed image, it is necessary to wait for the decompression to succeed before continuing to play the subsequent messages, which will greatly increase the simulation running time. Therefore, the order of compressed image messages can be adjusted. When the compressed image is placed in the playback window, if the Image message needs to be played at time t, the Image message is placed in the playback window at time t-dt, and the image_t message is placed at time t. At the same time, the operation mode of the image decompression module is changed to multi-threaded operation mode. When playing the message, the compressed image message is played in advance at time dt, so that the image decompression module can decompress in other threads. The adaptive playback module will cache the decompressed image message sent by the image decompression module, and the simulation main thread (flow control thread) will continue to play other messages. When the Image_t message needs to be played, the adaptive playback module will send the decompressed image message for use by the positioning, perception and other modules.
[0072] As an example, in the path planning and navigation simulation, there are some time points of sudden braking and collision, which are generally called key time points. This time point is the time point that users need to focus on in the simulation. In the path planning and navigation simulation, when the planning and control modules are about to trigger an early warning, the subsequent simulation timing can be adjusted to simulate the perception, prediction, planning and other modules to avoid certain risks. The simulation of the path planning and navigation needs to be run twice. The first simulation is run in the default way. The adaptive playback module records the key time points of collision or other risk items, and then restarts the simulation. When the key time point is about to be reached, the playback window is used to adjust the delay of the message set by the user in advance, such as playing the prediction message 100 milliseconds in advance to test the computing power of the planning module.
[0073] In some implementations, message adjustment rules may also be obtained, the message adjustment rules including message deletion operations and / or message addition operations; N messages are deleted and / or added according to the message adjustment rules to generate a message sequence.
[0074] Message adjustment rules are used to delete and / or add N messages. In some implementations, the message adjustment rules can be determined based on user needs. For example, the user expects to delete or add a certain type of message. The message adjustment rules are determined based on the user's expectations, and the messages are deleted or added based on the message adjustment rules.
[0075] In some implementations, during the simulation engine flow control process, a rule change instruction can be monitored; in response to receiving the rule change instruction, N messages are reordered according to the rule change instruction to obtain an updated message sequence. It can be understood that the rule change instruction is used to indicate whether the message arrangement rule is changed, that is, when the rule change instruction is monitored, it indicates that the message arrangement rule needs to be changed at this time. Therefore, when the rule change instruction is received, the N messages are reordered according to the new message arrangement rule in the rule change instruction to obtain an updated message sequence, so as to adjust the message arrangement according to user needs and improve the flexibility of the simulation system.
[0076] S203, extract keywords from the messages to obtain the message name and message time of each message.
[0077] Optionally, the keyword may be content related to the message time and the message name. The message name and the message time of each message are determined based on the extraction of the keyword, that is, the key information of each message is determined.
[0078] S204, generating a message list according to the order of the messages in the message sequence, based on the message names and message times.
[0079] In some implementations, the message sequence includes the adjusted message, so a corresponding message list can be generated based on the order in the message sequence. Optionally, the message list can only include the message name and message time, which can uniquely identify the corresponding message while reducing storage pressure, and perform simulation process control based on the message list to improve the efficiency of subsequent simulation.
[0080] S205, determining the simulation time, and generating simulation indication information based on the simulation time and key information of the message in the message list.
[0081] In the embodiments of the present disclosure, the implementation method of step S205 can be implemented by using any of the methods in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0082] S206, determining a target message to be sent from the message sequence according to the simulation indication information, and performing simulation processing on the target message.
[0083] In the embodiments of the present disclosure, the implementation method of step S206 may be implemented in any manner in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0084] In the disclosed embodiments, N messages are adjusted and sorted by message sorting rules / time adjustment rules / message adjustment rules to obtain a message sequence that meets user needs, and when a rule change instruction is monitored, the order of the messages can be flexibly changed according to the rule change instruction to improve the flexibility of the simulation process; further, a message list is generated according to the message time and message name of each message in the message sequence, so that the corresponding message can be determined according to the message list, and the corresponding simulation process control can be performed to improve the efficiency of the simulation.
[0085] Figure 3 Schematic diagram of an automatic driving simulation method provided by an embodiment of the present disclosure. Figure 3 As shown, the method includes:
[0086] S301, obtain a drive test information set, and read N messages from the drive test information set. In the embodiment of the present disclosure, the implementation method of step S301 can be implemented by any of the embodiments of the present disclosure, which is not limited here and will not be repeated.
[0087] S302, adjust N messages to generate a message sequence.
[0088] In the embodiments of the present disclosure, the implementation method of step S302 may be implemented in any manner in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0089] S303, extract key information from the messages in the message sequence, and generate a message list based on the key information of the messages.
[0090] In the embodiments of the present disclosure, the implementation method of step S303 may be implemented in any manner in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0091] S304: Determine a target message identifier of the target message according to the simulation time and key information of the message in the message list.
[0092] In some implementations, the simulation time may be the time of the simulation process control, wherein the simulation process control may be understood as advancing the next simulation time only when the message data of the current time is processed, that is, the simulation process control may be used to advance the simulation time.
[0093] Optionally, the simulation time can be matched with the message time in the message list; the target message time matching the simulation time is obtained, and the message identifier associated with the target message time is determined as the target message identifier. That is, after determining the simulation time, the target message time corresponding to the time can be determined in the message list; it can be understood that the target message time can be the time of the message corresponding to the simulation time.
[0094] Furthermore, the message identifier associated with the target message time is used as the target message identifier to ensure that an accurately associated target message identifier can be efficiently obtained; optionally, the target message identifier can be the message name and message time of the message, and thus the corresponding message name is determined according to the target message time as the target message identifier, so as to facilitate determination of the target message according to the target message identifier.
[0095] S305: Generate simulation indication information based on the target message identifier.
[0096] In some implementations, simulation indication information may be generated according to a target message identifier, and the simulation indication information may include a target message identifier, so as to determine a corresponding target message according to the simulation indication message.
[0097] S306: extract a target message identifier from the simulation indication information, and determine a target message in the message list based on the target message identifier.
[0098] After the simulation indication information is determined, the target message identifier is extracted from the simulation indication information. The target message identifier corresponds to the target message under the simulation time. Therefore, after the target message identifier is extracted, the corresponding target message can be determined in the message list based on the target message identifier.
[0099] It can be understood that the message list includes the message time, message name and data content corresponding to each message, so a more accurate and complete target message can be determined in the message list.
[0100] S307, performing simulation processing on the target message.
[0101] In the embodiments of the present disclosure, the implementation method of step S307 may be implemented in any manner in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0102] In an embodiment of the present disclosure, a target message identifier is determined based on a preset simulation time and key information of a message in a message list, and simulation indication information is generated based on the target message identifier to improve the accuracy and flexibility of process control during the simulation process, so that the simulation process control is more in line with user needs and requirements. The target message is determined based on the target message identifier in the simulation indication information and simulation processing is performed, thereby improving the effect and efficiency of the simulation processing.
[0103] Figure 4 Schematic diagram of an automatic driving simulation method provided by an embodiment of the present disclosure. Figure 4 As shown, the method includes:
[0104] S401, obtaining a drive test information set, and reading N messages from the drive test information set.
[0105] In the embodiments of the present disclosure, the implementation method of step S401 may be implemented in any manner in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0106] S402, adjust N messages to generate a message sequence.
[0107] In the embodiments of the present disclosure, the implementation method of step S402 may be implemented in any manner in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0108] S403, extracting key information from messages in the message sequence, and generating a message list based on the key information of the messages.
[0109] In the embodiments of the present disclosure, the implementation method of step S403 may be implemented in any manner in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0110] S404, determining the simulation time, and generating simulation indication information based on the simulation time and key information of the message in the message list.
[0111] In the embodiments of the present disclosure, the implementation method of step S404 may be implemented in any manner in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0112] S405: Determine a target message to be sent from the message sequence according to the simulation instruction information.
[0113] In the embodiments of the present disclosure, the implementation method of step S405 can be implemented by any of the methods in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0114] S406: Send the target message to the simulation processing node for simulation processing.
[0115] In some implementations, the target message includes data recorded during the actual road running, so the target message is sent to the simulation processing node, that is, the actual road running data is sent to the simulation processing node. Optionally, the simulation processing node is used to perform simulation processing according to the received target message, reproduce the problems encountered in the road running or analyze the complex situations encountered in the road test, so as to accurately realize the final simulation.
[0116] S407: In response to the target message being sent, delete the target message from the message sequence.
[0117] Optionally, when the target message is sent to the simulation processing node, in order to avoid redundant memory usage, the target message may be deleted from the message sequence.
[0118] S408: In response to the message sequence being empty, N messages are read again from the drive test information set and adjusted to generate a new message sequence.
[0119] When the message sequence is empty, it means that all the messages in the message sequence have been sent to the simulation node. Therefore, N messages can be read again from the drive test data set, and the N messages can be sorted to generate a new message sequence.
[0120] like Figure 4A As shown, it is a schematic diagram of deleting a target message. After the target message in the message sequence is sent, the target message is deleted from the message sequence. After all messages in the message sequence are sent, new messages are collected and read from the drive test data set.
[0121] It can be understood that key information can be extracted from the N messages read again at this time, and a new message list can be generated. According to the preset simulation configuration information and the new message list, corresponding simulation indication information can be generated, and then according to the simulation indication information, the target message to be sent can be determined from the new message list and simulation processing can be performed.
[0122] S409: In response to the message sequence being empty and the drive test data set being empty, the simulation ends.
[0123] When the message sequence is empty and the drive test data set is also empty, that is, all the messages in the drive test data set have been sent to the simulation processing node for simulation processing, so the simulation can be ended.
[0124] In the disclosed embodiment, after determining the target message to be sent, the target message is sent to the simulation processing node for simulation processing, and the sent target message is deleted from the message sequence after the target message is sent, thereby saving storage space; when the message in the message sequence is empty, the message continues to be read from the road test data set, and the messages are sorted again to determine the message sequence; when all the messages in the message sequence and the road test data set are empty, it is determined that all the messages have been sent to the simulation processing node for simulation processing, and the overall simulation process is terminated to avoid omission of messages in the simulation process.
[0125] Figure 5 Schematic diagram of an automatic driving simulation method provided by an embodiment of the present disclosure. Figure 5 As shown, the method includes:
[0126] S501: Acquire a drive test information set, and read N messages from the drive test information set.
[0127] In the embodiments of the present disclosure, the implementation method of step S501 may be implemented in any manner in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0128] S502: Adjust N messages to generate a message sequence.
[0129] In the embodiments of the present disclosure, the implementation method of step S502 may be implemented in any manner in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0130] S503, extract keywords from the messages to obtain the message name and message time of each message.
[0131] In the embodiments of the present disclosure, the implementation method of step S503 may be implemented in any manner in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0132] S504: Generate a message list based on the order of the messages in the message sequence, the message names and the message times.
[0133] In the embodiments of the present disclosure, the implementation method of step S504 may be implemented in any manner in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0134] S505, determining the simulation time, and determining the target message identifier of the target message based on the simulation time and the key information of the message in the message list.
[0135] In the embodiments of the present disclosure, the implementation method of step S505 may be implemented in any manner in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0136] S506, generating simulation indication information based on the target message identifier.
[0137] In the embodiments of the present disclosure, the implementation method of step S506 may be implemented in any manner in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0138] S507: extract a target message identifier from the simulation indication information, and determine a target message in the message list based on the target message identifier.
[0139] In the embodiment of the present disclosure, the implementation method of step S507 can be implemented by using any method in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0140] S508: Send the target message to the simulation processing node for simulation processing.
[0141] In the embodiments of the present disclosure, the implementation method of step S508 may be implemented in any manner in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0142] S509: In response to the target message being sent, delete the target message from the message sequence.
[0143] In the embodiments of the present disclosure, the implementation method of step S509 may be implemented in any manner in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0144] S510 : In response to the message sequence being empty, read N messages from the drive test information set again and sort them to generate a new message sequence.
[0145] In the embodiments of the present disclosure, the implementation method of step S510 may be implemented in any manner in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0146] S511, in response to the message sequence being empty and the drive test data set being empty, the simulation ends.
[0147] In the embodiments of the present disclosure, the implementation method of step S511 may be implemented in any manner in the embodiments of the present disclosure, which is not limited here and will not be described in detail.
[0148] In the disclosed embodiment, messages are read from a road test data set and adjusted through message sorting rules / time adjustment rules / message adjustment rules to generate a message sequence. When a rule change instruction is monitored, the order of the messages can be flexibly changed according to the rule change instruction, so as to adaptably meet the needs of users and flexibly adjust the order of messages. A message list is generated according to the message time and message name of the message, and then the target message to be sent is determined based on the message list and the simulation time, so that the simulation process control is more in line with the needs and requirements of users, the target message is sent to the simulation processing node for simulation processing, and the sent target message is deleted from the message sequence after the target message is sent, thereby saving storage space, reducing the coupling dependency between the various links in the autonomous driving simulation system, and improving the flexibility of the autonomous driving simulation and the efficiency of the simulation.
[0149] Figure 6 This is a schematic diagram of the structure of an automatic driving simulation device provided by an embodiment of the present disclosure. Figure 6 As shown, the automatic driving simulation device 600 includes:
[0150] The first acquisition module 601 is used to acquire a drive test information set and read N messages from the drive test information set, where N is a positive integer;
[0151] The second acquisition module 602 is used to adjust the N messages to generate a message sequence;
[0152] The third acquisition module 603 is used to extract key information from messages in the message sequence and generate a message list based on the key information of N messages;
[0153] A fourth acquisition module 604 is used to determine the simulation time and generate simulation indication information based on the simulation time and key information of the message in the message list;
[0154] The simulation module 605 is used to determine the target message to be sent from the message sequence according to the simulation indication information, and perform simulation processing on the target message.
[0155] In some implementations, the second acquisition module 602 includes:
[0156] Obtain a message arrangement rule, and sort N messages according to the message arrangement rule to generate a message sequence.
[0157] In some implementations, the second acquisition module 602 includes:
[0158] Obtaining time adjustment rules, where time adjustment includes time delay, time advance and time adaptation;
[0159] The time intervals of N messages are adjusted according to the time adjustment rule to generate a message sequence.
[0160] In some implementations, the second acquisition module 602 includes:
[0161] Obtaining message adjustment rules, where the message adjustment rules include a message deletion operation and / or a message addition operation;
[0162] N messages are deleted and / or added according to the message adjustment rule to generate a message sequence.
[0163] In some implementations, the third acquisition module 603 includes:
[0164] Extract keywords from N messages to obtain the message name and message time of each message;
[0165] According to the order of N messages in the message sequence, a message list is generated by the message name and the message time.
[0166] In some implementations, the fourth acquisition module 604 includes:
[0167] Determine the simulation time according to preset simulation configuration information;
[0168] Determine a target message identifier of a target message according to the simulation time and the message list;
[0169] Based on the target message identifier, simulation indication information is generated.
[0170] In some implementations, the simulation module 605 includes:
[0171] A target message identifier is extracted from the simulation indication information, and a target message is determined in the message list based on the target message identifier.
[0172] In some implementations, the simulation module 605 includes:
[0173] Match the simulation time,with the message time in the message list;
[0174] A target message time matching the simulation time is obtained, and a message identifier associated with the target message time is determined as the target message identifier.
[0175] In some implementations, the apparatus 600 further includes:
[0176] During the simulation engine flow control process, monitor the rule change instructions;
[0177] In response to receiving the rule change instruction, the N messages are reordered according to the rule change instruction to obtain an updated message sequence.
[0178] In some implementations, the simulation module 605 includes:
[0179] Send the target message to the simulation processing node for simulation processing.
[0180] In some implementations, the apparatus 600 further includes:
[0181] In response to the target message being sent, deleting the target message in the message sequence;
[0182] In response to the message sequence being empty, N messages are read again from the drive test information set and sorted to generate a new message sequence.
[0183] In some implementations, the apparatus 600 further includes:
[0184] In response to the message sequence being empty and the drive test data set being empty, the simulation is terminated.
[0185] In some implementations, the second acquisition module 602 includes:
[0186] Get the playback window of preset length;
[0187] According to the length of the playback window, N messages are read from the drive test data set and stored in the playback window, where N is not greater than the length of the playback window;
[0188] In the playback window, N messages are sorted to generate a message sequence.
[0189] In the disclosed embodiment, by reading messages from a road test data set and adjusting them to generate a message sequence, it is possible to adaptively meet user needs and flexibly adjust the order and time intervals of messages; a message list is generated based on the key information of the message, and then the target message to be sent is determined based on the key information of the message in the message list and the simulation time, and the target message is processed, thereby reducing the coupling dependency between the various links in the autonomous driving simulation system and improving the flexibility of the autonomous driving simulation and the efficiency of the simulation.
[0190] On the basis of the above embodiments, the embodiments of the present disclosure may provide a structural diagram of an autonomous driving simulation system. Different from the existing autonomous driving simulation system, the embodiments of the present disclosure introduce an adaptive playback module, which may include a data management module, a data sorting module and a data playback module. Figure 7As shown, the data management module is used to read messages from the road test data set record, and the data sorting module is used to sort the read messages according to the message arrangement rules, and obtain the message sequence and message list; further, in order to facilitate the simulation process control, the message list can be sent to the simulation engine so that the simulation engine performs simulation flow control, and the data playback module is used to include a message sequence, so that based on the simulation flow control from the data playback module, the target message is determined and sent to the subsequent calculation module or simulation module, so as to simulate the target message, so that the subsequent simulation process is more efficient and more flexible.
[0191] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.
[0192] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
[0193] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment 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 can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.
[0194] like Figure 8 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.
[0195] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0196] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as the autonomous driving simulation method. For example, in some embodiments, the autonomous driving simulation method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the autonomous driving simulation method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the autonomous driving simulation method in any other appropriate manner (e.g., by means of firmware).
[0197] Various implementations 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 chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0198] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0199] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0200] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the 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 acoustic input, voice input, or tactile input).
[0201] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.
[0202] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.
[0203] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.
[0204] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.
Claims
1. An automatic driving simulation method, comprising: Obtain a drive test information set, and read N messages from the drive test information set, where N is a positive integer; Adjusting the N messages to generate a message sequence; Extracting key information from messages in the message sequence, and generating a message list based on the key information of the messages; Determine a simulation time, and generate simulation indication information based on the simulation time and key information of the message in the message list; According to the simulation indication information, a target message to be sent is determined from the message sequence, and simulation processing is performed on the target message.
2. The method according to claim 1, wherein: The generation process of the message sequence includes: Acquire a message sorting rule, and sort the N messages according to the message sorting rule to generate the message sequence.
3. The method according to claim 1 or 2, wherein: The generation process of the message sequence includes: Obtaining time adjustment rules, where time adjustment includes time delay, time advance and time adaptation; The time intervals of the N messages are adjusted according to the time adjustment rule to generate the message sequence.
4. The method according to claim 1 or 2, wherein: The generation process of the message sequence includes: Acquire a message adjustment rule, where the message adjustment rule includes a message deletion operation and / or a message addition operation; The N messages are deleted and / or added according to the message adjustment rule to generate the message sequence.
5. The method according to claim 4, wherein: The extracting key information from the message and generating a message list based on the key information of the message includes: Extract keywords from the messages to obtain the message name and message time of each message; The message list is generated according to the order of the messages in the message sequence by the message names and the message times.
6. The method according to claim 5, wherein: The generating simulation indication information based on the simulation time and the key information of the message in the message list includes: Determine a target message identifier of the target message according to the simulation time and key information of the message in the message list; The simulation indication information is generated based on the target message identifier.
7. The method according to claim 6, wherein: The step of determining the target message to be sent from the message sequence according to the simulation indication information includes: The target message identifier is extracted from the simulation indication information, and the target message is determined in the message list based on the target message identifier.
8. The method according to claim 6, wherein: Determining the target message identifier of the target message according to the simulation time and the key information of the message in the message list includes: Matching the simulation time with the message time in the message list; A target message time matching the simulation time is acquired, and a message identifier associated with the target message time is determined as the target message identifier.
9. The method according to claim 8, wherein: The method further comprises: During the simulation engine flow control process, monitor the rule change instructions; In response to receiving the rule change instruction, the message is readjusted according to the rule change instruction to obtain the updated message sequence.
10. The method according to any one of claims 1 to 9, wherein: The simulating process of the target message includes: The target message is sent to a simulation processing node for simulation processing.
11. The method according to claim 10, wherein: The method further comprises: In response to the target message being sent, deleting the target message from the message sequence; In response to the message sequence being empty, N messages are read again from the drive test information set to generate a new message sequence.
12. The method according to claim 11, wherein: The method further comprises: In response to the message sequence being empty and the drive test data set being empty, the simulation is terminated.
13. The method according to claim 12, wherein: The step of reading N messages from the drive test information set and sorting them to generate a message sequence includes: According to the length of the simulation playback window, read N messages from the drive test data set and store them in the simulation playback window, wherein N is not greater than the length of the playback window; In the simulation playback window, the N messages are adjusted to generate a message sequence.
14. An automatic driving simulation device, comprising: A first acquisition module, configured to acquire a drive test information set and read N messages from the drive test information set, where N is a positive integer; A second acquisition module, used to adjust the N messages to generate a message sequence; A third acquisition module is used to extract key information from the messages in the message sequence and generate a message list based on the key information of the N messages; A fourth acquisition module, used to determine the simulation time, and generate simulation indication information based on the simulation time and key information of the message in the message list; The simulation module is used to determine the target message to be sent from the message sequence according to the simulation indication information, and perform simulation processing on the target message.
15. The device according to claim 14, wherein: The second acquisition module includes: Acquire a message sorting rule, and sort the N messages according to the message sorting rule to generate the message sequence.
16. The device according to claim 14 or 15, wherein: The second acquisition module includes: Obtaining time adjustment rules, where time adjustment includes time delay, time advance and time adaptation; The time intervals of the N messages are adjusted according to the time adjustment rule to generate the message sequence.
17. The device according to claim 14 or 15, wherein: The second acquisition module includes: Acquire a message adjustment rule, where the message adjustment rule includes a message deletion operation and / or a message addition operation; The N messages are deleted and / or added according to the message adjustment rule to generate the message sequence.
18. The device according to claim 17, wherein: The third acquisition module includes: Extract keywords from the messages to obtain the message name and message time of each message; The message list is generated according to the order of the messages in the message sequence by the message names and the message times.
19. The device according to claim 15, wherein: The fourth acquisition module includes: Determine a target message identifier of the target message according to the simulation time and key information of the message in the message list; The simulation indication information is generated based on the target message identifier.
20. The device according to claim 19, wherein The simulation module comprises: The target message identifier is extracted from the simulation indication information, and the target message is determined in the message list based on the target message identifier.
21. The device according to claim 19, wherein The simulation module comprises: Matching the simulation time with the message time in the message list; A target message time matching the simulation time is acquired, and a message identifier associated with the target message time is determined as the target message identifier.
22. The device according to claim 21, wherein The device also includes: During the simulation engine flow control process, monitor the rule change instructions; In response to receiving the rule change instruction, the message is readjusted according to the rule change instruction to obtain the updated message sequence.
23. The device according to any one of claims 14 to 22, wherein: The simulation module comprises: The target message is sent to a simulation processing node for simulation processing.
24. The device according to claim 23, wherein: The device also includes: In response to the target message being sent, deleting the target message from the message sequence; In response to the message sequence being empty, N messages are read again from the drive test information set to generate a new message sequence.
25. The device according to claim 24, wherein The device also includes: In response to the message sequence being empty and the drive test data set being empty, the simulation is terminated.
26. The device according to claim 25, wherein The second acquisition module includes: According to the length of the simulation playback window, read N messages from the drive test data set and store them in the simulation playback window, wherein N is not greater than the length of the playback window; In the simulation playback window, the N messages are adjusted to generate a message sequence.
27. 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, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 13.
28. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-13.
29. A computer program product comprising a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 13.
