Vehicle auxiliary driving method and vehicle

Abstract

The invention provides a vehicle auxiliary driving method and a vehicle, and relates to the technical field of intelligent driving, and the method comprises the steps: collecting vehicle driving data within a preset time period when a vehicle auxiliary driving function is not started; the corresponding driving scene is determined according to the vehicle driving data, and after the vehicle driving data is divided according to the driving scene, the auxiliary driving function scene can be refined, and it is ensured that auxiliary driving can be matched with the driving habit of a driver in each scene when the auxiliary driving function is started. And according to the vehicle driving data, determining driving adjustment control parameters in the driving scene. The driving habit and the driving style of the driver can be reflected through the driving adjustment control parameters. When the auxiliary driving function of the vehicle is started, the vehicle is controlled to run based on the driving adjustment control parameters, and the purpose of providing personalized auxiliary driving for a driver is achieved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a vehicle assisted driving method and a vehicle. Background Art

[0002] With the rapid development of vehicle intelligence, software-defined cars are becoming increasingly important, and autonomous driving technology has become a top priority in the development of the intelligent automotive industry. Currently, assisted intelligent driving functions are either developed in-house by manufacturers or developed on a platform-based basis by software vendors. These functions are limited to fixed control methods or strategies, and the user experience suffers from a failure to meet personalized intelligent driving needs. Summary of the Invention

[0003] In view of this, the purpose of this application is to propose a vehicle assisted driving method and vehicle to solve the problem that the current assisted intelligent driving function cannot meet the user's personalized intelligent driving needs.

[0004] Based on the above objectives, the first aspect of the present application provides a vehicle assisted driving method, comprising: Collect vehicle driving data within a preset time period when the vehicle's assisted driving function is not turned on; determining a corresponding driving scenario according to the vehicle driving data; According to the vehicle driving data, driving adjustment control parameters in the driving scenario are determined, so as to provide assisted driving for the driver based on the driving adjustment control parameters when the vehicle assisted driving function is turned on.

[0005] Optionally, determining the driving adjustment control parameters in the driving scenario based on the vehicle driving data includes: Filtering the vehicle driving data according to a preset data filtering condition corresponding to the driving scenario to obtain target learning data; Determine driving adjustment control parameters in the driving scenario according to the target learning data.

[0006] Optionally, the driving scenario includes an adaptive vehicle following scenario; the preset data screening condition includes a data validity filtering condition; The filtering of the vehicle driving data according to the preset data filtering condition corresponding to the driving scenario to obtain target learning data includes: filtering the vehicle driving data according to a data validity filtering condition corresponding to the adaptive vehicle following scenario to obtain initial learning data; Filtering the initial learning data according to preset sampled vehicle speeds, and determining an average vehicle speed corresponding to each preset sampled vehicle speed and a collision time corresponding to the average vehicle speed based on the filtered data; The average vehicle speed and the corresponding collision time are used as the target learning data.

[0007] Optionally, the driving adjustment control parameter includes a target collision time; The determining of the driving adjustment control parameters in the driving scenario according to the target learning data includes: Calculating a stable following distance at each preset sampling speed based on the target learning data; A target collision time is determined according to the stable following distance and the average vehicle speed.

[0008] Optionally, filtering the vehicle driving data according to the data validity filtering condition corresponding to the adaptive vehicle following scenario to obtain initial learning data includes: For the vehicle driving data collected at each moment within the preset time period, in response to the road curvature radius in the vehicle driving data being less than the curvature radius threshold, the collision time when following the vehicle is not within the preset collision time range, or the following distance is less than the safety distance threshold, the vehicle driving data collected at the moment is eliminated to obtain the initial learning data.

[0009] Optionally, the driving scenario includes a curve driving scenario; the preset data screening condition includes a data validity filtering condition; The filtering of the vehicle driving data according to the preset data filtering condition corresponding to the driving scenario to obtain target learning data includes: filtering the vehicle driving data according to a data validity filtering condition corresponding to the curve driving scenario to obtain initial learning data; Calculating a road curvature speed limit value corresponding to each road curvature radius in the initial learning data; and determining an average road curvature speed limit value corresponding to each preset road curvature radius range in a plurality of preset road curvature radius ranges based on the road curvature speed limit value; determining an average vehicle speed corresponding to each preset road curvature radius range based on the vehicle speed corresponding to each road curvature radius in the initial learning data and a plurality of preset road curvature radius ranges; The average road curvature speed limit value and the average vehicle speed are used as the target learning data.

[0010] Optionally, the driving adjustment control parameter includes a curve control coefficient; The determining of the driving adjustment control parameters in the driving scenario according to the target learning data includes: The curve control coefficient is determined based on a ratio of the average vehicle speed to the average road curvature speed limit value.

[0011] Optionally, the driving scenario includes an overtaking and lane changing scenario; the driving adjustment control parameter includes an overtaking and lane changing control coefficient; and the preset data screening condition includes a lane changing passable space screening condition and a lateral and longitudinal driving information screening condition. The filtering of the vehicle driving data according to the preset data filtering condition corresponding to the driving scenario to obtain target learning data includes: Filtering the vehicle driving data according to the lane change passable space screening condition and the lateral and longitudinal driving information screening condition corresponding to the overtaking and lane change scenario to obtain the target learning data; The determining of the driving adjustment control parameters in the driving scenario according to the target learning data includes: The overtaking lane change control coefficient is determined according to the lane change completion time in the target learning data.

[0012] Optionally, the driving scenario includes a merging / diverging scenario; the preset data screening condition includes a navigation data screening condition; and the driving adjustment control parameter includes a merging / diverging control style; The filtering of the vehicle driving data according to the preset data filtering condition corresponding to the driving scenario to obtain target learning data includes: Filtering the vehicle driving data according to the navigation data filtering condition in the diverging and merging scenario to obtain the target learning data; The determining of the driving adjustment control parameters in the driving scenario according to the target learning data includes: Calculating a target lane change distance based on the number of lane changes, vehicle speed, and preset lane change information in the target learning data; The merging and diverging control style is determined according to the actual lane changing distance and the target lane changing distance in the target learning data.

[0013] Based on the same inventive concept, the second aspect of the present application further provides a vehicle, comprising: a memory for storing executable program code; A processor is used to call and run the executable program code from the memory, so that the vehicle executes the method as described in the first aspect.

[0014] From the above, it can be seen that the vehicle assisted driving method and vehicle provided by the present application, wherein the method includes: collecting vehicle driving data within a preset time period when the vehicle assisted driving function is not turned on. The vehicle driving data when the assisted driving function is not turned on can reflect the driver's driving style and driving habits, and provide data reference for subsequent personalized assisted driving. Determining the corresponding driving scene based on the vehicle driving data, and dividing the vehicle driving data according to the driving scene is conducive to refining the assisted driving function scene, ensuring that when the assisted driving function is turned on, the assisted driving can match the driver's driving habits in each scene. Determine the driving adjustment control parameters under the driving scene based on the vehicle driving data. The driver's driving habits and driving style can be reflected by the driving adjustment control parameters. When the vehicle assisted driving function is turned on, the vehicle driving is controlled based on the driving adjustment control parameters to achieve the purpose of providing personalized assisted driving for the driver. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in this application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are merely embodiments of this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 A schematic flow chart of a vehicle assisted driving method according to an embodiment of the present application; Figure 2 A schematic diagram of the vehicle assisted driving logic of an embodiment of the present application; Figure 3 This is a schematic structural diagram of a vehicle assisted driving device according to an embodiment of the present application; Figure 4 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to make the objectives, technical solutions and advantages of this application more clear, this application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0018] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should have the usual meanings understood by people with ordinary skills in the field to which this application belongs. The "first", "second" and similar words used in the embodiments of the present application do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0019] As mentioned in the background technology, current assisted intelligent driving functions cannot meet the personalized needs of users and cannot create a differentiated intelligent driving function experience. Current assisted intelligent driving functions mainly include the following two types: First, vehicle control parameters primarily adjust the assisted driving following gear, and only adjust longitudinal control parameters. Assisted driving following gear typically refers to a mode in which the vehicle maintains a fixed distance from the vehicle ahead while in assisted driving mode. Each following gear corresponds to a different following distance. Different vehicle models and systems have different following gear settings. Table 1 shows examples of assisted driving following gears.

[0020] Table 1 Example of gear positions for assisted driving

[0021] The assisted driving following gears listed in Table 1 include six gears: automatic, 1st, 2nd, 3rd, 4th, and 5th. Each gear is suitable for different scenarios, and different gears are switched according to different scenarios. In each fixed scenario, the gear is also relatively fixed. In this assisted intelligent driving mode, only longitudinal following distance can be controlled. With the popularization of advanced intelligent functions, it cannot meet the differentiated intelligent driving experience needs of users.

[0022] Second, vehicle control parameters only support three fixed modes: Comfort, Standard, and Sport. These fixed modes require manual selection by the driver, and once selected, they apply to all scenarios. Table 2 shows examples of the three fixed modes for assisted driving.

[0023] Table 2 Examples of three fixed modes for assisted driving

[0024] In view of the limitations of the two current assisted driving functions mentioned above, this application proposes a vehicle assisted driving method that can achieve differentiated adjustment of the control parameters of the assisted driving function in different driving scenarios to meet the user's personalized intelligent driving needs. By learning vehicle driving data when the assisted driving function is not turned on, analyzing the user's driving style and driving habits, and determining the driving adjustment control parameters for different driving scenarios, the driving adjustment control parameters can be used to provide assisted driving to the driver and meet the user's personalized needs.

[0025] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0026] Figure 1 FIG. 1 shows a flow chart of a vehicle assisted driving method. Figure 1 As shown, the vehicle assisted driving method includes the following steps 102 to 106: Step 102: Collect vehicle driving data within a preset time period when the vehicle assisted driving function is not turned on.

[0027] Specifically, the method of this embodiment can be executed by an intelligent driving domain controller in a vehicle. The vehicle driving data collected by the intelligent driving domain controller is vehicle driving data when the assisted driving function is not enabled. In this case, the vehicle driving data is generated by the user while controlling the vehicle, and can reflect the user's driving habits and driving style.

[0028] Figure 2 FIG. 1 shows a schematic diagram of the vehicle assisted driving logic in this embodiment. Figure 2 As shown in the figure, the vehicle driving data collected by the intelligent driving domain controller consists of four parts: data transmitted by the cockpit domain controller, data transmitted by the intelligent driving settings module, data transmitted by actuators, and data transmitted by sensing devices. Users can input commands through the vehicle's human-machine interface to control the cockpit domain controller to set vehicle functions or adjust vehicle control parameters. The cockpit domain controller transmits the settings or adjustment data generated by the commands back to the intelligent driving domain controller. Users can enable or disable the assisted intelligent driving function through the intelligent driving settings module, which then transmits the current on / off status of the assisted intelligent driving function to the intelligent driving domain controller. Actuators refer to actuator components in the vehicle, such as the accelerator pedal, brake pedal, and steering wheel. These actuator components transmit data generated during vehicle operation back to the intelligent driving domain controller. Sensing devices include various sensors, cameras, and other data sensing components in the vehicle. These sensors transmit data collected during vehicle operation back to the intelligent driving domain controller.

[0029] Due to limited storage space in the intelligent driving domain controller, the intelligent driving domain controller only stores vehicle driving data for a preset duration while collecting real-time vehicle driving data. In other words, the intelligent driving domain controller only stores vehicle driving data within a preset duration before the current moment. For example, the preset duration can be 5 minutes or 10 minutes.

[0030] Step 104: Determine a corresponding driving scenario based on the vehicle driving data.

[0031] Specifically, after receiving vehicle driving data, the intelligent driving domain controller processes it through its internal data feedback module. This module then divides the vehicle driving data by driving scenario, generating data for each scenario. This allows for scenario-specific segmentation of the vehicle's assisted driving functions, ensuring that subsequent automatic vehicle control in different driving scenarios is consistent with the user's driving habits, providing a personalized intelligent driving experience.

[0032] Step 106: Determine driving adjustment control parameters in the driving scenario based on the vehicle driving data, so as to provide assisted driving for the driver based on the driving adjustment control parameters when the vehicle assisted driving function is turned on.

[0033] Specifically, in Figure 2 In the AI ​​​​system, vehicle driving data is divided into different driving scenarios. For each driving scenario, the data feedback module learns the vehicle driving data in that driving scenario, that is, learns the user's driving habits, and determines the driving adjustment and control parameters for each driving scenario. Differentiated intelligent driving functions are configured based on the driving adjustment and control parameters. When the user activates the assisted driving function, these parameters are fed back into the intelligent driving process. This cycle achieves closed-loop control to optimize the vehicle's assisted driving functions.

[0034] The driving adjustment control coefficient qualitatively characterizes the user's driving style, such as comfortable, standard, or aggressive. Different driving habits correspond to different driving adjustment control coefficients. When the vehicle's assisted driving function is subsequently activated, the driving adjustment control coefficient associated with the driving scenario is called based on the real-time driving scenario, and the vehicle's autonomous driving is controlled by the driving adjustment control coefficient. This not only provides assisted driving for the driver, but also aligns the autonomous driving style with the driver's own, enhancing the driver's intelligent driving experience.

[0035] Based on steps 102 to 106 above, the vehicle assisted driving method provided in this embodiment includes: collecting vehicle driving data within a preset time period when the vehicle assisted driving function is not enabled. The vehicle driving data when the assisted driving function is not enabled can reflect the driver's driving style and driving habits, providing data reference for subsequent personalized assisted driving. Determining corresponding driving scenarios based on the vehicle driving data. Dividing the vehicle driving data by driving scenario facilitates refining the assisted driving function scenarios, ensuring that assisted driving can match the driver's driving habits in each scenario when the assisted driving function is enabled. Determining driving adjustment control parameters for the driving scenario based on the vehicle driving data. The driver's driving habits and driving style can be reflected in the driving adjustment control parameters. When the vehicle assisted driving function is enabled, vehicle driving is controlled based on the driving adjustment control parameters to provide personalized assisted driving for the driver. The driving adjustment control parameters can be continuously updated using the real-time collected vehicle driving data, allowing the vehicle's autonomous driving behavior to adapt to changes in the user's driving style.

[0036] Driving adjustment control parameters can influence the autonomous driving behavior during assisted driving. Accurately determining these parameters can ensure that the user is provided with an autonomous driving behavior that is consistent with their driving style. The following describes a method for determining driving adjustment control parameters using a specific embodiment.

[0037] In some embodiments, determining the driving adjustment control parameters in the driving scenario based on the vehicle driving data includes: The vehicle driving data is screened according to preset data screening conditions corresponding to the driving scenario to obtain target learning data; and the driving adjustment control parameters under the driving scenario are determined according to the target learning data.

[0038] Specifically, the driving scenarios in this embodiment include adaptive following scenarios, curve driving scenarios, overtaking and lane changing scenarios, and merging and diverging scenarios. When determining each driving scenario, the following method can be used: 1. Adaptive Car Following Scenario: If the ego vehicle is traveling forward within its lane, within a preset collision time range, there is a vehicle ahead that can be selected as a Navigated Driving Assist (NDA) following target, and the ego vehicle's speed changes within a certain period of time are less than a preset value, then the current driving scenario is determined to be Adaptive Car Following.

[0039] The Time to Collision (TTC) is the estimated time between the ego vehicle and the preceding vehicle or obstacle. For example, the preset collision time range is within 2.4 seconds. That is, the collision time between the ego vehicle and the preceding vehicle must be less than 2.4 seconds. After exceeding the preset collision time range, the ego vehicle is generally not in a stable following state. The certain time period can be 1 second, and the preset value can be 10%. That is, the change in the ego vehicle's speed within 1 second is less than 10%. If the rate of change in the ego vehicle's speed is large, it indicates that the ego vehicle is not in a stable following state.

[0040] 2. Curved Driving Scenario: Based on the road curvature radius contained in the vehicle driving data, the system determines whether the vehicle is driving on a curve. If the road curvature radius is less than a certain threshold, the vehicle is determined to be driving on a curve, and the current driving scenario is a curved driving scenario. The threshold can be calibrated based on actual needs and is not specifically limited in this embodiment.

[0041] 3. Overtaking and lane-changing scenario: Determine whether the vehicle has changed lanes based on the vehicle driving data. If so, determine that the current driving scenario is an overtaking and lane-changing scenario. For example, based on the turn signal in the vehicle driving data and the changes in the vehicle's lateral and longitudinal driving data, it can be determined whether the vehicle has changed lanes and the lane-changing status. The lane-changing status includes lane-changing preparation, lane-changing execution, lane-changing reversal, lane-changing completion, lane-changing reversal completion, and lateral and longitudinal matching. Among them, lane-changing reversal refers to the lane-changing operation in which the vehicle fails to change lanes and returns to the starting lane. Correspondingly, lane-changing reversal completion refers to the completion of the lane-changing reversal operation. Horizontal and longitudinal matching refers to the coordination process of the longitudinal driving operation and the lateral driving operation during the lane-changing process. For example, the driver accelerates or decelerates after changing lanes to the target lane, and then the lane change is completed. That is, during the entire lane-changing process, both the longitudinal driving data and the lateral driving data of the vehicle have changed.

[0042] 4. Merging and diverging scenarios: Based on high-precision maps and navigation input from vehicle driving data, it can be determined whether the vehicle is in a merging or diverging scenario. Merging and diverging refers to the diverging or merging of vehicles when entering or exiting highways or on highway interchanges.

[0043] Among the vehicle driving data collected in the above-mentioned driving scenarios, there are some unreasonable driving behavior data. These data cannot be used as learning data for subsequent assisted driving and need to be eliminated. The preset data screening conditions are used to identify unreasonable driving behavior data. The unreasonable driving behavior data can be eliminated through the preset data screening conditions corresponding to each driving scenario, and reasonable driving behavior data can be retained as target learning data. For example, in certain driving scenarios, in order to ensure the smoothness and safety of the assisted intelligent driving process, the corresponding vehicle driving data when the vehicle speed is too low or too high, or the vehicle speed change rate is too large, is not referenceable. The determined target learning data is vehicle driving data with reference value. The driving adjustment control parameters determined according to the target learning data can reflect the driver's driving habits, so as to provide a control data basis for the vehicle's assisted driving function.

[0044] This embodiment provides a method for accurately determining driving adjustment control parameters. Based on preset data screening criteria, it can eliminate irrelevant or unreasonable vehicle driving data and determine target learning data with a reference learning mechanism. The driving adjustment control parameters determined using target learning data accurately reflect the driver's driving style and meet the smoothness and safety requirements of the assisted driving function. This provides the driver with a personalized intelligent driving experience while ensuring safe and comfortable driving.

[0045] The following describes a method for determining target learning data and driving adjustment control parameters in various driving scenarios through specific embodiments.

[0046] In some embodiments, the driving scenario includes an adaptive vehicle following scenario; the preset data screening condition includes a data validity filtering condition; The filtering of the vehicle driving data according to the preset data filtering condition corresponding to the driving scenario to obtain target learning data includes: filtering the vehicle driving data according to a data validity filtering condition corresponding to the adaptive vehicle following scenario to obtain initial learning data; Filtering the initial learning data according to preset sampled vehicle speeds, and determining an average vehicle speed corresponding to each preset sampled vehicle speed and a collision time corresponding to the average vehicle speed based on the filtered data; The average vehicle speed and the corresponding collision time are used as the target learning data.

[0047] Specifically, data validity filters are used to validate vehicle driving data in adaptive car-following scenarios and eliminate invalid data. For example, data showing excessively close or excessively distant following distances can be eliminated to ensure that the assisted driving function can maintain a stable and safe following distance after learning.

[0048] Furthermore, filtering the vehicle driving data according to the data validity filtering condition corresponding to the adaptive vehicle following scenario to obtain initial learning data includes: For the vehicle driving data collected at each moment within the preset time period, in response to the road curvature radius in the vehicle driving data being less than the curvature radius threshold, the collision time when following the vehicle is not within the preset collision time range, or the following distance is less than the safety distance threshold, the vehicle driving data collected at the moment is eliminated to obtain the initial learning data.

[0049] Data validity filtering is performed on the vehicle driving data collected at each moment within the preset time. The vehicle driving data collected at each moment include lateral and longitudinal speeds, lateral and longitudinal accelerations, accelerator pedal opening, brake pedal opening, steering wheel torque, steering wheel angle, road curvature radius, road slope, road friction, following distance, front and rear vehicle speeds, front and rear vehicle accelerations, etc. If the road curvature radius in the collected vehicle driving data is less than the curvature radius threshold, it means that the current road curvature is large. When the turning curvature is large, the steering motor controlling the cornering torque will have torque limitation, resulting in a poor turning control experience. Therefore, the vehicle driving data when the road curvature radius is less than the curvature radius threshold is not used as the final target learning data and needs to be eliminated. For example, the curvature radius threshold is 125m.

[0050] In addition, if the following distance is too close or too far, it is also invalid data and needs to be eliminated. In this embodiment, the following distance is characterized by the collision time. The shorter the collision time between the vehicle and the preceding vehicle, the closer the following distance of the vehicle. The longer the collision time between the vehicle and the preceding vehicle, the farther the following distance of the vehicle. If the collision time between the vehicle and the preceding vehicle is less than the lower limit of the preset collision time range, it is a case of too close following distance, and the vehicle driving data in this case needs to be eliminated. If the collision time between the vehicle and the preceding vehicle is greater than the upper limit of the preset collision time range, it is a case of too far following distance, and the vehicle driving data in this case needs to be eliminated. Only vehicle driving data with a collision time within the preset collision time range is retained. Exemplarily, the preset collision time range is 1.6s to 2.4s. The collision time is calculated as: TTC = d / v, where TTC represents the collision time, d represents the distance between the vehicle and the preceding vehicle, and v represents the relative speed between the vehicle and the preceding vehicle. In addition, if the following distance of the ego vehicle is less than the safety distance threshold, the vehicle driving data at this time needs to be eliminated for the sake of following safety. For example, the safety distance threshold is 3m.

[0051] After eliminating vehicle driving data that meets the data validity filtering criteria, the initial learning data is obtained. The vehicle driving data included in the initial learning data is valid data, providing accurate basic data for subsequent assisted driving function learning. This helps improve the accuracy, safety, and stability of assisted driving behavior.

[0052] To reduce the amount of vehicle driving data required for learning, this embodiment uses an interval sampling method to select target learning data. Multiple preset sampling speeds are pre-set, such as 0 km / h, 20 km / h, 40 km / h, 60 km / h, 80 km / h, 120 km / h, and 140 km / h. The initial learning data is screened based on the preset sampling speeds, and speeds close to the preset sampling speeds are selected from the initial learning data. Furthermore, for each preset sampling speed, a corresponding speed set is created. Speeds whose difference from the preset sampling speed is less than a difference threshold are assigned to the speed set to which the preset sampling speed belongs. For example, the difference threshold can be 10%. For each speed set, the average speed of the speed set is calculated and used as the target learning speed. Each speed in the speed set is associated with a collision time. The collision times corresponding to each speed are averaged to calculate the collision time corresponding to the average speed. It should be noted that if the same vehicle speed is collected and corresponds to multiple collision times, the maximum collision time is selected as the collision time corresponding to that speed. The average vehicle speed and the corresponding collision time are used as the target learning data for subsequent assisted driving learning.

[0053] It should be noted that for each speed set, the reliability of the speeds in that speed set must be determined. If the collection duration of all speeds in a speed set is less than a duration threshold, the data collection duration is short and unrepresentative, and the speed set should be discarded. For example, the duration threshold could be 5 minutes. After reliability screening, if a speed set is empty, a fitted speed is generated by interpolating or fitting the speeds in the speed set corresponding to the adjacent preset sampled speeds, and the fitted speed is then added to the empty speed set.

[0054] Through this embodiment, a method for screening and determining target learning data for an adaptive following scenario is provided. First, invalid data is eliminated to obtain valid initial learning data. The initial learning data is screened to select key data that can achieve a stable following effect in an adaptive following scenario, namely, the average vehicle speed and the collision time corresponding to the average vehicle speed. Using the average vehicle speed and collision time as target learning data for learning the assisted driving function can improve the stability and safety of assisted driving behavior in the adaptive following scenario. At the same time, it can also learn the driver's driving habits in the adaptive following scenario and provide the driver with personalized automatic following driving services.

[0055] The driving adjustment control parameters in the adaptive following scenario include the target collision time. By determining the target collision time of the vehicle at each speed, the assisted driving function can determine the assisted driving following gear in the adaptive following scenario with reference to the target collision time.

[0056] In some embodiments, determining the driving adjustment control parameters in the driving scenario according to the target learning data includes: Calculating a stable following distance at each preset sampling speed based on the target learning data; A target collision time is determined according to the stable following distance and the average vehicle speed.

[0057] Specifically, based on the target learning data, that is, based on the average vehicle speed and the collision time corresponding to the average speed, the stable following distance is calculated using the following formula: Stable following distance = Max (average speed × collision time, minimum following distance) The minimum following distance includes two situations. If the preceding vehicle is a large truck, a two-wheeled vehicle, or an unclassified vehicle, the minimum following distance is 4 meters. If the preceding vehicle is a normal four-wheeled vehicle, the minimum following distance is 3.5 meters. After calculating the stable following distance, the target time to collision is calculated using the collision time calculation formula: TTC = d / v. Here, d is the stable following distance, and the relative speed v = v1 - v2, where v1 represents the average speed of the ego vehicle and v2 represents the speed of the preceding vehicle. The calculated TTC is the target time to collision. If v1 = v2, there will be no collision between the ego vehicle and the preceding vehicle, and the ego vehicle's speed can be maintained.

[0058] After determining the target collision time, the target collision time corresponding to each preset sampling speed is obtained, such as the target collision time corresponding to a speed of 60km / h is 1.7s. After the assisted driving function is turned on, if it is detected that the current driving scene is an adaptive following scene and the current speed is 60km / h, the assisted driving following gear is selected according to the target collision time of 1.7s. At present, the assisted driving following gears commonly set in vehicles include 5 gears, which correspond to 1.6s, 1.8s, 2.0s, 2.2s and 2.4s. Since the target collision time is 1.7s, the principle of taking the larger collision time is adopted to select the adjacent following gear corresponding to 1.8s as the actual following gear of the assisted driving function. Taking a larger collision time is equivalent to increasing the following distance between the vehicle and the vehicle in front, meeting the safety requirements of the assisted driving function.

[0059] This embodiment provides a method for determining the target collision time. After the assisted driving function is turned on, the vehicle can refer to the target collision time to achieve safe automatic following behavior in an adaptive following scenario, providing users with a stable automatic following service that matches the driver's style, and improving the intelligent driving experience in adaptive driving scenarios.

[0060] In some embodiments, the driving scenario includes a curve driving scenario; the preset data screening condition includes a data validity filtering condition; The filtering of the vehicle driving data according to the preset data filtering condition corresponding to the driving scenario to obtain target learning data includes: filtering the vehicle driving data according to a data validity filtering condition corresponding to the curve driving scenario to obtain initial learning data; Calculating a road curvature speed limit value corresponding to each road curvature radius in the initial learning data; and determining an average road curvature speed limit value corresponding to each preset road curvature radius range in a plurality of preset road curvature radius ranges based on the road curvature speed limit value; determining an average vehicle speed corresponding to each preset road curvature radius range based on the vehicle speed corresponding to each road curvature radius in the initial learning data and a plurality of preset road curvature radius ranges; The average road curvature speed limit value and the average vehicle speed are used as the target learning data.

[0061] Specifically, the data efficiency filtering condition is used to filter out invalid data in the curve driving scenario. If the road curvature radius in the collected vehicle driving data is less than the curvature radius threshold, it means that the current road curvature is large. When the turning curvature is large, the steering motor controlling the turning torque will have torque limitation, resulting in a poor turning control experience. Therefore, the vehicle driving data when the road curvature radius is less than the curvature radius threshold is not used as the final target learning data and needs to be eliminated. For example, the curvature radius threshold is 125m. If the assisted driving function is turned on and it is detected that the road curvature radius of the road ahead is less than the curvature radius threshold, the driver can be notified to take over the vehicle.

[0062] Furthermore, for safe driving, the vehicle speed should not be too high when driving on a curve. If the current speed exceeds the maximum speed threshold, the vehicle driving data at that time is considered invalid and irrelevant. Furthermore, to ensure stability on a curve, the vehicle speed should not be too low. If the current speed is less than the minimum speed threshold, the vehicle driving data at that time is considered invalid and irrelevant. For example, the maximum speed threshold is 70 km / h, and the minimum speed threshold is 30 km / h.

[0063] Furthermore, to ensure smooth driving during assisted driving, if the speeds collected at adjacent acquisition times do not change linearly, the corresponding driving data is considered invalid and needs to be discarded. After filtering based on the road curvature radius, vehicle speed, and linearity conditions, the initial learning data is obtained. All data contained in the initial learning data is valid.

[0064] For the road curvature radius at each moment in the initial learning data, the corresponding road curvature speed limit is calculated using the following formula: Vcurve=[127×R×(μ+i)]^1 / 2 Where Vcurve represents the road curvature speed limit, R represents the road curvature radius, μ represents the lateral force coefficient, and i represents the lateral slope of the road surface. The road curvature speed limit represents the upper speed limit for the road corresponding to the current road curvature radius. The lateral force coefficient μ can be obtained by querying the preset correspondence table. The preset correspondence table specifies the correspondence between the lateral force coefficient and the road curvature radius. A unique lateral force coefficient can be queried based on the road curvature radius. Table 3 shows the preset correspondence table. Data not present in the preset correspondence table can be obtained through interpolation.

[0065] The transverse slope of a road surface refers to the lateral inclination of the top surface of the roadbed, expressed as a percentage. If the difference between adjacent road curvature speed limit values ​​calculated using vehicle driving data is less than the difference threshold, the change in the road curvature speed limit is considered small and the road curvature speed limit is not updated, thus reducing the amount of target learning data. If the difference between adjacent road curvature speed limit values ​​calculated using vehicle driving data is greater than or equal to the difference threshold, the road curvature speed limit is updated. If a speed limit sign is marked on the road (equivalent to the road curvature speed limit), the speed limit sign can be used directly without calculating the road curvature speed limit.

[0066] Table 3 Preset correspondence table

[0067] In this embodiment, multiple preset road curvature radius ranges are pre-set, such as 201m~300m, 301m~400m, etc., and each road curvature radius in the collected vehicle driving data is divided into the corresponding preset road curvature radius range. Since each road curvature radius corresponds to a calculated road curvature speed limit value, for each preset road curvature radius range, the average road curvature speed limit value corresponding to all road curvature radii within the range is calculated. At the same time, for each preset road curvature radius range, the average vehicle speed is calculated based on the vehicle speeds corresponding to all road curvature radii within the range. It should be noted that if the vehicle speeds corresponding to the same road curvature radius collected are different, the average vehicle speed is used as the vehicle speed corresponding to the road curvature radius. Finally, the average road curvature speed limit value and the average vehicle speed are used as the target learning data.

[0068] This embodiment provides a method for determining target learning data for a curve driving scenario. First, invalid data is eliminated to obtain valid initial learning data. When screening the initial learning data, key data that best reflects the driver's driving style in the current scenario is selected: average vehicle speed and average road curvature speed limit. Under the constraints of the average road curvature speed limit, average vehicle speed reflects the driver's aggressiveness in curve driving. Therefore, using average vehicle speed and average road curvature speed limit as target learning data for learning assisted driving functions can learn the driver's driving habits in adaptive car-following scenarios, providing the driver with personalized automatic car-following driving services.

[0069] Furthermore, after determining the target learning data for a curve driving scenario, it is necessary to further determine the driving adjustment control parameters for the curve driving scenario. The driving adjustment control parameters include a curve control coefficient. Determining the driving adjustment control parameters for the driving scenario based on the target learning data includes: The curve control coefficient is determined based on a ratio of the average vehicle speed to the average road curvature speed limit value.

[0070] Specifically, the driver's driving style can be determined by the ratio of the average vehicle speed and the average road curvature speed limit. If 0.8≤average vehicle speed / average road curvature speed limit<0.9, the corresponding curve control coefficient is determined to be 0.8, and the driver's driving style is comfortable. If the average vehicle speed / average road curvature speed limit is <0.8, the corresponding curve control coefficient is also determined to be 0.8. If 0.9≤average vehicle speed / average road curvature speed limit<0.95, the corresponding curve control coefficient is determined to be 0.9, and the driver's driving style is standard. If 0.95≤average vehicle speed / average road curvature speed limit, the corresponding curve control coefficient is determined to be 0.95, and the driver's driving style is aggressive.

[0071] After the assisted driving function is enabled, the vehicle's intelligent driving domain controller automatically controls the vehicle's curves according to the curve control coefficient determined during the learning process. The intelligent driving domain controller uses the current road curvature speed limit calculated in real time or directly obtained from the road speed limit sign to determine the target speed based on the curve control coefficient and control vehicle driving according to the target speed. For example, if the current road curvature speed limit is 60 km / h and the curve control coefficient is 0.8, the target speed = current road curvature speed limit × 0.8 = 48 km / h. The intelligent driving domain controller then controls the vehicle at a speed of 48 km / h. Furthermore, assisted driving typically controls the vehicle according to a fixed speed gradient, such as 30 km / h, 35 km / h, and 40 km / h. If the calculated target speed is 48 km / h, the vehicle will typically be controlled at an actual speed of 45 km / h.

[0072] This embodiment provides a method for determining the curve control coefficient in a curve driving scenario. After the assisted driving function is turned on, the vehicle can refer to the curve control coefficient to achieve safe curve driving behavior in the curve driving scenario, providing users with stable automatic curve driving that matches the driver's style, and improving the intelligent driving experience in the curve driving scenario.

[0073] In some embodiments, the driving scenario includes an overtaking lane change scenario; the driving adjustment control parameter includes an overtaking lane change control coefficient; the preset data screening condition includes a lane change passable space screening condition and a lateral and longitudinal driving information screening condition; The filtering of the vehicle driving data according to the preset data filtering condition corresponding to the driving scenario to obtain target learning data includes: Filtering the vehicle driving data according to the lane change passable space screening condition and the lateral and longitudinal driving information screening condition corresponding to the overtaking and lane change scenario to obtain the target learning data; The determining of the driving adjustment control parameters in the driving scenario according to the target learning data includes: The overtaking lane change control coefficient is determined according to the lane change completion time in the target learning data.

[0074] Specifically, the preset data screening conditions are used to screen out invalid vehicle driving data, including lane change passable space screening conditions and lateral and longitudinal driving information screening conditions. Lane change passable space refers to the space range that a vehicle can use when changing lanes, and the lane change is completed within this space range. If the vehicle driving data meets the lane change passable space screening conditions, it means that the current vehicle has sufficient space to change lanes. If the vehicle driving data meets the lateral and longitudinal driving information screening conditions, it means that the vehicle driving data changes relatively smoothly, and the driver is not currently performing emergency or excessive driving operations, which is conducive to maintaining smooth driving after the assisted driving function is turned on.

[0075] Furthermore, the passable space screening conditions for lane changes include passable space length screening conditions and passable space width screening conditions. The passable space length screening conditions include: if the vehicle's expected position in the target lane after lane change (hereinafter referred to as the expected position) is in front of the vehicle's center point, in order to avoid collision with the following vehicle when changing lanes, the speed of the following vehicle is prioritized, and the collision time between the vehicle and the following vehicle must be greater than or equal to the collision time threshold. If the collision time between the vehicle and the following vehicle is less than the collision time threshold, it indicates a collision risk, and the space length screening condition is determined to be unsatisfied. If the vehicle's expected position is behind or parallel to the vehicle's center point, there is a risk of collision with the preceding vehicle when changing lanes. In this case, the speed of the preceding vehicle is prioritized, and the collision time between the vehicle and the preceding vehicle must be greater than or equal to the collision time threshold. If the collision time between the vehicle and the preceding vehicle is less than the collision time threshold, it indicates a collision risk, and the space length screening condition is determined to be unsatisfied. Exemplarily, the collision time threshold is 1 second.

[0076] The passable space width screening conditions include: the passable space width should be within the preset width range, there should be no other vehicles invading the passable space, the deceleration of the leading vehicle and the acceleration of the following vehicle should meet the requirement that there is no collision risk with the ego vehicle, the predicted trajectories of vehicles traveling in the lanes on both sides of the ego vehicle's original vehicle should not conflict with the ego vehicle's lane change trajectory, the non-crossing side lane line of the ego vehicle's original lane should be clear and the original lane should be a non-emergency lane. If all of the above conditions are met, it is determined that the passable space width screening conditions are met.

[0077] The screening conditions for lateral and longitudinal driving information include: longitudinal acceleration condition, longitudinal deceleration condition, longitudinal speed change rate condition, longitudinal speed condition, lateral speed condition, lateral acceleration condition, lateral acceleration and deceleration change rate condition, steering wheel torque condition, steering wheel torque change rate condition, steering wheel angle condition and steering wheel angle speed condition, etc.

[0078] The longitudinal acceleration conditions include: when the vehicle speed is greater than the first speed threshold, the longitudinal acceleration should be less than or equal to 2m / s 2 When the vehicle speed is less than the second speed threshold, the longitudinal acceleration should be less than or equal to 4m / s2 . The first speed threshold is less than the second speed threshold. When the vehicle speed is between the second speed threshold and the first speed threshold, the longitudinal acceleration cannot exceed the target longitudinal acceleration. The target longitudinal acceleration is obtained by calculation: target longitudinal acceleration = -2 / 15×v+14 / 3, where v represents the vehicle speed. The first speed threshold can be 5m / s, and the second speed threshold can be 20 m / s. If the above conditions are met, it is determined that the longitudinal acceleration condition is met. The sampling period interval of the longitudinal acceleration is 2s, and the average of the multiple real-time longitudinal accelerations collected is calculated to determine whether the average of the real-time longitudinal acceleration meets the longitudinal acceleration condition, thereby avoiding the problem of misjudgment due to fluctuations in real-time longitudinal acceleration.

[0079] The longitudinal deceleration conditions include: when the vehicle speed is greater than the first speed threshold, the longitudinal deceleration should be less than or equal to 3.5m / s 2 When the vehicle speed is less than the second speed threshold, the longitudinal deceleration should be less than or equal to 5m / s 2 . The first speed threshold is less than the second speed threshold. When the vehicle speed is between the second speed threshold and the first speed threshold, the longitudinal deceleration cannot exceed the target longitudinal deceleration. The target longitudinal deceleration is obtained by calculation: target longitudinal deceleration = -0.1×v+5.5, where v represents the vehicle speed. The first speed threshold can be 5m / s, and the second speed threshold can be 20 m / s. If the above conditions are met, it is determined that the longitudinal deceleration condition is met. The sampling period interval of the longitudinal deceleration is 2s, and the average of the multiple real-time longitudinal decelerations collected is calculated to determine whether the average of the real-time longitudinal deceleration meets the longitudinal deceleration condition, thereby avoiding the problem of misjudgment due to fluctuations in the real-time longitudinal deceleration.

[0080] The longitudinal speed change rate condition includes: when the vehicle speed is greater than the first speed threshold, the longitudinal speed change rate should be less than or equal to 2.5m / s 3 When the vehicle speed is less than the second speed threshold, the longitudinal speed change rate should be less than or equal to 5m / s 3 . The first speed threshold is less than the second speed threshold. When the vehicle speed is between the second speed threshold and the first speed threshold, the longitudinal speed change rate cannot exceed the target longitudinal speed change rate. The target longitudinal speed change rate is obtained by calculation: target longitudinal speed change rate = -1 / 6×v+35 / 6, ​​where v represents the vehicle speed. The first speed threshold can be 5m / s, and the second speed threshold can be 20 m / s. If the above conditions are met, it is determined that the longitudinal speed change rate condition is met. The sampling period interval of the longitudinal speed change rate is 1s, and the average of the multiple real-time longitudinal speed change rates collected is calculated to determine whether the average of the real-time longitudinal speed change rate meets the longitudinal speed change rate condition, thereby avoiding the problem of misjudgment due to fluctuations in the real-time longitudinal speed change rate.

[0081] The longitudinal speed condition includes a longitudinal speed greater than or equal to 30km / h, the lateral speed condition includes a lateral speed less than or equal to 1.8m / s, and the lateral acceleration condition includes a lateral acceleration less than or equal to 2m / s. 2 , the lateral acceleration / deceleration rate of change conditions include the lateral acceleration / deceleration rate of change being less than or equal to 3m / s 3 , steering wheel torque conditions include a steering wheel torque of 4 Nm or less, steering wheel torque rate of change conditions include a steering wheel torque rate of change of 5 Nm / s or less, steering wheel angle conditions include a steering wheel angle of 180° or less, and steering wheel angular velocity conditions include a steering wheel angular velocity of 12 deg / s or less. The specific contents of the above lateral and longitudinal driving information screening conditions are for illustrative purposes only, and information screening conditions derived from any one or a combination of these conditions are also intended to fall within the scope of protection of this application.

[0082] After the vehicle driving data meets the above conditions, it is determined that the lateral and longitudinal driving information screening conditions are met. After filtering the lane change passable space screening conditions and the lateral and longitudinal driving information screening conditions, invalid data is eliminated to obtain target learning data.

[0083] Furthermore, for vehicle safety, if the current road section is a ramp and the vehicle is performing a lane change maneuver while overtaking, there is no need to learn the vehicle's driving data at that time. The vehicle's driving data at that time is discarded as invalid. If the current road section is a straight section and the vehicle's speed is outside the preset speed range, indicating that the speed is too low or too high, and the vehicle is not within the normal driving range, the vehicle's driving data at that time is determined to be invalid and needs to be discarded. An exemplary preset speed range is 15 km / h to 120 km / h.

[0084] Driving adjustment control parameters are determined based on the target learning data. In the overtaking lane change scenario, the driving adjustment control parameters include an overtaking lane change control coefficient. The lane change completion time for each lane change operation is selected from the target learning data. If the lane change completion time is within a first duration, the overtaking lane change control coefficient is equal to the first duration, indicating that the driver's driving style is aggressive. If the lane change completion time is greater than or equal to the first duration and less than a second duration, the overtaking lane change control coefficient is equal to the second duration, indicating that the driver's driving style is standard. If the lane change completion time is greater than or equal to the second duration and less than a third duration, the overtaking lane change control coefficient is equal to the third duration, indicating that the driver's driving style is comfortable. The third duration is greater than the second duration, and the second duration is greater than the first duration. For example, the first duration is 4 seconds, the second duration is 6 seconds, and the third duration is 8 seconds. In other words, the larger the overtaking lane change control coefficient, the more conservative the driver's lane change style.

[0085] After determining the overtaking lane change control coefficient, when the assisted driving function is enabled, the automatic overtaking lane change driving behavior is executed according to the overtaking lane change control coefficient, and the overtaking lane change completion time is controlled to be equal to the overtaking lane change control coefficient. For example, if the overtaking lane change control coefficient is 4 seconds, the overtaking lane change completion time is controlled to be 4 seconds.

[0086] It should be noted that the overtaking lane change control coefficient can also be determined in the following manner: the vehicle speed and the preceding vehicle speed at each lane change operation are selected from the target learning data. If the first threshold ≤ vehicle speed / previous vehicle speed < second threshold, the overtaking lane change control coefficient is equal to the first threshold, indicating that the driver's driving style is comfortable. If the second threshold ≤ vehicle speed / previous vehicle speed < third threshold, the overtaking lane change control coefficient is equal to the second threshold, indicating that the driver's driving style is standard. If the vehicle speed / previous vehicle speed ≥ third threshold, the overtaking lane change control coefficient is equal to the third threshold, indicating that the driver's driving style is aggressive. For example, the first threshold is 0.8, the second threshold is 0.9, and the third threshold is 0.95. In other words, the larger the overtaking lane change control coefficient, the more aggressive the driver's lane change style.

[0087] After determining the overtaking lane change control coefficient, when the assisted driving function is enabled, automatic overtaking lane change driving behavior is executed according to the overtaking lane change control coefficient. The speed at which the overtaking lane change is initiated is equal to the product of the overtaking lane change control coefficient and the speed of the preceding vehicle. For example, if the overtaking lane change control coefficient is 0.8, the overtaking lane change maneuver begins when the current vehicle speed equals 0.8 times the preceding vehicle speed.

[0088] This embodiment provides a method for determining the overtaking lane change control coefficient in an overtaking lane change scenario. After the assisted driving function is turned on, the vehicle can refer to the overtaking lane change control coefficient to achieve safe overtaking and lane change behavior in the overtaking lane change scenario, providing users with a stable overtaking lane change driving service that matches the driver's style, and improving the intelligent driving experience in the overtaking lane change scenario.

[0089] In some embodiments, the driving scenario includes a merging / diverging scenario; the preset data screening condition includes a navigation data screening condition; the driving adjustment control parameter includes a merging / diverging control style; The filtering of the vehicle driving data according to the preset data filtering condition corresponding to the driving scenario to obtain target learning data includes: Filtering the vehicle driving data according to the navigation data filtering condition in the diverging and merging scenario to obtain the target learning data; The determining of the driving adjustment control parameters in the driving scenario according to the target learning data includes: Calculating a target lane change distance based on the number of lane changes, vehicle speed, and preset lane change information in the target learning data; The merging and diverging control style is determined according to the actual lane changing distance and the target lane changing distance in the target learning data.

[0090] Specifically, the diverging and merging scene refers to the diverging or merging scene when vehicles are getting on and off the highway and driving on the highway interchange section. The navigation data screening conditions include: the current existence of high-precision map and navigation data information. If there is no high-precision map information and navigation data information, it is determined that the navigation data screening conditions are not met, so it is impossible to determine whether the vehicle is in the diverging and merging scene. Therefore, it is necessary to eliminate the vehicle driving data at this time to obtain the target learning data. In addition, in the diverging and merging scene, the vehicle speed is not within the preset speed range, indicating that the vehicle is driving abnormally, and the vehicle driving data at this time needs to be eliminated. Exemplarily, the preset speed range is 30km / h ~100km / h.

[0091] For each speed in the target learning data, a target lane change distance is calculated for each speed. The target lane change distance is the standard distance from the starting point of the lane change to the merging or diverging point during normal vehicle driving. If the driver's actual lane change distance equals the target lane change distance, it indicates that the driver's driving style is standard.

[0092] The target lane change distance is calculated as follows: L=(C-1)×(Tscr+Tscp+Tscs) ×v+(Tscr+Tscp) ×v Where L represents the target lane change distance, C represents the number of lane changes, Tscr represents the lane change preparation time, Tscp represents the time required to complete a lane change, and Tscs represents the lane change interval. The preset lane change information includes Tscr, Tscp, and Tscs.

[0093] It should be noted that if there is a solid-line area (non-lane-changeable area) on the road ahead and the actual length of the solid-line area cannot be measured, the target lane change distance should be appropriately extended. For example, add 200m to the target lane change distance. If the target lane change distance is 2600m, the extended target lane change distance = 2600 + 200 = 2800. If the length of the solid-line area on the road ahead can be accurately measured, simply add the actual length of the solid-line area to the target lane change distance.

[0094] If the actual lane change distance in the target learning data is less than the target lane change distance, which indicates that the vehicle delayed the lane change and the driver's driving style is relatively aggressive, the merging and diverging control style is determined to be aggressive. If the actual lane change distance in the target learning data is greater than the target lane change distance, which indicates that the vehicle prematurely changed lanes and the driver's driving style is relatively comfortable, the merging and diverging control style is determined to be comfortable. If the actual lane change distance in the target learning data is equal to the target lane change distance and the driver's driving style is relatively standard, the merging and diverging control style is determined to be standard.

[0095] After the assisted driving function is enabled, if the current driving scenario is detected as a merging or diverging situation through high-precision maps and navigation information, the diverging or merging maneuver is executed according to the merging or diverging control style. For example, if the merging or diverging control style is comfort, the target lane change distance is appropriately extended based on the calculated target lane change distance, that is, the lane change maneuver is executed in advance.

[0096] This embodiment provides a method for determining the merging and splitting control style in merging and splitting scenarios. After the assisted driving function is turned on, the vehicle can refer to the merging and splitting control style to achieve safe merging and splitting operations in merging and splitting scenarios, providing users with stable merging and splitting lane change services that match the driver's style, and improving the intelligent driving experience in merging and splitting scenarios.

[0097] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied in a distributed scenario and performed by multiple devices working together. In such a distributed scenario, one of the multiple devices may only perform one or more steps of the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the method.

[0098] It should be noted that the above describes some embodiments of the present application. In some cases, the actions or steps described in the above embodiments can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0099] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a vehicle assisted driving device.

[0100] refer to Figure 3 , the vehicle auxiliary driving device includes: The collection module 302 is configured to collect vehicle driving data within a preset time period when the vehicle assisted driving function is not turned on; A first determining module 304 is configured to determine a corresponding driving scenario according to the vehicle driving data; The second determination module 306 is configured to determine the driving adjustment control parameters in the driving scenario according to the vehicle driving data, so as to provide assisted driving for the driver based on the driving adjustment control parameters when the vehicle assisted driving function is turned on.

[0101] In some embodiments, the second determining module 306 is further configured to filter the vehicle driving data according to a preset data filtering condition corresponding to the driving scenario to obtain target learning data; Determine driving adjustment control parameters in the driving scenario according to the target learning data.

[0102] In some embodiments, the driving scenario includes an adaptive vehicle-following scenario; the preset data screening condition includes a data validity filtering condition; the second determining module 306 is further configured to filter the vehicle driving data according to the data validity filtering condition corresponding to the adaptive vehicle-following scenario to obtain initial learning data; Filtering the initial learning data according to preset sampled vehicle speeds, and determining an average vehicle speed corresponding to each preset sampled vehicle speed and a collision time corresponding to the average vehicle speed based on the filtered data; The average vehicle speed and the corresponding collision time are used as the target learning data.

[0103] In some embodiments, the driving adjustment control parameters include a target collision time; the second determination module 306 is further configured to calculate a stable following distance at each preset sampling speed based on the target learning data; and determine the target collision time based on the stable following distance and the average speed.

[0104] In some embodiments, the second determination module 306 is further configured to, for the vehicle driving data collected at each moment within the preset time period, in response to the road curvature radius in the vehicle driving data being less than a curvature radius threshold, the collision time when following a vehicle is not within a preset collision time range, or the following distance is less than a safety distance threshold, eliminate the vehicle driving data collected at the moment to obtain the initial learning data.

[0105] In some embodiments, the driving scenario includes a curved driving scenario; the preset data screening condition includes a data validity filtering condition; the second determining module 306 is further configured to filter the vehicle driving data according to the data validity filtering condition corresponding to the curved driving scenario to obtain initial learning data; Calculating a road curvature speed limit value corresponding to each road curvature radius in the initial learning data; and determining an average road curvature speed limit value corresponding to each preset road curvature radius range in a plurality of preset road curvature radius ranges based on the road curvature speed limit value; determining an average vehicle speed corresponding to each preset road curvature radius range based on the vehicle speed corresponding to each road curvature radius in the initial learning data and a plurality of preset road curvature radius ranges; The average road curvature speed limit value and the average vehicle speed are used as the target learning data.

[0106] In some embodiments, the driving adjustment control parameter includes a curve control coefficient; the second determination module 306 is further configured to determine the curve control coefficient based on a ratio of the average vehicle speed to the average road curvature speed limit value.

[0107] In some embodiments, the driving scenario includes an overtaking and lane changing scenario; the driving adjustment control parameter includes an overtaking and lane changing control coefficient; the preset data screening conditions include lane changing passable space screening conditions and lateral and longitudinal driving information screening conditions; the second determination module 306 is further configured to filter the vehicle driving data according to the lane changing passable space screening conditions and lateral and longitudinal driving information screening conditions corresponding to the overtaking and lane changing scenario to obtain the target learning data; and determine the overtaking and lane changing control coefficient according to the lane changing completion time in the target learning data.

[0108] In some embodiments, the driving scenario includes a merging / diverging scenario; the preset data filtering condition includes a navigation data filtering condition; the driving adjustment control parameter includes a merging / diverging control style; the second determination module 306 is further configured to filter the vehicle driving data according to the navigation data filtering condition under the merging / diverging scenario to obtain the target learning data; calculate the target lane change distance based on the number of lane changes, vehicle speed and preset lane change information in the target learning data; determine the merging / diverging control style based on the actual lane change distance and the target lane change distance in the target learning data.

[0109] For the convenience of description, the above device is described as being divided into various modules according to their functions. Of course, when implementing this application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0110] The device of the above embodiment is used to implement the corresponding vehicle assisted driving method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0111] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor, wherein when the processor executes the program, the vehicle assisted driving method described in any of the above embodiments is implemented.

[0112] Figure 4 A more specific hardware structure diagram of an electronic device provided in this embodiment is shown. The device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are communicatively connected to each other within the device via the bus 1050.

[0113] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0114] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage devices, dynamic storage devices, etc. The memory 1020 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0115] The input / output interface 1030 is used to connect to input / output modules to enable information input and output. The input / output modules can be configured as components within the device (not shown) or externally connected to the device to provide corresponding functions. Input devices may include a keyboard, mouse, touch screen, microphone, and various sensors. Output devices may include a display, speaker, vibrator, indicator light, and the like.

[0116] The communication interface 1040 is used to connect to a communication module (not shown) to enable communication between the device and other devices. The communication module can communicate via wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, Wi-Fi, Bluetooth, etc.).

[0117] The bus 1050 comprises a pathway for transmitting information between various components of the device, such as the processor 1010 , the memory 1020 , the input / output interface 1030 , and the communication interface 1040 .

[0118] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in a specific implementation, the device may also include other components necessary for normal operation. In addition, it will be understood by those skilled in the art that the above device may only include the components necessary to implement the embodiments of this specification, and does not necessarily include all the components shown in the figure.

[0119] The electronic device of the above embodiment is used to implement the corresponding vehicle assisted driving method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0120] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable the computer to execute the vehicle assisted driving method described in any of the above embodiments.

[0121] The computer-readable media of this embodiment includes permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0122] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the vehicle assisted driving method described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0123] Based on the same concept, corresponding to any of the above-mentioned embodiments, the present application also provides a computer program product, including computer program instructions. When the computer program instructions are run on a computer, the computer executes the method described in any of the above embodiments, which has the beneficial effects of the corresponding method embodiments and will not be repeated here.

[0124] It is understandable that before using the technical solutions of each embodiment of the present disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved will be informed to the user in an appropriate manner, and the user's authorization will be obtained.

[0125] For example, in response to a user's active request, a prompt message is sent to the user to clearly inform the user that the operation requested will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operation of the technical solution of the present disclosure based on the prompt message.

[0126] As an optional but non-limiting implementation, in response to receiving the user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also contain a selection control for the user to select "Agree" or "Disagree" with the provision of personal information by the electronic device.

[0127] It is understandable that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0128] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application is limited to these examples. In line with the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0129] In addition, to simplify the description and discussion, and to avoid obscuring the understanding of the embodiments of the present application, well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided figures. Furthermore, devices may be shown in block diagram form to avoid obscuring the understanding of the embodiments of the present application, and this also takes into account the fact that the implementation details of these block diagram devices are highly dependent on the platform on which the embodiments of the present application will be implemented (i.e., these details should be fully understood by those skilled in the art). Where specific details (e.g., circuits) are set forth to describe the exemplary embodiments of the present application, it will be apparent to those skilled in the art that the embodiments of the present application can be implemented without these specific details or with variations therefrom. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0130] Although the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those skilled in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may utilize the embodiments discussed.

[0131] The embodiments of the present application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the present application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of the present application.

Claims

1. A vehicle assisted driving method, characterized in that: include: Collect vehicle driving data within a preset time period when the vehicle's assisted driving function is not turned on; determining a corresponding driving scenario according to the vehicle driving data; According to the vehicle driving data, driving adjustment control parameters in the driving scenario are determined, so as to provide assisted driving for the driver based on the driving adjustment control parameters when the vehicle assisted driving function is turned on.

2. The method according to claim 1, characterized in that The determining, based on the vehicle driving data, the driving adjustment control parameters in the driving scenario includes: Filtering the vehicle driving data according to a preset data filtering condition corresponding to the driving scenario to obtain target learning data; Determine driving adjustment control parameters in the driving scenario according to the target learning data.

3. The method according to claim 2, characterized in that The driving scenario includes an adaptive vehicle following scenario; the preset data screening condition includes a data validity filtering condition; The filtering of the vehicle driving data according to the preset data filtering condition corresponding to the driving scenario to obtain target learning data includes: filtering the vehicle driving data according to a data validity filtering condition corresponding to the adaptive vehicle following scenario to obtain initial learning data; Filtering the initial learning data according to preset sampled vehicle speeds, and determining an average vehicle speed corresponding to each preset sampled vehicle speed and a collision time corresponding to the average vehicle speed based on the filtered data; The average vehicle speed and the corresponding collision time are used as the target learning data.

4. The method according to claim 3, characterized in that The driving adjustment control parameters include target collision time; The determining of the driving adjustment control parameters in the driving scenario according to the target learning data includes: Calculating a stable following distance at each preset sampling speed based on the target learning data; A target collision time is determined according to the stable following distance and the average vehicle speed.

5. The method according to claim 3, characterized in that The filtering of the vehicle driving data according to the data validity filtering condition corresponding to the adaptive vehicle following scenario to obtain initial learning data includes: For the vehicle driving data collected at each moment within the preset time period, in response to the road curvature radius in the vehicle driving data being less than the curvature radius threshold, the collision time when following the vehicle is not within the preset collision time range, or the following distance is less than the safety distance threshold, the vehicle driving data collected at the moment is eliminated to obtain the initial learning data.

6. The method according to claim 2, characterized in that The driving scenario includes a curve driving scenario; the preset data screening condition includes a data validity filtering condition; The filtering of the vehicle driving data according to the preset data filtering condition corresponding to the driving scenario to obtain target learning data includes: filtering the vehicle driving data according to a data validity filtering condition corresponding to the curve driving scenario to obtain initial learning data; Calculating a road curvature speed limit value corresponding to each road curvature radius in the initial learning data; and determining an average road curvature speed limit value corresponding to each preset road curvature radius range in a plurality of preset road curvature radius ranges based on the road curvature speed limit value; determining an average vehicle speed corresponding to each preset road curvature radius range based on the vehicle speed corresponding to each road curvature radius in the initial learning data and a plurality of preset road curvature radius ranges; The average road curvature speed limit value and the average vehicle speed are used as the target learning data.

7. The method according to claim 6, characterized in that The driving adjustment control parameters include a curve control coefficient; The determining of the driving adjustment control parameters in the driving scenario according to the target learning data includes: The curve control coefficient is determined based on a ratio of the average vehicle speed to the average road curvature speed limit value.

8. The method according to claim 2, characterized in that The driving scenario includes an overtaking and lane changing scenario; the driving adjustment control parameter includes an overtaking and lane changing control coefficient; the preset data screening condition includes a lane changing passable space screening condition and a lateral and longitudinal driving information screening condition; The filtering of the vehicle driving data according to the preset data filtering condition corresponding to the driving scenario to obtain target learning data includes: Filtering the vehicle driving data according to the lane change passable space screening condition and the lateral and longitudinal driving information screening condition corresponding to the overtaking and lane change scenario to obtain the target learning data; The determining of the driving adjustment control parameters in the driving scenario according to the target learning data includes: The overtaking lane change control coefficient is determined according to the lane change completion time in the target learning data.

9. The method according to claim 2, characterized in that The driving scenario includes a merging / diverging scenario; the preset data screening condition includes a navigation data screening condition; the driving adjustment control parameter includes a merging / diverging control style; The filtering of the vehicle driving data according to the preset data filtering condition corresponding to the driving scenario to obtain target learning data includes: Filtering the vehicle driving data according to the navigation data filtering condition in the diverging and merging scenario to obtain the target learning data; The determining of the driving adjustment control parameters in the driving scenario according to the target learning data includes: Calculating a target lane change distance based on the number of lane changes, vehicle speed, and preset lane change information in the target learning data; The merging and diverging control style is determined according to the actual lane changing distance and the target lane changing distance in the target learning data.

10. A vehicle, characterized in that: The vehicle comprises: a memory for storing executable program code; A processor is configured to call and run the executable program code from the memory, so that the vehicle executes the method according to any one of claims 1 to 9.

Images