Auxiliary driving parameter determination method, device, equipment, medium and product of vehicle

Abstract

The application discloses a kind of vehicle's auxiliary driving parameter determination method, device, equipment, medium and program product, it is related to auxiliary driving technical field, comprising: according to the current manual driving information of user, at least one dimension of the current driving style label of the user is determined;According to the current driving information of vehicle and the current road condition information of road, the current collision risk degree of the vehicle is determined;According to the current driving style label of each dimension and the current collision risk degree, find matched auxiliary driving parameter combination;According to the auxiliary driving parameter combination, control the vehicle carries out auxiliary driving.The embodiment of the application can realize the auxiliary driving similar to the manual driving style of user, improve user experience.

Description

Technical Field

[0001] This invention relates to the field of driver assistance technology, and in particular to a method, device, equipment, medium, and program product for determining driver assistance parameters for a vehicle. Background Technology

[0002] Assisted driving technology is a technology that relies on artificial intelligence, sensor fusion, high-precision maps and real-time decision-making algorithms to complete environmental perception, path planning and vehicle driving control without human intervention or with only limited human intervention.

[0003] Existing technologies mainly determine assisted driving parameters by generating fixed driving styles through self-learning. The assisted driving styles corresponding to the assisted driving parameters determined by existing technologies have a low degree of matching with the user's manual driving style, resulting in a poor user riding experience. Summary of the Invention

[0004] This invention provides a method, device, equipment, medium, and program product for determining vehicle assisted driving parameters to improve the user's riding experience.

[0005] In a first aspect, embodiments of the present invention provide a method for determining assisted driving parameters of a vehicle, comprising:

[0006] Based on the user's current manual driving information, determine the user's current driving style label in at least one dimension;

[0007] Based on the vehicle's current driving information and the road's current traffic conditions, determine the vehicle's current collision risk level;

[0008] Based on the current driving style label of each dimension and the current collision risk level, find a matching combination of driver assistance parameters;

[0009] The vehicle is controlled to perform assisted driving based on the combination of assisted driving parameters.

[0010] Secondly, embodiments of the present invention also provide a vehicle auxiliary driving parameter determination device, comprising:

[0011] The acquisition module is used to determine the user's current driving style label in at least one dimension based on the user's current manual driving information;

[0012] The determination module is used to determine the current collision risk level of the vehicle based on the vehicle's current driving information and the current road conditions.

[0013] The search module is used to find matching combinations of driver assistance parameters based on the current driving style labels of each dimension and the current collision risk level.

[0014] The control module is used to control the vehicle to perform assisted driving based on the combination of assisted driving parameters.

[0015] Thirdly, embodiments of the present invention also provide an electronic device, comprising:

[0016] At least one processor; and

[0017] A memory that is communicatively connected to at least one processor; wherein

[0018] The memory stores instructions that can be executed by at least one processor, which enables the at least one processor to perform the vehicle assisted driving parameter determination method provided in any embodiment of the present invention.

[0019] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the method for determining assisted driving parameters of a vehicle according to any embodiment of the present invention.

[0020] Fifthly, embodiments of the present invention also provide a computer program product, which includes a computer program that, when executed by a processor, implements the method for determining assisted driving parameters of a vehicle according to any embodiment of the present invention.

[0021] This invention, through the user's current manual driving information, determines the user's current driving style label in at least one dimension, thereby ensuring the real-time nature of the user's driving style label and a high degree of matching with the user; through current driving information and current road condition information, it determines the current collision risk level; and through the current collision risk level and the current driving style labels in each dimension, while ensuring safe vehicle operation, it determines a combination of assisted driving parameters that matches the user, and then controls the vehicle to perform assisted driving. Under the premise of ensuring safe vehicle operation, it makes the vehicle's driving style in assisted driving similar to the user's manual driving style, thereby improving the user's riding experience.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of a method for determining auxiliary driving parameters of a vehicle according to Embodiment 1 of the present invention;

[0025] Figure 2 This is a flowchart of a method for determining auxiliary driving parameters of a vehicle according to Embodiment 2 of the present invention;

[0026] Figure 3 This is a schematic diagram of a vehicle auxiliary driving parameter determination device according to Embodiment 3 of the present invention;

[0027] Figure 4 This is a structural diagram of an electronic device that implements a method for determining auxiliary driving parameters of a vehicle according to an embodiment of the present invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first" and "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] In the technical solutions of this invention, the acquisition, storage, and application of current manual driving information and current driving information all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0031] Example 1

[0032] Figure 1This is a flowchart of a method for determining assisted driving parameters of a vehicle according to Embodiment 1 of the present invention. This embodiment can be applied to the situation of determining the assisted driving parameters of a vehicle and controlling the vehicle to perform assisted driving. The method can be executed by a vehicle assisted driving parameter determining device, which can be implemented in hardware and / or software and specifically configured in an electronic device.

[0033] See Figure 1 The method for determining the assisted driving parameters of the vehicle shown includes:

[0034] S101. Based on the user's current manual driving information, determine the user's current driving style label for at least one dimension.

[0035] S102. Determine the current collision risk level of the vehicle based on the vehicle's current driving information and the road's current road conditions.

[0036] S103. Based on the current driving style label of each dimension and the current collision risk level, find a matching combination of driver assistance parameters.

[0037] S104. Control the vehicle to perform assisted driving according to the combination of assisted driving parameters.

[0038] In this embodiment, "user" refers to the vehicle driver. Current manual driving information refers to the vehicle driving information during the user's most recent manual driving process; wherein, the user's most recent manual driving process can be the manual driving process most recent to the execution time of the vehicle assisted driving parameter determination method provided in this embodiment of the invention. In an optional embodiment, if the current time is 9:00 AM on January 1st, and the user started manual driving at 8:00 AM on January 1st and engaged in assisted driving at 9:00 AM, then the current manual driving information is the driving information collected during the manual driving process between 8:00 AM and 9:00 AM on January 1st. In another optional embodiment, if the current time is 8:00 AM on January 31st, and the user immediately engages in assisted driving upon boarding, and the user engaged in manual driving between 8:00 AM and 9:00 AM on January 1st, and between 8:00 AM and 9:00 AM on January 15th, with no manual driving at other times, then the current manual driving information is the driving information collected during the manual driving process between 8:00 AM and 9:00 AM on January 15th.

[0039] The current driving style label can be a driving style label determined based on current manual driving information; the current driving style label can include at least one dimension of driving style label; the dimension can include, but is not limited to, following dimension, lane change dimension, and speed change dimension; wherein, the driving style label of the following dimension can be used to represent the user's specific driving style in the following dimension; the driving style label of the lane change dimension can be used to represent the user's specific driving style in the lane change dimension; the driving style label of the speed change dimension can be used to represent the user's specific driving style in the speed change dimension.

[0040] Current driving information refers to the vehicle's current driving information, including but not limited to instantaneous speed and average speed. Current road condition information refers to the road condition information of the road the vehicle is currently on, including but not limited to current traffic flow and current obstacle density. Current collision risk level can be used to characterize the likelihood of a collision occurring on the current road; the higher the current collision risk level, the higher the likelihood of a collision; the lower the current collision risk level, the lower the likelihood of a collision.

[0041] The combination of driver assistance parameters may include at least one driver assistance parameter; wherein, the driver assistance parameter may include, but is not limited to, at least one of the following distance, gear shift threshold, lane change distance threshold, and overtaking decision waiting time; wherein, the following distance may be the ratio between the distance to the front of the vehicle and the vehicle speed, used to characterize the time required for the vehicle to travel to the current position of the vehicle in front at the current speed; the gear shift threshold may be the maximum threshold of the vehicle's acceleration and deceleration; the lane change distance threshold may be the minimum travel distance during the vehicle's lane change process; the overtaking decision waiting time may be the waiting time from when the vehicle completes the overtaking decision and turns on the turn signal until the vehicle begins to execute the overtaking action.

[0042] For example, a specific combination of driver assistance parameters could be: following distance 2.6s, shift threshold 1.1s, lane change distance threshold 26m, and overtaking decision trigger waiting time 5.6s.

[0043] Specifically, based on the user's current manual driving information, the user's current driving style label in the following, lane-changing, and speed-changing dimensions is determined; based on the vehicle's current driving information and the current road conditions, the current collision risk level of the vehicle is determined; based on the current driving style label in each dimension and the current collision risk level, a matching assisted driving parameter combination is searched from multiple candidate combinations; each assisted driving parameter in the matching assisted driving parameter combination is converted into a recognizable control command, and then the vehicle is controlled to perform assisted driving through the recognizable control command, so that the vehicle is constrained by assisted driving parameters such as following distance, speed-changing threshold, and lane-changing distance threshold during assisted driving. For example, at least one of the existing technologies can be used to determine specific decision parameters for assisted driving, such as acceleration values, braking force values, or steering angles; the determined acceleration values ​​are verified using the speed-changing threshold in the assisted driving parameter combination; if the verification fails, the acceleration values ​​are modified until the verification passes; then, vehicle control commands are generated based on the verified specific decision parameters to control the vehicle to perform assisted driving.

[0044] Optionally, the step of finding a matching combination of driver assistance parameters based on the current driving style label of each dimension and the current collision risk level includes: if the current collision risk level is greater than or equal to a second preset threshold, then a preset combination of driver assistance safety parameters is determined as the matching combination of driver assistance parameters; if the current collision risk level is less than the second preset threshold, then a matching combination of driver assistance parameters is found based on the mapping relationship of the preset combination of driver assistance parameters, as well as the current driving style label of each dimension and the current collision risk level.

[0045] It should be noted that the second set threshold can be used to characterize the maximum acceptable level of collision risk. This second set threshold can be set independently by technicians based on actual needs or practical experience, and this invention does not limit this. The current level of collision risk and the second set threshold can be expressed numerically. For example, they can be expressed as levels, such as a total of 5 collision risk levels and a second set threshold of level 4; they can also be expressed as percentages.

[0046] The assisted driving safety parameter combination can be a combination of assisted driving parameters that can ensure safe vehicle operation and minimize collision risk; the assisted driving safety parameter combination can be determined through collision risk simulation verification. The preset mapping relationship of the assisted driving parameter combinations can include pre-set mapping relationships between each driving style label in each dimension, different collision risk levels, and each candidate assisted driving parameter combination. Optionally, the user can adjust the mapping relationship of the assisted driving parameter combinations on the vehicle's central control screen.

[0047] Specifically, if the current collision risk level is greater than or equal to the second preset threshold, then the preset combination of assisted driving safety parameters is determined as the matching combination of assisted driving parameters; for example, the following distance is 2.2s; the speed change threshold is 1.0m / s², the lane change distance threshold is 28m, and the overtaking decision triggering waiting time is 7.0s.

[0048] If the current collision risk level is less than the second preset threshold, then according to the preset mapping relationship of the assisted driving parameter combinations, in at least one candidate assisted driving parameter combination, a assisted driving parameter combination that matches the current driving style label of each dimension and the current collision risk level is searched.

[0049] Understandably, by adopting the above technical solution, when the current collision risk level is greater than or equal to the second set threshold, i.e. when a collision event is likely to occur, the assisted driving safety parameters can be determined as assisted driving parameters, thereby avoiding the influence of driving style labels on the determination of assisted driving parameters and prioritizing vehicle safety; when the current collision risk level is less than the second set threshold, the combination of assisted driving parameters can be quickly determined through a pre-set mapping relationship, with low latency, high efficiency in parameter determination, and the ability to quickly respond to sudden road conditions.

[0050] Optionally, the combination of assisted driving parameters includes a target value for at least one assisted driving parameter; controlling the vehicle to perform assisted driving based on the combination of assisted driving parameters includes: for each assisted driving parameter, determining the amount of change between the target value of the assisted driving parameter and the current value of the assisted driving parameter; if the amount of change is greater than or equal to a third preset threshold, then smoothly adjusting the assisted driving parameter from the current value to the target value; if the amount of change is less than the third preset threshold, then switching the assisted driving parameter from the current value to the target value.

[0051] It should be noted that the target value of the assisted driving parameter can be the specific value of the assisted driving parameter in the combination of assisted driving parameters; the current value of the assisted driving parameter can refer to the specific value of the assisted driving parameter currently used to control the vehicle; the third setting threshold can be set independently by technicians according to actual needs or practical experience, and this invention does not limit it.

[0052] Specifically, for each driver assistance parameter, the difference between the target value and the current value of the driver assistance parameter is calculated as the numerical change of the driver assistance parameter; if the numerical change is greater than or equal to a third preset threshold, the driver assistance parameter is smoothly adjusted from the current value to the target value using a linear interpolation algorithm; if the numerical change is less than the third preset threshold, the driver assistance parameter is switched from the current value to the target value.

[0053] Understandably, by adopting the above technical solution, it is possible to directly switch between assisted driving parameters with small changes, thereby reducing switching latency and improving the switching efficiency of assisted driving parameters; and to smoothly transition between assisted driving parameters with large changes, avoiding the jerky feeling caused by large parameter adjustments, thus balancing real-time performance and user experience.

[0054] This invention, through the user's current manual driving information, determines the user's current driving style label in at least one dimension, thereby ensuring the real-time nature of the user's driving style label and a high degree of matching with the user; through current driving information and current road condition information, it determines the current collision risk level; and through the current collision risk level and the current driving style labels in each dimension, while ensuring safe vehicle operation, it determines a combination of assisted driving parameters that matches the user, and then controls the vehicle to perform assisted driving. Under the premise of ensuring safe vehicle operation, it makes the vehicle's driving style in assisted driving similar to the user's manual driving style, thereby improving the user's riding experience.

[0055] Example 2

[0056] Figure 2 This is a flowchart of a method for determining assisted driving parameters of a vehicle according to Embodiment 2 of the present invention. Based on the technical solution of the above embodiments, the present invention optimizes and improves the operation of determining the current driving style label.

[0057] Furthermore, the phrase "determine at least one dimension of the user's current driving style label based on the user's current manual driving information" is refined to "determine at least one dimension of the user's current driving style label based on the user's current manual driving information" to improve the operation of determining the current driving style label.

[0058] It should be noted that for any parts not described in detail in the embodiments of the present invention, please refer to the description in the foregoing embodiments.

[0059] See Figure 2 The method for determining the assisted driving parameters of the vehicle shown includes:

[0060] S201. For each dimension, input the current human driving information corresponding to the dimension into the driving style recognition model corresponding to the dimension, and output the current driving style label of the dimension; the human driving information corresponding to each dimension is different; the driving style recognition model is trained by the user's historical human driving information.

[0061] S202. Determine the current collision risk level of the vehicle based on the vehicle's current driving information and the road's current road conditions.

[0062] S203. Based on the current driving style label of each dimension and the current collision risk level, find a matching combination of driver assistance parameters.

[0063] S204. Control the vehicle to perform assisted driving according to the combination of assisted driving parameters.

[0064] In this embodiment, the driving style recognition model can employ either XGBoost (Extreme Gradient Boosting) or Random Forest. Each dimension has its own dedicated driving style recognition model; each driving style recognition model is deployed independently and trained in parallel; the parameters, loss function, and historical human driving information required for training of each driving style recognition model are completely independent, and the training process and hyperparameter adjustments of any one driving style model do not affect the other two sub-models.

[0065] Current human driving information can be further subdivided into different dimensions; the human driving information corresponding to each dimension is different.

[0066] For example, the current manual driving information in the following dimension may include, but is not limited to, average following distance, following distance fluctuation coefficient, vehicle speed fluctuation coefficient, and following distance adjustment coefficient for rain and snow. The following distance fluctuation coefficient can be used to characterize the fluctuation of following distance relative to its average value, and can be determined by the standard deviation of following distance and the average following distance. The vehicle speed fluctuation coefficient can refer to the fluctuation of vehicle speed relative to its average value, and can be determined by the standard deviation of vehicle speed and the average vehicle speed. The following distance adjustment coefficient for rain and snow can be used to characterize the adjustment of following distance in rain and snow compared to following distance in normal weather, and can be determined by following distance in rain and snow and following distance in normal weather. Normal weather can be sunny, cloudy, or overcast.

[0067] For example, the current manual driving information in the speed dimension may include, but is not limited to, maximum acceleration amplitude, maximum deceleration amplitude, speed shift smoothness, and nighttime driving speed control coefficient; the speed shift smoothness can be used to characterize the degree of smoothness of speed change over time; the nighttime speed control coefficient can be used to characterize the degree of control of nighttime speed compared to daytime speed, and can be determined by the average nighttime vehicle speed and the average daytime vehicle speed.

[0068] For example, the current manual driving information in the lane change dimension may include, but is not limited to, lane change frequency, lane change decision waiting time, overtaking decision waiting time, and intersection passage decision waiting time. Lane change decision waiting time may refer to the waiting time from when the user turns on the vehicle's turn signal until the vehicle begins to execute the lane change action; intersection passage decision waiting time may refer to the waiting time from when the user turns on the vehicle's turn signal until the vehicle begins to execute the turning action.

[0069] In this embodiment, driving style labels can be represented by scores. For example, each dimension can include 10 driving style labels, ranging from 1 to 10. For the following vehicle dimension, a higher driving style label score indicates a more aggressive following vehicle, while a lower score indicates a more conservative following vehicle. For the lane changing dimension, a higher driving style label score indicates a more decisive lane changing vehicle, while a lower score indicates a more conservative lane changing vehicle. For the gear shifting dimension, a higher driving style label score indicates a faster gear shifting vehicle, while a lower score indicates a slower gear shifting vehicle.

[0070] Historical manual driving information can be manual driving information collected before the current manual driving information was collected; the specific information types included in historical manual driving information are similar to those included in current manual driving information, and will not be repeated here.

[0071] In one optional embodiment, user-generated driving data can be collected via onboard sensors and a controller, covering multiple scenarios such as highway cruising, urban congestion, suburban roads, nighttime driving, and rain / snow. Preferably, the historical user-generated driving information collection period is greater than 30 hours, and the number of historical user-generated driving information records is greater than 10,000; historical user-generated driving data for each dimension is stored separately according to the dimension. Furthermore, abnormal data caused by emergency braking, vehicle malfunction, or user error can be removed from the historical user-generated driving information, and the 3σ criterion can be used to filter historical user-generated driving information that deviates from the mean by three times the standard deviation.

[0072] Specifically, for each dimension, the user's historical manual driving information in that dimension is manually labeled; based on the user's historical manual driving information and the labels of the historical manual driving information, the initial model corresponding to that dimension is trained to obtain the trained driving style recognition model for that dimension; the current manual driving information corresponding to that dimension is input into the driving style recognition model corresponding to that dimension, and the current driving style label for that dimension is output.

[0073] Optionally, for each dimension, the mean deviation between the current human driving information and the historical human driving information of the dimension is calculated; if the mean deviation is greater than or equal to a first set threshold, the current human driving information and the historical human driving information are merged into training driving information; and the driving style recognition model of the dimension is incrementally trained based on the training driving information.

[0074] It should be noted that the mean deviation can be set independently by technical personnel based on actual needs or practical experience, and this invention does not impose any limitations on it. Specifically, for each dimension, the mean deviation of each piece of manual driving information in that dimension is calculated.

[0075] For example, for the following dimension, the mean distance of the average following distance in each historical manual driving information is calculated; the difference between the average following distance in the current manual driving information and the mean distance is calculated; the ratio between the difference and the mean distance is determined as the mean deviation of the average following distance; a similar process is used to determine the mean deviation of the following distance fluctuation coefficient, the mean deviation of the vehicle speed fluctuation coefficient, and the mean deviation of the following distance adjustment coefficient in rain and snow; the maximum mean deviation of each manual driving information corresponding to the following dimension is determined as the mean deviation between the current manual driving information and the historical manual driving information in the following dimension.

[0076] If the mean deviation is greater than or equal to the first set threshold, the current manual driving information and the historical manual driving information are merged into training driving information; based on the training driving information, the driving style recognition model of the dimension is incrementally trained; if the mean deviation is less than the first set threshold, the driving style recognition model of the dimension is not incrementally trained.

[0077] Understandably, by adopting the above technical solution, the mean deviation between current human driving data and historical human driving data can be determined. Incremental training can be performed on the driving style recognition model for dimensions with larger mean deviations, so that the driving style recognition model can learn the characteristic patterns of user driving behavior in the stated dimension under highly efficient incremental training, thereby improving the driving style recognition accuracy in the stated dimension; and without affecting the model parameters of the driving style recognition model for dimensions with smaller mean deviations, ensuring the recognition accuracy of other driving style recognition models.

[0078] In an alternative embodiment, users can also select one or more driving style recognition models for training via the vehicle's central control screen to meet their personalized adjustment needs.

[0079] Optionally, determining the current collision risk level of the vehicle based on the vehicle's current driving information and the road's current road condition information includes: performing a weighted calculation on the vehicle's current speed, current traffic flow, and current obstacle density to obtain the vehicle's current collision risk level.

[0080] The current driving information may include, but is not limited to, the current vehicle speed, which is the vehicle speed at the current moment. The current road condition information may include, but is not limited to, the current traffic flow and the current obstacle density; the current traffic flow may be the traffic flow on the road where the vehicle is located at the current moment; the current obstacle density may be the obstacle density in the road environment where the vehicle is located at the current moment.

[0081] In one alternative embodiment, current traffic information can be collected in real time through channels such as vehicle-mounted cameras, millimeter-wave radar, lidar, positioning modules, and high-precision maps.

[0082] Specifically, the current vehicle speed, current traffic flow, and current obstacle density are converted to the same dimension, and the converted results are weighted to obtain the current collision risk level of the vehicle.

[0083] Optionally, the current vehicle speed, current traffic flow, and current obstacle density can be converted to the same dimension using the mapping relationship in the table below:

[0084]

[0085] The conversion results of current vehicle speed, current traffic flow, and current obstacle density are weighted to obtain a weighted score; the weighted score is then mapped to the current collision risk level. It should be noted that the weights of current vehicle speed, current traffic flow, and current obstacle density can be set independently by technical personnel based on practical experience, provided that the sum of current vehicle speed, current traffic flow, and current obstacle density is 1, and that the weight of current obstacle density is strictly greater than the weight of current traffic flow, and the weight of current traffic flow is greater than the weight of current vehicle speed.

[0086] For example, the weighted score can be converted into the current collision risk level using the following mapping rule:

[0087] 1 ≤ weighted score ≤ 1.8: Level 1 (indicating low risk); 1.8 < weighted score ≤ 2.6: Level 2 (indicating relatively low risk); 2.6 < weighted score ≤ 3.4: Level 3 (indicating medium risk); 3.4 < weighted score ≤ 4.2: Level 4 (indicating high risk); 4.2 < weighted score ≤ 5: Level 5 (indicating extremely high risk).

[0088] Understandably, by adopting the above technical solution, the current collision risk level can be determined comprehensively based on multi-dimensional information such as current vehicle speed, current traffic flow, and current obstacle density, thereby improving the accuracy of the current collision risk assessment.

[0089] This invention, in its embodiments, inputs the current human-driven information corresponding to each dimension into the driving style recognition model corresponding to that dimension, and outputs the current driving style label for that dimension. The human-driven information corresponding to each dimension is different. The driving style recognition model is trained using the user's historical human-driven information. By dividing the user's driving style into dimensions and independently training the driving style recognition model for each dimension using the human-driven information corresponding to that dimension, the driving style recognition models do not affect each other, thus outputting a multi-dimensional driving style and improving the accuracy of user driving style recognition. Furthermore, by recognizing the current driving style label using the current human-driven information, the real-time performance and matching of the recognized driving style with the current driving situation are improved, further enhancing the accuracy of user driving style recognition.

[0090] Example 3

[0091] Figure 3 This is a schematic diagram of a vehicle assisted driving parameter determination device according to Embodiment 3 of the present invention. This embodiment of the invention is applicable to situations where vehicle assisted driving parameters are determined and the vehicle is controlled to perform assisted driving. The device can execute a vehicle assisted driving parameter determination method and can be implemented in hardware and / or software. The device can be configured in an electronic device.

[0092] See Figure 3 The vehicle's assisted driving parameter determination device shown includes an acquisition module 301, a determination module 302, a search module 303, and a control module 304, wherein...

[0093] The acquisition module 301 is used to determine the user's current driving style label in at least one dimension based on the user's current manual driving information;

[0094] The determination module 302 is used to determine the current collision risk level of the vehicle based on the vehicle's current driving information and the current road condition information.

[0095] The search module 303 is used to search for a matching combination of driver assistance parameters based on the current driving style label of each dimension and the current collision risk level.

[0096] The control module 304 is used to control the vehicle to perform assisted driving based on the combination of assisted driving parameters.

[0097] This invention, through the user's current manual driving information, determines the user's current driving style label in at least one dimension, thereby ensuring the real-time nature of the user's driving style label and a high degree of matching with the user; through current driving information and current road condition information, it determines the current collision risk level; and through the current collision risk level and the current driving style labels in each dimension, while ensuring safe vehicle operation, it determines a combination of assisted driving parameters that matches the user, and then controls the vehicle to perform assisted driving. Under the premise of ensuring safe vehicle operation, it makes the vehicle's driving style in assisted driving similar to the user's manual driving style, thereby improving the user's riding experience.

[0098] Optionally, the acquisition module 301 is specifically used for:

[0099] For each dimension, the current human driving information corresponding to that dimension is input into the driving style recognition model corresponding to that dimension, and the current driving style label for that dimension is output. The human driving information corresponding to each dimension is different. The driving style recognition model is trained by the user's historical human driving information.

[0100] Optionally, the device further includes:

[0101] The deviation determination module is used to calculate the mean deviation between the current human driving information and the historical human driving information of each dimension.

[0102] The information merging module is used to merge the current manual driving information and the historical manual driving information into training driving information if the mean deviation is greater than or equal to a first set threshold.

[0103] The incremental training module is used to incrementally train the driving style recognition model of the dimension based on the training driving information.

[0104] Optionally, the determining module 302 is specifically used for:

[0105] The current collision risk level of the vehicle is obtained by weighting the vehicle's current speed, current traffic flow, and current obstacle density.

[0106] Optionally, the search module 303 is specifically used for:

[0107] If the current collision risk level is greater than or equal to the second preset threshold, then the preset combination of assisted driving safety parameters will be determined as the matching combination of assisted driving parameters.

[0108] If the current collision risk level is less than the second preset threshold, then a matching combination of driver assistance parameters is found based on the mapping relationship of the preset driver assistance parameter combinations, the current driving style label of each dimension and the current collision risk level.

[0109] Optionally, the combination of driver assistance parameters includes a target value for at least one driver assistance parameter;

[0110] The control module 304 is specifically used for:

[0111] For each driver assistance parameter, determine the numerical change between the target value and the current value of the driver assistance parameter;

[0112] If the change in the value is greater than or equal to the third preset threshold, the assisted driving parameter will be smoothly adjusted from the current value to the target value.

[0113] If the change in the value is less than the third preset threshold, then the assisted driving parameter is switched from the current value to the target value.

[0114] The vehicle assisted driving parameter determination device provided in the embodiments of the present invention can execute the vehicle assisted driving parameter determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the vehicle assisted driving parameter determination method.

[0115] Example 4

[0116] Figure 4A schematic diagram of a vehicle's driver assistance parameter determination device 410, which can be used to implement embodiments of the present invention, is shown. The vehicle's driver assistance parameter determination device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The vehicle's driver assistance parameter determination device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0117] like Figure 4 As shown, the vehicle's driver assistance parameter determination device 410 includes at least one processor 411 and a memory, such as a read-only memory (ROM) 412 or a random access memory (RAM) 413, communicatively connected to the at least one processor 411. The memory stores computer programs executable by the at least one processor. The processor 411 can perform various appropriate actions and processes based on the computer program stored in the ROM 412 or loaded from storage unit 418 into the RAM 413. The RAM 413 may also store various programs and data required for the operation of the vehicle's driver assistance parameter determination device 410. The processor 411, ROM 412, and RAM 413 are interconnected via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0118] Multiple components in the vehicle's driver assistance parameter determination device 410 are connected to the I / O interface 415, including: an input unit 416, such as a keyboard, mouse, etc.; an output unit 417, such as various types of displays, speakers, etc.; a storage unit 418, such as a disk, optical disk, etc.; and a communication unit 419, such as a network card, modem, wireless communication transceiver, etc. The communication unit 419 allows the vehicle's driver assistance parameter determination device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0119] Processor 411 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 411 performs the various methods and processes described above, such as methods for determining assisted driving parameters for a vehicle.

[0120] In some embodiments, the vehicle's driver assistance parameter determination method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of the computer program may be loaded into and / or installed onto the vehicle's driver assistance parameter determination device 410 via ROM 412 and / or communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the vehicle's driver assistance parameter determination method described above may be performed. Alternatively, in other embodiments, processor 411 may be configured to perform the vehicle's driver assistance parameter determination method by any other suitable means (e.g., by means of firmware).

[0121] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0122] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable vehicle's driver assistance parameter determination device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0123] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0124] To provide interaction with the user, the systems and techniques described herein can be implemented on a vehicle's driver assistance parameter determination device, which includes: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the vehicle's driver assistance parameter determination device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0125] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0126] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability.

[0127] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0128] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining auxiliary driving parameters for a vehicle, characterized in that, The method includes: Based on the user's current manual driving information, determine the user's current driving style label in at least one dimension; Based on the vehicle's current driving information and the road's current traffic conditions, determine the vehicle's current collision risk level; Based on the current driving style label of each dimension and the current collision risk level, find a matching combination of driver assistance parameters; The vehicle is controlled to perform assisted driving based on the combination of assisted driving parameters.

2. The method according to claim 1, characterized in that, The step of determining the user's current driving style label in at least one dimension based on the user's current manual driving information includes: For each dimension, the current human driving information corresponding to that dimension is input into the driving style recognition model corresponding to that dimension, and the current driving style label for that dimension is output. The human driving information corresponding to each dimension is different. The driving style recognition model is trained by the user's historical human driving information.

3. The method according to claim 2, characterized in that, The method further includes: For each dimension, calculate the mean deviation between the current human driving information and the historical human driving information of that dimension; If the mean deviation is greater than or equal to the first set threshold, the current manual driving information and the historical manual driving information are merged into training driving information; Based on the training driving information, the driving style recognition model for the aforementioned dimension is incrementally trained.

4. The method according to claim 1, characterized in that, Determining the current collision risk level of the vehicle based on its current driving information and current road conditions includes: The current collision risk level of the vehicle is obtained by weighting the vehicle's current speed, current traffic flow, and current obstacle density.

5. The method according to claim 1, characterized in that, The step of finding a matching combination of driver assistance parameters based on the current driving style label of each dimension and the current collision risk level includes: If the current collision risk level is greater than or equal to the second preset threshold, then the preset combination of assisted driving safety parameters will be determined as the matching combination of assisted driving parameters. If the current collision risk level is less than the second preset threshold, then a matching combination of driver assistance parameters is found based on the mapping relationship of the preset driver assistance parameter combinations, the current driving style label of each dimension and the current collision risk level.

6. The method according to claim 1, characterized in that, The combination of driver assistance parameters includes a target value for at least one driver assistance parameter; The step of controlling the vehicle to perform assisted driving based on the combination of assisted driving parameters includes: For each driver assistance parameter, determine the numerical change between the target value and the current value of the driver assistance parameter; If the change in the value is greater than or equal to the third preset threshold, the assisted driving parameter will be smoothly adjusted from the current value to the target value. If the change in the value is less than the third preset threshold, then the assisted driving parameter is switched from the current value to the target value.

7. A device for determining auxiliary driving parameters for a vehicle, characterized in that, The device includes: The acquisition module is used to determine the user's current driving style label in at least one dimension based on the user's current manual driving information; The determination module is used to determine the current collision risk level of the vehicle based on the vehicle's current driving information and the current road conditions. The search module is used to find matching combinations of driver assistance parameters based on the current driving style labels of each dimension and the current collision risk level. The control module is used to control the vehicle to perform assisted driving based on the combination of assisted driving parameters.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method for determining the assisted driving parameters of the vehicle according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for determining the assisted driving parameters of the vehicle as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method for determining the assisted driving parameters of the vehicle as described in any one of claims 1-6.

Images