Parallel scene data collection method and system

Abstract

The application provides a parallel avoidance scene data collection method and system, which comprises the following steps: in a no-following vehicle scene, when a target vehicle enters an actual parallel domain or a predicted parallel domain, a parallel scene starting time is recorded; the target vehicle is continuously tracked, and when the target vehicle drives out of the actual parallel domain or the predicted parallel domain, an actual parallel scene ending time is recorded; and parallel avoidance scene data processed automatically by a vehicle controller from the parallel scene starting time to the ending time is collected. Through the scheme, automatic extraction of parallel avoidance scene data can be realized, the amount of redundant data collection is reduced, and manpower and material resources are saved.

Description

Technical Field

[0001] This invention belongs to the field of intelligent driving, and in particular relates to a method and system for parallel avoidance of scene data acquisition. Background Technology

[0002] With the rapid development of intelligent vehicle technology, advanced intelligent driving systems have been widely applied in mass-produced passenger vehicles. However, in actual use, intelligent driving functions are too mechanical. For example, navigation-assisted driving does not actively accelerate or decelerate to avoid parallel traffic when there are vehicles driving alongside it. To improve the "human-like" driving experience, it is necessary to collect a large amount of data from natural human driving and iteratively optimize the system.

[0003] However, existing parallel scenario data acquisition methods require extraction from massive amounts of driving data and manual judgment. Alternatively, parallel scenarios can be subjectively identified by humans, and data acquisition nodes can be set. Both methods can extract scenarios of interest, but they also consume a significant amount of human and material resources. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a parallel avoidance method and system for scene data acquisition, which is used to solve the problem of time-consuming and labor-intensive scene data acquisition in the present invention.

[0005] In a first aspect of the present invention, a method for parallel avoidance of scene data acquisition is provided, comprising:

[0006] In a scenario without following another vehicle, obtain the start and end times of the target vehicle's entry into the parallel scenario;

[0007] Specifically, when a target vehicle is detected to have entered the actual parallel domain and traveled within the actual parallel domain for a period of time exceeding a first predetermined value, the start time of the actual parallel scenario is recorded.

[0008] The target vehicle is continuously tracked. When the target vehicle leaves the actual parallel domain and the duration of the departure exceeds the second predetermined value, the end time of the actual parallel scenario is recorded.

[0009] Alternatively, when a target vehicle is detected to have entered the prediction parallel domain and traveled within the parallel domain for a period exceeding a first predetermined value, the start time of the prediction parallel scenario is recorded.

[0010] The target vehicle is continuously tracked. When the target vehicle leaves the prediction parallel domain and the duration of the departure exceeds the second predetermined value, the end time of the prediction parallel scenario is recorded.

[0011] The vehicle controller automatically processes parallel avoidance scenario data from the start to the end of the parallel scenario.

[0012] In a second aspect of the present invention, a parallel scene data acquisition system is provided, comprising:

[0013] The time acquisition module is used to acquire the start and end times of the target vehicle in the parallel scenario in a non-following scenario.

[0014] Specifically, when a target vehicle is detected to have entered the actual parallel domain and traveled within the actual parallel domain for a period of time exceeding a first predetermined value, the start time of the actual parallel scenario is recorded.

[0015] The target vehicle is continuously tracked. When the target vehicle leaves the actual parallel domain and the duration of the departure exceeds the second predetermined value, the end time of the actual parallel scenario is recorded.

[0016] Alternatively, when a target vehicle is detected to have entered the prediction parallel domain and traveled within the parallel domain for a period exceeding a first predetermined value, the start time of the prediction parallel scenario is recorded.

[0017] The target vehicle is continuously tracked. When the target vehicle leaves the prediction parallel domain and the duration of the departure exceeds the second predetermined value, the end time of the prediction parallel scenario is recorded.

[0018] The data acquisition module is used to collect parallel avoidance scenario data automatically processed by the vehicle controller from the start time to the end time of the parallel scenario.

[0019] In a third aspect of the present invention, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor executes the computer program to implement the steps of the method as described in the first aspect of the present invention.

[0020] In a fourth aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method provided in the first aspect of the present invention.

[0021] In this embodiment of the invention, by setting an actual parallel domain and a predicted parallel domain, the data start and end collection nodes are determined, and the data on the vehicle controller is extracted accordingly. This achieves parallel avoidance of automatic identification and collection of scene data, which reduces the amount of scene data collection, reduces the consumption of manpower and material resources, and further reduces the burden of cloud data processing. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a schematic flowchart of a parallel scenario data acquisition method according to an embodiment of the present invention;

[0024] Figure 2 A schematic diagram of a parallel region provided in one embodiment of the present invention;

[0025] Figure 3 This is a schematic diagram of parallel scene partitioning provided in one embodiment of the present invention;

[0026] Figure 4 This is a schematic diagram of the structure of a parallel scene avoidance data acquisition system provided in one embodiment of the present invention;

[0027] Figure 5 This is a schematic diagram of the structure of an electronic device provided in one embodiment of the present invention. Detailed Implementation

[0028] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0029] It should be understood that the terms "comprising" and other similar expressions in the specification, claims, and accompanying drawings of this invention are intended to cover a non-exclusive inclusion, such as a process, method, system, or apparatus that includes a series of steps or units and is not limited to the listed steps or units. Furthermore, "first" and "second" are used to distinguish different objects and are not intended to describe a specific order.

[0030] It should be noted that, in order to extract the behavior scenarios of avoiding parallel driving between human and natural driving, data collection only occurs when the intelligent driving function is not activated, that is, when the intelligent driving function is not activated and the perception and fusion module is still running in the background.

[0031] It should be understood that vehicle parallelism avoidance involves two main behavioral scenarios: one is when the vehicle breaks out of parallelism after it has already established parallelism; the other is when the vehicle anticipates that it will parallel with a target vehicle in front or behind based on its current driving state, and therefore takes action in advance to avoid the parallelism. Two regions are defined: the actual parallelism domain and the predicted parallelism domain, with four boundaries. When the target vehicle is within the parallelism domain (between the actual parallel lines in front and behind), it is considered to have established an actual parallel relationship. When the target vehicle is within the predicted parallelism domain (between the predicted parallel lines in front and behind), it is believed that the vehicle will perform advance prediction and avoidance of the parallelism state.

[0032] Please see Figure 1 The present invention provides a flowchart illustrating a method for parallel data acquisition in a scenario, comprising:

[0033] S101. In a scenario without following another vehicle, obtain the start and end times of the target vehicle in the parallel scenario;

[0034] The "no following scenario" refers to a situation where the vehicle is not currently following another vehicle, or there are no other vehicles traveling within a certain distance in front of the vehicle.

[0035] In this embodiment, the system can determine whether a vehicle is in a following scenario based on the longitudinal distance between the vehicle and the vehicle in front, combined with the vehicle's lane location. The longitudinal distance can be adjusted according to the vehicle's speed; a lower speed results in a shorter longitudinal distance, while a higher speed results in a longer longitudinal distance.

[0036] The parallel scenarios include actual parallel scenarios and predicted parallel scenarios. The start time of a parallel scenario corresponds to the time when the target vehicle enters the actual parallel domain or the predicted parallel domain, and the end time of a parallel scenario corresponds to the time when the target vehicle leaves the actual parallel domain or the predicted parallel domain.

[0037] The target vehicle refers to another vehicle that is parallel to the vehicle itself, which can be any vehicle around the vehicle that may be parallel to the vehicle itself.

[0038] Specifically, when a target vehicle is detected to have entered the actual parallel domain and traveled within the actual parallel domain for a period of time exceeding a first predetermined value, the start time of the actual parallel scenario is recorded.

[0039] The target vehicle is continuously tracked. When the target vehicle leaves the actual parallel domain and the duration of the departure exceeds the second predetermined value, the end time of the actual parallel scenario is recorded.

[0040] Alternatively, when a target vehicle is detected to have entered the prediction parallel domain and traveled within the parallel domain for a period exceeding a first predetermined value, the start time of the prediction parallel scenario is recorded.

[0041] The target vehicle is continuously tracked. When the target vehicle leaves the prediction parallel domain and the duration of the departure exceeds the second predetermined value, the end time of the prediction parallel scenario is recorded.

[0042] It should be noted that the start time of the parallel scenario can be calculated based on the current time of the vehicle, the first preset value, and the compensation parameter. For example, if the current time is t, the first preset value is t1, and the start time compensation parameter is Δt1, then the start time is t-t1-Δt1. The compensation parameter is a calibrated quantity used to compensate for objective errors in time measurement.

[0043] Similarly, the end time of a parallel scenario can be calculated based on the current time of the vehicle and the compensation parameters. For example, if the current time is t, the second preset value is t2, and the start time compensation parameter is Δt2, then the start time is t+Δt2.

[0044] In one embodiment, the regions represented by the actual parallel domain and the predicted parallel domain are as follows: Figure 2 As shown in the figure, the area formed by the actual parallel lines in front, the actual parallel lines behind, and the road is the actual parallel domain, and the area formed by the predicted parallel lines in front, the predicted parallel lines behind, and the road is the predicted parallel domain.

[0045] Preferably, the predicted parallel domain is larger than the actual parallel domain, and the predicted parallel domain and the actual parallel domain have no overlapping parts.

[0046] Distinguishing between the prediction parallel domain and the actual parallel domain, and ensuring that their regions do not overlap, can prevent overlapping of scene data when dividing the scene.

[0047] It is understood that the actual parallel domain can be set by the size of the vehicle, the size of the target vehicle, the safe driving distance, the lane width, etc., or it can be set according to actual driving experience, such as setting it to be within 20m in front of and behind the vehicle.

[0048] The predicted parallel domain is a region that can be paralleled based on the current state of the vehicle and surrounding vehicles. Specifically, it can be set according to the vehicle speed, target vehicle speed, safe driving distance, lane type, etc.

[0049] S102. Collect parallel avoidance scenario data automatically processed by the vehicle controller from the start time to the end time of the parallel scenario.

[0050] The vehicle controller is a self-vehicle vehicle controller, which may include a vehicle controller, body controller, engine ECU, transmission ECU, etc. The parallel avoidance scenario data may include other vehicle status perception data and self-vehicle status perception data. The vehicle fusion perception unit will collect perception data, such as images and laser point clouds, through on-board sensors such as cameras and radar, and perform status perception through technologies such as computer vision and deep learning. The parallel avoidance scenario data may also include control parameters issued by the vehicle controller, such as steering parameters and vehicle speed control parameters. The above data can be obtained through the CAN bus.

[0051] The vehicle extracts parallel avoidance scenario data stored in the vehicle based on the time point of the parallel avoidance scenario, which includes scenario data from the start to the end of parallelism.

[0052] In this embodiment, based on the actual parallel domain and the predicted parallel domain, the scene data acquisition node is determined, and data is collected from the controller of the vehicle equipped with intelligent driving function to realize automatic data extraction. This not only reduces the amount of data collected, but also saves manpower and material resources.

[0053] In one embodiment, the target vehicle is classified into at least two types: large vehicles and small vehicles, depending on the type of the target vehicle.

[0054] Among them, the actual parallel domain sizes corresponding to the large vehicle and the small vehicle are different, as are the prediction parallel domain sizes corresponding to the large vehicle and the small vehicle.

[0055] The large vehicles can be buses, trucks, semi-trailers, or special vehicles, while the small vehicles can be four-wheeled sedans, SUVs, MPVs, or two-wheeled motorcycles, bicycles, etc. Due to the different types of target vehicles, their sizes also vary, and they can be simply divided into large vehicles and small vehicles. The size of the parallel domain will also differ depending on the vehicle type.

[0056] Furthermore, the parallel scenarios are divided into at least the actual parallel scenario of the small vehicle, the predicted parallel scenario of the small vehicle, the actual parallel scenario of the large vehicle, and the predicted parallel scenario of the large vehicle.

[0057] The parallel prediction scenario for small vehicles includes a parallel prediction scenario for small vehicles that is then implemented in parallel, while the parallel prediction scenario for large vehicles includes a parallel prediction scenario for large vehicles that is then implemented in parallel.

[0058] For example, such as Figure 3 As shown, based on the start and end times of parallelism, the parallel scenarios can be divided into: actual parallelism avoidance for small vehicles, actual parallelism for small vehicles, actual parallelism avoidance for large vehicles, actual parallelism avoidance for large vehicles, predicted parallelism avoidance for small vehicles, predicted parallelism for small vehicles, predicted parallelism for small vehicles to actual parallelism, predicted parallelism avoidance for large vehicles, predicted parallelism for large vehicles, and predicted parallelism for large vehicles to actual parallelism.

[0059] For example, in combination Figure 2 Taking a real-world scenario as an example, when another vehicle enters the parallel domain (cuts in / cuts out / suddenly accelerates in) and remains there for a certain period of time, the vehicle can actively break away from the parallel state by changing lanes and accelerating / decelerating, or the target vehicle can actively break away, and the vehicle can cooperate with it to break away from the parallel state.

[0060] The "actual parallel domain of the vehicle" is defined as the lateral distance (Dx1, Dx2) and longitudinal distance (Dy1, Dy2) in the vehicle's coordinate system. Dx1 and Dx2 represent lanes.

[0061] When the intelligent driving perception fusion module identifies the target vehicle as a car, and the duration of the car's time in the "actual parallel domain" reaches t1, the triggering condition for this scenario is considered met, and the start time is recorded as t-t1-Δt1. For example, when t1 = 3s and Δt1 = 2s, the triggering condition for this scenario is met when the car's time in the actual parallel domain reaches 3s. At the same time, the current time is subtracted by 5s as the start time of the data tag for this segment.

[0062] The target is continuously tracked. When the target leaves the "actual parallel domain of the car" and the duration exceeds t2, the termination condition of the scenario is considered to be met, and the termination time is recorded as t+Δt2.

[0063] The data from the vehicle's start time to its end time is the "actual parallel avoidance of vehicles" scenario data that is automatically processed by the vehicle-side intelligent driving controller.

[0064] For example, when the target vehicle is in the predicted parallel domain, the driver may avoid paralleling with the target by accelerating, braking, or steering.

[0065] Define the "parallel domain for vehicle prediction" as the horizontal distance (Dx1,Dx2) and the vertical distance (Dy3,Dy1) && (Dy2,Dy4) in the vehicle coordinate system.

[0066] When the target is a car, and it enters the "car prediction parallel domain", and the duration in the "car prediction parallel domain" reaches t1, it is considered that the triggering condition of the scenario is met, and the start time is recorded as t-t1-Δt1.

[0067] The target vehicle is continuously tracked. If the target vehicle is farther and farther away from the vehicle and leaves the "car prediction parallel domain", that is, when the target vehicle leaves the "car prediction parallel domain" and the duration exceeds t2, the termination condition of the scenario is considered to be met, and the termination time is recorded as t+Δt2.

[0068] This data segment represents the "car prediction and parallel avoidance" scenario data that is automatically processed by the vehicle-side intelligent driving controller.

[0069] In one embodiment, in step S101, when it is detected that the target vehicle has entered the actual parallel domain and the driving time in the actual parallel domain exceeds a third predetermined value, the end time of the actual parallel scenario is automatically recorded.

[0070] Alternatively, when a target vehicle is detected to have entered the predicted parallel domain and traveled within the predicted parallel domain for a time exceeding a third predetermined value, the actual end time of the parallel scenario is automatically recorded; the third predetermined value is greater than the first predetermined value.

[0071] When the target vehicle remains within the actual or predicted parallel domain for an extended period, the driving scenario is still considered a parallel scenario. In this case, neither the driver nor the target vehicle takes any action to avoid parallelism. To facilitate data analysis and mining, the end time is automatically recorded when the parallel scenario exceeds a certain time threshold.

[0072] For example, if the target vehicle enters the vehicle's parallel domain and remains in the actual or predicted parallel domain for more than 3 minutes, the parallel scenario time recording will automatically end.

[0073] In one embodiment, in step S101, when the target vehicle is detected to have left the predicted parallel domain and entered the actual parallel domain, the start time to end time of the predicted parallel scenario and the start time to end time of the actual parallel scenario are recorded respectively. Parallel avoidance scenario data of predicted parallel and parallel avoidance scenario data of actual parallel are collected respectively and marked as predicted parallel to actual parallel scenario.

[0074] The scenario of predictive parallelism to actual parallelism refers to the scenario in which a vehicle travels from the predictive parallel domain to the actual parallel domain. This scenario includes both predictive parallelism and actual parallelism. The data from the two scenarios can be combined and marked as predictive parallelism to actual parallelism for data acquisition and processing.

[0075] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0076] Figure 4 This is a schematic diagram of a parallel scene avoidance data acquisition system provided in an embodiment of the present invention. The system includes:

[0077] The time acquisition module 410 is used to acquire the start and end times of the target vehicle in the parallel scenario in a non-following scenario.

[0078] In this data acquisition system, the vehicle perception module can determine whether a following scenario is in progress based on the longitudinal distance between the vehicle and the vehicle in front, combined with the vehicle's lane location. The longitudinal distance can be adjusted according to the vehicle's speed; the longitudinal distance is shorter at lower speeds and longer at higher speeds.

[0079] The parallel scenarios include actual parallel scenarios and predicted parallel scenarios. The start time of a parallel scenario corresponds to the time when the target vehicle enters the actual parallel domain or the predicted parallel domain, and the end time of a parallel scenario corresponds to the time when the target vehicle leaves the actual parallel domain or the predicted parallel domain.

[0080] Specifically, when a target vehicle is detected to have entered the actual parallel domain and traveled within the actual parallel domain for a period of time exceeding a first predetermined value, the start time of the actual parallel scenario is recorded.

[0081] The target vehicle is continuously tracked. When the target vehicle leaves the actual parallel domain and the duration of the departure exceeds the second predetermined value, the end time of the actual parallel scenario is recorded.

[0082] Alternatively, when a target vehicle is detected to have entered the prediction parallel domain and traveled within the parallel domain for a period exceeding a first predetermined value, the start time of the prediction parallel scenario is recorded.

[0083] The target vehicle is continuously tracked. When the target vehicle leaves the prediction parallel domain and the duration of the departure exceeds the second predetermined value, the end time of the prediction parallel scenario is recorded.

[0084] Wherein, the predicted parallel domain is larger than the actual parallel domain, and the predicted parallel domain and the actual parallel domain have no overlapping parts.

[0085] The data acquisition module 420 is used to collect parallel avoidance scenario data that is automatically processed by the vehicle controller from the start time to the end time of the parallel scenario.

[0086] The data acquisition module can be connected to vehicle perception sensors and controllers, or directly acquire parallel avoidance scenario data via the CAN bus. The parallel avoidance scenario data may include external perception data, vehicle status perception data, and vehicle control command data.

[0087] In one embodiment, obtaining the start and end times of the target vehicle in the parallel scenario includes:

[0088] Based on the different types of target vehicles, the target vehicles are divided into at least large vehicles and small vehicles;

[0089] Among them, the actual parallel domain sizes corresponding to the large vehicle and the small vehicle are different, as are the prediction parallel domain sizes corresponding to the large vehicle and the small vehicle.

[0090] Furthermore, the parallel scenarios are divided into at least the actual parallel scenario of the small vehicle, the predicted parallel scenario of the small vehicle, the actual parallel scenario of the large vehicle, and the predicted parallel scenario of the large vehicle.

[0091] The parallel prediction scenario for small vehicles includes a parallel prediction scenario for small vehicles that is then implemented in parallel, while the parallel prediction scenario for large vehicles includes a parallel prediction scenario for large vehicles that is then implemented in parallel.

[0092] For example, by combining the start and end times of parallelism of the target vehicles, the parallel scenarios can be divided into: actual parallelism avoidance of small vehicles, actual parallelism of small vehicles, actual parallelism avoidance of large vehicles, actual parallelism of large vehicles, predicted parallelism avoidance of small vehicles, predicted parallelism of small vehicles, predicted parallelism of small vehicles to actual parallelism, predicted parallelism avoidance of large vehicles, predicted parallelism of large vehicles, and predicted parallelism of large vehicles to actual parallelism.

[0093] For example, taking a car in a real parallel scenario, when another vehicle enters the parallel domain (cuts in / cuts out / suddenly accelerates in) and remains there for a certain period of time, the car can actively break away from the parallel state by changing lanes and accelerating / decelerating, or the target car can actively break away, and the car can cooperate with it to break away from the parallel state.

[0094] The "actual parallel domain of the car" is defined as the lateral distance (Dx1, Dx2) and longitudinal distance (Dy1, Dy2) in the car's coordinate system. Dx1 and Dx2 represent lanes, and Dy1 and Dy2 represent the actual parallel lines in front and behind.

[0095] When the intelligent driving perception fusion module identifies the target vehicle as a car, and the duration of the car's time in the "actual parallel domain" reaches t1, the triggering condition for this scenario is considered met, and the start time is recorded as t-t1-Δt1. For example, when t1 = 3s and Δt1 = 2s, the triggering condition for this scenario is met when the car's time in the actual parallel domain reaches 3s, and the current time minus 5s is taken as the start time of the data tag for this segment.

[0096] The target is continuously tracked. When the target leaves the "actual parallel domain of the car" and the duration exceeds t2, the termination condition of the scenario is considered to be met, and the termination time is recorded as t+Δt2.

[0097] The data from the vehicle's start time to its end time is the "actual parallel avoidance of vehicles" scenario data that is automatically processed by the vehicle-side intelligent driving controller.

[0098] In one embodiment, the time acquisition module further includes:

[0099] When the target vehicle is detected to have entered the actual parallel domain and traveled in the actual parallel domain for more than the third predetermined value, the end time of the actual parallel scenario is automatically recorded.

[0100] Alternatively, when a target vehicle is detected to have entered the predicted parallel domain and traveled within the predicted parallel domain for more than a third predetermined value, the actual end time of the parallel scenario is automatically recorded.

[0101] The third predetermined value is greater than the first predetermined value.

[0102] In one embodiment, when the time acquisition module 410 detects that the target vehicle leaves the predicted parallel domain and enters the actual parallel domain, it records the start time to end time of the predicted parallel scenario and the start time to end time of the actual parallel scenario, respectively, collects the parallel avoidance scenario data of the predicted parallel scenario and the parallel avoidance scenario data of the actual parallel scenario, and marks them as predicted parallel to actual parallel scenario.

[0103] In this embodiment, the scene data collection time point is obtained through the time acquisition module, and the scene data is directly obtained from the vehicle controller in the data acquisition module based on the collection time point, thereby realizing automatic extraction of scene data and saving manpower and material resources.

[0104] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described apparatus and modules can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0105] Figure 5 This is a schematic diagram of an electronic device according to an embodiment of the present invention. The electronic device is used for parallel data acquisition of a scene. Figure 5 As shown, the electronic device 5 of this embodiment includes at least: a memory 510, a processor 520, and a system bus 530. The memory 510 includes an executable program 4101 stored thereon. As those skilled in the art will understand, Figure 5 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0106] The following is combined Figure 5 A detailed introduction to each component of the electronic device:

[0107] The memory 510 can be used to store software programs and modules. The processor 520 executes various functional applications and data processing of the electronic device by running the software programs and modules stored in the memory 510. The memory 510 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device (such as cached data), etc. In addition, the memory 510 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0108] The memory 510 contains an executable program 5101 for a network request method. This executable program 5101 can be divided into one or more modules / units, which are stored in the memory 510 and executed by the processor 520 to perform tasks such as scene data acquisition. Each module / unit can be a series of computer program instruction segments capable of performing a specific function, describing the execution process of the computer program 5101 in the electronic device 5. For example, the computer program 5101 can be divided into a time acquisition module and a data acquisition module, etc.

[0109] The processor 520 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 510, and by calling data stored in the memory 510, it performs various functions and processes data, thereby monitoring the overall status of the electronic device. Optionally, the processor 520 may include one or more processing units; preferably, the processor 520 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, application programs, etc., and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into the processor 520.

[0110] The system bus 530 is used to connect various functional components inside the computer, transmitting data, address, and control information. Its type can be, for example, a PCI bus, an ISA bus, or a CAN bus. Instructions from the processor 520 are transmitted to the memory 510 via the bus, and the memory 510 sends data back to the processor 520. The system bus 530 is responsible for data and instruction exchange between the processor 520 and the memory 510. Of course, the system bus 530 can also connect to other devices, such as network interfaces and display devices.

[0111] In this embodiment of the invention, the executable program executed by the processing 520 of the electronic device includes:

[0112] In a scenario without following another vehicle, obtain the start and end times of the target vehicle's entry into the parallel scenario;

[0113] Specifically, when a target vehicle is detected to have entered the actual parallel domain and traveled within the actual parallel domain for a period of time exceeding a first predetermined value, the start time of the actual parallel scenario is recorded.

[0114] The target vehicle is continuously tracked. When the target vehicle leaves the actual parallel domain and the duration of the departure exceeds the second predetermined value, the end time of the actual parallel scenario is recorded.

[0115] Alternatively, when a target vehicle is detected to have entered the prediction parallel domain and traveled within the parallel domain for a period exceeding a first predetermined value, the start time of the prediction parallel scenario is recorded.

[0116] The target vehicle is continuously tracked. When the target vehicle leaves the prediction parallel domain and the duration of the departure exceeds the second predetermined value, the end time of the prediction parallel scenario is recorded.

[0117] The vehicle controller automatically processes parallel avoidance scenario data from the start to the end of the parallel scenario.

[0118] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0119] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0120] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for parallel scene data acquisition, the method comprising: Comprise: In the no-following vehicle scene, the starting time and the ending time of the target vehicle in the parallel scene are acquired; Wherein, when the target vehicle is detected to enter the actual parallel domain and the driving time in the actual parallel domain exceeds the first predetermined value, the starting time of the actual parallel scene is recorded; The target vehicle is continuously tracked, and when the target vehicle drives out of the actual parallel domain and the driving-out duration exceeds the second predetermined value, the ending time of the actual parallel scene is recorded; Or, when the target vehicle is detected to enter the predicted parallel domain and the driving time in the predicted parallel domain exceeds the first predetermined value, the starting time of the predicted parallel scene is recorded; The target vehicle is continuously tracked, and when the target vehicle drives out of the predicted parallel domain and the driving-out duration exceeds the second predetermined value, the ending time of the predicted parallel scene is recorded; Wherein, the actual parallel domain and the predicted parallel domain are defined, and four boundaries are defined, when the target vehicle is in the parallel domain, i.e. between the front actual parallel line and the rear actual parallel line, it is considered that the actual parallel relationship is formed, and when the target vehicle is in the predicted parallel domain, i.e. between the front predicted parallel line and the rear predicted parallel line, it is considered that the host vehicle will make early prediction and avoidance for the parallel state; The predicted parallel domain is larger than the actual parallel domain, and the predicted parallel domain and the actual parallel domain have no overlapping part; The parallel avoidance scene data of the vehicle controller from the starting time to the ending time of the parallel scene is collected.

2. The method of claim 1, wherein, The acquisition of the starting time and the ending time of the target vehicle in the parallel scene comprises: According to the different types of target vehicles, the target vehicles are divided into at least large vehicles and small vehicles; Wherein, the actual parallel domain sizes corresponding to the large vehicles and the small vehicles are different, and the predicted parallel domain sizes corresponding to the large vehicles and the small vehicles are also different.

3. The method of claim 1, wherein, The recording of the starting time of the actual parallel scene when the target vehicle is detected to enter the actual parallel domain and the driving time in the actual parallel domain exceeds the first predetermined value further comprises: When the target vehicle is detected to enter the actual parallel domain and the driving time in the actual parallel domain exceeds the third predetermined value, the ending time of the actual parallel scene is automatically recorded; Or, when the target vehicle is detected to enter the predicted parallel domain and the driving time in the predicted parallel domain exceeds the third predetermined value, the ending time of the actual parallel scene is automatically recorded; The third predetermined value is greater than the first predetermined value.

4. The method of claim 1, wherein, The recording of the ending time of the predicted parallel scene when the target vehicle drives out of the predicted parallel domain and the driving-out duration exceeds the second predetermined value further comprises: When the target vehicle is detected to drive out of the predicted parallel domain and drive into the actual parallel domain, the starting time to the ending time of the predicted parallel scene and the starting time to the ending time of the actual parallel scene are respectively recorded, the parallel avoidance scene data of the predicted parallel and the parallel avoidance scene data of the actual parallel are respectively collected, and it is marked as the predicted parallel to the actual parallel scene.

5. The method of claim 2, wherein, The division of the target vehicles according to the different types of target vehicles further comprises: The parallel scene is divided into at least the small vehicle actual parallel scene, the small vehicle predicted parallel scene, the large vehicle actual parallel scene, and the large vehicle predicted parallel scene; The trolley prediction parallel scene includes a trolley prediction parallel to an actual parallel scene, and the large trolley prediction parallel scene includes a large trolley prediction parallel to an actual parallel scene.

6. A parallel-avoidance scene data acquisition system, characterized by, The method comprises: a time acquisition module, configured to acquire a starting time and an ending time of a parallel scene of a target vehicle in a no-following vehicle scene; wherein, when it is detected that the target vehicle enters an actual parallel domain and drives in the actual parallel domain for more than a first predetermined value, the starting time of the actual parallel scene is recorded; the target vehicle is continuously tracked, and when the target vehicle drives out of the actual parallel domain and drives out for more than a second predetermined value, the ending time of the actual parallel scene is recorded; or, when it is detected that the target vehicle enters a prediction parallel domain and drives in the prediction parallel domain for more than the first predetermined value, the starting time of the prediction parallel scene is recorded; the target vehicle is continuously tracked, and when the target vehicle drives out of the prediction parallel domain and drives out for more than the second predetermined value, the ending time of the prediction parallel scene is recorded; wherein, two regions, i.e., an actual parallel domain and a prediction parallel domain, and four boundaries are defined, and when the target vehicle is in the parallel domain, i.e., between a front actual parallel line and a rear actual parallel line, it is considered that an actual parallel relationship is formed, and when the target vehicle is in the prediction parallel domain, i.e., between a front prediction parallel line and a rear prediction parallel line, it is considered that the ego vehicle will make an early prediction and avoidance for the parallel state; the prediction parallel domain is larger than the actual parallel domain, and the prediction parallel domain and the actual parallel domain have no overlapping part; a data acquisition module, configured to acquire parallel avoidance scene data processed automatically by a vehicle controller from a starting time to an ending time of a parallel scene.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the steps of the parallel avoidance scene data acquisition method according to any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, the computer-readable storage medium comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 7. The computer program is executed to realize the steps of the parallel avoidance scene data acquisition method according to any one of claims 1 to 5.

Images