Auxiliary driving system updating method and device, equipment and medium

Abstract

The invention discloses an auxiliary driving system updating method and device, equipment and a medium, and relates to the technical field of intelligent driving, and the method comprises the steps: inputting a first driving behavior feature of a current driving scene into a trained auxiliary driving system model corresponding to the current driving scene, so as to output an optimized auxiliary driving system planning track; the driving behavior characteristics comprise driving habit parameters and an auxiliary driving system planning track; planning a track to control the vehicle based on the optimized auxiliary driving system, recording a second driving behavior characteristic after detecting a driver intervention behavior, and calculating deviation data generated based on the intervention behavior; and training according to an error correction data set constructed based on the first driving behavior characteristics, the second driving behavior characteristics and the deviation data to obtain a new auxiliary driving system model so as to update the auxiliary driving system. Effective adaptation to different auxiliary driving habits is achieved, and personalized, accurate and safe auxiliary driving experience is provided for different drivers.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to an assisted driving system updating method, device, equipment and medium. Background Art

[0002] Nowadays, the assisted driving systems installed on the same model maintain unified standards. However, since each driver has formed a unique driving style and habits during the driving process, when different drivers enable the assisted driving system, they often feel that the vehicle is being controlled by someone else. This difference affects the consistency and comfort of the driving experience to a certain extent. Therefore, the above technical issues need to be solved urgently. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide a method, device, equipment and medium for updating an assisted driving system, which can achieve effective adaptation to different assisted driving habits. The specific scheme is as follows:

[0004] In a first aspect, the present application discloses a method for updating an assisted driving system, comprising:

[0005] Recording a first driving behavior feature of a current driving scene, and inputting the first driving behavior feature into a pre-trained assisted driving system model corresponding to the current driving scene, so as to output an optimized assisted driving system planning trajectory; the driving behavior feature includes a driving habit parameter and an assisted driving system planning trajectory;

[0006] Controlling the vehicle based on the trajectory planned by the optimized auxiliary driving system, and after detecting the driver's intervention behavior, recording the second driving behavior characteristics, and calculating deviation data generated based on the intervention behavior;

[0007] A new assisted driving system model is obtained by training the error correction data set constructed based on the first driving behavior feature, the second driving behavior feature and the deviation data, so as to update the assisted driving system.

[0008] Optionally, after detecting the driver's intervention behavior, recording the second driving behavior feature includes:

[0009] After detecting the driver's intervention behavior, at least one driving scenario at the time when the intervention behavior occurs is determined, and the second driving behavior characteristics corresponding to the at least one driving scenario are recorded, and then the second driving behavior characteristics corresponding to the driving scenarios that do not meet the conditions are eliminated.

[0010] Optionally, the driving scenarios that do not meet the conditions include emergency braking of the vehicle within the first driving distance and the data is inconsistent with the cloud data, a construction area is detected within the second driving distance and the data is inconsistent with the cloud data, and the vehicle changes lanes.

[0011] Optionally, the deviation data includes trajectory deviation data, and the calculation is based on the deviation data generated by the intervention behavior, including:

[0012] determining a current driver driving trajectory corresponding to the intervention behavior, and determining a first trajectory difference between the current driver driving trajectory and a target trajectory to be optimized,

[0013] Obtaining an optimized target trajectory based on the product of the first trajectory difference and the first coefficient;

[0014] Determine a second trajectory difference between the optimized target trajectory and the current assisted driving system planned trajectory, and determine the second trajectory difference as the trajectory deviation data.

[0015] Optionally, obtaining an optimized target trajectory based on the product of the first trajectory difference and a first coefficient includes:

[0016] A first loss function is determined based on the product of the first trajectory difference and a first coefficient, and the optimized target trajectory is obtained based on the minimum function value of the first loss function; wherein, the driving distance is not less than a third driving distance, the first coefficient is a first value, the driving distance is less than the third driving distance, the first coefficient is a second value, and the second value is less than the first value.

[0017] Optionally, the deviation data includes speed deviation data, and the calculation is based on the deviation data generated by the intervention behavior, including:

[0018] Determining a current driver driving speed corresponding to the intervention behavior, and determining a first speed difference between the current driver driving speed and a target speed to be optimized;

[0019] Obtaining an optimized target speed based on the product of the first speed difference and a second coefficient;

[0020] A second speed difference between the optimized target speed and the current planned speed of the driving assistance system is determined, and the second speed difference is determined as the speed deviation data.

[0021] Optionally, obtaining the optimized target speed based on the product of the first speed difference and the second coefficient includes:

[0022] A second loss function is determined based on the product of the first speed difference and a second coefficient, and the optimized target speed is obtained based on the minimum function value of the second loss function; wherein, the driving distance is not less than a fourth driving distance, the second coefficient is a third value, the driving distance is less than the fourth driving distance, the second coefficient is a fourth value, and the fourth value is less than the third value.

[0023] In a second aspect, the present application discloses an assisted driving system updating device, comprising:

[0024] A planning trajectory output module, used for recording a first driving behavior feature of a current driving scene, and inputting the first driving behavior feature into a pre-trained assisted driving system model corresponding to the current driving scene, so as to output an optimized assisted driving system planning trajectory; the driving behavior feature includes a driving habit parameter and an assisted driving system planning trajectory;

[0025] a deviation data calculation module, configured to control the vehicle based on the trajectory planned by the optimized auxiliary driving system, and after detecting the driver's intervention behavior, record the second driving behavior feature and calculate the deviation data generated based on the intervention behavior;

[0026] The assisted driving system update module is used to obtain a new assisted driving system model through training based on the error correction data set constructed based on the first driving behavior characteristics, the second driving behavior characteristics and the deviation data, so as to realize the update of the assisted driving system.

[0027] In a third aspect, the present application discloses an electronic device, comprising:

[0028] Memory, used to store computer programs;

[0029] The processor is used to execute the computer program to implement the aforementioned assisted driving system update method disclosed above.

[0030] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; when the computer program is executed by a processor, the aforementioned assisted driving system update method disclosed above is implemented.

[0031] It can be seen that the present application proposes a method for updating an assisted driving system, including: recording a first driving behavior feature of the current driving scene, and inputting the first driving behavior feature into a pre-trained assisted driving system model corresponding to the current driving scene to output an optimized assisted driving system planning trajectory; the driving behavior feature includes driving habit parameters and assisted driving system planning trajectory; controlling the vehicle based on the optimized assisted driving system planning trajectory, and after detecting the driver's intervention behavior, recording the second driving behavior feature, and calculating the deviation data generated based on the intervention behavior; training a new assisted driving system model based on an error correction data set constructed based on the first driving behavior feature, the second driving behavior feature and the deviation data, so as to realize the update of the assisted driving system. In summary, when a driver uses the assisted driving system, the present application records his first driving behavior features under various road conditions, and inputs these data into a pre-trained assisted driving system model to output an optimized assisted driving system planning trajectory, and then controls the vehicle accordingly. If the driver intervenes due to his own habits, the second driving behavior characteristics are recorded, and the deviation data generated by the intervention behavior is calculated. Then, a new assisted driving system model is trained based on the error correction data set constructed based on the first driving behavior characteristics, the second driving behavior characteristics and the deviation data, so as to update the assisted driving system. In this way, the assisted driving system model will focus on learning the differences between the driver's habits and the original plan in order to adjust the internal parameter weights, thereby achieving effective adaptation to different assisted driving habits and providing personalized, accurate and safe assisted driving experience for different drivers. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0033] Figure 1 A flowchart of a method for updating an assisted driving system disclosed in this application;

[0034] Figure 2 A trajectory optimization schematic diagram disclosed in this application;

[0035] Figure 3 A schematic diagram of trajectory deviation data disclosed in this application;

[0036] Figure 4 A speed optimization schematic diagram disclosed in this application;

[0037] Figure 5A schematic diagram of speed deviation data disclosed in this application;

[0038] Figure 6 A flowchart of a specific method for updating an assisted driving system disclosed in this application;

[0039] Figure 7 This is a schematic diagram of the structure of an assisted driving system updating device disclosed in this application;

[0040] Figure 8 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] Today, the same model of car is equipped with a unified standard for autonomous driving systems. However, since each driver has developed a unique driving style and habits during driving, when different drivers enable the assisted driving system, they often feel that the vehicle is being controlled by someone else. This difference affects the consistency and comfort of the driving experience to a certain extent. Therefore, the above technical issues need to be solved urgently.

[0043] To this end, an embodiment of the present application proposes an assisted driving system update solution that can effectively adapt to different assisted driving habits and provide different drivers with a personalized, accurate and safe assisted driving experience.

[0044] The present application discloses a method for updating an assisted driving system. Figure 1 As shown, the method includes:

[0045] Step S11: Record the first driving behavior feature of the current driving scene, and input the first driving behavior feature into a pre-trained assisted driving system model corresponding to the current driving scene to output an optimized assisted driving system planning trajectory; the driving behavior feature includes driving habit parameters and the assisted driving system planning trajectory.

[0046] In this embodiment, different driving scenarios correspond to different time series models, and the training data of the driving scenario is given to the corresponding time series model to obtain the assisted driving system model of the driving scenario. The training data is obtained based on the driving behavior characteristics of the historical driving scenarios. The driving behavior characteristics include assisted driving habit parameters and assisted driving system planning trajectories. The assisted driving habit parameters can reflect the driver's driving habits. The driving scenarios include following, cutting in, cutting out, changing lanes, avoiding, starting, crossing intersections, passing through merging areas, and passing through diverging areas.

[0047] The following is an explanation of the driving scenarios: when the vehicle does not cross the lane and the ID (Identity document) of the following vehicle in front of the vehicle remains unchanged, it is determined to be a following scenario; when the vehicle does not cross the lane and the ID of the following vehicle changes, and the distance between the vehicles is shortened, it is determined to be a cut-in scenario; when the vehicle does not cross the lane and the ID of the following vehicle does not change, the distance between the vehicles increases or there is no vehicle in front, it is determined to be a cut-out scenario; when the distance between the vehicle and the left line of the lane changes from a positive value to 0, then to a negative value and then to a non-zero positive value, it is determined to be a left lane change scenario; when the distance between the vehicle and the right line of the lane changes from a negative value to 0, then to a positive value and then to a non-zero negative value, it is determined to be a right lane change scenario; when there are other vehicles in the left or right lane, it is determined to be an avoidance scenario; When the vehicle speed increases from 0 to a preset low speed value or the driving distance is within a preset short distance range, it is determined as a starting scenario; when the vehicle first detects that the left or right lane lines change from dotted lines to solid lines, it indicates entering the lane. When the vehicle passes the traffic light and travels a preset distance on the standard lane, it is determined to be a crossing intersection scenario; when the number of roads decreases and the vehicle is in the area with reduced lanes, at the merging point with reduced lanes, a preset merging area length range is extended forward or backward, respectively, and it is determined to be a passing merging area scenario; when the number of roads increases and the vehicle is in the area with increased lanes, at the diverging point with increased lanes, a preset diverging area length range is extended forward or backward, respectively, and it is determined to be a passing diverging area scenario.

[0048] The following is an explanation of the auxiliary driving habit parameters: The auxiliary driving habit parameters cover important information in multiple aspects: (1) The deviation distance of the lane center line, that is, the vertical distance between the center point of the vehicle's rear axle and the center line of the lane. This data can intuitively reflect the relative position deviation of the vehicle in the lane; (2) The distance of the lane boundary line, refers to the vertical distance between the center point of the vehicle's rear axle and the left and right boundary lines of the lane, recorded as the left boundary distance and the right boundary distance respectively. This data helps to clarify the lateral position range of the vehicle in the lane; (3) The distance to the curb, that is, the vertical distance between the center point of the vehicle's rear axle and the left and right curbs. This data is of great significance for judging the position of the vehicle when it is driving close to the roadside; (4) In terms of parameters related to following the vehicle, it includes the following target The data of the horizontal and longitudinal distance of the large vehicle, that is, the projection of the large vehicle to the self-vehicle coordinate system, along the projection of the front direction of the self-vehicle is the longitudinal coordinate, and the vertical direction is the horizontal coordinate. The angle between the large vehicle and the front of the self-vehicle, that is, the angle between the front of the large vehicle and the front of the self-vehicle, the horizontal and longitudinal distance of the large vehicle and the angle between the large vehicle and the front of the self-vehicle help to fully grasp the relative position and direction relationship between the large vehicle and the self-vehicle; (6) The horizontal and longitudinal distance of the small vehicle, that is, the projection of the small vehicle to the self-vehicle coordinate system, along the projection of the front direction of the self-vehicle is the longitudinal coordinate, and the vertical direction is the horizontal coordinate. The angle between the front of the small vehicle and the front of the self-vehicle, that is, the angle between the front of the small vehicle and the front of the self-vehicle, The front angle of the own vehicle, the horizontal and longitudinal distance of the small vehicle, and the angle between the small vehicle and the front of the own vehicle help to accurately judge the relative situation of the small vehicle and the own vehicle in a multi-vehicle driving scene; (7) The horizontal and longitudinal distance maintained by the non-motor vehicle, that is, the projection of the non-motor vehicle to the own vehicle coordinate system, along the projection of the front of the own vehicle is the longitudinal coordinate, and the perpendicular to the front direction is the transverse coordinate; the angle between the non-motor vehicle and the own vehicle, that is, the angle between the front of the non-motor vehicle and the own vehicle, this data can clearly reflect the relative direction of the non-motor vehicle and the own vehicle; (8) The horizontal and longitudinal distance maintained by the pedestrian, that is, the projection of the pedestrian to the own vehicle coordinate system, along the projection of the front of the own vehicle is the longitudinal coordinate, and the perpendicular to the front direction is the transverse coordinate; the angle between the pedestrian and the own vehicle, that is, the angle between the front of the pedestrian and the own vehicle, this data can clearly reflect the pedestrian. The relative direction of the vehicle; (9) The distance between the zebra crossing stop line, that is, the distance between the vehicle and the zebra crossing stop line. This data plays a key role in driving decisions in scenarios such as intersection traffic; (10) Traffic light related parameters, that is, the traffic light distance, traffic light countdown and light status. This data is extremely critical for the auxiliary driving system to plan the path and speed adjustment at the intersection; (11) Lane changing distance and lateral collision time, divided into lane changing distance and lateral collision time with large vehicles and small vehicles. The lane changing distance refers to the distance between the vehicle and the target lane vehicle when the vehicle changes lanes, and the lateral collision time is the collision time with the target lane vehicle. These two parameters can effectively ensure the safety of the lane changing process; (12) Road curvature, that is, the curvature of the road detected by the visual sensor / map;Road width, that is, the width of the road detected by the visual sensor / map. Both road curvature and road width have an important impact on the assisted driving system to plan a reasonable driving trajectory; (13) Driving speed, that is, the speed of the vehicle; (14) Weather, that is, the weather conditions when the vehicle is driving. Different weather conditions will have different degrees of impact on the performance and decision-making of the assisted driving system.

[0049] In this embodiment, the first driving behavior feature of the current driving scene is input into the assisted driving system model corresponding to the current driving scene, and the assisted driving system planning trajectory after optimization is output through the assisted driving system model.

[0050] Step S12: Control the vehicle based on the optimized assisted driving system planning trajectory, and after detecting the driver's intervention behavior, record the second driving behavior characteristics and calculate the deviation data generated based on the intervention behavior.

[0051] The vehicle is controlled based on the trajectory planned by the optimized assisted driving system. After detecting the driver's intervention behavior, at least one driving scenario at the time of the intervention behavior is determined, and the second driving behavior characteristics corresponding to at least one driving scenario are recorded, and then the second driving behavior characteristics corresponding to the driving scenarios that do not meet the conditions are eliminated. Among them, the driving scenarios that do not meet the conditions include emergency braking of the vehicle within the first driving distance and inconsistent with the cloud data, detection of a construction area within the second driving distance and inconsistent with the cloud data, and the vehicle changing lanes. That is, when the driver intervenes, the data and scenarios of the following three situations will not be recorded: ① When the driver takes over, the assisted driving system plans emergency braking within the last 500 meters of the vehicle (here emergency braking refers to braking deceleration a<-1.8). It should be noted that the planning here refers to storing the information of the last 500 meters of the vehicle and using this information for planning, rather than planning based on the current state of the vehicle when the driver takes over. This regulation is to solve specific working conditions. For example, there is congestion 300 meters ahead on the highway. The driver can see it in advance and slow down in advance with the naked eye, and the effective recognition distance of the sensor is about 150 meters. Relying on the vehicle's own planning to slow down will start to slow down 150 meters later than the driver, resulting in a greater braking deceleration. ② When the driver takes over, the assisted driving system encounters a construction section within the last 500 meters of the vehicle (the construction section includes but is not limited to cone barrels, construction signs, etc.). ③ When the driver takes over, the vehicle changes lanes. In addition, if there is a cloud synchronization module, for the first two situations mentioned above (i.e., those involving emergency braking planning and encountering construction sections), if the data is consistent with the cloud data, the relevant data will be recorded; if it is inconsistent with the cloud data, the data will not be recorded.

[0052] In this embodiment, the deviation data generated based on the intervention behavior is calculated so that the deviation data can be used to accurately quantify the difference from the original assisted driving system plan caused by the driver's intervention, thereby updating and improving the assisted driving system model to make it more in line with the driver's expectations and actual driving conditions. In addition, since different drivers have different driving habits and preferences, by calculating the deviation data, the assisted driving system can learn the preferences of each driver in a specific scenario, thereby providing more personalized driving services and improving the driver's satisfaction and trust in the assisted driving system. It should be pointed out that the deviation data includes trajectory deviation data and speed deviation data. The calculation process of the above two types of deviation data is explained below:

[0053] See also Figure 2 and Figure 3 As shown, on the one hand, the current driver's driving trajectory corresponding to the intervention behavior is determined, and the first trajectory difference between the current driver's driving trajectory and the target trajectory to be optimized is determined, and then the optimized target trajectory is obtained based on the product of the first trajectory difference and the first coefficient. Further, the second trajectory difference between the optimized target trajectory and the current assisted driving system planning trajectory is determined, and the second trajectory difference is determined as the trajectory deviation data. For example, d1, d2, d3 and d4 are all trajectory deviation data. It should be pointed out that in the process of obtaining the optimized target trajectory based on the product of the first trajectory difference and the first coefficient, the first loss function is specifically determined based on the product of the first trajectory difference and the first coefficient, and the function value of the first loss function is controlled to be the minimum function value to obtain the optimized target trajectory; wherein, the driving distance is not less than the third driving distance, the first coefficient is the first value, the driving distance is less than the third driving distance, the first coefficient is the second value, and the second value is less than the first value. The above process can be implemented by the following calculation model:

[0054] ;

[0055] ;

[0056] in, is the first coefficient, is the third driving distance, 0.1 is the second value, 0.9 is the first value, is the first loss function, is the point on the current driver’s driving trajectory, is the point on the target trajectory to be optimized, max is the maximum distance of the path, and n is the number of points.

[0057] After the driver intervenes, the vehicle will shake at first due to the strong intervention of the steering wheel, resulting in large fluctuations in the curve of the current driver's trajectory. At this time, the vehicle is unstable, so a smaller first coefficient is given. As the driving distance increases, the vehicle tends to be stable, and a larger first coefficient is given. By calculating the trajectory deviation data, the assisted driving system can clearly identify the specific differences between the actual driving trajectory after the driver's intervention and the original planned trajectory. In this way, the algorithm and parameters of the trajectory planning part can be adjusted in a targeted manner to make the trajectory planned by the assisted driving system closer to the driver's desired driving route.

[0058] See also Figure 4 and Figure 5 As shown, on the other hand, the current driver's driving speed corresponding to the intervention behavior is determined, and the first speed difference between the current driver's driving speed and the target speed to be optimized is determined, and then the optimized target speed is obtained based on the product of the first speed difference and the second coefficient. Further, the second speed difference between the optimized target speed and the current assisted driving system planning speed is determined, and the second speed difference is determined as speed deviation data, for example, v1 and v2 are both speed deviation data. Among them, obtaining the optimized target speed based on the product of the first speed difference and the second coefficient specifically includes: determining the second loss function based on the product of the first speed difference and the second coefficient, and controlling the function value of the second loss function to be the minimum function value to obtain the optimized target speed; the driving distance is not less than the fourth driving distance, the second coefficient is the third value, the driving distance is less than the fourth driving distance, the second coefficient is the fourth value, and the fourth value is less than the third value. The above process can be implemented by the following calculation model:

[0059] ;

[0060] ;

[0061] in, is the second coefficient, is the fourth driving distance, 0.2 is the fourth value, 0.8 is the third value, is the second loss function, is the point on the current driver’s driving speed, is the point on the target speed to be optimized, max is the maximum distance of the path, and n is the number of points.

[0062] After the driver intervenes, the vehicle will shake at first due to the strong intervention of the steering wheel, resulting in a large fluctuation in the curve of the current driver's speed at the beginning, that is, the vehicle is unstable at this time, so a smaller second coefficient is given. As the driving distance increases, the vehicle tends to be stable, and a larger second coefficient is given at this time. In this embodiment, calculating the speed deviation data helps the assisted driving system understand the driver's preference for speed control. By determining the difference between the optimized target speed and the current assisted driving system planned speed, the assisted driving system can adjust the speed planning module to make the planned speed more in line with the driver's habits.

[0063] Step S13: obtaining a new assisted driving system model by training according to the error correction data set constructed based on the first driving behavior feature, the second driving behavior feature and the deviation data, so as to update the assisted driving system.

[0064] In this embodiment, the corresponding timing model is retrained according to the error correction data set constructed based on the first driving behavior feature, the second driving behavior feature and the deviation data to obtain a new assisted driving system model, thereby realizing the update of the assisted driving system. It should be pointed out that in this embodiment, a scene classification model can be pre-trained, and the model is used to determine the driving scene corresponding to the error correction data set, so as to determine the timing model corresponding to the driving scene. After determining the timing model, the timing model is retrained using the error correction data set. In this way, the assisted driving system model will focus on learning the differences between the driver's habits and the original plan, so as to adjust the internal parameter weights, thereby realizing effective adaptation to different assisted driving habits and providing personalized, accurate and safe assisted driving experience for different drivers.

[0065] Figure 6 For a specific flowchart of the updating method of the assisted driving system, see Figure 6 As shown, data is first collected, and then the driving scenarios are screened and determined. Furthermore, the corresponding timing model is trained according to the corresponding driving scenarios to obtain the assisted driving system model, and the assisted driving system planning trajectory is optimized through the assisted driving system model output. After the driver intervenes and the data is recorded, the driving behavior characteristics are updated, and then the timing model is retrained based on the updated data to realize the update of the assisted driving system.

[0066] It can be seen that the present application proposes a method for updating an assisted driving system, including: recording a first driving behavior feature of the current driving scene, and inputting the first driving behavior feature into a pre-trained assisted driving system model corresponding to the current driving scene to output an optimized assisted driving system planning trajectory; the driving behavior feature includes driving habit parameters and assisted driving system planning trajectory; controlling the vehicle based on the optimized assisted driving system planning trajectory, and after detecting the driver's intervention behavior, recording the second driving behavior feature, and calculating the deviation data generated based on the intervention behavior; training a new assisted driving system model based on an error correction data set constructed based on the first driving behavior feature, the second driving behavior feature and the deviation data, so as to realize the update of the assisted driving system. In summary, when a driver uses the assisted driving system, the present application records his first driving behavior features under various road conditions, and inputs these data into a pre-trained assisted driving system model to output an optimized assisted driving system planning trajectory, and then controls the vehicle accordingly. If the driver intervenes due to his own habits, the second driving behavior characteristics are recorded, and the deviation data generated by the intervention behavior is calculated. Then, a new assisted driving system model is trained based on the error correction data set constructed based on the first driving behavior characteristics, the second driving behavior characteristics and the deviation data, so as to update the assisted driving system. In this way, the assisted driving system model will focus on learning the differences between the driver's habits and the original plan in order to adjust the internal parameter weights, thereby achieving effective adaptation to different assisted driving habits and providing personalized, accurate and safe assisted driving experience for different drivers.

[0067] Correspondingly, the embodiment of the present application also discloses an auxiliary driving system update device, see Figure 7 As shown, the device comprises:

[0068] The planning trajectory output module 11 is used to record the first driving behavior feature of the current driving scene, and input the first driving behavior feature into a pre-trained assisted driving system model corresponding to the current driving scene to output an optimized assisted driving system planning trajectory; the driving behavior feature includes a driving habit parameter and an assisted driving system planning trajectory;

[0069] a deviation data calculation module 12, configured to control the vehicle based on the optimized assisted driving system planning trajectory, and after detecting the driver's intervention behavior, record the second driving behavior feature, and calculate the deviation data generated based on the intervention behavior;

[0070] The assisted driving system update module 13 is used to obtain a new assisted driving system model through training based on the error correction data set constructed based on the first driving behavior characteristics, the second driving behavior characteristics and the deviation data, so as to realize the update of the assisted driving system.

[0071] Among them, for more specific working processes of the above-mentioned modules, please refer to the corresponding contents disclosed in the aforementioned embodiments, which will not be repeated here.

[0072] It can be seen that the present application proposes a method for updating an assisted driving system, including: recording a first driving behavior feature of the current driving scene, and inputting the first driving behavior feature into a pre-trained assisted driving system model corresponding to the current driving scene to output an optimized assisted driving system planning trajectory; the driving behavior feature includes driving habit parameters and assisted driving system planning trajectory; controlling the vehicle based on the optimized assisted driving system planning trajectory, and after detecting the driver's intervention behavior, recording the second driving behavior feature, and calculating the deviation data generated based on the intervention behavior; training a new assisted driving system model based on an error correction data set constructed based on the first driving behavior feature, the second driving behavior feature and the deviation data, so as to realize the update of the assisted driving system. In summary, when a driver uses the assisted driving system, the present application records his first driving behavior features under various road conditions, and inputs these data into a pre-trained assisted driving system model to output an optimized assisted driving system planning trajectory, and then controls the vehicle accordingly. If the driver intervenes due to his own habits, the second driving behavior characteristics are recorded, and the deviation data generated by the intervention behavior is calculated. Then, a new assisted driving system model is trained based on the error correction data set constructed based on the first driving behavior characteristics, the second driving behavior characteristics and the deviation data, so as to update the assisted driving system. In this way, the assisted driving system model will focus on learning the differences between the driver's habits and the original plan in order to adjust the internal parameter weights, thereby achieving effective adaptation to different assisted driving habits and providing personalized, accurate and safe assisted driving experience for different drivers.

[0073] Furthermore, an embodiment of the present application also provides an electronic device. Figure 8 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0074] Figure 8 A schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a display screen 23, an input / output interface 24, a communication interface 25, a power supply 26, and a communication bus 27. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the assisted driving system update method disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0075] In this embodiment, the power supply 26 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 25 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 24 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0076] In addition, the memory 22, as a carrier for storing resources, may be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon may include a computer program 221, and the storage method may be temporary storage or permanent storage. In addition to including a computer program that can be used to complete the auxiliary driving system update method executed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 221 may further include a computer program that can be used to complete other specific tasks.

[0077] Furthermore, an embodiment of the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the aforementioned assisted driving system update method disclosed above is implemented.

[0078] For the specific steps of the method, reference may be made to the corresponding contents disclosed in the aforementioned embodiments, which will not be described in detail here.

[0079] The various embodiments in this application are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0080] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0081] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0082] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0083] The above is a detailed introduction to the assisted driving system update method, device, equipment, and storage medium provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for updating an auxiliary driving system, characterized in that: include: Recording a first driving behavior feature of a current driving scene, and inputting the first driving behavior feature into a pre-trained assisted driving system model corresponding to the current driving scene, so as to output an optimized assisted driving system planning trajectory; the driving behavior feature includes a driving habit parameter and an assisted driving system planning trajectory; Controlling the vehicle based on the trajectory planned by the optimized auxiliary driving system, and after detecting the driver's intervention behavior, recording the second driving behavior characteristics, and calculating deviation data generated based on the intervention behavior; A new assisted driving system model is obtained by training the error correction data set constructed based on the first driving behavior feature, the second driving behavior feature and the deviation data, so as to update the assisted driving system.

2. The method for updating the assisted driving system according to claim 1, characterized in that: After detecting the driver's intervention behavior, recording the second driving behavior feature includes: After detecting the driver's intervention behavior, at least one driving scenario at the time when the intervention behavior occurs is determined, and the second driving behavior characteristics corresponding to the at least one driving scenario are recorded, and then the second driving behavior characteristics corresponding to the driving scenarios that do not meet the conditions are eliminated.

3. The method for updating the assisted driving system according to claim 2, characterized in that: The driving scenarios that do not meet the conditions include emergency braking of the vehicle within the first driving distance and the data is inconsistent with the cloud data, a construction area is detected within the second driving distance and the data is inconsistent with the cloud data, and the vehicle changes lanes.

4. The method for updating the assisted driving system according to claim 1, characterized in that: The deviation data includes trajectory deviation data, and the calculation is based on the deviation data generated by the intervention behavior, including: determining a current driver driving trajectory corresponding to the intervention behavior, and determining a first trajectory difference between the current driver driving trajectory and a target trajectory to be optimized, Obtaining an optimized target trajectory based on the product of the first trajectory difference and the first coefficient; Determine a second trajectory difference between the optimized target trajectory and the current assisted driving system planned trajectory, and determine the second trajectory difference as the trajectory deviation data.

5. The method for updating the assisted driving system according to claim 4, characterized in that: The step of obtaining an optimized target trajectory based on the product of the first trajectory difference and the first coefficient includes: A first loss function is determined based on the product of the first trajectory difference and a first coefficient, and the optimized target trajectory is obtained based on the minimum function value of the first loss function; wherein, the driving distance is not less than a third driving distance, the first coefficient is a first value, the driving distance is less than the third driving distance, the first coefficient is a second value, and the second value is less than the first value.

6. The method for updating the auxiliary driving system according to claim 1, characterized in that: The deviation data includes speed deviation data, and the calculation is based on the deviation data generated by the intervention behavior, including: Determining a current driver driving speed corresponding to the intervention behavior, and determining a first speed difference between the current driver driving speed and a target speed to be optimized; Obtaining an optimized target speed based on the product of the first speed difference and a second coefficient; A second speed difference between the optimized target speed and the current planned speed of the driving assistance system is determined, and the second speed difference is determined as the speed deviation data.

7. The method for updating the assisted driving system according to claim 6, characterized in that: The step of obtaining the optimized target speed based on the product of the first speed difference and the second coefficient includes: A second loss function is determined based on the product of the first speed difference and a second coefficient, and the optimized target speed is obtained based on the minimum function value of the second loss function; wherein, the driving distance is not less than a fourth driving distance, the second coefficient is a third value, the driving distance is less than the fourth driving distance, the second coefficient is a fourth value, and the fourth value is less than the third value.

8. An assisted driving system updating device, characterized in that: include: A planning trajectory output module, used for recording a first driving behavior feature of a current driving scene, and inputting the first driving behavior feature into a pre-trained assisted driving system model corresponding to the current driving scene, so as to output an optimized assisted driving system planning trajectory; the driving behavior feature includes a driving habit parameter and an assisted driving system planning trajectory; a deviation data calculation module, configured to control the vehicle based on the trajectory planned by the optimized auxiliary driving system, and after detecting the driver's intervention behavior, record the second driving behavior feature and calculate the deviation data generated based on the intervention behavior; The assisted driving system update module is used to obtain a new assisted driving system model through training based on the error correction data set constructed based on the first driving behavior characteristics, the second driving behavior characteristics and the deviation data, so as to realize the update of the assisted driving system.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the method for updating the assisted driving system as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store computer programs; wherein, when the computer program is executed by a processor, the assisted driving system updating method as described in any one of claims 1 to 7 is implemented.

Images