A method, device, equipment and medium for realizing high-order automatic driving

Abstract

The application provides a method for realizing high-order automatic driving, comprising the following steps: receiving a to-be-processed request sent by a target vehicle in a driving process, wherein the to-be-processed request carries to-be-processed running information of the target vehicle in the driving process; obtaining sample driving data from a data center; the sample driving data is determined based on road driving data collected by a sample vehicle; analyzing the to-be-processed running information and the sample driving data to obtain a running processing strategy corresponding to the to-be-processed running information; and sending the running processing strategy to the target vehicle, so that the target vehicle processes the to-be-processed running information based on the running processing strategy. In the above technical solution, the target vehicle can actively interact with information when processing information to obtain a running processing strategy to process to-be-processed running information, so as to integrate the target vehicle into internet self-learning, and improve the information processing efficiency and processing capacity of the target vehicle in the driving process.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a method, apparatus, device and medium for realizing high-level autonomous driving. Background Technology

[0002] Autonomous driving solutions focus on the integration of vision systems and artificial intelligence algorithms. Specifically, the information collected by the vision system is labeled as video, and the algorithm is used to recognize and learn the scene, gradually optimizing the software logic and accumulating driving experience, similar to how humans drive cars with their eyes. Its core requires an excellent software fusion system and a wealth of video labeling samples.

[0003] Currently, existing technologies focus on solutions that integrate visual and artificial intelligence algorithms, such as... Figure 1 As shown, the autonomous driving system in this scheme is a relatively closed system that relies on the efficient integration of information processing system and surrounding sensor information to optimize the software system in order to obtain a better autonomous driving experience. This scheme has significant knowledge limitations in machine learning, and it does not integrate intelligent vehicle self-learning with the Internet big data environment system, thus failing to support high-level autonomous driving. Summary of the Invention

[0004] This application provides a method, apparatus, device, and medium for realizing high-level autonomous driving to overcome the defects of the prior art, which can integrate intelligent vehicles into Internet self-learning, thereby improving the information processing efficiency and processing capability of intelligent vehicles during driving.

[0005] To solve the above-mentioned technical problems, this application provides the following technical solution:

[0006] According to a first aspect of the embodiments of this application, a method for implementing high-level autonomous driving is provided, comprising:

[0007] Receive a pending request sent by the target vehicle during its driving process, wherein the pending request carries pending operation information of the target vehicle during its driving process;

[0008] Sample driving data is obtained from the data center; the sample driving data is determined based on road driving data collected from sample vehicles.

[0009] Analyze the pending operation information and the sample driving data to obtain the operation processing strategy corresponding to the pending operation information;

[0010] The operation processing strategy is sent to the target vehicle so that the target vehicle processes the operation information to be processed based on the operation processing strategy.

[0011] In an exemplary embodiment, the target vehicle is in a factory state, and the method further comprises a step of training and learning the intelligent vehicle in an unfactory state, and the training and learning the intelligent vehicle in the unfactory state comprises:

[0012] obtaining road driving data of a target scene; the road driving data of the target scene is determined based on the road driving data collected by the sample vehicle;

[0013] editing the road driving data of the target scene to obtain training information;

[0014] training and learning the intelligent vehicle in the unfactory state based on the training information to obtain a trained intelligent vehicle;

[0015] testing the trained intelligent vehicle;

[0016] updating the state of the trained intelligent vehicle to the factory state when the test result meets a preset condition.

[0017] In an exemplary embodiment, the method further comprises:

[0018] analyzing the test process of the trained intelligent vehicle when the test result does not meet the preset condition to obtain an analysis result corresponding to the test process;

[0019] repeating the training and learning of the trained intelligent vehicle based on the analysis result until the test result of the trained intelligent vehicle meets the preset condition.

[0020] In an exemplary embodiment, the method further comprises:

[0021] obtaining running state information of the target vehicle;

[0022] obtaining the training information when the running state information of the target vehicle is in a non-driving state;

[0023] sending the training information to the target vehicle to enable the target vehicle to autonomously learn based on the training information.

[0024] In an exemplary embodiment, the obtaining of the sample driving data from the data center comprises:

[0025] obtaining road driving data stored in the data center; the road driving data stored in the data center is obtained by pre-analysis based on the road driving data collected by the sample vehicle;

[0026] Based on the to-be-processed running information, analyze road driving data stored in the data center to obtain the sample driving data.

[0027] In an exemplary embodiment, the obtaining the training information comprises:

[0028] obtaining the training information from a learning platform, the learning platform being configured to store the training information.

[0029] In an exemplary embodiment, the testing the intelligent vehicle after the training and learning comprises:

[0030] performing software intelligent simulation testing and road testing on the intelligent vehicle after the training and learning.

[0031] According to a second aspect of the embodiments of the present application, a device for implementing high-order automatic driving is provided, and the device comprises:

[0032] an information receiving module configured to receive a to-be-processed request sent by a target vehicle during driving, the to-be-processed request carrying to-be-processed running information of the target vehicle during driving;

[0033] a sample data obtaining module configured to obtain sample driving data from a data center, the sample driving data being determined based on road driving data collected by a sample vehicle;

[0034] an information analyzing module configured to analyze the to-be-processed running information and the sample driving data to obtain a running processing strategy corresponding to the to-be-processed running information;

[0035] a processing strategy sending module configured to send the running processing strategy to the target vehicle, so that the target vehicle processes the to-be-processed running information based on the running processing strategy.

[0036] According to a third aspect of the embodiments of the present application, an electronic device is provided, comprising a processor and a memory, the memory storing at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by the processor to implement the method for implementing high-order automatic driving.

[0037] According to a fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, the storage medium storing at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by a processor to implement the method for implementing high-order automatic driving.

[0038] By adopting the above technical solutions, the present application has the following beneficial effects:

[0039] The application provides a method, device, equipment and medium for realizing high-order automatic driving. When there is to-be-processed running information of a target vehicle in a driving process, a to-be-processed request sent by the target vehicle is received, the to-be-processed request carrying the to-be-processed running information of the target vehicle in the driving process. Sample driving data is obtained from a data center. Through analysis of the to-be-processed running information and the sample driving data, a running processing strategy corresponding to the to-be-processed running information is obtained, and the running processing strategy is sent to the target vehicle to process the to-be-processed running information. In the above technical solution, the target vehicle can actively interact with information when processing the information to obtain a running processing strategy to process to-be-processed running information, so that the target vehicle is integrated into Internet self-learning, and the information processing efficiency and processing capability of the target vehicle in the driving process are improved. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0041] Figure 1 A scheme diagram focusing on the fusion of vision and artificial intelligence algorithm provided by the prior art;

[0042] Figure 2 A flowchart of a method for realizing high-order automatic driving provided by the embodiment of the present application;

[0043] Figure 3 A flowchart of training an intelligent automobile in an unshipped state provided by the embodiment of the present application;

[0044] Figure 4 A flowchart of training an intelligent automobile in a shipped state provided by the embodiment of the present application;

[0045] Figure 5 A structure block diagram of a device for realizing high-order automatic driving provided by the embodiment of the present application;

[0046] Figure 6 A hardware structure block diagram of an electronic device for running a method for realizing high-order automatic driving provided by the embodiment of the present application. DETAILED DESCRIPTION

[0047] With reference to the drawings and the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0048] The "one embodiment" or "an embodiment" as referred to herein means a specific feature, structure, or characteristic under discussion. In describing the embodiments of the present application, it should be understood that the terms "upper", "lower", "top", "bottom", and the like refer to the orientation or position as shown in the drawings, and are used for convenience and simplicity of description and are not intended to indicate or imply that a specific orientation of the device or element is required for the proper working of the present application, and therefore should not be construed as limiting the present application. In addition, the terms "first", "second", are used for descriptive purposes only and should not be construed as indicating or implying relative importance or an indicated number of technical features. Therefore, the features defined as "first", "second" can explicitly or implicitly include one or more of the features. Moreover, the terms "first", "second", and the like are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0049] Referring to Figure 2 , which shows a flowchart of a method for implementing high-level automatic driving provided by an embodiment of the present application. The method for implementing high-level automatic driving comprises:

[0050] Step S101: receiving a to-be-processed request sent by a target vehicle during driving, the to-be-processed request carrying to-be-processed running information of the target vehicle during driving;

[0051] Step S102: obtaining sample driving data from a data center; the sample driving data is determined based on road driving data collected by a sample vehicle;

[0052] Step S103: analyzing the to-be-processed running information and the sample driving data to obtain a running processing strategy corresponding to the to-be-processed running information;

[0053] Step S104: sending the running processing strategy to the target vehicle, so that the target vehicle processes the to-be-processed running information based on the running processing strategy.

[0054] In one specific embodiment, a to-be-processed request sent by a target vehicle during driving is received through step S101, and the to-be-processed request carries to-be-processed running information of the target vehicle during driving; wherein the target vehicle is a smart vehicle in a factory state, and the to-be-processed running information can include running fault information, scene decision demand information, software cognition demand information and self-learning demand information; sample driving data is obtained from a data center through step S102; wherein the sample driving data is determined based on road driving data collected by a sample vehicle, the sample vehicle is a smart vehicle in a factory state, and the road driving data collected by the sample vehicle is real-time updated data; optionally, the sample vehicle collects road driving data through a sensing module, and then sends the road driving data to the data center for storage; the to-be-processed running information and the sample driving data are analyzed through step S103 to obtain a running processing strategy corresponding to the to-be-processed running information; in the case that corresponding target driving data of the to-be-processed running information exists in the sample driving data, the running processing strategy is obtained through a target processing strategy corresponding to the target driving data; in the case that corresponding target driving data of the to-be-processed running information does not exist in the sample driving data, the sample driving data is analyzed to obtain analyzed driving data, the analyzed driving data is processed to further obtain the running processing strategy capable of processing the to-be-processed running information; the running processing strategy is sent to the target vehicle through step S104, so that the target vehicle processes the to-be-processed running information based on the running processing strategy, and the effect of processing information through active information interaction is realized.

[0055] The method for implementing high-order automatic driving described in this embodiment enables the target vehicle to actively interact information when processing information to obtain a running processing strategy to process to-be-processed running information, thereby integrating the target vehicle into Internet self-learning and improving the information processing efficiency and processing capability of the target vehicle during driving.

[0056] Please refer to Figure 3 which is a flowchart of training a smart vehicle in a factory state provided by the embodiment of the application, and the training step includes:

[0057] Step S201: obtaining road driving data of a target scene; the road driving data of the target scene is determined based on road driving data collected by a sample vehicle;

[0058] Step S202: editing the road driving data of the target scene to obtain training information;

[0059] Step S203: training and learning the smart car in the unshipped state based on the training information, to obtain a trained and learned smart car;

[0060] Step S204: testing the trained and learned smart car;

[0061] Step S205: determining whether the test result meets a preset condition;

[0062] Step S206: if yes, updating the state of the trained and learned smart car to a shipped state;

[0063] Step S207: if no, analyzing the test process of the trained and learned smart car, to obtain an analysis result corresponding to the test process;

[0064] Step S208: training and learning the trained and learned smart car based on the analysis result;

[0065] Steps S204 and S205 are repeated until the test result of the trained and learned smart car meets the preset condition.

[0066] In one specific embodiment, the road driving data of the target scene is obtained through step S201; wherein the road driving data of the target scene is determined based on the road driving data collected by the sample vehicle; optionally, the sample vehicle collects the road driving data through a sensing module, and then sends the road driving data to the data center for storage, and the road driving data of the target scene is obtained based on the road driving data stored in the data center after marking processing, analysis and screening; the road driving data of the target scene is edited through step S202 to obtain training information; optionally, the training information can specifically be a driving training course corresponding to the target scene, and the driving training course can include a software logic training course for improving the driving intelligence level of the intelligent vehicle and a knowledge reserve training course for improving the driving experience level of the intelligent vehicle; the intelligent vehicle in the unshipped state is trained and learned based on the training information through step S203 to obtain the intelligent vehicle after training and learning; optionally, the intelligent vehicle in the unshipped state is trained and learned based on the driving training course corresponding to the target scene; the intelligent vehicle after training and learning is tested through step S204 to obtain a test result; it is judged whether the test result meets a preset condition through step S205; when the test result meets the preset condition, step S206 is executed to update the state of the intelligent vehicle after training and learning to a shipped state, that is, the intelligent vehicle after training and learning is qualified for testing and can be shipped; when the test result does not meet the preset condition, step S207 is executed to analyze the testing process of the intelligent vehicle after training and learning, determine the test items of the intelligent vehicle after training and learning that do not meet the preset condition in the testing process, and obtain an analysis result corresponding to the testing process; the intelligent vehicle after training and learning is trained and learned based on the analysis result through step S208, and steps S204 and S205 are repeated until the test result of the intelligent vehicle after training and learning meets the preset condition. Through the above training, the driving intelligence level and the driving experience level of the intelligent vehicle in the unshipped state can be improved, so that the intelligent vehicle meets the preset condition when it is shipped, and optionally, the intelligent vehicle meets the software logic requirements and scene operation requirements integrated by the real-time updated road driving data when it is shipped, so that when the intelligent vehicle is in the target scene during driving, the corresponding training information can be directly called for processing, avoiding a large amount of screening and analysis work of road driving data and affecting normal driving.

[0067] Please refer to Figure 4 which shows a flowchart of training an intelligent vehicle in an unshipped state according to an embodiment of the present application, and the training step includes:

[0068] Step S301: obtaining running state information of the target vehicle;

[0069] Step S302: In the case that the running state information of the target vehicle is in a non-driving state, the training information is acquired;

[0070] Step S303: The training information is sent to the target vehicle, so that the target vehicle autonomously learns based on the training information.

[0071] In one specific embodiment, the running state information of the target vehicle is acquired through step S301; wherein the target vehicle is a smart car in a factory state; the training information is acquired through step S302 in the case that the running state information of the target vehicle is in a non-driving state; wherein the training information is real-time updated information; optionally, when the target vehicle is in a parking state, the intelligent information processing hub of the target vehicle acquires the training information on a learning platform by accessing the Internet; the training information is sent to the target vehicle through step S303, so that the target vehicle autonomously learns based on the training information. Through the above steps, if the target vehicle is a smart car that meets the preset conditions, the intelligence level and experience level can be further improved through the real-time updated training information; if the target vehicle is a smart car that does not meet the preset conditions, the training information can be used for training learning to meet the preset conditions, and the intelligence level and experience level can be further improved through the real-time updated training information.

[0072] In an optional embodiment, in the above step S102, the sample driving data acquired from the data center can include:

[0073] The road driving data stored in the data center is acquired; the road driving data stored in the data center is obtained based on pre-analysis of the road driving data collected by the sample vehicle;

[0074] Based on the to-be-processed running information, the road driving data stored in the data center is analyzed to obtain the sample driving data.

[0075] Specifically, the sample vehicle collects road driving data through a sensing module, analyzes the road driving data through a pre-analysis module, and sends the analyzed road driving data to the data center for storage, thereby obtaining the road driving data stored in the data center; the sample driving data is the road driving data within a preset range corresponding to the to-be-processed running information obtained by filtering and analyzing the road driving data stored in the data center, i.e., the sample driving data.

[0076] In an optional embodiment, in the above step S302, the training information can be acquired by:

[0077] obtaining the training information from a learning platform, the learning platform being configured to store the training information.

[0078] Specifically, after the step S202 is performed, the training information is sent to the learning platform for storage; and when the step S302 is performed, the training information is obtained from the learning platform.

[0079] In an optional embodiment, in the step S204, the testing of the intelligent vehicle after the training and learning can include:

[0080] The intelligent vehicle after the training and learning is tested by software intelligent simulation and road test.

[0081] Specifically, the software intelligent simulation and the road test are respectively provided with a plurality of test items, in a case where the plurality of test items respectively meet the preset condition, the test result is qualified, and the state of the intelligent vehicle after the training and learning is updated to a factory state; in a case where the test result does not meet the preset condition, a test process of the intelligent vehicle after the training and learning is analyzed, i.e., a test process of the plurality of test items is analyzed, a plurality of analysis results corresponding to the test items are obtained, an analysis result not meeting the preset condition is screened out, a test item corresponding to the analysis result not meeting the preset condition is obtained, i.e., an unqualified test item is obtained, the training and learning of the intelligent vehicle after the training and learning are repeated for the training information corresponding to the unqualified test item, until the test result of the intelligent vehicle after the training and learning meets the preset condition.

[0082] As can be seen from the above technical solutions of the embodiments of the present application, in the embodiments of the present application, when there is to-be-processed running information of a target vehicle in a driving process, a to-be-processed request sent by the target vehicle is received, the to-be-processed request carries the to-be-processed running information of the target vehicle in the driving process, sample driving data is obtained from a data center, a running processing strategy corresponding to the to-be-processed running information is obtained by analyzing the to-be-processed running information and the sample driving data, and the running processing strategy is sent to the target vehicle to process the to-be-processed running information; in the above technical solutions, the target vehicle can actively perform information interaction when processing information to obtain a running processing strategy to process to-be-processed running information, so as to integrate the target vehicle into Internet self-learning, and improve the information processing efficiency and processing capability of the target vehicle in the driving process.

[0083] Corresponding to the method for implementing high-order automatic driving provided in the foregoing embodiments, the embodiments of the present application further provide a device for implementing high-order automatic driving. Since the device for implementing high-order automatic driving provided in the embodiments of the present application corresponds to the method for implementing high-order automatic driving provided in the foregoing embodiments, the foregoing implementation manners of the method for implementing high-order automatic driving are also applicable to the device for implementing high-order automatic driving provided in the embodiments of the present application, and will not be described in detail herein.

[0084] Please refer to Figure 5 which is a structural block diagram of a device for implementing high-order automatic driving provided in the embodiments of the present application; the device comprises:

[0085] an information receiving module, configured to receive a to-be-processed request sent by a target vehicle in a driving process, the to-be-processed request carrying to-be-processed running information of the target vehicle in the driving process;

[0086] a sample data obtaining module, configured to obtain sample driving data from a data center; the sample driving data is determined based on road driving data collected by a sample vehicle;

[0087] an information analyzing module, configured to analyze the to-be-processed running information and the sample driving data, to obtain a running processing strategy corresponding to the to-be-processed running information;

[0088] a processing strategy sending module, configured to send the running processing strategy to the target vehicle, so that the target vehicle processes the to-be-processed running information based on the running processing strategy.

[0089] In one specific embodiment, a target vehicle in the process of driving sends a to-be-processed request through an information receiving module, and the to-be-processed request carries to-be-processed running information of the target vehicle in the process of driving; wherein the target vehicle is a smart car in a factory state, and the to-be-processed running information can include running fault information, scene decision demand information, software cognition demand information and self-learning demand information; a sample data acquisition module acquires sample driving data from a data center; wherein the sample driving data is determined based on road driving data collected by a sample vehicle, the sample vehicle is a smart car in a factory state, and the road driving data collected by the sample vehicle is real-time updated data; optionally, the sample vehicle collects road driving data through a sensing module and sends the road driving data to the data center for storage; an information analysis module analyzes the to-be-processed running information and the sample driving data to obtain a running processing strategy corresponding to the to-be-processed running information; in the case that the to-be-processed running information has corresponding target driving data in the sample driving data, the running processing strategy is obtained through a target processing strategy corresponding to the target driving data; in the case that the to-be-processed running information does not have corresponding target driving data in the sample driving data, the sample driving data is analyzed to obtain analyzed driving data, the analyzed driving data is processed to obtain the running processing strategy capable of processing the to-be-processed running information; and a processing strategy sending module sends the running processing strategy to the target vehicle, so that the target vehicle processes the to-be-processed running information based on the running processing strategy, and the effect of processing information through active information interaction is realized.

[0090] The device for implementing high-order automatic driving described in the embodiment enables the target vehicle to actively interact information when processing information to obtain a running processing strategy to process to-be-processed running information, thereby integrating the target vehicle into Internet self-learning and improving the information processing efficiency and processing capability of the target vehicle in the process of driving.

[0091] In one optional embodiment, the above device can further include:

[0092] A target data acquisition module is configured to acquire road driving data of a target scene; the road driving data of the target scene is determined based on the road driving data collected by the sample vehicle;

[0093] An editing module is configured to edit the road driving data of the target scene to obtain training information;

[0094] A training module is configured to train and learn the smart car in the un-factory state based on the training information to obtain a trained and learned smart car;

[0095] a test module configured to test the intelligent vehicle after the training and learning;

[0096] a judgment module configured to judge whether the test result meets a preset condition;

[0097] a factory shipment module configured to update a state of the intelligent vehicle after the training and learning to a factory shipment state when the test result meets the preset condition;

[0098] a test analysis module configured to analyze a test process of the intelligent vehicle after the training and learning when the test result does not meet the preset condition, and obtain an analysis result corresponding to the test process;

[0099] a continuous training module configured to train and learn the intelligent vehicle after the training and learning based on the analysis result;

[0100] In one specific embodiment, road driving data of a target scene is acquired by a target data acquisition module; wherein the road driving data of the target scene is determined based on road driving data collected by a sample vehicle; optionally, the sample vehicle collects road driving data by a sensing module, and then sends the road driving data to the data center for storage, and the road driving data of the target scene is obtained based on marking processing and analysis screening of the road driving data stored in the data center; the road driving data of the target scene is edited by an editing module to obtain training information; optionally, the training information can specifically be a driving training course corresponding to the target scene, and the driving training course can include a software logic training course for improving the intelligent vehicle driving intelligence level and a knowledge reserve training course for improving the intelligent vehicle driving experience level; the intelligent vehicle in an unshipped state is trained and learned based on the training information by a training module to obtain an intelligent vehicle after training and learning; optionally, the intelligent vehicle in the unshipped state is trained and learned based on the driving training course corresponding to the target scene; the intelligent vehicle after training and learning is tested by a testing module to obtain a test result; whether the test result meets a preset condition is judged by a judging module; when the test result meets the preset condition, the state of the intelligent vehicle after training and learning is updated to a shipped state by a shipping module, that is, the intelligent vehicle after training and learning is qualified for testing and can be shipped; when the test result does not meet the preset condition, the testing process of the intelligent vehicle after training and learning is analyzed by a test analysis module to determine a test item in the testing process in which the intelligent vehicle after training and learning does not meet the preset condition, and an analysis result corresponding to the testing process is obtained; the intelligent vehicle after training and learning is trained and learned based on the analysis result by a continuous training module, and the testing module and the judging module are used until the test result of the intelligent vehicle after training and learning meets the preset condition. Through the above modules, the driving intelligence level and the driving experience level of the intelligent vehicle in the unshipped state can be improved, so that the intelligent vehicle meets the preset condition when it is shipped, and optionally, the intelligent vehicle meets the software logic requirement and the scene operation requirement integrated from the real-time updated road driving data when it is shipped, so that when the intelligent vehicle is in the target scene during driving, the corresponding training information can be directly called for processing, avoiding a large amount of screening and analysis work of road driving data and affecting normal driving.

[0101] In one optional embodiment, the above device can further include:

[0102] a state information acquisition module configured to acquire running state information of the target vehicle;

[0103] a training information obtaining module, configured to obtain the training information when the running state information of the target vehicle is in a non-driving state;

[0104] a training information sending module, configured to send the training information to the target vehicle, so that the target vehicle autonomously learns based on the training information.

[0105] In one specific embodiment, the running state information of the target vehicle is obtained by a state information obtaining module; the target vehicle is a smart car in a factory state; the training information is obtained by a training information obtaining module when the running state information of the target vehicle is in a non-driving state; the training information is real-time updated information; optionally, when the target vehicle is in a parking state, the intelligent information processing hub of the target vehicle accesses the Internet and obtains the training information on a learning platform; the training information is sent to the target vehicle by a training information sending module, so that the target vehicle autonomously learns based on the training information. Through the above steps, if the target vehicle is a smart car that meets the preset conditions, the intelligence level and experience level can be further improved through the real-time updated training information; if the target vehicle is a smart car that does not meet the preset conditions, the training information can be used for training learning to meet the preset conditions, and the intelligence level and experience level can be further improved through the real-time updated training information.

[0106] In one optional embodiment, the above sample data obtaining module can include:

[0107] a driving data obtaining module, configured to obtain road driving data stored in a data center; the road driving data stored in the data center is obtained based on pre-analysis of road driving data collected by the sample vehicle;

[0108] a driving data analysis module, configured to analyze the road driving data stored in the data center based on the to-be-processed running information, to obtain the sample driving data.

[0109] In one optional embodiment, the above device can further include:

[0110] a platform module, configured to store the training information sent by the editing module.

[0111] In one optional embodiment, the above test module can include:

[0112] a software test module, configured to perform software intelligent simulation testing on the smart car after training and learning;

[0113] ​A road test module is configured to perform road tests on the intelligent vehicle after the training.

[0114] It should be noted that the device provided in the above embodiment is only exemplified by the above-mentioned division of functional modules when realizing its functions, and in actual application, the above-mentioned functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above-described functions. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be described here.

[0115] The device for implementing high-order automatic driving provided in the embodiment of the application, when there is to-be-processed running information of a target vehicle in a driving process, receives a to-be-processed request sent by the target vehicle through an information receiving module, the to-be-processed request carries to-be-processed running information of the target vehicle in the driving process, then obtains sample driving data from a data center through a sample data obtaining module, analyzes the to-be-processed running information and the sample driving data through an information analyzing module, obtains a running processing strategy corresponding to the to-be-processed running information, and sends the running processing strategy to the target vehicle through a processing strategy sending module to process the to-be-processed running information. In the above technical solution, the target vehicle can actively interact information when processing information to obtain a running processing strategy to process to-be-processed running information, so as to integrate the target vehicle into Internet self-learning, and improve the information processing efficiency and processing capability of the target vehicle in the driving process.

[0116] The embodiment of the application further provides an electronic device, including a processor and a memory, the memory stores at least one instruction or at least one program, the at least one instruction or the at least one program is loaded and executed by the processor to realize the method for implementing high-order automatic driving provided in the above method embodiment.

[0117] The memory can be used to store software programs and modules, and the processor can execute various functions and applications and realize high-order automatic driving by running the software programs and modules stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs required by functions, etc.; the data storage area can store data created according to the use of the device, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory can also include a memory controller to provide access to the memory for the processor.

[0118] The method embodiments provided by the embodiments of the present application can be executed in a computer terminal, a server or a similar computing device, that is, the electronic device described above can include a computer terminal, a server or a similar computing device. Figure 6 is a hardware structure block diagram of an electronic device running a method for implementing high-order automatic driving provided by the embodiments of the present application, as shown in Figure 6 The internal structure of the electronic device can include but is not limited to a processor, a network interface and a memory. Among them, the processor, the network interface and the memory in the electronic device can be connected through a bus or other means. In the embodiments of the present application Figure 6 , the connection through the bus is taken as an example.

[0119] Among them, the processor (or CPU (Central Processing Unit, Central Processing Unit)) is the computing core and control core of the electronic device. The network interface can optionally include a standard wired interface, a wireless interface (such as WI-FI, a mobile communication interface, etc.). The memory is a memory device in the electronic device, used to store programs and data. It can be understood that the memory here can be a high-speed RAM storage device, or a non-volatile storage device (non-volatile memory), for example, at least one disk storage device; optionally, it can also be at least one storage device located away from the aforementioned processor. The memory provides a storage space that stores the operating system of the electronic device, which can include but is not limited to: Windows system (an operating system), Linux (an operating system), Android (an operating system) system, IOS (a mobile operating system) system, etc., and the present application does not limit this; and in the storage space, one or more instructions suitable for being loaded and executed by the processor are also stored, and these instructions can be one or more computer programs (including program codes). In the embodiments of the present application, the processor loads and executes one or more instructions stored in the memory to implement the method for implementing high-order automatic driving provided by the method embodiments.

[0120] The embodiments of the present application also provide a computer readable storage medium, and the storage medium stores at least one instruction or at least one program. The at least one instruction or at least one program is loaded and executed by the processor to implement the method for implementing high-order automatic driving provided by the method embodiments.

[0121] Optionally, in the embodiment, the storage medium can include, but is not limited to, a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0122] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The above-mentioned embodiments of the present application are described. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multiple sample image classification and parallel processing are also possible or can be advantageous.

[0123] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other. Each embodiment focuses on the difference from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0124] A person of ordinary skill in the art can understand that all or part of the steps of the above-mentioned embodiments can be completed by hardware, or by program to instruct relevant hardware to complete. The program can be stored in a computer readable storage medium. The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk.

[0125] The above is only a preferred embodiment of the present application, and is not used to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for implementing high-order autonomous driving, characterized in that, Comprise: Receiving a to-be-processed request sent by a target vehicle during driving, the to-be-processed request carrying to-be-processed running information of the target vehicle during driving; The target vehicle is a smart car in a factory state; Filtering and analyzing road driving data stored in a data center to obtain sample driving data; the sample driving data is road driving data corresponding to the to-be-processed running information; The road driving data is collected by a sample vehicle; Analyzing the to-be-processed running information and the sample driving data to obtain a running processing strategy corresponding to the to-be-processed running information; Send the running processing strategy to the target vehicle, so that the target vehicle processes the to-be-processed running information based on the running processing strategy; In the case that the running state information of the target vehicle is in a non-driving state, real-time updated training information is obtained; The training information is a driving training course corresponding to a target scene; the driving training course includes a software logic training course for improving the driving intelligence level of a smart car and a knowledge reserve training course for improving the driving experience level of a smart car; The training information is obtained by acquiring and editing road driving data of a target scene; The road driving data of the target scene is obtained based on road driving data stored in the data center and marked, analyzed and filtered; Send the training information to the target vehicle to enable the target vehicle to learn autonomously based on the training information.

2. The method for realizing high-order automatic driving according to claim 1, characterized in that, The target vehicle is in a factory state, and the method further comprises a step of training and learning a smart car in an unmanufactured state, wherein the training and learning of the smart car in the unmanufactured state comprises: Training and learning the smart car in the unmanufactured state based on the training information to obtain a trained and learned smart car; Testing the trained and learned smart car; In the case that the test result meets the preset condition, updating the state of the trained and learned smart car to a factory state.

3. The method for realizing high-order automatic driving according to claim 2, characterized in that, The method further comprises: In the case that the test result does not meet the preset condition, analyzing the test process of the trained and learned smart car to obtain an analysis result corresponding to the test process; Based on the analysis result, repeatedly training and learning the trained and learned smart car until the test result of the trained and learned smart car meets the preset condition.

4. The method for realizing high-order automatic driving according to claim 1, characterized in that, The method further comprises: Obtaining the training information from a learning platform; the learning platform is used to store the training information.

5. The method for realizing high-order automatic driving according to claim 2, characterized in that, The testing of the trained and learned smart car comprises: Software intelligent simulation testing and road testing of the trained and learned smart car.

6. An apparatus for implementing high-order autonomous driving, characterized by comprising: The device comprises: An information receiving module for receiving a to-be-processed request sent by a target vehicle during driving, the to-be-processed request carrying to-be-processed running information of the target vehicle during driving; the target vehicle is a smart car in a factory state; The sample data acquisition module is configured to analyze and filter road driving data stored in the data center to obtain sample driving data, wherein the sample driving data is road driving data corresponding to the to-be-processed operation information, and the road driving data is collected by a sample vehicle; The information analysis module is configured to analyze the to-be-processed operation information and the sample driving data to obtain an operation processing strategy corresponding to the to-be-processed operation information; The processing strategy sending module is configured to send the operation processing strategy to the target vehicle, so that the target vehicle processes the to-be-processed operation information based on the operation processing strategy; The training information acquisition module is configured to acquire real-time updated training information when the operation state information of the target vehicle is in a non-driving state, wherein the training information is a driving training course corresponding to a target scene, the driving training course includes a software logic training course for improving the driving intelligence level of an intelligent vehicle and a knowledge reserve training course for improving the driving experience level of the intelligent vehicle, the training information is obtained by acquiring and editing road driving data of the target scene, and the road driving data of the target scene is obtained based on road driving data stored in the data center and marked, analyzed and filtered. The training information sending module is configured to send the training information to the target vehicle, so that the target vehicle autonomously learns based on the training information.

7. An electronic device, comprising: The processor and the memory, the memory stores at least one instruction or at least one program, the at least one instruction or the at least one program is loaded and executed by the processor to realize the method for realizing high-order automatic driving in any one of claims 1-5.

8. A computer-readable storage medium, the storage medium stores at least one instruction or at least one program, the at least one instruction or the at least one program is loaded and executed by the processor to realize the method for realizing high-order automatic driving in any one of claims 1-5.

Images