Vehicle control method and device

Abstract

The application discloses a vehicle control method and device. The method comprises the following steps: obtaining first driving data of a first vehicle and road information of a road on which the first vehicle drives, wherein the first driving data at least comprises lane line information drawn on the road, and second driving data of a second vehicle adjacent to the first vehicle and driving in front of the first vehicle; in response to the lane line information being invalid data and the second vehicle satisfying a first preset condition, determining relative position data of positions of the second vehicle at different historical time points and a current position of the first vehicle based on the first driving data and the second driving data; performing linear fitting on the relative position data to obtain a target driving track of the second vehicle; and controlling the first vehicle to drive based on the target driving track. The application solves the technical problem of limited lateral control function of the vehicle.

Description

Technical Field

[0001] This invention relates to the field of vehicle control, and more specifically, to a vehicle control method and apparatus. Background Technology

[0002] When driving at high speeds or on similarly high-speed urban roads, drivers may become inattentive over extended periods, causing the vehicle to drift out of its lane and posing a safety hazard. Lane keeping assist's lateral control function ensures the vehicle automatically stays centered in the lane, maximizing driving safety.

[0003] However, the lane-keeping assist function in most existing vehicles can only be used when both lane markings are clear, or when only one lane marking is clear. If lane markings are missing, such as when lane markings are partially obscured by rain, covered by dust or snow, or when the vehicle is approaching a traffic light in urban conditions, the lateral assist function will be limited and disengaged, affecting the driving experience. This is especially true in some urban areas where there are many traffic lights and intersections without lane markings, making the lateral assist function virtually unusable.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This invention provides a vehicle control method and apparatus to at least solve the technical problem of limited lateral control function of a vehicle.

[0006] According to one aspect of the present invention, a vehicle control method is provided, comprising: acquiring first driving data of a first vehicle and road information of the road on which the first vehicle is traveling, wherein the first driving data includes at least: the road information includes at least lane line information drawn on the road, and second driving data of a second vehicle adjacent to the first vehicle and traveling in front of the first vehicle; in response to the lane line information being invalid data and the second vehicle meeting a first preset condition, determining relative position data between the positions of the second vehicle at multiple different historical times and the current position of the first vehicle based on the first driving data and the second driving data, wherein the first preset condition is used to characterize allowing the first vehicle to follow the second vehicle; performing linear fitting on the multiple relative position data to obtain a target driving trajectory of the second vehicle; and controlling the first vehicle to drive based on the target driving trajectory.

[0007] Further, based on the first driving data and the second driving data, the relative position data between the positions of the second vehicle at multiple different historical moments and the current position of the first vehicle is determined, including: determining the first position of the first vehicle at multiple different historical moments based on the first driving data; establishing multiple first coordinate systems with the multiple first positions as the origin and the driving direction of the first vehicle as the first horizontal axis; determining the second position of the second vehicle at multiple different historical moments based on the second driving data, wherein the second position at multiple different historical moments is used to characterize the position of the second vehicle in the first coordinate system corresponding to the multiple different historical moments; and determining the relative position data based on the first position, the second position, and the current position of the first vehicle.

[0008] Further, based on the first position, the second position, and the current position of the first vehicle, relative position data is determined, including: establishing a second coordinate system with the current position as the origin and the driving direction as the second horizontal axis; determining a first position vector based on the current position and the first position, and determining a second position vector based on the first position and the second position, wherein the first position vector is used to characterize the position change of the first vehicle at different historical moments, and the second position vector is used to characterize the relative position change of the first vehicle and the second vehicle at multiple different historical moments; determining a third position vector based on the vector sum of the first position vector and the second position vector, wherein the third position vector is used to characterize the relative position change of the second vehicle at multiple different historical moments and the current position of the first vehicle; and transforming the third position vector from the first coordinate system to the second coordinate system to determine the relative position data.

[0009] Furthermore, controlling vehicle driving based on the target driving trajectory includes: determining a first lateral error and a first deflection error based on the current position, driving direction, and target driving trajectory of the first vehicle; performing proportional-integral-differential processing on the first lateral error and the first deflection error based on preset calibration parameters to obtain a target deflection angle; and controlling the first vehicle to drive according to the target driving trajectory based on the target deflection angle and second driving data.

[0010] Furthermore, the preset conditions include at least one of the following: the longitudinal distance between the second vehicle and the first vehicle is less than a first distance threshold within a preset time period, wherein the longitudinal direction is used to characterize the driving direction of the first vehicle; the lateral distance between the second vehicle and the first vehicle is less than a second distance threshold within a preset time period; and the lateral relative speed between the second vehicle and the first vehicle is less than a first speed threshold within a preset time period.

[0011] Furthermore, the method also includes: in response to the lane line information being invalid data and the second vehicle not meeting the preset conditions, pushing a first prompt message to the user, wherein the first prompt message is used to prompt the user that the first vehicle has exited the lateral automatic control function; in response to the lane line information being valid data, controlling the first vehicle to drive based on the lane line trajectory.

[0012] Furthermore, in response to the lane line information being valid data, controlling the first vehicle's movement based on the lane line trajectory includes: acquiring valid flag bits corresponding to the lane line information on both sides of the first vehicle, wherein the valid flag bits are used to indicate whether the lane line information on both sides is valid data; in response to the valid flag bits indicating that the lane line information on both sides is valid data, controlling the first vehicle's movement based on the centerline of the lane line trajectory in the lane line information on both sides; in response to the valid flag bits indicating that the lane line information on either side is valid data, controlling the first vehicle's movement based on the lane line trajectory in the lane line information on either side and the width of the driving road.

[0013] Furthermore, in response to the valid flag indicating that the lane line information on either side is valid data, the method further includes: in response to the failure to obtain the width of the driving road, controlling the first vehicle to drive based on a preset control distance and the lane line trajectory in the lane line information on either side.

[0014] According to another aspect of the present invention, a vehicle control device is also provided, comprising: a first acquisition module, configured to acquire first driving data of a first vehicle and road information of the road on which the first vehicle travels, wherein the first driving data includes at least: the road information includes at least lane line information drawn on the road, and second driving data of a second vehicle adjacent to the first vehicle and traveling in front of the first vehicle; a position data determination module, configured to, in response to the lane line information being invalid data and the second vehicle meeting a first preset condition, determine relative position data between the positions of the second vehicle at multiple different historical times and the current position of the first vehicle based on the first driving data and the second driving data, wherein the first preset condition is used to indicate that the first vehicle is allowed to follow the second vehicle; a driving trajectory fitting module, configured to perform linear fitting on the multiple relative position data to obtain a target driving trajectory of the second vehicle; and a vehicle control module, configured to control the driving of the first vehicle based on the target driving trajectory.

[0015] According to another aspect of the present invention, a vehicle is also provided, including one or more processors and a storage device, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to perform the vehicle control method described above.

[0016] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform the above-described vehicle control method.

[0017] According to another aspect of the present invention, a processor is also provided, which is used to run a program, wherein the program executes the vehicle control method described above when it runs.

[0018] In this embodiment of the invention, by acquiring the first driving data of the first vehicle and the road information of the road on which the first vehicle is traveling, in response to the lane line information being invalid data and the second vehicle meeting the first preset condition, based on the first and second driving data, the relative position data of the second vehicle at multiple different historical moments and the current position of the first vehicle are determined. Then, the multiple relative position data are linearly fitted to obtain the target driving trajectory of the second vehicle. Finally, the first vehicle is controlled to drive based on the target driving trajectory. It is easy to imagine that when the lane line information of the road on which the first vehicle is traveling is invalid data, the target trajectory of the second vehicle can be fitted based on the driving data of the first vehicle and the second vehicle in front. Then, the target turning angle or target torque that the first vehicle should have at this moment can be calculated through the lateral control algorithm, and the automatic lateral control function of the vehicle is activated. This achieves the technical effect of ensuring that the vehicle travels along the lane line in the lateral direction or follows the target vehicle in front, ensuring driving safety, and thus solving the technical problem of limited lateral control function of the vehicle. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0020] Figure 1 This is a flowchart of a vehicle control method according to an embodiment of the present invention;

[0021] Figure 2 This is a flowchart of the control algorithm for a vehicle control method according to an embodiment of the present invention;

[0022] Figure 3 This is a schematic diagram of the vehicle coordinate system of a vehicle control method according to an embodiment of the present invention;

[0023] Figure 4 This is a schematic diagram of the target vehicle coordinate information at four time points according to a vehicle control method of an embodiment of the present invention.

[0024] Figure 5 This is a schematic diagram of coordinate information transformation according to an embodiment of the present invention;

[0025] Figure 6 This is a schematic diagram of a vehicle control device according to an embodiment of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] Example 1

[0029] According to an embodiment of the present invention, an embodiment of a vehicle control method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0030] Figure 1 This is a flowchart of a vehicle control method according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0031] Step S102: Obtain first driving data of the first vehicle and road information of the road on which the first vehicle is traveling. The first driving data includes at least the following: the road information includes at least the lane line information drawn on the road, and the second driving data of the second vehicle that is adjacent to the first vehicle and traveling in front of the first vehicle.

[0032] Specifically, the first vehicle mentioned above refers to the self-driving vehicle, that is, the lateral control of the self-driving vehicle's driving process.

[0033] The aforementioned first driving data includes at least external data during vehicle operation and the vehicle's own driving data. External data includes road information about the road the vehicle is traveling on, as well as driving data of other vehicles around the vehicle; the vehicle's own driving data includes data such as speed and direction of travel during the driving process.

[0034] The aforementioned road information can be specifically understood as the lane line information drawn on the road on which the vehicle travels, i.e., whether lane lines exist and whether existing lane lines are clear.

[0035] The "second vehicle" mentioned above refers to another vehicle. In the absence of lane markings, by collecting and analyzing the trajectory of the second vehicle, its trajectory can be used as the following trajectory of the first vehicle, facilitating lateral control of the first vehicle during its journey. Therefore, the second vehicle needs to be adjacent to the first vehicle in the same direction and travel in front of the first vehicle.

[0036] The aforementioned second driving data includes at least the driving data of the second vehicle relative to the first vehicle, namely the driving yaw angle of the second vehicle relative to the first vehicle, the driving relative speed, and the longitudinal distance and lateral distance of the second vehicle relative to the first vehicle.

[0037] In one optional embodiment, the image acquisition device of the first vehicle can acquire images of the road information on which the first vehicle is traveling, and determine whether lane lines are drawn on the road based on the images. If no lane lines are drawn on the road, or the existing lane lines are unclear, second driving data of the second vehicle can be acquired, facilitating vehicle control of the first vehicle using the target driving trajectory of the second driving data relative to the first driving data. Simultaneously, the first vehicle's own driving data can be acquired using its driving system, and the second driving data can be acquired using its navigation system.

[0038] In another alternative embodiment, the image acquisition device described above includes, but is not limited to, a vehicle-mounted forward-facing camera; any device with image acquisition capabilities can be used as an image acquisition device.

[0039] Step S104: In response to the lane line information being invalid data and the second vehicle meeting the first preset condition, based on the first driving data and the second driving data, determine the relative position data of the second vehicle at multiple different historical moments and the current position of the first vehicle, wherein the first preset condition is used to characterize that the first vehicle is allowed to follow the second vehicle.

[0040] The first preset condition includes at least one of the following: the longitudinal distance between the second vehicle and the first vehicle is less than a first distance threshold within a preset time period, wherein the longitudinal direction is used to characterize the driving direction of the first vehicle; the lateral distance between the second vehicle and the first vehicle is less than a second distance threshold within a preset time period; and the lateral relative speed between the second vehicle and the first vehicle is less than a first speed threshold within a preset time period.

[0041] Specifically, the aforementioned invalid data can be understood as information such as the absence of lane line information or unclear lane lines on the road in which the first vehicle is traveling.

[0042] The aforementioned preset time can be understood as the preset effective tracking time for the first vehicle to follow the second vehicle.

[0043] The aforementioned first distance threshold can be understood as a preset longitudinal distance difference between the first vehicle and the second vehicle during travel in the direction of travel of the first vehicle. It is important to note that the first distance threshold indicates the effective following distance of the first vehicle to the second vehicle in the direction of travel. When the longitudinal distance difference between the second vehicle and the first vehicle during travel is less than the first distance threshold, the first vehicle can effectively follow the second vehicle in the direction of travel.

[0044] The aforementioned second distance threshold can be understood as the difference in lateral distance between the first and second vehicles during their travel. It's important to note that this second distance threshold indicates that the first vehicle maintains an effective lateral distance from the second vehicle during travel. When the lateral distance difference is less than the second distance threshold, the second vehicle can effectively guide the first vehicle. Conversely, if the difference exceeds the second distance threshold, the second vehicle's trajectory provides no reference for the first vehicle.

[0045] The aforementioned first speed threshold can be understood as the lateral speed threshold of the second vehicle relative to the first vehicle during driving. It is important to note that the first speed threshold indicates the degree of lateral stability of the second vehicle relative to the first vehicle during driving. If the lateral speed threshold of the second vehicle relative to the first vehicle is less than the first speed threshold, it indicates that the second vehicle's lateral control is relatively stable during driving, and it can guide the first vehicle while following it.

[0046] In one optional embodiment, the longitudinal distance between the second vehicle and the first vehicle must be less than 30m (corresponding to the first distance threshold mentioned above), the lateral distance between the second vehicle and the first vehicle must be less than 1.5m (corresponding to the second distance threshold mentioned above), the lateral speed of the second vehicle must be less than 1m / s (corresponding to the first speed threshold mentioned above), and the tracking time of the first vehicle to the second vehicle must be greater than 1s (corresponding to the preset time mentioned above), etc.

[0047] The aforementioned multiple historical moments can be understood as multiple time points prior to the current moment that have time intervals (which can be equal or unequal).

[0048] The aforementioned relative position data refers to the relative position data of the second vehicle at multiple historical time points relative to the position of the first vehicle at the current moment.

[0049] For example, the location of the first vehicle is marked as O, and the locations of the second vehicle at multiple different historical moments are marked as A1, A2, A3, etc.

[0050] In one optional embodiment, lane line features are extracted from the road image captured by the camera, and the extraction results are output. If lane lines are present, the extraction result is set to 1; otherwise, it is set to 0. Road images with an extraction result of 0 are invalidally output, resulting in the aforementioned invalid data. Simultaneously, depth image analysis is performed on road images with an extraction result of 1, specifically analyzing the resolution and sharpness of the lane line feature images. Resolution reflects the clarity of the lane line feature images, and sharpness reflects the contour boundary of the lane line feature images. By determining whether the resolution and sharpness of the lane line feature images meet preset image parameters, if not, it indicates that the lane lines are unclear and do not meet the lateral control requirements; therefore, the road image is invalidally output.

[0051] In one optional embodiment, in determining the relative position data between the position of the second vehicle at multiple different historical moments and the current position of the first vehicle, the position coordinates O of the first vehicle at the current time t can be determined first. Simultaneously, the position coordinates O1 of the first vehicle at historical time t-Δt and the position coordinates A of the second vehicle at historical time t-Δt can also be determined, thus obtaining vectors OO1 and O1A. By adding vectors OO1 and O1A, the coordinates (x, y, y) of the second vehicle at time t relative to the first vehicle can be obtained. t y t Furthermore, the coordinates (x, y) of the second vehicle relative to the first vehicle at time t-Δt can also be obtained. t-Δt y t-Δt Similarly, by analogy, we can obtain the coordinates (x, y) of the second vehicle based on the first vehicle at time t-2Δt. t-2Δt y t-2Δt The coordinates (x, y) of the second vehicle at time t-3Δt are based on those of the first vehicle. t-3Δt y t-3Δt ).

[0052] In summary, (x t yt ), (x t-Δt y t-Δt ), (x t-2Δt y t-2Δt ), (x t-3Δt y t-3Δt These constitute the aforementioned multiple relative position data.

[0053] Step S106: Perform linear fitting on multiple relative position data to obtain the target driving trajectory of the second vehicle;

[0054] Step S108: Control the first vehicle to drive based on the target driving trajectory.

[0055] Step S108 includes:

[0056] Based on the current position, driving direction, and target driving trajectory of the first vehicle, the first lateral error and the first deflection error are determined; based on preset calibration parameters, the first lateral error and the first deflection error are processed by proportional-integral-differential to obtain the target deflection angle; based on the target deflection angle and the second driving data, the first vehicle is controlled to drive according to the target driving trajectory.

[0057] Specifically, the linear fitting described above is a type of curve fitting. Let x and y be the observed quantities, and y be a function of x: y = f(x; b). Curve fitting seeks the best estimate of parameter b through the observed values ​​of x and y, and thus seeks the best theoretical curve y = f(x; b).

[0058] The target driving trajectory mentioned above, which is the target driving trajectory of the second vehicle obtained by fitting the above-mentioned multiple relative position data, can be expressed as: Y 前车目标 =C3*x 3 +C2*x 2 +C1*x+C0, where Y 前车目标 C1 is the ordinate of the second vehicle's position relative to the first vehicle, C2, C1, and C0 are the curve parameters of the target driving trajectory, and x is the abscissa of the second vehicle's position relative to the first vehicle.

[0059] The aforementioned first lateral error can be understood as the difference between the target trajectory and the trajectory of the first vehicle. It reflects the lateral error between the trajectory of the first vehicle and the target trajectory.

[0060] The aforementioned first deflection error can be understood as the angle between the tangent direction of the first vehicle's location at a certain historical moment and the tangent direction of the second vehicle's location at that moment. It reflects the deflection angle error between the first vehicle's travel direction and the travel direction of the target trajectory (i.e., the travel direction of the second vehicle).

[0061] The aforementioned preset calibration parameters can be understood as pre-set calculation parameters in the vehicle's dual PI (Proportional Integral) controller module, used to continuously correct the lateral error and deflection error input to the dual PI controller module, so that the lateral error and deflection error gradually decrease to 0, that is, the first vehicle is allowed to follow the target driving trajectory of the second vehicle, thereby realizing lateral control of the vehicle during the driving process.

[0062] The target deflection angle mentioned above is obtained by performing integral and differential processing on the first deflection error through the proportional-integral-derivative algorithm embedded in the dual-PI controller module. The result is used to perform lateral control of the deflection angle of the first vehicle.

[0063] In addition, by using the proportional-integral-derivative algorithm embedded in the dual-PI controller module to perform integral-derivative processing on the first lateral error, the corresponding target control torque can be obtained, which can be used to perform torque lateral control on the first vehicle.

[0064] In one optional embodiment, after determining the target driving trajectory of the second vehicle and simultaneously determining that the second vehicle meets stable following conditions, the lateral control system of the first vehicle can be activated. Then, based on the target driving trajectory, the lateral position error Δd and the orientation error Δθ in the equation of the first vehicle and the target driving trajectory at the current moment can be calculated. After obtaining the lateral position error Δd and the orientation error Δθ, they can be input into the vehicle's dual PI controller module to calculate the target control angle or torque. Then, the target control angle or torque of the steering wheel of the first vehicle is sent to the vehicle to control automatic lateral driving.

[0065] The specific formula for calculating the target control angle can be expressed as:

[0066]

[0067] Where, θ target To control the turning angle for the target, K p1 K 11 K represents the proportional and integral coefficients of the lateral position error. p2 K 12 These are the proportional coefficient and integral coefficient for the lateral orientation error, respectively. Where K... p1 K 11 K p2 K 12 Both θ and t are parameters used in the later calibration of the control algorithm. (When the target control input is torque, only θ...) target Simply replace it with the target torque.

[0068] Figure 2This is a flowchart of a control algorithm for a vehicle control method according to an embodiment of the present invention, such as... Figure 2 As shown:

[0069] S11 uses cameras to collect data on the road environment for vehicles;

[0070] S12, deep learning is performed on the acquired images to determine lane line information and perceive target information (which can be understood as the driving data of the second vehicle);

[0071] S13, after determining the vehicle's steering information, throttle information, lateral control system fault information, lane line information, perceived target information, and vehicle position information (coordinates x=0, y=0), determine whether the lane lines on both sides are clear or whether the lane lines on one side are clear.

[0072] S14. When the lane lines on both sides are clear or the lane lines on one side are clear, the corresponding target trajectory equation can be determined.

[0073] S15. When the lane markings on both sides are clear, or the lane markings on one side are unclear, it is necessary to determine whether the first vehicle and the following target (i.e., the second vehicle) are driving stably.

[0074] S16, under the condition that the first vehicle and the following target (i.e. the second vehicle) are driving stably, the corresponding target trajectory equation can be determined;

[0075] S17, in the event that the first vehicle and the following target (i.e. the second vehicle) are driving unstably, the vehicle's lateral control system can be disengaged.

[0076] S18, through the target trajectory equation, can activate the vehicle's lateral control system;

[0077] S19, based on the target trajectory equation of lateral control, calculate the lateral error (i.e., lateral position error Δd) and angle error (i.e., orientation error Δθ) between the vehicle and the target trajectory equation.

[0078] S20, input the lateral error and angular error into the PID (Proportion Integration Differential) controller (same as the dual PI controller mentioned above) for integral and derivative processing;

[0079] S21, the PID controller outputs the processing result, including the target torque or target angle, and generates lateral control commands based on the target torque or target angle to control the vehicle's automatic lateral movement.

[0080] In summary, by acquiring images of the road ahead using the vehicle's front camera and processing them through perception algorithms, information on lane lines and obstacles / vehicles ahead is obtained. Using information on lane lines on both sides, the trajectory of obstacles / vehicles ahead, the vehicle's position, and its steering, speed, and acceleration information, a lateral control algorithm is used to calculate the target turning angle or target torque that the vehicle should have at that moment. This activates the vehicle's automatic lateral control function, ensuring that the vehicle travels along the lane lines in the lateral direction or follows the target vehicle in front, thus ensuring driving safety.

[0081] Optionally, based on the first driving data and the second driving data, the relative position data between the position of the second vehicle at multiple different historical moments and the current position of the first vehicle is determined. Step S104 includes:

[0082] Based on the first driving data, determine the first position of the first vehicle at multiple different historical times; establish multiple first coordinate systems with the multiple first positions as the origin and the driving direction of the first vehicle as the first horizontal axis; based on the second driving data, determine the second position of the second vehicle at multiple different historical times, wherein the second position at multiple different historical times is used to characterize the position of the second vehicle in the first coordinate system corresponding to the multiple different historical times; based on the first position, the second position, and the current position of the first vehicle, determine the relative position data.

[0083] Specifically, the aforementioned first position can be understood as the position of the first vehicle at different historical times, including the position of the first vehicle at the current time t, the position at the historical time t-Δt, the position at the historical time t-2Δt, and the position at the historical time t-3Δt.

[0084] The aforementioned multiple first coordinate systems are constructed by taking the positions at time t, t-Δt, t-2Δt, and t-3Δt as the origin, the driving direction of the first vehicle as the longitudinal position coordinate x, and the coordinate perpendicular to the longitudinal position coordinate x as the lateral position coordinate y.

[0085] The aforementioned second position can be understood as the position of the second vehicle at multiple different historical moments, including the position of the second vehicle at the current time t, the position at the historical time t-Δt, the position at the historical time t-2Δt, and the position at the historical time t-3Δt.

[0086] In one optional embodiment, a first coordinate system can be constructed using the position of the first vehicle at the current time t (the current position of the first vehicle) as the origin. Simultaneously, the position of the first vehicle at a historical time t-Δt is determined as a first position, and the coordinates of the first position are mapped to the constructed first coordinate system. Similarly, the position of the second vehicle at a historical time t-Δt is determined as a second position, and the coordinates of the second position are mapped to the constructed first coordinate system. Therefore, based on the origin of the first coordinate system, the coordinates of the first position, and the coordinates of the second position, the relative position of the second vehicle with respect to the first vehicle at historical time t-Δt can be determined.

[0087] The aforementioned relative position data can be understood as the position data of the second vehicle relative to the first vehicle at various historical moments, determined based on multiple pre-constructed first coordinate systems. Specifically, it includes, but is not limited to, the offset angle and relative distance of the second vehicle relative to the first vehicle.

[0088] Figure 3 This is a schematic diagram of the vehicle coordinate system according to an embodiment of the present invention. Figure 3 As shown, the driving direction of the vehicle (i.e., the first vehicle) is used as the x-axis to construct the vehicle coordinate system. O is the coordinate value of the vehicle (0,0), and A is the coordinate value of the target vehicle (i.e., the second vehicle) (x,y).

[0089] Figure 4 This is a schematic diagram illustrating the target vehicle coordinate information at four time points according to an embodiment of the present invention. Figure 4 As shown, four coordinate values ​​of the target vehicle are recorded. Because the coordinates of the vehicle in front are based on the vehicle's coordinate system at each moment, and the vehicle is moving, the coordinates of the target vehicle are recorded in four coordinate systems at four different moments:

[0090] Record the current coordinates of the vehicle (O, 0) and the target vehicle (A, y) in the xy coordinate system.

[0091] Record the coordinates of the vehicle in the first 250ms (i.e., t-Δt) as O1(0,0) and the coordinates of the target vehicle in front as A1(x1,y1), with the coordinate system being x1y1;

[0092] Record the coordinates of the vehicle in the first 500ms (i.e., t-2Δt) as O2((0,0) and the coordinates of the target vehicle in front as A2(x2,y2), with the coordinate system being x2y2;

[0093] Record the coordinates of the vehicle in front of it (O3(0,0)) and the coordinates of the target vehicle in front (A3(x3,y3)) in the first 750ms (t-3Δt), with the coordinate system being x3y3.

[0094] By rendering the position data of the second vehicle relative to the first vehicle at multiple different historical moments into the first coordinate system, the relative position data of the second vehicle at multiple different historical moments and the current position of the first vehicle can be clearly determined, which facilitates further data fitting processing.

[0095] Optionally, relative position data is determined based on the first position, the second position, and the current position of the first vehicle, including: establishing a second coordinate system with the current position as the origin and the driving direction as the second horizontal axis; determining a first position vector based on the current position and the first position, and determining a second position vector based on the first position and the second position, wherein the first position vector is used to characterize the position change of the first vehicle at different historical moments, and the second position vector is used to characterize the relative position change of the first vehicle and the second vehicle at multiple different historical moments; determining a third position vector based on the vector sum of the first position vector and the second position vector, wherein the third position vector is used to characterize the relative position change of the second vehicle at multiple different historical moments and the current position of the first vehicle; and transforming the third position vector from the first coordinate system to the second coordinate system to determine the relative position data.

[0096] Specifically, the aforementioned second coordinate system is a second coordinate system constructed by taking the current position of the first vehicle as the origin and the driving direction of the first vehicle as the second horizontal axis.

[0097] The first position vector mentioned above can be understood as the change in position of the first vehicle at historical time t-Δt relative to the current time t. It should be noted that the different historical times mentioned above include, but are not limited to, historical time t-Δt; this explanation only uses historical time t-Δt as an example.

[0098] The aforementioned second position vector can be understood as the change in the position of the second vehicle at historical time t-Δt relative to the position of the first vehicle at historical time t-Δt.

[0099] The third position vector mentioned above is the result of summing the first and second position vectors. It reflects the change in the position of the second vehicle at historical time t-Δt relative to the position of the first vehicle at the current time t.

[0100] By performing coordinate data transformation on the third position vector, the position data of the second vehicle relative to the first vehicle at the historical time t-Δt can be determined.

[0101] Figure 5 This is a schematic diagram illustrating coordinate information transformation according to an embodiment of the present invention, specifically a vehicle control method. Figure 5As shown, the coordinate information of the preceding vehicle at the previous 250ms, 500ms, and 750ms times is uniformly transformed into coordinate information based on the current vehicle's position. Specifically, the coordinates A(x1, y1) based on the x1y1 coordinate system at the previous 250ms time are transformed into coordinates (x, y1) based on the current xy coordinate system. 250ms y 250ms Taking the vehicle as an example, based on the current vehicle speed v and yaw rate ω, the predicted trajectory equation is (assuming the vehicle is in constant curvature circular motion at this moment). If the vehicle speed is v and the yaw rate is ω, then the vehicle's trajectory at the current moment is: Based on the vehicle's longitudinal speed multiplied by -250ms, the preceding... Then the coordinates of the origin relative to the current time point are: This yields the coordinate transformation vector OO1 and the coordinate rotation angle θ. The vector O1A of the target vehicle relative to the x1y1 coordinate system at the previous 250ms is transformed into a vector OA relative to the current xy coordinate system by rotating the vector by angle θ. Adding vector OO1 to vector O1A yields the target vehicle's coordinates (x, y, y) relative to its own vehicle at the previous 250ms. 250ms y 250ms Similarly, the coordinates (x, y) of the first 500ms and the first 750ms based on the current xy coordinate system are obtained. 500ms y 500ms ), (x 750ms y 750ms ).

[0102] In summary, by using the vector method to transform the coordinates of the position data of the second vehicle relative to the first vehicle at different historical moments, the relative position data can be accurately determined, which facilitates subsequent fitting of the relative position data.

[0103] Optionally, the method further includes: in response to the lane line information being invalid data and the second vehicle not meeting preset conditions, pushing a first prompt message to the user, wherein the first prompt message is used to prompt the user that the first vehicle has exited the lateral automatic control function; and in response to the lane line information being valid data, controlling the first vehicle to drive based on the lane line trajectory.

[0104] Specifically, the aforementioned invalid data can be understood as the absence of lane markings on the road ahead of the first vehicle, or the existing lane markings being unclear and unable to support the vehicle's automatic lane keeping function.

[0105] The aforementioned first notification message is used to prompt the user that the first vehicle has exited the lateral automatic control function.

[0106] In one optional embodiment, an image acquisition device can be used to acquire the road environment ahead of the first vehicle, resulting in an environmental image. A deep learning algorithm is then used to learn from the environmental image, yielding lane line information and obstacle information ahead of the first vehicle. If the lane line information is invalid and the second vehicle does not meet the stable following target, the first vehicle cannot perform lateral automatic control. Therefore, the driving control module of the first vehicle needs to push a first prompt message to the user, instructing the user to disengage the lateral automatic control function. Conversely, if the lane line information is valid (i.e., both lane lines are available, or one lane line is valid), lateral control of the first vehicle can be performed based on the lane line information (lane line trajectory).

[0107] Optionally, in response to the lane line information being valid data, controlling the first vehicle to drive based on the lane line trajectory of the lane lines includes: acquiring valid flag bits corresponding to the lane line information on both sides of the first vehicle, wherein the valid flag bits are used to indicate whether the lane line information on both sides is valid data; in response to the valid flag bits indicating that the lane line information on both sides is valid data, controlling the first vehicle to drive based on the center line of the lane line trajectory in the lane line information on both sides; in response to the valid flag bits indicating that the lane line information on either side is valid data, controlling the first vehicle to drive based on the lane line trajectory in the lane line information on either side and the width of the driving road.

[0108] In response to the valid flag indicating that lane line information on either side is valid data, the method further includes: in response to the failure to obtain the width of the driving road, controlling the first vehicle to drive based on a preset control distance and the lane line trajectory in the lane line information on either side.

[0109] Specifically, the aforementioned valid markers can be used to indicate whether the lane line information on both sides is valid data, that is, whether the lane lines exist and are clearly visible.

[0110] The aforementioned preset control distance can be understood as the safe driving distance between vehicles (including the safe driving distance between vehicles in front and behind, and between vehicles on the left and right) that is preset in the vehicle driving system.

[0111] In one optional embodiment, the lane line information on both sides of the road ahead of the first vehicle is valid data, meaning the lane lines on both sides exist and are clearly visible. The centerline of the lane line trajectory in the lane line information on both sides can be determined, and the movement of the first vehicle can be controlled accordingly. Specifically, if both lane lines are available, the equation of the left lane line is: Y 左 =C3*x 3 +C2*x 2 +C1*x+C0, the equation for the right side of the lane line is: Y 右 =C3*x 3+C2*x 2 +C1*x+C0, therefore, the center line of the target trajectory Then it can be done through y 中心线 Control the movement of the first vehicle.

[0112] In another optional embodiment, lane line information on either side of the road ahead of the first vehicle is considered valid data; that is, only the left or right lane line is valid. This allows determination of the lane line trajectory and road width on either side, thereby controlling the first vehicle's movement. Specifically, if only the left lane line is detected, then... Conversely, if only the right-hand single lane line is detected, then Where L is half the lane width, typically 1.8m.

[0113] In a third alternative embodiment, if the lane line information on any side of the road in front of the first vehicle is valid data, but the width of the driving road cannot be obtained, the first vehicle can be controlled by the safe driving distance between vehicles and the known lane line trajectory on any side.

[0114] Example 2

[0115] According to an embodiment of the present invention, a vehicle control device is also provided, which can execute a vehicle control method provided in Embodiment 1 above. The specific implementation method and preferred application scenario are the same as those in Embodiment 1 above, and will not be repeated here.

[0116] Figure 6 This is a schematic diagram of a vehicle control device according to an embodiment of the present invention, such as... Figure 6 As shown, the device includes:

[0117] The first acquisition module 602 is used to acquire first driving data of the first vehicle and road information of the road on which the first vehicle is traveling. The first driving data includes at least the following: the road information includes at least lane line information drawn on the road, and the second driving data of the second vehicle that is adjacent to the first vehicle and traveling in front of the first vehicle.

[0118] The location data determination module 604 is used to determine the relative position data of the second vehicle at multiple different historical times and the current position of the first vehicle based on the first driving data and the second driving data in response to the lane line information being invalid data and the second vehicle meeting the first preset condition. The first preset condition is used to indicate that the first vehicle is allowed to follow the second vehicle.

[0119] The driving trajectory fitting module 606 is used to perform linear fitting on multiple relative position data to obtain the target driving trajectory of the second vehicle.

[0120] The vehicle control module 608 is used to control the movement of the first vehicle based on the target driving trajectory.

[0121] Optionally, the position data determination module 604 includes: a first position determination module, used to determine the first position of the first vehicle at multiple different historical times based on the first driving data; a coordinate system construction unit, used to establish multiple first coordinate systems with the multiple first positions as coordinate origins and the driving direction of the first vehicle as the first horizontal axis; a second position determination module, used to determine the second position of the second vehicle at multiple different historical times based on the second driving data, wherein the second position at multiple different historical times is used to characterize the position of the second vehicle in the first coordinate system corresponding to the multiple different historical times; and a relative position determination module, used to determine relative position data based on the first position, the second position, and the current position of the first vehicle.

[0122] Optionally, the relative position determination module includes: a coordinate system construction unit, used to establish a second coordinate system with the current position as the origin and the driving direction as the second horizontal axis; a position vector determination unit, used to determine a first position vector based on the current position and a first position, and to determine a second position vector based on the first position and a second position, wherein the first position vector is used to characterize the position change of the first vehicle at different historical moments, and the second position vector is used to characterize the relative position change of the first vehicle and the second vehicle at multiple different historical moments; a third position vector determination unit, used to determine a third position vector based on the vector sum of the first position vector and the second position vector, wherein the third position vector is used to characterize the relative position change of the second vehicle at multiple different historical moments with respect to the current position of the first vehicle; and a relative position determination unit, used to transform the third position vector from the first coordinate system to the second coordinate system to determine the relative position data.

[0123] Optionally, the vehicle control module 608 includes: an error determination unit, used to determine a first lateral error and a first deflection error based on the current position, driving direction and target driving trajectory of the first vehicle; a data processing unit, used to perform proportional-integral-differential processing on the first lateral error and the first deflection error based on preset calibration parameters to obtain a target deflection angle; and a vehicle control unit, used to control the first vehicle to drive according to the target driving trajectory based on the target deflection angle and second driving data.

[0124] Optionally, the device further includes: a message push module, used to push a first prompt message to the user in response to invalid lane line information and the second vehicle not meeting preset conditions, wherein the first prompt message is used to prompt the user that the first vehicle exits the lateral automatic control function; and a vehicle control module, used to control the first vehicle to drive based on the lane line trajectory in response to valid lane line information.

[0125] Optionally, the vehicle control module includes: a marker acquisition module, used to acquire valid markers corresponding to lane line information on both sides of the first vehicle, wherein the valid markers are used to indicate whether the lane line information on both sides is valid data; a first valid data determination module, used to control the first vehicle to drive based on the centerline of the lane line trajectory in the lane line information on both sides in response to the valid markers indicating that the lane line information on both sides is valid data; and a second valid data determination module, used to control the first vehicle to drive based on the lane line trajectory in the lane line information on either side and the width of the driving road in response to the valid markers indicating that the lane line information on either side is valid data.

[0126] Optionally, the second valid data determination module includes: a vehicle driving control module, used to control the driving of the first vehicle based on a preset control distance and the lane line trajectory in the lane line information on any one side in response to the failure to obtain the width of the driving road.

[0127] Example 3

[0128] According to an embodiment of the present invention, a vehicle is also provided, including one or more processors and a storage device, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to perform the vehicle control method described above.

[0129] Example 4

[0130] According to an embodiment of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to execute the above-described vehicle control method.

[0131] Example 5

[0132] According to an embodiment of the present invention, a processor is also provided, which is used to run a program, wherein the program executes the vehicle control method described above when it runs.

[0133] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0134] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0135] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0136] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0137] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0138] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0139] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A vehicle control method, characterized in that, The method includes: Acquire first driving data of a first vehicle and road information of the road on which the first vehicle is traveling, wherein the first driving data includes at least: the road information includes at least lane line information drawn on the road, and second driving data of a second vehicle that is adjacent to and in front of the first vehicle. In response to the lane line information being invalid data and the second vehicle meeting the first preset condition, based on the first driving data and the second driving data, the relative position data of the second vehicle at multiple different historical moments and the current position of the first vehicle is determined, wherein the first preset condition is used to indicate that the first vehicle is allowed to follow the second vehicle. By performing linear fitting on multiple relative position data, the target driving trajectory of the second vehicle is obtained; The first vehicle is controlled to drive based on the target driving trajectory; The method of controlling the first vehicle to travel based on the target travel trajectory includes: determining a first lateral error and a first deflection error based on the current position, travel direction, and target travel trajectory of the first vehicle; performing proportional-integral-differential processing on the first lateral error and the first deflection error based on preset calibration parameters to obtain a target deflection angle; and controlling the first vehicle to travel according to the target travel trajectory based on the target deflection angle and the second travel data.

2. The method according to claim 1, characterized in that, Based on the first driving data and the second driving data, the relative position data between the position of the second vehicle at multiple different historical moments and the current position of the first vehicle is determined, including: The first position of the first vehicle at the multiple different historical moments is determined based on the first driving data. Multiple first coordinate systems are established with multiple first positions as coordinate origins and the driving direction of the first vehicle as the first horizontal axis; Based on the second driving data, the second position of the second vehicle at the multiple different historical times is determined, wherein the second position at the multiple different historical times is used to characterize the position of the second vehicle in the first coordinate system corresponding to the multiple different historical times; The relative position data is determined based on the first position, the second position, and the current position of the first vehicle.

3. The method according to claim 2, characterized in that, Based on the first location, the second location, and the current location of the first vehicle, the relative position data is determined, including: A second coordinate system is established with the current position as the origin and the driving direction as the second horizontal axis; A first position vector is determined based on the current position and the first position, and a second position vector is determined based on the first position and the second position, wherein the first position vector is used to characterize the position change of the first vehicle at different historical times, and the second position vector is used to characterize the relative position change of the first vehicle and the second vehicle at the multiple different historical times; Based on the vector sum of the first position vector and the second position vector, a third position vector is determined, wherein the third position vector is used to characterize the relative position change of the second vehicle at the multiple different historical times with the current position of the first vehicle. The third position vector is transformed from the first coordinate system to the second coordinate system to determine the relative position data.

4. The method according to claim 1, characterized in that, The preset conditions include at least one of the following: Within a preset time period, the longitudinal distance between the second vehicle and the first vehicle is less than a first distance threshold, wherein the longitudinal direction is used to characterize the driving direction of the first vehicle; Within the preset time period, the lateral distance between the second vehicle and the first vehicle is less than the second distance threshold. Within the preset time period, the lateral relative speed between the second vehicle and the first vehicle is less than the first speed threshold.

5. The method according to claim 1, characterized in that, The method further includes: In response to the lane line information being invalid data and the second vehicle not meeting the preset conditions, a first prompt message is pushed to the user, wherein the first prompt message is used to prompt the user that the first vehicle has exited the lateral automatic control function; In response to the lane line information being valid data, the first vehicle is controlled to move based on the lane line trajectory.

6. The method according to claim 5, characterized in that, In response to the lane line information being valid data, based on the lane line trajectory, controlling the first vehicle's movement includes: Obtain valid flag bits corresponding to the lane line information on both sides of the first vehicle, wherein the valid flag bits are used to characterize whether the lane line information on both sides is valid data; In response to the valid flag indicating that the lane line information on both sides is valid data, the first vehicle is controlled to drive based on the centerline of the lane line trajectory in the lane line information on both sides. In response to the valid flag indicating that lane line information on either side is valid data, the first vehicle is controlled to move based on the lane line trajectory in the lane line information on either side and the width of the driving road.

7. The method according to claim 6, characterized in that, In response to the condition that the lane line information on either side is valid data, the method further includes: In response to the failure to obtain the width of the driving road, the first vehicle is controlled to drive based on a preset control distance and the lane line trajectory in the lane line information on either side.

8. A vehicle control device, characterized in that, The device includes: The first acquisition module is used to acquire first driving data of a first vehicle and road information of the road on which the first vehicle is traveling. The first driving data includes at least the following: the road information includes at least lane line information drawn on the road; and second driving data of a second vehicle that is adjacent to the first vehicle and traveling in front of the first vehicle. The location data determination module is used to respond to the lane line information being invalid data and the second vehicle meeting a first preset condition, and to determine the relative position data of the second vehicle at multiple different historical moments and the current position of the first vehicle based on the first driving data and the second driving data, wherein the first preset condition is used to indicate that the first vehicle is allowed to follow the second vehicle. The driving trajectory fitting module is used to perform linear fitting on multiple relative position data to obtain the target driving trajectory of the second vehicle. The vehicle control module is used to control the driving of the first vehicle based on the target driving trajectory; The vehicle control module is further configured to determine a first lateral error and a first deflection error based on the current position, driving direction, and target driving trajectory of the first vehicle; perform proportional-integral-differential processing on the first lateral error and the first deflection error based on preset calibration parameters to obtain a target deflection angle; and control the first vehicle to drive according to the target driving trajectory based on the target deflection angle and the second driving data.

9. A vehicle, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 7.

Images