Data processing method, apparatus and vehicle

Abstract

The application discloses a data processing method and device and a vehicle. The method comprises the following steps: obtaining first driving data generated by an automatic driving vehicle and second driving data generated by an automatic driving system during driving of the automatic driving vehicle by a driver, wherein the automatic driving system is installed on the automatic driving vehicle; determining a current driving scene of the automatic driving vehicle in response to the first driving data being different from the second driving data; and obtaining scene data corresponding to the current driving scene to obtain target scene data. The application solves the technical problem of data redundancy and low efficiency of automatic driving scene data collection in the related art.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to a data processing method and device and vehicle. BACKGROUND

[0002] An automatic driving car can obtain road traffic environment data, vehicle driving state data and driver driving behavior data by means of a sensing system. In order to filter out an automatic driving demand scene from a large amount of scene data, an automatic driving system can be run to output a virtual control instruction in a manual driving state, and the output instruction can be compared with the driver's behavior. When the two are inconsistent, the scene is determined as an effective scene.

[0003] However, the accuracy of the difference type distinction and difference data processing of the driver's behavior and the automatic driving system is low, resulting in low effectiveness and data redundancy of the difference target scene data obtained by the automatic driving system.

[0004] At present, no effective solution has been proposed for the above problems. SUMMARY

[0005] Embodiments of the present application provide a data processing method, device and vehicle to at least solve the technical problem of low effectiveness and data redundancy of difference target scene data obtained by an automatic driving system in the related art.

[0006] According to an aspect of an embodiment of the present application, a data processing method is provided, including: obtaining first driving data generated by an automatic driving vehicle and second driving data generated by an automatic driving system during driving of the automatic driving vehicle by a driver, the automatic driving system being installed on the automatic driving vehicle; determining a current driving scene of the automatic driving vehicle in response to the first driving data being different from the second driving data; obtaining scene data corresponding to the current driving scene to obtain target scene data.

[0007] Optionally, determining the current driving scene of the automatic driving vehicle includes: obtaining a driving direction of the automatic driving vehicle; determining, in response to the driving direction being a lateral direction, that the current driving scene is a first preset scene or a second preset scene based on the first driving data and the second driving data; and determining, in response to the driving direction being a longitudinal direction, that the current driving scene is a third preset scene or a fourth preset scene based on vehicle speed and vehicle acceleration in a historical time period.

[0008] Optionally, the determining that the current driving scene is the first preset scene or the second preset scene comprises: determining a first issuing time of the first lane-changing instruction in the first driving data and a second issuing time of the second lane-changing instruction in the second driving data; obtaining a time difference between the first issuing time and the second issuing time; and in response to the time difference being greater than a first preset time difference, determining that the current driving scene is the first preset scene.

[0009] Optionally, the obtaining of the scene data corresponding to the current driving scene to obtain target scene data comprises: determining a lane-changing time of the autonomous vehicle based on the first issuing time and the second issuing time; determining a target time period corresponding to the target scene data based on the lane-changing time; and obtaining scene data in the target time period to obtain the target scene data.

[0010] Optionally, the determining of the target time period corresponding to the target scene data based on the lane-changing time comprises: in response to the time difference being greater than the first preset time difference and less than a second preset time difference, determining that a start time of the target time period is a difference value between the lane-changing time and a first preset value, and a termination time of the target time period is a sum value of the lane-changing time and the time difference; and in response to the time difference being greater than the second preset time difference, determining that the start time of the target time period is the difference value between the lane-changing time and the first preset value, and the termination time of the target time period is a sum value of the lane-changing time and the second preset time difference; wherein the second preset time difference is greater than the first preset time difference.

[0011] Optionally, in response to the time difference being less than or equal to the first preset time difference, the method further comprises: obtaining a first driving track in the first driving data and a second driving track in the second driving data; obtaining a distance between the first driving track and the second driving track; and in response to the distance being greater than a preset distance, determining that the current driving scene is the second preset scene.

[0012] Optionally, the obtaining of the scene data corresponding to the current driving scene to obtain target scene data comprises: determining a track start time based on the first driving track and the second driving track; and obtaining scene data at the track start time to obtain the target scene data.

[0013] Optionally, the determining that the current driving scene is the third preset scene or the fourth preset scene comprises: obtaining a first maximum value and a first average value of a vehicle speed, and a second maximum value and a second average value of a vehicle acceleration; in response to the first maximum value and the second maximum value both being within a first preset range, and the first average value and the second average value both being within a second preset range, determining that the current driving scene is the third preset scene; and in response to the first maximum value not being within the first preset range, or the second maximum value not being within the first preset range, or the first average value not being within the second preset range, or the second average value not being within the second preset range, determining that the current driving scene is the fourth preset scene.

[0014] Optionally, the determining that the current driving scenario is the third preset scenario comprises: obtaining an acceleration instruction output by the automatic driving system, wherein the acceleration instruction is generated by the automatic driving system in a case where a first vehicle speed in the first driving data is different from a second vehicle speed in the second driving data; obtaining a difference between the acceleration instruction and the target acceleration in the first driving data to obtain a first difference value; and in response to the first difference value being greater than a first preset difference value, determining that the current driving scenario is the third preset scenario.

[0015] Optionally, the determining that the current driving scenario is the fourth scenario comprises: obtaining a difference between the first maximum value and the second maximum value to obtain a second difference value, and a difference between the first average value and the second average value to obtain a third difference value; and in response to the second difference value being greater than a second preset difference value or the third difference value being greater than a third preset difference value, determining that the current driving scenario is the fourth preset scenario.

[0016] Optionally, the obtaining of the target scenario data corresponding to the current driving scenario comprises: determining a preset time period centered on a difference time point, wherein the difference time point is used to represent a time point at which the current driving scenario is determined; and obtaining scenario data in the preset time period to obtain the target scenario data.

[0017] According to another aspect of the embodiments of the present application, a vehicle data processing apparatus is further provided, comprising: a first obtaining module, configured to obtain first driving data generated by an automatic driving vehicle and second driving data generated by an automatic driving system during driving of the automatic driving vehicle by a driver, the automatic driving system being installed on the automatic driving vehicle; a determining module, configured to determine a current driving scenario of the automatic driving vehicle based on a response to a difference between the first driving data and the second driving data; and a second obtaining module, configured to obtain target scenario data by obtaining scenario data corresponding to the current driving scenario.

[0018] According to another aspect of the embodiments of the present application, a vehicle is further provided, comprising the vehicle data processing apparatus in any of the above embodiments.

[0019] According to another aspect of the embodiments of the present application, a computer readable storage medium is further provided, comprising a stored program, wherein the program, when executed, controls a device in which the computer readable storage medium is located to perform the data processing method in any of the above embodiments.

[0020] According to another aspect of the embodiments of the present application, a processor is further provided, configured to execute a program, wherein the program, when executed, performs the data processing method in any of the above embodiments.

[0021] In the embodiment of the present application, during the process that the driver drives the automatic driving vehicle, the first driving data generated by manually controlling the automatic driving vehicle and the second driving data generated by the automatic driving system are acquired, the automatic driving system performs difference comparison on the first driving data and the second driving data, the current driving scene of the automatic driving vehicle is determined according to the difference type, the scene data corresponding to the current driving scene is acquired, and the target scene data is obtained. It is easy to note that the automatic driving system performs difference comparison on the first driving data generated by the automatic driving vehicle in the manual driving state and the second driving data generated by the automatic driving system, and acquires the corresponding target scene data based on the current driving scene, so as to improve the accuracy of difference division and difference data processing, and further solve the technical problems of low effectiveness and data redundancy of the difference target scene data acquired by the automatic driving system in the related art. BRIEF DESCRIPTION OF DRAWINGS

[0022] The accompanying drawings, which are included to provide a further understanding of the present application and constitute a part of this application, illustrate embodiments of the present application and together with the description serve to explain the present application. In the drawings:

[0023] Figure 1 is a flowchart of a data processing method according to an embodiment of the present application;

[0024] Figure 2 is a processing flowchart of an optional difference analysis model according to an embodiment of the present application;

[0025] Figure 3 is a schematic diagram of the automatic driving system issuing a lane changing instruction under the lateral decision difference according to an embodiment of the present application;

[0026] Figure 4 is a schematic diagram of the automatic driving system not issuing a lane changing instruction under the lateral decision difference according to an embodiment of the present application;

[0027] Figure 5 is a schematic diagram of a data processing device according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings of the embodiments of the present application. 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 other embodiments obtained by persons skilled in the art without creative labor should fall within the protection scope of the present application.

[0029] It should be noted that the terms "first", "second", and the like in the description and claims of the application and the above-described drawings are used to distinguish similar objects and are not necessarily used to describe a particular sequential or chronological order. It should be understood that the use of such terms in some aspects can be interchanged with one another, so that the embodiments of the application described herein can be practiced in other sequences than the one illustrated or described herein. Furthermore, the terms "comprise" and "have", and any variations thereof, are intended to cover a non-exclusive inclusion, for example, a process, method, system, product, or apparatus that comprises a list of steps or units is not necessarily limited to those steps or units that are clearly listed, but can include other steps or units that are not clearly listed or inherent to such processes, methods, products, or apparatuses.

[0030] Embodiment 1

[0031] According to an aspect of an embodiment of the application, a data processing method is provided, it should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that here.

[0032] Figure 1 is a flowchart of a data processing method according to an embodiment of the application, as shown in Figure 1 The method comprises the following steps:

[0033] Step S102, during driving of the driver driving the automatic driving vehicle, acquiring first driving data generated by the automatic driving vehicle and second driving data generated by the automatic driving system, the automatic driving system being installed on the automatic driving vehicle;

[0034] Step S104, in response to the first driving data and the second driving data being different, determining the current driving scene of the automatic driving vehicle;

[0035] Step S106, acquiring scene data corresponding to the current driving scene to obtain target scene data.

[0036] The application scenario of the method is that when a driver drives an automatic driving vehicle, the driver uses an automatic driving vehicle with an automatic driving system, manually drives the vehicle, and starts the automatic driving system, but the automatic driving system does not control the vehicle, and only generates simulation running data for comparison with data generated by manual driving. During driving, the automatic driving system automatically acquires data related to a vehicle driving state in a driving process, data related to manual driving operation, and data related to automatic driving system simulation driving operation, and performs difference comparison and records a scene label of effective target scene data. The first driving data is acquired from data generated during manual driving, and the second driving data is acquired from data generated during automatic driving system simulation driving.

[0037] In an optional embodiment, as shown in Figure 1 The first driving data can be an operation instruction, an operation time, a driving direction and a trajectory of the vehicle, a driving speed and an acceleration of the vehicle, and the like, which are performed on the vehicle in a corresponding scene by the driver during manual driving of the automatic driving vehicle. The second driving data can be an operation instruction, an operation time, a driving direction and a trajectory of the vehicle, a driving speed and an acceleration of the vehicle, and the like, which are performed on the vehicle in a corresponding scene by the automatic driving system during simulation control of the vehicle. For example, the driver drives an automatic driving vehicle to drive at a constant speed in a straight line, drives to T0 in a scene during driving, and performs lane changing. The automatic driving system simulates driving to T1 to perform lane changing. The first driving data can be a lane changing time T0 of the automatic driving vehicle, and the second driving data can be a lane changing time T1 of the automatic driving vehicle.

[0038] After the automatic control system automatically acquires the first driving data and the second driving data, the automatic control system compares whether a difference between the first driving data and the second driving data exceeds a set difference range. If the difference does not exceed the set difference range, the data is not recorded. If the difference exceeds the set difference range, a current driving scene is determined according to the difference range and the difference type.

[0039] The driving scene refers to a scene in which lane changing, turning, U-turn, and the like need to be performed during vehicle driving. The driving trajectories of the vehicle during the operations are different. The vehicle also has constant speed driving, acceleration driving, and deceleration driving, which form different driving scenes. After the corresponding driving scene is determined according to the different difference ranges and the difference types, the first driving data and the second driving data are recorded as scene data corresponding to the current scene, and are stored into a database, to facilitate big data analysis.

[0040] It should be noted that, Figure 2 is a schematic diagram of a flow of an optional difference analysis model according to an embodiment of the application, as shown in Figure 2As shown, according to the current driving scene, the difference between the driver behavior and the automatic driving system mainly includes lateral difference and longitudinal difference. Among them, according to the road conditions and the driver behavior, the lateral difference is divided into lateral decision difference and lateral trajectory difference. The driving scene of the lateral decision difference is the lane changing operation scene of the automatic driving vehicle, and the driving scene of the lateral trajectory decision difference is divided into straight driving without lane changing scene, turning or U-turn scene, and lane changing scene. The driving scene of the longitudinal difference is divided into manual uniform speed driving scene and manual acceleration and deceleration driving scene.

[0041] In the embodiment of the application, in the process of driving the automatic driving vehicle by the driver, the first driving data generated by the manual control of the automatic driving vehicle and the second driving data generated by the automatic driving system are obtained. The automatic driving system performs difference comparison on the first driving data and the second driving data, determines the current driving scene of the automatic driving vehicle according to the difference type, obtains the scene data corresponding to the current driving scene, and obtains the target scene data. It is easy to note that the automatic driving system performs difference comparison on the first driving data generated by the manual driving state of the automatic driving vehicle and the second driving data generated by the automatic driving system, and obtains the corresponding target scene data based on the current driving scene. The technical effect of improving the accuracy of difference division and difference data processing is achieved, and the technical problem of low effectiveness and data redundancy of the difference target scene data obtained by the automatic driving system in the related art is solved.

[0042] Optionally, according to the method of the above-mentioned embodiment of the application, the current driving scene of the automatic driving vehicle is determined, including: obtaining the driving direction of the automatic driving vehicle; in response to the driving direction being a lateral direction, determining the current driving scene to be a first preset scene or a second preset scene based on the first driving data and the second driving data; and in response to the driving direction being a longitudinal direction, determining the current driving scene to be a third preset scene or a fourth preset scene based on the vehicle speed and the vehicle acceleration in the historical time period.

[0043] The automatic driving system automatically obtains a driving direction of the vehicle, and the difference in the decision or the trajectory can be determined by judging the generated driving data. In the driving scene of the automatic driving vehicle, for the lateral direction, for example, the driver drives the vehicle to change lanes, but the automatic driving system does not give a lane change instruction to control the vehicle to change lanes, and at this time, the decision difference occurs; for another example, the driver drives the vehicle to change lanes, and the automatic driving system also gives a lane change instruction to control the vehicle to change lanes, but the trajectory of the driver driving the vehicle to change lanes is different from the trajectory of the vehicle changing lanes given by the automatic driving system, and at this time, the trajectory difference occurs. Therefore, in the case of the driving direction being the lateral direction, the first preset scene can be a lateral decision difference scene, and the second preset scene can be a lateral trajectory difference scene. For the longitudinal direction, the third preset scene can be a manual driving constant speed scene, and the fourth preset scene can be a manual driving acceleration or deceleration scene.

[0044] In an optional embodiment, the automatic driving system automatically obtains the driving direction of the vehicle, including the vehicle driving trajectory and the vehicle driving speed in the driving process. In the manual driving state, the driver drives the vehicle to change lanes, but the automatic driving system does not give a lane change instruction to control the vehicle to change lanes, and at this time, the decision difference occurs. The driver drives the vehicle to change lanes, and the automatic driving system also gives a lane change instruction to control the vehicle to change lanes, but the trajectory of the driver driving the vehicle to change lanes is different from the trajectory of the vehicle changing lanes given by the automatic driving system, and at this time, the trajectory difference occurs. In response to the driving direction being the lateral direction, it is determined that the current driving scene is the first preset scene or the second preset scene. In the manual driving state, the driver drives the automatic driving vehicle to drive forward, and the automatic control system automatically obtains the actual average speed, the actual maximum speed, the actual average acceleration, and the actual maximum acceleration of the vehicle driving. If the difference between these data exceeds the set difference threshold, a speed difference occurs. In response to the driving direction being the longitudinal direction, it is determined that the current driving scene is the third preset scene or the fourth preset scene.

[0045] Optionally, according to the method of the above embodiment of the application, the current driving scene is determined to be the first preset scene or the second preset scene, including: determining a first issuing time of a first lane change instruction in the first driving data and a second issuing time of a second lane change instruction in the second driving data; obtaining a time difference between the first issuing time and the second issuing time; and in response to the time difference being greater than a first preset time difference, determining that the current driving scene is the first preset scene.

[0046] In the above embodiment of the application, the automatic driving system automatically obtains the driving direction of the vehicle, including the vehicle driving trajectory and the vehicle driving speed in the driving process. In the manual driving state, the driver drives the vehicle to change lanes, but the automatic driving system does not give a lane change instruction to control the vehicle to change lanes, and at this time, the decision difference occurs. The driver drives the vehicle to change lanes, and the automatic driving system also gives a lane change instruction to control the vehicle to change lanes, but the trajectory of the driver driving the vehicle to change lanes is different from the trajectory of the vehicle changing lanes given by the automatic driving system, and at this time, the trajectory difference occurs. In response to the driving direction being the lateral direction, it is determined that the current driving scene is the first preset scene or the second preset scene. In the manual driving state, the driver drives the automatic driving vehicle to drive forward, and the automatic control system automatically obtains the actual average speed, the actual maximum speed, the actual average acceleration, and the actual maximum acceleration of the vehicle driving. If the difference between these data exceeds the set difference threshold, a speed difference occurs. In response to the driving direction being the longitudinal direction, it is determined that the current driving scene is the third preset scene or the fourth preset scene. Figure 3 is a schematic diagram of the automatic driving system giving a lane change instruction in the lateral decision difference according to an optional embodiment of the application, as Figure 3 shown in FIG. 1, the first driving data (such as Figure 3The first lane change instruction in the middle solid line L can be a lane change instruction issued when the vehicle is manually driven, and the first issuance time is the lane change instruction issuance time T0 (as shown in the left part of FIG. 1). Figure 3 The second lane change instruction in the middle solid pentagram can be a lane change instruction issued when the vehicle is automatically driven, and the second issuance time is the lane change instruction issuance time T1 (as shown in the right part of FIG. 1). Figure 3 The second lane change instruction in the middle solid pentagram can be a lane change instruction issued when the vehicle is automatically driven, and the second issuance time is the lane change instruction issuance time T1 (as shown in the right part of FIG. 1). Figure 3 The first preset time can be a threshold value corresponding to the time difference T-delta between the time T1 and the time T0. It should be noted that the time axis direction is to the right (as shown in the T axis in FIG. 1). Figure 3

[0047] In an alternative embodiment, when the driver drives the autonomous vehicle forward, the time at which the driver issues a lane change instruction when manually controlling the vehicle is T0, the time at which the autonomous driving system issues a lane change instruction when simulating driving is T1, and the time difference T-delta between the first issuance time and the second issuance time is obtained. When the time difference is greater than the set time difference threshold value, it indicates that the lane change instruction is issued by manual control, but the autonomous driving system does not issue the lane change instruction at the same time domain as the manual driving, and it is determined that the driving scene is a lateral decision difference scene.

[0048] Optionally, according to the method of the above-mentioned embodiment of the application, the scene data corresponding to the current driving scene is obtained to obtain target scene data, including: determining the lane change time of the autonomous vehicle based on the first issuance time and the second issuance time; determining the target time period corresponding to the target scene data based on the lane change time; and obtaining the scene data in the target time period to obtain the target scene data.

[0049] The lane change time refers to the time at which the driver issues a lane change operation instruction when manually controlling the autonomous vehicle. The target time period refers to the time period during which scene data needs to be collected in the lateral decision difference scene. When the driver manually controls the autonomous vehicle, several lane change operation instructions will be issued according to the actual road conditions. In order to accurately obtain the difference data corresponding to a certain lane change operation instruction, it is required to obtain the lane change instruction issued when manually controlling the vehicle and the lane change instruction issued by the autonomous driving system in the same time domain corresponding to the target time period, and to include the time period before the first issuance time, so as to record effective and valuable scene labels for analysis.

[0050] ​In an optional embodiment, the driver drives the automatic driving vehicle to move forward, and in a certain case, the time for the driver to manually control to issue a lane change instruction is a first issuing time T0, and the time for the automatic driving system to issue a lane change instruction when simulating driving is T1, and the lane change time is T0 at this time. Based on the time difference between the first issuing time and the second issuing time, if the time difference is greater than the time difference threshold set for the driving scene, it is indicated that the lane change instruction is manually controlled, but the automatic driving system does not issue the lane change instruction within the set time. It is determined that the vehicle driving scene at this time is a lateral decision difference scene. Based on the lane change time T0, a response target time period can be selected. For example, if the automatic driving system does not issue a lane change instruction within a certain time T-chage after the lane change time, it is identified that the current scene is a lateral decision difference scene, the data at a time before the lane change time, such as 10s to T-chg, is taken as the lateral decision difference scene data of this time, and the scene label is recorded.

[0051] Optionally, according to the method of the above-mentioned embodiment of the application, based on the lane change time, the target time period corresponding to the target scene data is determined, including: in response to the time difference being greater than a first preset time difference and less than a second preset time difference, determining that the starting time of the target time period is a difference value of the lane change time and the first preset value, and the ending time of the target time period is a sum value of the lane change time and the time difference; and the time difference is greater than the second preset time difference, and the starting time of the target time period is a difference value of the lane change time and the first preset value, and the ending time of the target time period is a sum value of the lane change time and the second preset time difference; wherein the second preset time difference is greater than the first preset time difference.

[0052] The second preset time difference can be a time T-chg after the first issuing time, and the automatic driving system collects whether there is a second issuing operation instruction within this time. The starting time and the ending time can be the start time and the end time of the target time period of the automatic driving system in the lateral decision difference scene, and the scene data required before and after the lane change time is collected as the standard.

[0053] In an optional embodiment, as Figure 3As shown, when the driver drives the automatic driving vehicle to travel forward, a certain time difference T-delta is generated between the lane changing time T0 of the driver and the lane changing time T1 of the automatic driving decision, if T-delta is greater than the set time difference threshold, the difference is judged as a lateral decision difference, the current driving scene is the first preset scene (i.e. the lateral decision difference scene), and T-delta is less than the second preset time difference T-chg, it is determined that the automatic driving system has no lane changing instruction issued within a period of time after the first issuing time of the lane changing instruction, the starting time of the target time period is determined as the difference between the lane changing time and the first preset value, and the ending time is determined as the sum of the lane changing time and the time difference, that is, the target time period is a period of time before the lane changing time T0 of the driver to the lane changing time T1 of the automatic driving decision. Figure 4 is a schematic diagram of the automatic driving system without issuing a lane changing instruction under the lateral decision difference according to an embodiment of the present application, as shown in Figure 4 If the time difference is greater than the second preset time difference T-chg, it is greater than the set time difference threshold, the difference is judged as a lateral decision difference, the current driving scene is the first preset scene (i.e. the lateral decision difference scene), and it is explained that the automatic driving system has no lane changing instruction issued within a period of time after the first issuing time T0 of the lane changing instruction (as shown by the solid pentagram in Figure 4 ), then the starting time of the target time period is determined as the difference between the lane changing time and the first preset value, and the ending time is determined as the sum of the lane changing time and the second preset time difference, that is, the target time period is a period of time before the lane changing time T0 of the driver to the time T-chg.

[0054] For example, in the manual driving state, if the driver changes lane at a time T0, and the automatic driving system issues a lane changing instruction at a time T1 within a certain time after the time T0, then the starting time and the ending time of the target time period include the following steps:

[0055] 1. Set the first preset time to 10s, and the second preset time T-chg to 15s;

[0056] 2. Calculate the difference between the time T1 and the time T0 as T-delta;

[0057] 3. If 10s < T-delta < 15s, it is explained that the automatic driving system issues a lane changing instruction at the time T1 within the second preset time;

[0058] 4. The starting time of the target time period is 10s before the lane changing time T0, and the ending time is the time T1;

[0059] 5. If T-delta > 15s, it is explained that the automatic driving system has no lane changing instruction issued within the second preset time;

[0060] 6、the target time period starts 10s before the lane changing time T0 and ends 15s after the lane changing time T0.

[0061] It should be noted that if the automatic driving system issues a lane changing instruction at a time T0, and the driver performs lane changing at a time T1 within a certain time T-chg after the time T0, the difference between the time T1 and the time T0 is calculated as T-delta, wherein a threshold value is set for T-delta, which is less than T-chg. If the difference is greater than the set threshold value and less than T-chg, the current scene is identified as a lateral decision difference scene, the data from the difference between the lane changing time and the threshold value to the time T1 is taken as the lateral decision difference scene data of this time, and the scene label is recorded. If the difference is greater than T-chg, the data from the difference between the lane changing time and the threshold value to the time T-chg is taken as the lateral decision difference scene data of this time, and the scene label is recorded.

[0062] Optionally, in response to the time difference being less than or equal to the first preset time difference, the method according to the embodiment of the application further includes: obtaining a first driving trajectory in the first driving data and a second driving trajectory in the second driving data; obtaining a distance between the first driving trajectory and the second driving trajectory; and in response to the distance being greater than a preset distance, determining that the current driving scene is a second preset scene.

[0063] The first driving trajectory in the first driving data can be a motion trajectory X0 of the vehicle after a lane changing instruction is issued by the human driving control. The second driving trajectory in the second driving data can be a motion trajectory X1 of the vehicle after a lane changing instruction is issued by the automatic driving system simulation driving. The second preset scene can be a lateral trajectory difference, for example, the scene can include a straight lane without lane changing scene, a turning or U-turn scene, and a lane changing scene.

[0064] It should be noted that when the vehicle is straight in the lane without lane changing, the lateral trajectory of the human driving is less different from that of the automatic driving system, and therefore no difference comparison is performed in such a scene. In the turning, U-turn, and lane changing scenes, the historical driving trajectory of the vehicle after the operation is completed is compared with the trajectory output by the automatic driving system, the distance between the trajectory points at the same time is calculated, and if the distance exceeds a certain threshold value, the difference data in the target scene can be recorded.

[0065] For example, when the human driving vehicle performs lane changing, the automatic driving system issues a lane changing operation instruction. When the vehicle performs lane changing, the running trajectory of the human driving vehicle is X0, and the running trajectory of the vehicle controlled by the automatic driving system simulation is X1. In the process of lane changing, the automatic driving system automatically compares X0 and X1, and if the distance between the trajectory points at the same time exceeds a set distance threshold value, it is determined that the current driving scene is a lateral trajectory difference.

[0066] Optionally, according to the method of the above-mentioned embodiments of the application, the method further comprises: determining a trajectory starting time based on the first driving trajectory and the second driving trajectory; and obtaining the target scene data by obtaining scene data at the trajectory starting time.

[0067] In an optional embodiment, when the vehicle executes the instruction issued by the driver's manual control, the vehicle starts to change the running trajectory and the driving trajectory is X0, the automatic driving system simulates the vehicle changing the running trajectory and the trajectory is X1 under the same scene, and the trajectory starting time is determined as the time when the operation instruction is issued. Starting from the trajectory starting time, the automatic driving system automatically compares X0 and X1, and determines that the current driving scene is a lateral trajectory difference. The automatic driving system automatically obtains the target scene data in a period of time and records the scene label.

[0068] For example, for a turning or U-turn scene, after the driver completes the turning or U-turn, the vehicle driving history trajectory data X0 at the turning or U-turn starting time is compared with the trajectory X1 output by the automatic driving system, the distance between the trajectory points at the same time is calculated, and if the distance exceeds a certain threshold, the current scene is identified as a lateral trajectory difference scene. The data at the turning or U-turn starting time is taken as the lateral trajectory difference scene data of this time, and the scene label is recorded.

[0069] For a lane changing scene, if there is no lateral decision difference, after the driver completes the lane changing, the vehicle driving trajectory data X0 at the lane changing starting time is compared with the trajectory X1 output by the automatic driving system when the lane changing is decided, the lane changing starting time of the driver is aligned with the lane changing time when the automatic driving system decides, and then the distance between the trajectory points at the same time is calculated. If the distance exceeds a certain distance threshold, the current scene is identified as a lateral trajectory difference scene. The data at the lane changing starting time is taken as the lateral trajectory difference scene data of this time, and the scene label is recorded.

[0070] Optionally, according to the method of the above-mentioned embodiments of the application, the method further comprises: obtaining a first maximum value and a first average value of the vehicle speed, and a second maximum value and a second average value of the vehicle acceleration; in response to the first maximum value and the second maximum value being within a first preset range, and the first average value and the second average value being within a second preset range, determining that the current driving scene is a third preset scene; and in response to the first maximum value not being within the first preset range, or the second maximum value not being within the first preset range, or the first average value not being within the second preset range, or the second average value not being within the second preset range, determining that the current driving scene is a fourth preset scene.

[0071] The first maximum value and the first average value of the vehicle speed can be a maximum value and an average value of an actual acceleration speed when the driver performs manual driving. The second maximum value and the second average value of the vehicle acceleration can be a maximum value and an average value of an actual acceleration when the automatic control system simulates driving. The first preset range can be a maximum value range of the actual acceleration when the vehicle uniform driving scene is determined. The second preset range can be a preset average value range of the actual acceleration. The third preset scene can be a manual driving uniform speed scene. The fourth preset scene can be a manual driving acceleration or deceleration scene.

[0072] In an optional embodiment, when the driver performs manual driving, the automatic driving system automatically obtains a maximum value Am0 of an actual acceleration of the automatic driving vehicle, an average value A0 of the actual acceleration, a maximum value Am1 of the actual acceleration when the automatic driving system simulates vehicle driving, and an average value A1 of the actual acceleration. A numerical range is set for the maximum value and the average value of the actual acceleration. If Am0 and Am1 are within the set range of the maximum value of the actual acceleration, and A0 and A1 are within the set range of the average value of the actual acceleration, it is determined that the vehicle is actually in uniform motion, and the scene is determined to be a manual driving uniform speed scene. If one or more than one value in the four value types exceeds the set numerical range, the scene is determined to be a manual driving acceleration or deceleration scene.

[0073] Optionally, according to the method of the above-mentioned embodiment of the application, determining that the current driving scene is the fourth scene comprises: obtaining an acceleration instruction output by the automatic driving system, wherein the acceleration instruction is generated by the automatic driving system when the first vehicle speed in the first driving data is different from the second vehicle speed in the second driving data; obtaining a difference between the acceleration instruction and the target acceleration in the first driving data to obtain a first difference; and in response to the first difference being greater than a first preset difference, determining that the current driving scene is the third preset scene.

[0074] The first vehicle speed in the first driving data can be a speed at which the vehicle is driven when the driver performs manual control. The second vehicle speed in the second driving data can be a speed at which the vehicle is driven when the automatic driving system simulates driving. The first difference can be a difference between the average value of the vehicle driving speed controlled by the manual control and the automatic driving system. The first preset difference is a threshold value set for the difference.

[0075] In an optional embodiment, the driver drives the automatic driving vehicle, and controls the driving speed of the vehicle to be V0 by manual control. In the same period of time, the driving speed of the vehicle is simulated to be V1 by the automatic driving system. When V0 is not equal to V1, it indicates that the actual driving speed of the driver is inconsistent with the target speed of the automatic driving system. At this time, the automatic driving system outputs a larger acceleration instruction according to the difference between the actual speed and the target speed. It should be additionally explained that the positive value of the acceleration represents the acceleration motion of the vehicle, and the negative value of the acceleration represents the deceleration motion of the vehicle. After generating an acceleration instruction, the automatic driving system automatically acquires the output acceleration instruction, and compares the difference between V0 and V1. At this time, the actual acceleration of the vehicle is close to 0. Therefore, in the scene of the approximate uniform speed of the vehicle, when the difference is greater than the threshold value set by the system in advance, the current scene is identified as the manual driving uniform speed difference scene. A certain time, for example, 10 s, before and after the difference time is taken as the difference scene data this time, and the scene label is recorded.

[0076] Optionally, according to the method of the above-mentioned embodiment of the application, the method further comprises: obtaining a difference between the first maximum value and the second maximum value to obtain a second difference value, and a difference between the first average value and the second average value to obtain a third difference value; and determining that the current driving scene is the fourth preset scene in response to the second difference value being greater than a second preset difference value or the third difference value being greater than a third preset difference value.

[0077] In an optional embodiment, when the driver drives manually, the automatic driving system automatically acquires the maximum value Am0 of the actual acceleration of the automatic driving vehicle, the average value A0 of the actual acceleration, the maximum value Am1 of the actual acceleration of the vehicle driven by the automatic driving system, and the average value A1 of the actual acceleration. The second difference value can be the difference between Am0 and Am1. The third difference value can be the difference between A0 and A1. The second preset difference value can be a set threshold value of the difference between the maximum values Am0 and Am1 of the actual acceleration. The third preset difference value can be a set threshold value of the difference between the average values A0 and A1 of the actual acceleration.

[0078] In an optional embodiment, when the driver drives the automatic driving vehicle, the maximum value Am0 of the actual acceleration of the vehicle driven by the driver, and the average value A0 of the actual acceleration, the maximum value Am1 of the actual acceleration of the vehicle driven by the automatic driving system, and the average value A1 of the actual acceleration are simulated. After the automatic driving system automatically acquires these data, the difference between Am0 and Am1 is calculated as a second difference value, and the difference between A0 and A1 is calculated as a third difference value. If one or more of the difference values exceeds the corresponding set threshold value, the current scene is identified as the manual driving acceleration and deceleration difference scene, a certain time before and after the difference time is identified as the difference scene data this time, and the scene label is recorded.

[0079] Optionally, according to the method of the above-mentioned embodiment of the application, the scene data corresponding to the current driving scene is acquired to obtain target scene data, comprising: determining a preset time period with a difference time as the center, wherein the difference time is used to represent the time when the current driving scene is determined; and acquiring the scene data in the preset time period to obtain the target scene data.

[0080] The difference time can be a time when the second difference value or the third difference value exceeds a corresponding set threshold, indicating that the vehicle driving scene is an artificial driving acceleration or deceleration scene.

[0081] In an optional embodiment, when the driver drives the automatic driving vehicle, the maximum value of the actual acceleration of the manually controlled vehicle and the maximum value of the actual acceleration of the automatic driving system simulation driving are different by more than a maximum value difference threshold, or the average value of the actual acceleration of the manually controlled vehicle and the average value of the actual acceleration of the automatic driving system simulation driving are different by more than an average value difference threshold, confirming that the difference time is set at this time, and the data of a certain time before and after the difference time is taken as the difference scene data, for example, a time period of 10s before and after the difference time, and the scene label is recorded.

[0082] In the embodiment of the application, in view of the technical problem of data redundancy and low efficiency in collecting scene data for automatic driving, the embodiment of the application proposes a scheme of comparing the difference between the virtual control instruction output by the automatic driving system and the behavior of the driver, comparing the lateral difference and the longitudinal difference according to the direction of vehicle movement, and performing difference analysis and effective data recording according to different scene characteristics to obtain high-quality scene data required by the automatic driving system. This data processing method includes:

[0083] 1. In order to ensure accurate identification and acquisition of real scene data effective for the automatic driving system, the automatic driving system is virtually run during manual driving, the lateral and longitudinal differences are compared in different scenes according to the direction of vehicle movement, and the time of data recording is set according to the characteristics of the scene, greatly improving the effectiveness of the data;

[0084] 2. In order to effectively analyze the lateral motion difference, the lateral decision is analyzed first, and then the distance difference of the lateral trajectory is analyzed for different roads and driver behavior scenes;

[0085] 3. For longitudinal motion scenes, according to the vehicle state in a certain time, the uniform speed driving and acceleration and deceleration driving scenes are compared and analyzed respectively, avoiding the misjudgment caused by uniform analysis of acceleration difference.

[0086] Embodiment 2

[0087] According to another aspect of the embodiments of the present application, a vehicle data processing device is also provided, which can perform the vehicle data processing method in the above-mentioned embodiments, and the specific implementation scheme and preferred application scenarios are the same as those of the above-mentioned embodiments, which will not be repeated here.

[0088] Figure 5 is a schematic diagram of a data processing device according to an embodiment of the present application, as shown in Figure 5 , the device comprises:

[0089] The first acquisition module 52 is configured to acquire first driving data generated by the autonomous vehicle and second driving data generated by the autonomous driving system during driving of the autonomous vehicle by the driver, the autonomous driving system being installed on the autonomous vehicle.

[0090] The determination module 54 is configured to determine the current driving scene of the autonomous vehicle based on the difference between the first driving data and the second driving data.

[0091] The second acquisition module 56 is configured to acquire scene data corresponding to the current driving scene to obtain target scene data.

[0092] In the embodiments of the present application, the first acquisition module can acquire the lane changing operation instruction time to determine whether it is a lateral decision difference, acquire the driving trajectory of the vehicle when performing lane changing, turning, U-turn and other operations to determine whether it is a lateral trajectory difference, acquire the maximum and average values of the actual vehicle speed at the current time to determine whether it is a longitudinal difference artificial driving constant speed scene, and acquire the maximum and average values of the actual acceleration at the current time to determine whether it is a longitudinal difference artificial driving acceleration or deceleration scene. The second acquisition module can be used to confirm the scene data corresponding to the current driving scene to obtain target scene data and record the scene label after the difference comparison, so that the useful difference data of the corresponding target scene can be used for subsequent development of the autonomous driving system.

[0093] For example, when the driver manually drives the automatic driving vehicle, the automatic driving system automatically acquires, through the first acquisition module, a lane changing instruction time when the driver manually controls driving and a lane changing instruction time when the automatic driving system simulates driving; the determination module compares the two data and determines that the scene is a lateral decision difference if the difference exceeds a set difference range; the second acquisition module acquires data of a period of time before and after the lane changing time as the scene data of the lateral decision difference, and records the scene label.

[0094] Optionally, in the method according to the embodiments of the application, the determination module comprises: a direction acquisition unit, configured to acquire a driving direction of the automatic driving vehicle; a first scene determination unit, configured to, in response to the driving direction being a lateral direction, determine, based on the first driving data and the second driving data, that the current driving scene is the first preset scene or the second preset scene; and a second scene determination unit, configured to, in response to the driving direction being a longitudinal direction, determine, based on a vehicle speed and a vehicle acceleration in a historical time period, that the current driving scene is the third preset scene or the fourth preset scene.

[0095] Optionally, in the method according to the embodiments of the application, the first acquisition module comprises: a time acquisition unit, configured to acquire a first issuing time of the first lane changing instruction in the first driving data and a second issuing time of the second lane changing instruction in the second driving data; and a time difference acquisition unit, configured to acquire a time difference between the first issuing time and the second issuing time; and the first scene determination unit in the determination module comprises: a first scene region determination unit, configured to, in response to the time difference being greater than a first preset time difference, determine that the current driving scene is the first preset scene.

[0096] Optionally, in the method according to the embodiments of the application, the first acquisition module comprises: a time acquisition unit, configured to determine, based on the first issuing time and the second issuing time, a lane changing time of the automatic driving vehicle; and determine, based on the lane changing time, a target time period corresponding to target scene data; and the second acquisition module is configured to acquire scene data in the target time period to obtain the target scene data.

[0097] Optionally, in the method according to the embodiments of the application, the first acquisition module further comprises: a trajectory acquisition unit, configured to acquire a first driving trajectory in the first driving data and a second driving trajectory in the second driving data; and a distance acquisition unit, configured to acquire a distance between the first driving trajectory and the second driving trajectory; and the first scene determination unit in the determination module further comprises: a first scene region two determination unit, configured to, in response to the distance being greater than a preset distance, determine that the current driving scene is the second preset scene.

[0098] Optionally, in the method according to the embodiments of the application, the first acquisition module further comprises: a time acquisition unit, configured to determine, based on the first driving trajectory and the second driving trajectory, a trajectory starting time; and the second acquisition module is configured to acquire scene data at the trajectory starting time to obtain the target scene data.

[0099] Optionally, according to the method of the above-mentioned embodiments of the application, the first obtaining module further comprises: a speed obtaining module, configured to obtain a first maximum value and a first average value of the vehicle speed, and an acceleration obtaining module, configured to obtain a second maximum value and a second average value of the vehicle acceleration; and the second scene determining unit of the determining module comprises: a second scene region one determining unit, configured to determine that the current driving scene is a third preset scene, in response to the first maximum value and the second maximum value both being within a first preset range, and the first average value and the second average value both being within a second preset range; and a second scene region two determining unit, configured to determine that the current driving scene is a fourth preset scene, in response to the first maximum value not being within the first preset range, or the second maximum value not being within the first preset range, or the first average value not being within the second preset range, or the second average value not being within the second preset range.

[0100] Optionally, according to the method of the above-mentioned embodiments of the application, the first obtaining module further comprises: an instruction obtaining unit, further configured to obtain an acceleration instruction output by the automatic driving system, wherein the acceleration instruction is generated by the automatic driving system in a case where the first vehicle speed in the first driving data is different from the second vehicle speed in the second driving data; and a difference value obtaining unit, configured to obtain a difference value between the acceleration instruction and the target acceleration in the first driving data, to obtain a first difference value; and the second scene determining unit of the determining module comprises: a second scene region one determining unit, configured to determine that the current driving scene is the third preset scene, in response to the first difference value being greater than a first preset difference value.

[0101] Optionally, according to the method of the above-mentioned embodiments of the application, the first obtaining module further comprises: a difference value obtaining unit, further configured to obtain a difference value between the first maximum value and the second maximum value, to obtain a second difference value, and a difference value between the first average value and the second average value, to obtain a third difference value; and the second scene determining module of the determining module further comprises: a second scene region two determining unit, configured to determine that the current driving scene is the fourth preset scene, in response to the second difference value being greater than a second preset difference value, or the third difference value being greater than a third preset difference value.

[0102] Optionally, according to the method of the above-mentioned embodiments of the application, the first obtaining module further comprises: a time obtaining unit, configured to determine a preset time period centered on a difference time point, wherein the difference time point is used to represent a time point at which the current driving scene is determined; and the second obtaining module is configured to obtain scene data in the preset time period, to obtain target scene data.

[0103] Embodiment 3

[0104] According to another aspect of the embodiments of the application, there is also provided a vehicle, which is equipped with the data processing device in the above-mentioned embodiments, and can also perform the data processing method of any one of the above-mentioned embodiments.

[0105] Embodiment 4

[0106] According to another aspect of the embodiments of the present application, a computer readable storage medium is also provided, which includes a stored program, wherein the program, when executed, controls a device where the computer readable storage medium is located to perform the data processing method of any of the above embodiments.

[0107] Embodiment 5

[0108] According to another aspect of the embodiments of the present application, a processor is also provided, which is configured to execute a program, wherein the program, when executed, performs the data processing method of any of the above embodiments.

[0109] The above-mentioned embodiment numbers of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments.

[0110] In the above-mentioned embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0111] In several embodiments provided in the present application, it should be understood that the disclosed technical contents can be implemented by other manners. Among them, the above-mentioned device embodiments are only schematic, for example, the division of the units can be a logical function division, and in actual implementation, there can be another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or modules shown or discussed can be indirect coupling or communication connection through some interfaces, units or modules, which can be electrical or other forms.

[0112] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on a plurality of units. According to actual needs, part or all of the units can be selected to achieve the purpose of the present embodiment.

[0113] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be realized in the form of hardware or in the form of software functional unit.

[0114] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to make a computer device (which can be a personal computer, a server or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0115] The above is only the preferred embodiment of the present application, it should be pointed out that, for those skilled in the art, without departing from the principles of the present application, can make a number of improvements and refinements, these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A data processing method, characterized by, The method comprises the following steps: During driving of an automatic driving vehicle by a driver, first driving data generated by the automatic driving vehicle and second driving data generated by an automatic driving system installed on the automatic driving vehicle are acquired, the first driving data being driving data of the automatic driving vehicle when the driver manually drives the automatic driving vehicle, and the second driving data being simulation running data of the automatic driving vehicle when the automatic driving system simulates control of the automatic driving vehicle; In response to the first driving data being different from the second driving data, a current driving scene of the automatic driving vehicle is determined, wherein the current driving scene is determined according to a difference type of the first driving data and the second driving data; Scene data corresponding to the current driving scene is acquired to obtain target scene data; In a case where the difference type is a lateral decision difference, the acquisition of the scene data corresponding to the current driving scene to obtain the target scene data comprises the following steps: a first issuing time of a first lane changing instruction in the first driving data and a second issuing time of a second lane changing instruction in the second driving data are determined; a lane changing time of the automatic driving vehicle is determined based on the first issuing time and the second issuing time; in response to a time difference between the first issuing time and the second issuing time being greater than a first preset time difference and less than a second preset time difference, a start time of a target time period is determined as a difference value between the lane changing time and the first preset time difference, and an end time of the target time period is determined as a sum value of the lane changing time and the time difference; in response to the time difference being greater than the second preset time difference, the start time of the target time period is determined as the difference value between the lane changing time and the first preset time difference, and the end time of the target time period is determined as a sum value of the lane changing time and the second preset time difference, wherein the second preset time difference is greater than the first preset time difference; scene data in the target time period is acquired to obtain the target scene data; The method further comprises the following steps: an acceleration instruction output by the automatic driving system is acquired, wherein the acceleration instruction is generated by the automatic driving system in a case where a first vehicle speed in the first driving data is different from a second vehicle speed in the second driving data; a difference value between the acceleration instruction and a target acceleration in the first driving data is acquired to obtain a first difference value; in response to the first difference value being greater than a first preset difference value, the current driving scene is determined to be a manual driving constant speed scene.

2. The method of claim 1, wherein, The determination of the current driving scene of the automatic driving vehicle comprises the following steps: A driving direction of the automatic driving vehicle is acquired; In response to the driving direction being a lateral direction, the current driving scene is determined to be a first preset scene or a second preset scene based on the first driving data and the second driving data; In response to the driving direction being a longitudinal direction, the current driving scene is determined to be a third preset scene or a fourth preset scene based on vehicle speed and vehicle acceleration in a historical time period.

3. The method of claim 2, wherein, The determining the current driving scene being the first preset scene or the second preset scene comprises: In response to the time difference being greater than a first preset time difference, the current driving scene is determined to be the first preset scene.

4. The method of claim 3, wherein, In response to the time difference being less than or equal to the first preset time difference, the method further comprises: Obtaining a first driving trajectory in the first driving data and a second driving trajectory in the second driving data; Obtaining a distance of the first driving trajectory and the second driving trajectory; In response to the distance being greater than a preset distance, the current driving scene is determined to be the second preset scene.

5. The method of claim 4, wherein, Obtaining scene data corresponding to the current driving scene to obtain target scene data comprises: Determining a trajectory starting time based on the first driving trajectory and the second driving trajectory; Obtaining scene data at the trajectory starting time to obtain the target scene data.

6. The method of claim 2, wherein, The determining the current driving scene being the third preset scene or the fourth preset scene comprises: Obtaining a first maximum value and a first average value of the vehicle speed, and a second maximum value and a second average value of the vehicle acceleration; In response to the first maximum value and the second maximum value being within a first preset range, and the first average value and the second average value being within a second preset range, the current driving scene is determined to be the third preset scene; In response to the first maximum value not being within the first preset range, or the second maximum value not being within the first preset range, or the first average value not being within the second preset range, or the second average value not being within the second preset range, the current driving scene is determined to be the fourth preset scene.

7. The method of claim 6, wherein, Obtaining scene data corresponding to the current driving scene to obtain target scene data comprises: Determining a preset time period centered on a difference time, wherein the difference time is used to represent the time of determining the current driving scene; Obtaining scene data in the preset time period to obtain the target scene data.

8. A data processing apparatus, characterized by, Comprise: The first obtaining module is used for obtaining first driving data generated by an automatic driving vehicle and second driving data generated by an automatic driving system during driving of the automatic driving vehicle by a driver, the automatic driving system being installed on the automatic driving vehicle, the first driving data being driving data of the automatic driving vehicle when the driver manually drives the automatic driving vehicle, and the second driving data being simulation running data of the automatic driving vehicle when the automatic driving system simulates control of the automatic driving vehicle; The determining module is used for determining a current driving scene of the automatic driving vehicle based on the first driving data and the second driving data being different, wherein the current driving scene is determined based on a difference type of the first driving data and the second driving data; The second obtaining module is used for obtaining scene data corresponding to the current driving scene to obtain target scene data. In a case where the difference type is a lateral decision difference, the second obtaining module is further configured to obtain the scene data corresponding to the current driving scene, i.e., target scene data, by the following steps: determining a first issuing time of a first lane-changing instruction in the first driving data and a second issuing time of a second lane-changing instruction in the second driving data; determining a lane-changing time of the autonomous vehicle based on the first issuing time and the second issuing time; in response to a time difference between the first issuing time and the second issuing time being greater than a first preset time difference and less than a second preset time difference, determining a start time of a target time period as a difference between the lane-changing time and the first preset time difference, and determining an end time of the target time period as a sum of the lane-changing time and the time difference; in response to the time difference being greater than the second preset time difference, determining the start time of the target time period as the difference between the lane-changing time and the first preset time difference, and determining the end time of the target time period as a sum of the lane-changing time and the second preset time difference, wherein the second preset time difference is greater than the first preset time difference; and obtaining scene data in the target time period to obtain the target scene data. The device is further configured to: obtain an acceleration instruction output by the autonomous driving system, wherein the acceleration instruction is generated by the autonomous driving system in a case where a first vehicle speed in the first driving data is different from a second vehicle speed in the second driving data; obtain a difference between the acceleration instruction and a target acceleration in the first driving data to obtain a first difference; and in response to the first difference being greater than a first preset difference, determine that the current driving scene is a manual constant-speed driving scene.

9. A vehicle characterized by comprising: The data processing device of claim 8. The data processing device of claim 8.

Images