Vehicle behavior prediction and induction method and system based on edge perception data

Abstract

The invention discloses a vehicle behavior prediction and induction method and system based on edge perception data, and relates to the technical field of vehicle-road cooperation. The method comprises the following steps: acquiring target sensing data; analyzing a behavior mode of each target according to the target sensing data, the historical track and the scene data; according to the behavior pattern of each target, generating and sending early warning information to the target vehicle, performing induced intervention on the corresponding target, and generating induced intervention data; and next behavior mode data of the target are collected in real time, feedback data are produced and sent according to the induction intervention data and the next behavior mode data of the target, and feedback interaction is performed on the vehicle. Through the vehicle-road cooperation technology, behavior prediction based on beyond visual range and global information is carried out on each traffic target, traffic safety risks, traffic jam points, prison game difficulty and the like are analyzed, and a real-time active induction scheme is provided to avoid the safety risks and improve the traffic efficiency.

Description

Technical Field

[0001] The present invention relates to the field of vehicle-road collaboration technology, and in particular to a vehicle behavior prediction and induction method and system based on edge perception data. Background Art

[0002] Autonomous driving has currently developed two major routes: single-vehicle intelligence and vehicle-road collaboration. Among them, single-vehicle intelligence has been developed for many years and the technology is relatively mature, but there are still some technical bottlenecks. Therefore, vehicle-road collaboration, which can complement single-vehicle intelligence in terms of technology, has become a must under the proposition of autonomous driving. Vehicle-road collaboration: An intelligent transportation system based on vehicle-to-everything (V2X) direct communication technology to achieve intelligent collaboration between vehicles (Vehicle to Vehicle, V2V), vehicles and roads (Vehicle to Infrastructure, V2I), and vehicles and pedestrians (Vehicle to Pedestrian, V2P).

[0003] Traffic induction has been developed in the field of smart transportation for many years, and a large number of research papers and products have emerged. However, traffic induction at the current stage is all about macro traffic flow prediction, and the only intervention measures that can be taken are lane-level induction such as adjusting traffic light timing plans and road sign reminders. In addition, traffic forecasts must accumulate a certain amount of data before they can be calculated, but serious congestion or accidents may have occurred at this time. The advantage of vehicle-road collaboration is that it opens up the connection between the vehicle and the road, provides a full-process link of roadside perception, cloud analysis, and vehicle-side induction, and provides the basic conditions for real-time vehicle induction.

[0004] The current pain points in the transportation field mainly include:

[0005] Traffic safety risks: Regardless of whether the car has an autonomous driving function or not, due to the limited field of view of the driver and the sensor, they cannot perceive safety risks beyond the visual range, which may lead to accidents. Common dangerous scenarios include foreign objects on the road, emergency stops at highway exits, and blind spots.

[0006] Traffic abnormality: Most traffic jams are not caused by a large number of vehicles, but by some abnormally driven vehicles, which we call traffic jams. For example, when multiple slow-moving vehicles are driving in parallel, the following vehicle cannot overtake, which can only cause the following vehicles to drive slowly or even cause congestion. If these traffic jams are discovered in time through the vehicle-road cooperative system and the relevant vehicles are actively induced and intervened, congestion can be avoided in advance, greatly improving road traffic efficiency.

[0007] Another scenario is when there are many vehicles driving slowly, each vehicle chooses its own optimal driving behavior, which leads to the phenomenon of cutting in and other phenomena that significantly affect the overall traffic efficiency. For this prisoner's dilemma, only by actively intervening and inducing the driving behavior of vehicles from the perspective of global optimization of the vehicle-road cooperative system can the overall traffic operation efficiency be greatly improved.

[0008] For the above-mentioned traffic pain points, the premise of actively intervening and guiding vehicles is to conduct behavioral prediction and analysis on traffic targets. Therefore, how to predict future traffic conditions in advance, infer the possible future behavior patterns of the targets, and then output them to the planning module to help make safe and effective induction plans has become an urgent problem to be solved. Summary of the invention

[0009] In order to overcome the above problems or at least partially solve the above problems, the present invention provides a vehicle behavior prediction and induction method and system based on edge perception data. Through vehicle-road collaborative technology, the behavior of each traffic target is predicted based on beyond-visual-range and global information, and traffic safety risks, traffic congestion points, prisoner's dilemma, etc. are analyzed, and real-time active induction solutions are provided to avoid safety risks and improve traffic efficiency.

[0010] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0011] In a first aspect, the present invention provides a vehicle behavior prediction and induction method based on edge sensing data, comprising the following steps:

[0012] Acquire target perception data;

[0013] Analyze the behavior pattern of each target based on target perception data and historical trajectory and scenario data;

[0014] Generate and send warning information to target vehicles based on the behavior patterns of each target, perform induction intervention on the corresponding target, and generate induction intervention data;

[0015] Collect the target's next behavior pattern data in real time, and generate and send feedback data based on the induced intervention data and the target's next behavior pattern data to interact with the vehicle.

[0016] The present invention uses vehicle-road cooperative technology to predict the behavior of each traffic target based on beyond-visual-range and global information, analyze traffic safety risks, traffic congestion points, prisoner's dilemma, etc., and provide real-time active induction solutions to avoid safety risks and improve traffic efficiency. The present invention can provide accurate and efficient traffic safety risk warnings and actively guide vehicles to avoid safety risks. The present invention predicts traffic behavior for individual targets to achieve real-time response and individual independent induction.

[0017] Based on the first aspect, further, the method for obtaining target perception data includes the following steps:

[0018] Target perception processing is performed based on sensors to carry out target detection, target tracking and target recognition processing to obtain the final target perception data.

[0019] Based on the first aspect, further, the method for analyzing the behavior pattern of each target according to the target perception data and the historical trajectory and scene data comprises the following steps:

[0020] Predict the target's motion trajectory data and confidence data within a preset time period in the future based on historical trajectory and scene data;

[0021] Based on the predicted motion trajectory data and the target three-dimensional spatial data in the target perception data, it is calculated whether there is a collision risk of the predicted target within the credible time interval. If there is a collision risk, the collision intensity and confidence are calculated based on the target type, speed and weight in the target perception data.

[0022] Based on the first aspect, further, the method for generating and sending warning information to the target vehicle according to the behavior pattern of each target includes the following steps:

[0023] Determine the target vehicle information that needs to be induced based on the behavior prediction data;

[0024] Generate warning information based on behavior prediction data and send it to the target vehicle.

[0025] Based on the first aspect, further, the method for generating and sending feedback data according to the induced intervention data and the target's subsequent behavior pattern data, and performing feedback interaction on the vehicle includes the following steps:

[0026] Analyze the difference between the vehicle's current behavior and the induced behavior based on the induced intervention data and the target's next behavior pattern data, and generate a difference analysis result;

[0027] If the result of the difference analysis is that the current behavior is consistent with the induced behavior, reward information is generated and sent; otherwise, guidance and suggestion information is generated and sent.

[0028] In a second aspect, the present invention provides a vehicle behavior prediction and induction system based on edge perception data, including a perception data acquisition module, a behavior prediction and analysis module, an induction intervention module, and a feedback interaction module, wherein:

[0029] A perception data acquisition module, used to acquire target perception data;

[0030] Behavior prediction and analysis module, used to analyze the behavior pattern of each target based on target perception data and historical trajectory and scenario data;

[0031] The induction intervention module is used to generate and send warning information to the target vehicle according to the behavior pattern of each target, perform induction intervention on the corresponding target, and generate induction intervention data;

[0032] The feedback interaction module is used to collect the target's subsequent behavior pattern data in real time, and to generate and send feedback data based on the induced intervention data and the target's subsequent behavior pattern data, so as to perform feedback interaction with the vehicle.

[0033] This system uses the cooperation of multiple modules such as the perception data acquisition module, the behavior prediction and analysis module, the induction intervention module, and the feedback interaction module, combined with the vehicle-road collaborative technology, to predict the behavior of each traffic target based on beyond-visual-range and global information, analyze traffic safety risks, traffic congestion points, prisoner's dilemma, etc., and provide real-time active induction solutions to avoid safety risks and improve traffic efficiency. The present invention can provide accurate and efficient traffic safety risk warnings and actively induce vehicles to avoid safety risks. The present invention predicts traffic behavior for individual targets to achieve real-time response and individual independent induction.

[0034] In a third aspect, the present application provides an electronic device, comprising a memory for storing one or more programs; a processor; when the one or more programs are executed by the processor, the method as described in any one of the first aspects above is implemented.

[0035] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in any one of the first aspects above.

[0036] The present invention has at least the following advantages or beneficial effects:

[0037] The present invention provides a vehicle behavior prediction and induction method and system based on edge sensing data. Through vehicle-road cooperative technology, the behavior of each traffic target is predicted based on beyond-visual-range and global information, and traffic safety risks, traffic congestion points, prisoner's dilemma, etc. are analyzed to provide a real-time active induction solution to avoid safety risks and improve traffic efficiency. The present invention can provide accurate and efficient traffic safety risk warnings and actively guide vehicles to avoid safety risks. The present invention predicts traffic behavior for individual targets to achieve real-time response and individual independent induction. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0039] Figure 1 A flow chart of a vehicle behavior prediction and induction method based on edge sensing data according to an embodiment of the present invention;

[0040] Figure 2 This is an example diagram of a foreign body warning on a highway in an embodiment of the present invention;

[0041] Figure 3 This is an example diagram of a vehicle emergency stop warning in an embodiment of the present invention;

[0042] Figure 4 This is an example diagram of a blind spot collision warning in an embodiment of the present invention;

[0043] Figure 5 This is a principle block diagram of a vehicle behavior prediction and induction system based on edge sensing data according to an embodiment of the present invention;

[0044] Figure 6 A structural block diagram of an electronic device provided by an embodiment of the present invention.

[0045] Explanation of reference numerals: 100, perception data acquisition module; 200, behavior prediction and analysis module; 300, induction intervention module; 400, feedback interaction module; 101, memory; 102, processor; 103, communication interface. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0047] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0049] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0050] In the description of the embodiments of the present invention, "plurality" means at least 2.

[0051] Example:

[0052] like Figure 1 As shown, in a first aspect, an embodiment of the present invention provides a vehicle behavior prediction and induction method based on edge sensing data, comprising the following steps:

[0053] S1, obtain target perception data;

[0054] S2. Analyze the behavior pattern of each target based on the target perception data, historical trajectory and scene data; the behavior pattern of each target includes multiple warning behaviors, and different levels of warning information are generated by distance and speed, such as collision behavior, speeding behavior, etc.

[0055] S3, generating and sending warning information to target vehicles according to the behavior patterns of each target, inducing intervention on the corresponding target, and generating induced intervention data;

[0056] S4. Collect the target's next behavior pattern data in real time, and generate and send feedback data based on the induced intervention data and the target's next behavior pattern data to perform feedback interaction with the vehicle.

[0057] The present invention uses vehicle-road cooperative technology to predict the behavior of each traffic target based on beyond-visual-range and global information, analyze traffic safety risks, traffic congestion points, prisoner's dilemma, etc., and provide real-time active induction solutions to avoid safety risks and improve traffic efficiency. The present invention can provide accurate and efficient traffic safety risk warnings and actively guide vehicles to avoid safety risks. The present invention predicts traffic behavior for individual targets to achieve real-time response and individual independent induction.

[0058] Based on the first aspect, further, the method for obtaining target perception data includes the following steps:

[0059] Target perception processing is performed based on sensors to carry out target detection, target tracking and target recognition processing to obtain the final target perception data.

[0060] In some embodiments of the present invention, the sensor includes a camera, a laser radar, a millimeter-wave radar, etc., and it is only necessary to be able to return the position data and three-dimensional spatial data of the target. The above-mentioned target perception includes detection, tracking, and recognition processing. The target detection algorithm is a typical method in the field of computer vision and will not be described in detail here. The target detection result in the present invention includes 3D detection frame data. For laser radar and millimeter-wave radar, it can be directly obtained using a point cloud detection algorithm. For cameras, there are two ways to obtain the 3D detection frame: the first way is to obtain it using a monocular 3D detection algorithm; the second way is to use data such as the vehicle model, combined with the size information of the vehicle model (obtained through public inquiries on the Internet), to calculate the 3D detection frame data. The above-mentioned target recognition includes vehicle model recognition, license plate recognition, and color recognition.

[0061] Based on the first aspect, further, the method for analyzing the behavior pattern of each target according to the target perception data and the historical trajectory and scene data comprises the following steps:

[0062] Predict the target’s motion trajectory data and confidence data within a preset time period in the future based on historical trajectory and scene data. The confidence data refers to the trajectory prediction algorithm, which is similar to the target detection algorithm. The model will automatically output a confidence value.

[0063] Based on the predicted motion trajectory data and the target three-dimensional spatial data in the target perception data, it is calculated whether there is a collision risk of the predicted target within the credible time interval. If there is a collision risk, the collision intensity and confidence are calculated based on the target type, speed and weight in the target perception data. The confidence refers to the confidence that a collision has occurred, and a quantitative value can be calculated using data such as speed and distance.

[0064] In some embodiments of the present invention, the motion prediction algorithm is used to predict the motion trajectory, confidence and other data of the target within a period of time, and predict the trajectory, confidence and other data of the next period of time (for example, 3s) through historical trajectory data, scene data, etc. . Based on the predicted trajectory data and the target three-dimensional space data, it is calculated whether the predicted target has a collision risk within the credible time interval. Of course, collisions are not limited to collisions between vehicles, but also include vehicles and non-vehicle targets, vehicles and obstacle targets, etc. The specific calculation formula for the collision can be measured by the distance and overlap between two three-dimensional targets. If there is a collision risk, the collision intensity and confidence are calculated based on the target type, speed, weight, etc. For example, the mass is estimated based on the target type, and then the impact force of the collision is calculated based on the speed value, and finally the collision intensity and risk factor are quantified based on the impact force. Analyzing the behavior pattern of each target includes analyzing whether the target has a safety risk, whether it is a blocking-related vehicle, whether there is difficulty in passing, etc. Corresponding warnings are made in combination with different behavior patterns, for example, foreign body warnings on highways, vehicle emergency stop warnings, collision warnings in blind spots, etc. Figure 2-Figure 4 shown.

[0065] Based on the first aspect, further, the method for generating and sending warning information to the target vehicle according to the behavior pattern of each target includes the following steps:

[0066] Determine the target vehicle information that needs to be induced based on the behavior prediction data;

[0067] Generate warning information based on behavior prediction data and send it to the target vehicle.

[0068] In some embodiments of the present invention, the target vehicle to be induced is determined in combination with the behavior prediction data, including data such as the license plate and communication connection; based on the behavior prediction data, warning information is generated, such as how many seconds it will take for a collision with a certain target to occur, how much the risk factor is, etc. Then, the warning information is sent to the target vehicle.

[0069] Based on the first aspect, further, the method for generating and sending feedback data according to the induced intervention data and the target's subsequent behavior pattern data, and performing feedback interaction on the vehicle includes the following steps:

[0070] Analyze the difference between the vehicle's current behavior and the induced behavior based on the induced intervention data and the target's next behavior pattern data, and generate a difference analysis result;

[0071] If the result of the difference analysis is that the current behavior is consistent with the induced behavior, reward information is generated and sent; otherwise, guidance and suggestion information is generated and sent.

[0072] In some embodiments of the present invention, the difference between the vehicle's current behavior and the induced behavior, such as trajectory or intention, is analyzed. Figure 1 If the current behavior is consistent with the induced behavior, the system will issue relevant reward information, such as rewarding cash, increasing points, commending and encouraging information, etc. If the current behavior is inconsistent with the induced behavior, the system will issue guidance and suggestion information, such as analyzing the degree of danger warning information, etc.

[0073] Second, as Figure 5 As shown, an embodiment of the present invention provides a vehicle behavior prediction and induction system based on edge perception data, including a perception data acquisition module 100, a behavior prediction and analysis module 200, an induction intervention module 300 and a feedback interaction module 400, wherein:

[0074] The perception data acquisition module 100 is used to acquire target perception data;

[0075] A behavior prediction and analysis module 200 is used to analyze the behavior pattern of each target based on the target perception data and historical trajectory and scene data;

[0076] The induction intervention module 300 is used to generate and send warning information to the target vehicle according to the behavior pattern of each target, perform induction intervention on the corresponding target, and generate induction intervention data;

[0077] The feedback interaction module 400 is used to collect the target's subsequent behavior pattern data in real time, and to generate and send feedback data based on the induced intervention data and the target's subsequent behavior pattern data, so as to perform feedback interaction with the vehicle.

[0078] This system, through the cooperation of multiple modules such as the perception data acquisition module 100, the behavior prediction and analysis module 200, the induction intervention module 300, and the feedback interaction module 400, combines the vehicle-road cooperative technology to predict the behavior of each traffic target based on beyond-visual-range and global information, analyze traffic safety risks, traffic congestion points, prisoner's dilemma, etc., and provide real-time active induction solutions to avoid safety risks and improve traffic efficiency. The present invention can provide accurate and efficient traffic safety risk warnings and actively induce vehicles to avoid safety risks. The present invention predicts traffic behavior for individual targets to achieve real-time response and individual independent induction.

[0079] like Figure 6 As shown, in a third aspect, an embodiment of the present application provides an electronic device, which includes a memory 101 for storing one or more programs and a processor 102. When the one or more programs are executed by the processor 102, any method in the first aspect described above is implemented.

[0080] The memory 101, the processor 102 and the communication interface 103 are directly or indirectly electrically connected to each other to achieve data transmission or interaction. For example, these elements can be electrically connected to each other through one or more communication buses or signal lines. The memory 101 can be used to store software programs and modules, and the processor 102 executes various functional applications and data processing by executing the software programs and modules stored in the memory 101. The communication interface 103 can be used to communicate signaling or data with other node devices.

[0081] Among them, the memory 101 can be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), etc.

[0082] The processor 102 may be an integrated circuit chip with signal processing capability. The processor 102 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0083] In the embodiments provided in the present application, it should be understood that the disclosed method and system can also be implemented in other ways. The method and system embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the method and system, method and computer program product according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of boxes in the block diagram and / or the flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0084] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0085] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by the processor 102, a method as in any one of the first aspects described above is implemented. If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or part of the contribution to the prior art or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk.

[0086] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0087] It will be apparent to those skilled in the art that the present application is not limited to the details of the exemplary embodiments described above, and that the present application can be implemented in other specific forms without departing from the spirit or essential features of the present application. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the present application is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims be included in the present application. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A vehicle behavior prediction and induction method based on edge sensing data, characterized in that: The following steps are involved: Acquire target perception data; Analyze the behavior pattern of each target based on target perception data and historical trajectory and scenario data; Generate and send warning information to target vehicles based on the behavior patterns of each target, perform induction intervention on the corresponding target, and generate induction intervention data; Collect the target's next behavior pattern data in real time, and generate and send feedback data based on the induced intervention data and the target's next behavior pattern data to interact with the vehicle.

2. The vehicle behavior prediction and induction method based on edge sensing data according to claim 1 is characterized in that: The method for acquiring target perception data comprises the following steps: Target perception processing is performed based on sensors to carry out target detection, target tracking and target recognition processing to obtain the final target perception data.

3. The vehicle behavior prediction and induction method based on edge sensing data according to claim 1 is characterized in that: The method for analyzing the behavior pattern of each target based on target perception data and historical trajectory and scene data comprises the following steps: Predict the target's motion trajectory data and confidence data within a preset time period in the future based on historical trajectory and scene data; Based on the predicted motion trajectory data and the target three-dimensional spatial data in the target perception data, it is calculated whether there is a collision risk of the predicted target within the credible time interval. If there is a collision risk, the collision intensity and confidence are calculated based on the target type, speed and weight in the target perception data.

4. The vehicle behavior prediction and induction method based on edge sensing data according to claim 1 is characterized in that: The method for generating and sending warning information to the target vehicle according to the behavior pattern of each target comprises the following steps: Determine the target vehicle information that needs to be induced based on the behavior prediction data; Generate warning information based on behavior prediction data and send it to the target vehicle.

5. The vehicle behavior prediction and induction method based on edge sensing data according to claim 1 is characterized in that: The method of generating and sending feedback data according to the induced intervention data and the target's subsequent behavior pattern data, and performing feedback interaction on the vehicle comprises the following steps: Analyze the difference between the vehicle's current behavior and the induced behavior based on the induced intervention data and the target's next behavior pattern data, and generate a difference analysis result; If the result of the difference analysis is that the current behavior is consistent with the induced behavior, reward information is generated and sent; otherwise, guidance and suggestion information is generated and sent.

6. A vehicle behavior prediction and guidance system based on edge sensing data, characterized in that: It includes a perception data acquisition module, a behavior prediction and analysis module, an induction intervention module, and a feedback interaction module, among which: A perception data acquisition module, used to acquire target perception data; Behavior prediction and analysis module, used to analyze the behavior pattern of each target based on target perception data and historical trajectory and scenario data; The induction intervention module is used to generate and send warning information to the target vehicle according to the behavior pattern of each target, perform induction intervention on the corresponding target, and generate induction intervention data; The feedback interaction module is used to collect the target's subsequent behavior pattern data in real time, and to generate and send feedback data based on the induced intervention data and the target's subsequent behavior pattern data, so as to perform feedback interaction with the vehicle.

7. An electronic device, characterized in that: include: A memory for storing one or more programs; processor; When the one or more programs are executed by the processor, the method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images