Path tracking method, device, vehicle and storage medium

Abstract

The present application discloses a path tracking method, device, vehicle and storage medium. The method includes: obtaining the actual driving parameters of the vehicle; obtaining the path information of the planned path, the path information including the curvature of the target path point in the planned path, the target path point being determined based on the current position of the vehicle; determining a first reference point based on the actual driving parameters and the curvature of the target path point; searching for p second reference points in the planned path based on the first reference point; determining lateral control parameters and longitudinal control parameters based on the first reference point and the p second reference points; controlling the vehicle driving based on the lateral control parameters and the longitudinal control parameters to achieve tracking of the planned path. The technical solution provided by the embodiment of the present application introduces a curvature term when selecting a reference point, so that the selection of the reference point matches the actual working condition of the road, optimizes the path tracking effect, and improves riding comfort.

Description

Technical Field

[0001] The present application relates to the field of path tracking technology, and in particular to a path tracking method, device, vehicle, and storage medium. Background Art

[0002] Path tracking technology is a key technology in the research direction of unmanned driving. It refers to the control technology that enables the vehicle to drive safely and stably along the preset path.

[0003] The path tracking solution provided by the related technology is as follows: first obtain the current position of the vehicle, then select a foresight point in the planned path based on the current position of the vehicle, and then calculate the lateral deviation and longitudinal deviation based on the foresight point and the current position of the vehicle. Then, the vehicle is controlled based on the above lateral deviation and longitudinal deviation to correct the deviation between the vehicle's driving path and the planned path.

[0004] In related technologies, the actual road conditions are not considered when selecting the foresight point, which results in the calculated lateral and longitudinal deviations not being consistent with the actual situation. This ultimately leads to a large deviation between the vehicle's driving path and the planned path, resulting in poor path tracking results. Summary of the Invention

[0005] The present application proposes a path tracking method, device, vehicle, and storage medium.

[0006] In a first aspect, an embodiment of the present application provides a path tracking method, which is applied to a vehicle, and the method includes: obtaining actual driving parameters of the vehicle, the actual driving parameters of the vehicle include the current position of the vehicle; obtaining path information of a planned path, the path information includes the curvature of a target path point in the planned path, and the target path point is determined based on the current position of the vehicle; determining a first reference point based on the actual driving parameters and the curvature of the target path point; searching for p second reference points in the planned path based on the first reference point, where p is an integer greater than 1, the distance between the i-th second reference point and the first reference point is less than the distance between the i+1-th second reference point and the first reference point, and i is less than or equal to p-1; determining lateral control parameters and longitudinal control parameters based on the p second reference points, the lateral control parameters being used to characterize the lateral deviation between the actual driving path of the vehicle and the planned path, and the longitudinal control parameters being used to characterize the longitudinal deviation between the actual driving path of the vehicle and the planned path; controlling vehicle driving based on the lateral control parameters and the longitudinal control parameters to achieve tracking of the planned path.

[0007] In a second aspect, an embodiment of the present application provides a path tracking device, which includes: a first acquisition module for acquiring actual driving parameters of a vehicle, the actual driving parameters of the vehicle including the current position of the vehicle; a second acquisition module for acquiring path information of a planned path, the path information including the curvature of a target path point in the planned path, the target path point being determined based on the current position of the vehicle; a reference point determination module for determining a first reference point based on the actual driving parameters and the curvature of the target path point; a reference point search module for searching for p second reference points in the planned path based on the first reference point, where p is an integer greater than 1, the distance between the i-th second reference point and the first reference point is less than the distance between the i+1-th second reference point and the first reference point, and i is less than or equal to p-1; a parameter determination module for determining lateral control parameters and longitudinal control parameters based on the p second reference points, the lateral control parameters being used to characterize the lateral deviation between the actual driving path of the vehicle and the planned path, and the longitudinal control parameters being used to characterize the longitudinal deviation between the actual driving path of the vehicle and the planned path; and a path tracking module for controlling vehicle driving based on the lateral control parameters and the longitudinal control parameters to achieve tracking of the planned path.

[0008] In a third aspect, an embodiment of the present application provides a vehicle comprising: one or more processors; a memory; and one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to execute the path tracking method as described in the first aspect.

[0009] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer program instructions are stored. The computer program instructions can be called by a processor to execute the method of the first aspect.

[0010] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when executed, is used to implement the path tracking method as described in the first aspect.

[0011] Compared with the existing technology, the path tracking method provided in the embodiment of the present application introduces a curvature term when selecting a reference point, so that the selection of the reference point matches the actual working condition of the road. The lateral deviation and longitudinal deviation calculated subsequently are also in line with the actual situation, effectively reducing the deviation between the vehicle's driving path and the planned path, and reducing the probability of the vehicle drawing a dragon and turning inward due to unreasonable selection of path reference points. Ultimately, the robustness and stability of the path tracking solution are improved, the path tracking effect is optimized, and the ride comfort is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 It is a schematic diagram of the implementation environment provided by the embodiment of the present application.

[0014] Figure 2 This is a structural block diagram of the console provided in an embodiment of the present application.

[0015] Figure 3 This is a flowchart of a path tracking method provided by an embodiment of the present application.

[0016] Figure 4 This is a flowchart of a path tracking method provided by another embodiment of the present application.

[0017] Figure 5 This is a flowchart of a path tracking method provided by another embodiment of the present application.

[0018] Figure 6 This is a schematic diagram of longitudinal control provided by another embodiment of the present application.

[0019] Figure 7 This is a structural block diagram of a path tracking device provided by an embodiment of the present application.

[0020] Figure 8 This is a structural block diagram of a vehicle provided in one embodiment of the present application.

[0021] Figure 9 This is a structural block diagram of a computer storage medium provided by an embodiment of the present application. DETAILED DESCRIPTION

[0022] The embodiments of the present application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application and are not to be construed as limiting the present application.

[0023] In order to enable those skilled in the art to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0024] After extensive research, the inventors discovered that when implementing path tracking solutions in related technologies, the actual road conditions were not taken into account. This resulted in the calculated lateral and longitudinal deviations being inconsistent with the actual conditions, ultimately causing the vehicle's driving path to deviate significantly from the planned path and resulting in poor path tracking. For example, when a vehicle is traveling on a curve, the lack of constraints on the angular velocity of the corners results in severe "dragging" (a phenomenon known as "dragging"), resulting in poor ride comfort. The "dragging" phenomenon refers to the phenomenon in which a vehicle deviates from a straight track and veers to the left or right.

[0025] Based on the above problems, the inventors of this application designed a path tracking solution, which introduces a curvature term when selecting a reference point, so that the selection of the reference point matches the actual working conditions of the road, and the subsequently calculated lateral deviation and longitudinal deviation also conform to the actual situation, effectively reducing the deviation between the vehicle's driving path and the planned path, and reducing the probability of the vehicle's dragon-drawing phenomenon and inward-cutting phenomenon caused by unreasonable selection of path reference points, ultimately improving the robustness and stability of the path tracking solution, optimizing the path tracking effect, and improving riding comfort.

[0026] Please refer to Figure 1 , which shows a schematic diagram of an implementation environment for one embodiment of the present application. This implementation environment includes a vehicle 100. Vehicle 100 refers to a vehicle driven or towed by a power unit for passengers or for transporting goods. Vehicle 100 can be an electric vehicle, a fuel vehicle, a hybrid vehicle, etc., and this embodiment of the present application is not limited to this. In this application, vehicle 100 includes a body 110 and a console 120.

[0027] The control console 120 is the control center of the vehicle 100, responsible for processing data and information acquired during driving and generating control commands for controlling the vehicle body 110. In this embodiment of the present application, the control console 120 acquires the posture and curvature of multiple reference points in the planned path, and designs a multi-reference-point curvature feedforward control and an error-based wheel angle feedback control. This effectively reduces vehicle swerves in straight lines and understeer in curves. Furthermore, the vehicle's multiple forward-looking reference points significantly enhance its stability and comfort during driving.

[0028] Combined with reference Figure 2 , which shows a structural block diagram of the console 120 provided by an embodiment of the present application. Figure 2 In the embodiment, the console 120 includes a path planning module 121 , a positioning module 122 , a path tracking module 123 , and a transverse and longitudinal control module 124 .

[0029] The path planning module 121 is used to output the path information of the planned path, which includes the path point parameters of multiple path points in the planned path, and the above-mentioned path point parameters include but are not limited to: horizontal coordinates, vertical coordinates, speed, azimuth and curvature, etc. The path planning module 121 can formulate a planned path based on the path starting point (that is, the current position of the vehicle 100), the path end point, the road conditions between the path starting point and the path end point (including but not limited to speed limit information, traffic light location information, congestion information, obstacle information, etc.), the owner's driving habit information, etc. The algorithm used by the path planning module 121 to formulate the planned path includes but is not limited to: heuristic search, bidirectional search algorithm, ant colony algorithm, Dijkstra algorithm, etc., and the embodiments of the present application do not limit this.

[0030] The positioning module 122 is used to obtain the positioning information of the vehicle 100. In an embodiment of the present application, the positioning module 122 includes a global navigation satellite system (GPSS). GPSS is a high-precision radio navigation positioning system based on artificial earth satellites, which can provide the vehicle 100 with an accurate actual position anywhere in the world and in near-Earth space. In other embodiments, the positioning module 120 also includes an inertial measurement unit (IPU). The IPU is a device that measures the three-axis attitude angle (or angular rate) and acceleration of the vehicle 100. In the present application, the IPU is used to obtain the attitude information of the vehicle, for example, the actual heading angle of the vehicle.

[0031] In an embodiment of the present application, the path tracking module 123 is used to determine the lateral control parameters and longitudinal control parameters of the vehicle based on the planned path and the actual driving conditions of the vehicle 100. The subsequent lateral and longitudinal control modules 124 control the vehicle 100 according to the above lateral control parameters and longitudinal control parameters, so that the vehicle 100 travels according to the planned path (that is, to track the planned path), thereby achieving autonomous driving above the L4 level.

[0032] The lateral and longitudinal control module 124 is used to control the vehicle 100 based on the lateral and longitudinal control parameters. Specifically, the lateral and longitudinal control module 124 determines the vehicle's throttle control, brake control, and steering wheel angle control based on the lateral and longitudinal control parameters, and controls the vehicle 100 based on these control variables. In some embodiments, the lateral and longitudinal control module 124 includes a lateral control submodule and a longitudinal control submodule. The lateral control submodule can implement lateral control of the vehicle 100, while the longitudinal control submodule can implement longitudinal control of the vehicle 100.

[0033] In some embodiments, the vehicle body 110 further includes a detection module, which is used to detect environmental information of the vehicle 100. Optionally, the above-mentioned detection module includes but is not limited to: a lidar, an ultrasonic radar, a surround-view camera, etc. The surround-view camera is a wide-angle camera used to obtain environmental images outside the vehicle 100. An ultrasonic sensor is a sensor that converts ultrasonic signals into other energy signals (for example, electrical signals). A lidar is a radar system that uses laser signals to detect obstacles. In an embodiment of the present application, a surround-view camera, an ultrasonic sensor, and a lidar are used to detect whether there are obstacles on the vehicle's driving path, so as to facilitate the path planning module 121 to formulate a safer planned path.

[0034] Please refer to Figure 3 , which shows a flow chart of a path tracking method provided by an embodiment of the present application. The method includes the following steps S301-S306.

[0035] Step S301: Acquire actual driving parameters of the vehicle.

[0036] The actual driving parameters of the vehicle include the vehicle's current position. In some embodiments, the vehicle's current position is represented by the vehicle's coordinates in a geodetic coordinate system, which can be directly obtained by the positioning module. The geodetic coordinate system is a coordinate system established using a reference ellipsoid as a reference surface in geodetic surveying. The vehicle's coordinates in the geodetic coordinate system include two coordinate values, x and y, where x represents the vehicle's longitude in the geodetic coordinate system and y represents the vehicle's latitude in the geodetic coordinate system.

[0037] In some embodiments, the actual driving parameters of the vehicle also include the vehicle's speed. Optionally, a speed sensor is provided on the vehicle's body, and the vehicle's speed is measured by the speed sensor. In some embodiments, the actual driving parameters of the vehicle also include the vehicle's heading angle, which refers to the angle between the vehicle's center of mass velocity and the horizontal axis in the geodetic coordinate system. Optionally, the vehicle's heading angle is measured by an inertial measurement unit.

[0038] For example, the vehicle obtains its actual driving parameters [x, y, v, ψ] t, which is the vehicle's horizontal coordinate (x), vertical coordinate (y), speed (v), and heading angle (ψ) at time t. Time t is the current time.

[0039] Step S302: Acquire path information of the planned path.

[0040] Path information includes path point parameters for multiple path points in the planned path. These path point parameters include abscissa, ordinate, speed, azimuth, and curvature. The distance between any two adjacent path points in the multiple path points may or may not be fixed.

[0041] The horizontal coordinate is the x-axis coordinate value of the path point in the geodetic coordinate system, which is also the longitude information of the path point. The vertical coordinate is the y-axis coordinate value of the path point in the geodetic coordinate system, which is also the latitude information of the path point. The speed is the expected speed of the vehicle when traveling to the path point. The azimuth is the angle between the tangent direction of the path point and the x-axis of the geodetic coordinate system. The curvature is the rotation rate of the tangent direction of the path point with respect to the arc length. It can be used to represent the degree of curvature of the curve at the path point, or the degree to which the curve deviates from a straight line.

[0042] In an embodiment of the present application, the path information includes the curvature of the target path point. The target path point is determined based on the current position of the vehicle. In some embodiments, the target path point is the path point in the planned path that is closest to the current position of the vehicle. Optionally, the vehicle calculates the distance between each path point in the planned path and the current position of the vehicle, and then selects the path point with the smallest distance from the current position of the vehicle as the target path point. Alternatively, the vehicle first detects whether there is a path point on the vertical line between the current position of the vehicle and the road boundary. If so, the path point is determined as the target path point. If not, the path point is searched along the road direction and the opposite direction of the road direction, and the distance between the path points searched in the two directions and the vehicle is compared, and the path point with the smallest distance from the vehicle is determined as the target path point. In this way, the search efficiency of the target path point can be improved.

[0043] For example, the vehicle obtains the path information of the planned path [x m ,y m ,v m ,ψ m ,k m ] t , that is, the horizontal coordinate (x m ), vertical coordinate (y m ), speed (v m ), azimuth (ψ m ), curvature (k m ).

[0044] Step S303: determining a first reference point based on the actual driving parameters and the curvature of the target path point.

[0045] The first reference point is determined based on the preview mechanism, also known as the preview reference point. During autonomous driving, the vehicle follows the preview mechanism, probing forward while driving to simulate the driver's actual driving experience.

[0046] In some embodiments, the vehicle determines the first reference point through the following sub-steps: determining a preview distance based on the vehicle speed and the curvature of the target path point, and searching for the first reference point on the planned path based on the preview distance.

[0047] The preview distance is positively correlated with vehicle speed. The faster the vehicle speed, the longer the preview distance, while the slower the vehicle speed, the shorter the preview distance. The curvature of the target path and the preview distance are negatively correlated. The greater the curvature of the target path, the shorter the preview distance, and the shorter the curvature of the target path, the longer the preview distance.

[0048] Optionally, the preview distance is obtained by the following steps: obtaining a vehicle speed gain parameter and a curvature gain parameter; obtaining a first product between the vehicle speed gain parameter and the vehicle speed, and a second product between the curvature gain parameter and the curvature parameter; and determining the difference between the first product and the second product as the preview distance.

[0049] The speed gain parameter is a parameter that automatically increases with vehicle speed to determine the responsiveness of the speed loop. The speed gain parameter and curvature gain parameter can be set by default on the vehicle or by a technician based on experimentation or experience.

[0050] In some embodiments, the preview distance can be calculated using the following formula.

[0051] d=k1*v-k2*k m .

[0052] Among them, d is the preview distance, k1 is the vehicle speed gain parameter, v is the vehicle speed, k2 is the curvature gain parameter, k m is the curvature of the target path point. By introducing the curvature gain parameter, the path tracking algorithm can select the appropriate path reference point under different road conditions.

[0053] After determining the preview distance, the vehicle identifies a preview point (the point whose distance from the vehicle's current position is the preview distance). The vehicle then searches for the path point on the planned path closest to the preview point, using it as the first reference point. Optionally, the vehicle can start the search from the target path point to improve the efficiency of the first reference point search.

[0054] Step S304: searching for p second reference points in the planned path based on the first reference point.

[0055] p is an integer greater than 1. The value of p can be set based on practical experience and can be any number between 5 and 10, such as 8. The distance between the i-th second reference point and the first reference point is less than the distance between the i+1-th second reference point and the first reference point, and i is less than or equal to p-1. In other words, the p second reference points are arranged in ascending order of distance from the first reference point.

[0056] In some embodiments, the vehicle searches for p reference points following the first reference point in the planned path as the p second reference points. For example, if the vehicle determines the 21st path point in the planned path as the first reference point, then the eight path points following the 21st path point (i.e., path points 22-29) are determined as the second reference points.

[0057] In the above method, when the planned path does not achieve third-order continuity, selecting multiple reference points can effectively solve the problem of control overshoot caused by the discontinuous curvature of the planned path.

[0058] Step S305 : determining a lateral control parameter and a longitudinal control parameter based on the first reference point and the p second reference points.

[0059] The lateral control parameter characterizes the lateral deviation between the vehicle's actual driving path and the planned path. Also known as the lateral deviation, the lateral control parameter is used to control the vehicle laterally, specifically by controlling the vehicle's steering wheel angle to compensate for deviations in the vehicle's current position perpendicular to the road from the planned path.

[0060] Longitudinal control parameters characterize the longitudinal deviation between the vehicle's actual driving path and the planned path. These parameters, also known as longitudinal deviations, are used to control the vehicle's longitudinal direction. Specifically, they control the throttle and brake settings to compensate for deviations in the vehicle's current position relative to the planned path.

[0061] The process of determining the lateral control parameters and the process of determining the longitudinal control parameters will be described in the following embodiments.

[0062] Step S306 : Control the vehicle to move based on the lateral control parameters and the longitudinal control parameters to track the planned path.

[0063] In some embodiments, the vehicle determines a control amount of the steering wheel angle based on a lateral control parameter, and controls the vehicle based on the control amount of the steering wheel angle to correct a lateral deviation between the actual driving path of the vehicle and the planned path.

[0064] In some embodiments, the vehicle determines the control amount of throttle opening and closing and the control amount of brake opening and closing based on longitudinal control parameters, and controls the vehicle based on the control amount of throttle opening and closing and the control amount of brake opening and closing to correct the longitudinal deviation between the actual driving path of the vehicle and the planned path.

[0065] To sum up, the technical solution provided by the embodiment of the present application introduces a curvature term when selecting a reference point, so that the selection of the reference point matches the actual working conditions of the road, and the subsequently calculated lateral deviation and longitudinal deviation also conform to the actual situation, effectively reducing the deviation between the vehicle's driving path and the planned path, and reducing the probability of the vehicle drawing a dragon and turning inward due to unreasonable selection of path reference points, ultimately improving the robustness and stability of the path tracking solution, optimizing the path tracking effect, and improving riding comfort.

[0066] Please refer to Figure 4 , which shows a flow chart of an improved path tracking method according to an embodiment of the present application. The method may include the following steps S401-S408.

[0067] Step S401: Acquire actual driving parameters of the vehicle.

[0068] The actual driving parameters of the vehicle include the current position of the vehicle.

[0069] Step S402: Acquire path information of the planned path.

[0070] The path information includes the curvature of the target waypoints in the planned path, which are determined based on the current position of the vehicle.

[0071] Step S403: determining a first reference point based on the actual driving parameters and the curvature of the target path point.

[0072] Step S404: searching for p second reference points in the planned path based on the first reference point.

[0073] p is an integer greater than 1, the distance between the i-th second reference point and the first reference point is less than the distance between the i+1-th second reference point and the first reference point, and i is less than or equal to p-1.

[0074] Step S405: Determine the expected reference point based on the p second reference points.

[0075] In this embodiment of the present application, the vehicle determines the parameters of the desired reference point based on the parameters of the first reference point and the p second reference points, and then uniquely determines the desired reference point based on the parameters of the desired reference point. It should be noted that the desired reference point can be within or outside the planned path.

[0076] In some embodiments, the vehicle determines the abscissa of the desired reference point based on the abscissa of the first reference point and the abscissas of p second reference points. Alternatively, the vehicle determines the abscissa of the desired reference point as the average of the abscissas of the p second reference points and the abscissa of the first reference point. The abscissa of the desired reference point can be calculated using the following formula.

[0077]

[0078] x des is the horizontal coordinate of the desired reference point. n is the sum of the number of the first reference point and the number of the second reference point, which is equal to p+1. For example, when p is 8, n is 9. i is the horizontal coordinate of a reference point, which may be the horizontal coordinate of the first reference point or the horizontal coordinate of any second reference point among the p second reference points.

[0079] Optionally, the vehicle numbers the first reference point and the p second reference points in order from near to far, with the first one being x1, followed by x2, ..., x n .

[0080] In some embodiments, the vehicle determines the ordinate of the desired reference point based on the ordinate of the first reference point and the ordinates of p second reference points. Alternatively, the vehicle determines the ordinate of the desired reference point as the average of the ordinates of the p second reference points and the ordinate of the first reference point. The ordinate of the desired reference point can be calculated using the following formula.

[0081]

[0082] y des is the ordinate of the desired reference point. n is the sum of the number of first reference points and the number of second reference points, which is equal to p+1. i is the ordinate of a reference point, which may be the ordinate of the first reference point or the ordinate of any second reference point among the p second reference points.

[0083] In some embodiments, the vehicle determines a desired reference point speed based on a speed at the first reference point and the speeds of p second reference points. Alternatively, the vehicle determines the desired reference point speed as the average of the speeds of the p second reference points and the speed of the first reference point. The desired reference point speed can be calculated using the following formula.

[0084]

[0085] v des is the velocity of the desired reference point. n is the sum of the number of the first reference point and the number of the second reference point, which is equal to p+1. iis the speed of a certain reference point, which can be the speed of the first reference point or the speed of any second reference point among the p second reference points.

[0086] In some embodiments, the vehicle determines the azimuth of the desired reference point based on the azimuth of the first reference point and the azimuths of p second reference points. Alternatively, the vehicle determines the azimuth of the desired reference point as the average of the azimuths of the p second reference points and the azimuth of the first reference point. The azimuth of the desired reference point can be calculated using the following formula.

[0087]

[0088] ψ des is the azimuth of the desired reference point. n is the sum of the number of first reference points and the number of second reference points, which is equal to p+1. i is the azimuth of a certain reference point, which may be the azimuth of the first reference point or the azimuth of any second reference point among the p second reference points.

[0089] In some embodiments, the vehicle determines the curvature of the desired reference point based on the curvature of the first reference point and the curvatures of p second reference points. Alternatively, the vehicle determines the curvature of the desired reference point as the average of the curvatures of the p second reference points and the curvature of the first reference point. The curvature of the desired reference point can be calculated using the following formula.

[0090]

[0091] k des is the curvature of the desired reference point. n is the sum of the number of first reference points and the number of second reference points, which is equal to p+1. k i is the curvature of a certain reference point, which may be the curvature of the first reference point or the curvature of any second reference point among the p second reference points.

[0092] Step S406: determining lateral control parameters based on the desired reference point.

[0093] In some embodiments, the horizontal coordinate of the current position of the vehicle is labeled as a first abscissa, the vertical coordinate of the current position of the vehicle is labeled as a first ordinate, the horizontal coordinate of the desired reference point is labeled as a second abscissa, the vertical coordinate of the desired reference point is labeled as a second ordinate, and the azimuth angle of the desired reference point is recorded as a first azimuth angle.

[0094] In this embodiment, step S406 may include the following sub-steps:

[0095] Step S4061: Obtain a first difference between the first horizontal coordinate and the second horizontal coordinate.

[0096] The calculation process of the first difference can be expressed by the following formula:

[0097] dx=xx des .

[0098] Wherein, dx is the first difference, which can also be called the horizontal coordinate difference. x is the horizontal coordinate of the current position of the vehicle. des is the abscissa of the desired reference point.

[0099] Step S4062: Obtain a second difference between the first ordinate and the second ordinate.

[0100] The calculation process of the second difference can be expressed by the following calculation formula.

[0101] dy=yy des .

[0102] Where dy is the second difference, also known as the vertical coordinate difference. y is the vertical coordinate of the vehicle's current position. des is the ordinate of the desired reference point.

[0103] Step S4063: Determine a lateral control parameter based on the first difference, the second difference, and the first azimuth angle.

[0104] The lateral control parameter and the first difference are negatively correlated. The smaller the first difference, the larger the lateral control parameter; the larger the first difference, the larger the lateral control parameter. The lateral control parameter and the second difference are positively correlated. The smaller the second difference, the smaller the lateral control parameter; the larger the second difference, the larger the lateral control parameter.

[0105] When the first azimuth angle falls within the first interval, the lateral control parameter and the first azimuth angle are negatively correlated. That is, when the first azimuth angle falls within the first interval, the larger the first azimuth angle, the smaller the lateral control parameter, and the smaller the first azimuth angle, the larger the lateral control parameter. Optionally, the first interval is 0 to 90 degrees. When the first azimuth angle falls within the second interval, the lateral control parameter and the first azimuth angle are positively correlated. That is, when the first azimuth angle falls within the second interval, the larger the first azimuth angle, the larger the lateral control parameter, and the smaller the first azimuth angle, the smaller the lateral control parameter. Optionally, the first interval is 90 to 180 degrees.

[0106] In some embodiments, the lateral control parameter can be calculated using the following formula.

[0107] e1=-sinψ des *dx+cosψ des *dy.

[0108] Where, e1 is the lateral control parameter, also called lateral deviation. desis the azimuth of the desired reference point.

[0109] Step S407: determining longitudinal control parameters according to the desired reference point.

[0110] In some embodiments, the azimuth angle of the desired reference point is recorded as a first azimuth angle, and the azimuth angle of the current position of the vehicle is recorded as a second azimuth angle.

[0111] The longitudinal control parameter is positively correlated with the second azimuth angle, meaning that the larger the second azimuth angle, the larger the longitudinal control parameter, and the smaller the second azimuth angle, the smaller the longitudinal control parameter. The longitudinal control parameter is negatively correlated with the first azimuth angle, meaning that the larger the first azimuth angle, the smaller the longitudinal control parameter, and the smaller the second azimuth angle, the larger the longitudinal control parameter.

[0112] In some embodiments, the longitudinal control parameter can be calculated using the following formula.

[0113] e2=ψ-ψ des .

[0114] Where, e2 is the longitudinal control parameter, also called the longitudinal deviation. ψ is the azimuth angle of the vehicle's current position. des is the azimuth of the desired reference point.

[0115] Step S408 : Controlling the vehicle to move based on the lateral control parameters and the longitudinal control parameters to track the planned path.

[0116] To sum up, the technical solution provided by the embodiment of the present application introduces a curvature term when selecting a reference point, so that the selection of the reference point matches the actual working conditions of the road, and the subsequently calculated lateral deviation and longitudinal deviation also conform to the actual situation, effectively reducing the deviation between the vehicle's driving path and the planned path, and reducing the probability of the vehicle drawing a dragon and turning inward due to unreasonable selection of path reference points, ultimately improving the robustness and stability of the path tracking solution, optimizing the path tracking effect, and improving riding comfort.

[0117] Please refer to Figure 5 , which shows a flow chart of an improved path tracking method according to an embodiment of the present application. The method may include the following steps S501-S511.

[0118] Step S501: Acquire actual driving parameters of the vehicle.

[0119] The actual driving parameters of the vehicle include the current position of the vehicle.

[0120] Step S502: Acquire path information of the planned path.

[0121] The path information includes the curvature of the target waypoints in the planned path, which are determined based on the current position of the vehicle.

[0122] Step S503: determining a first reference point based on the actual driving parameters and the curvature of the target path point.

[0123] Step S504: searching for p second reference points in the planned path based on the first reference point.

[0124] p is an integer greater than 1, the distance between the i-th second reference point and the first reference point is less than the distance between the i+1-th second reference point and the first reference point, and i is less than or equal to p-1.

[0125] Step S505 : determining a desired reference point based on the first reference point and p second reference points.

[0126] Step S506 : determining lateral control parameters based on the desired reference point.

[0127] The lateral control parameter is used to characterize the lateral deviation between the actual driving path of the vehicle and the planned path.

[0128] Step S507: determining the vehicle's turning angle control parameters based on the vehicle's lateral control parameters.

[0129] The vehicle's turning angle control parameters include a first control variable, a second control variable, and a third control variable. The first control variable is the desired horizontal coordinate of the center of the vehicle's rear axle. The second control variable is the desired vertical coordinate of the center of the rear axle. The third control variable is the desired heading angle. In some embodiments, the vehicle may determine the vehicle's turning angle control parameters through the following sub-steps: determining the first control variable and the second control variable based on the vehicle's current speed, azimuth, and the first parameter, and then determining the third control variable based on the first parameter, the second parameter, the third parameter, the fourth parameter, the fifth parameter, and the vehicle's current speed.

[0130] The first parameter is the vehicle's sideslip angle. The second parameter is the distance between the vehicle's center of mass and the front axle. The third parameter is the distance between the vehicle's center of mass and the rear axle. The fourth parameter is the turning angle of the vehicle's front wheels. The fifth parameter is the turning angle of the vehicle's rear wheels.

[0131] In some embodiments, the first control amount is calculated using the following formula.

[0132] X=vcos(ψ+β).

[0133] Wherein, X is the first control variable and β is the first parameter.

[0134] In some embodiments, the second control amount is calculated using the following formula.

[0135] Y = vsin (ψ + β).

[0136] Among them, Y is the first control variable and β is the first parameter.

[0137] In some embodiments, the third control amount is calculated using the following formula.

[0138]

[0139] Among them, ψ1 is the third control variable, l f is the second parameter, l r is the third parameter, δ f is the fourth parameter, δ r is the fifth parameter.

[0140] In an embodiment of the present application, a kinematic model equation is established for the vehicle based on the Ackerman steering model, and the control variable for steering angle control of the vehicle is calculated based on the error and the Model Predictive Control (MPC) algorithm.

[0141] Step S508: Implement lateral control of the vehicle based on the turning angle control parameter.

[0142] In the embodiments of the present application, a vehicle establishes kinematic model equations based on the Ackerman steering model, and calculates the control variable for vehicle angle control based on the error and the MPC algorithm. Lateral control is then performed according to the control variable. On the one hand, the two-degree-of-freedom vehicle kinematic model has a high degree of simulation and consumes less computing resources. On the other hand, compared to other path tracking algorithms, the MPC lateral path tracking algorithm has additional numerical constraint equations for the output, which can explicitly control the rate of change of wheel angles and minimize wheel steering movements, significantly improving fuel economy and control robustness.

[0143] Step S509: determining longitudinal control parameters according to the desired reference point.

[0144] The longitudinal control parameter is used to characterize the longitudinal deviation between the actual driving path and the planned path of the vehicle.

[0145] Step S510 : determining a longitudinal position error, a velocity error, and an acceleration error based on longitudinal control parameters.

[0146] In some embodiments, the longitudinal position error of the vehicle can be calculated using the following formula.

[0147] e3=dx*cosθ des +dy*sinθ des .

[0148] Where e3 is the longitudinal position error of the vehicle.des is the desired front wheel steering angle when the vehicle reaches the desired reference point. dx is the horizontal difference, and dy is the vertical difference.

[0149] In some embodiments, the speed error can be calculated using the following formula.

[0150] e v =vv des .

[0151] Among them, e v is the speed error, v is the speed of the vehicle at its current position, and v des is the desired reference point velocity.

[0152] In some embodiments, the acceleration error can be calculated using the following formula.

[0153] e a =aa des .

[0154] Among them, e a is the acceleration error, a is the acceleration of the vehicle’s current position, and a des is the desired reference point acceleration.

[0155] In an embodiment of the present application, the vehicle calculates the control variable for longitudinal control of the vehicle based on dual-loop PID control.

[0156] Step S511 : Implementing longitudinal control of the vehicle based on the longitudinal position error, velocity error, and acceleration error.

[0157] In an embodiment of the present application, the vehicle calculates the control variable for longitudinal control based on double-loop PID control. This not only takes into account the vehicle's longitudinal position error, but also uses the control result of the vehicle's longitudinal position error as a compensation variable to further control the vehicle's longitudinal velocity error, thereby controlling the vehicle's acceleration. This control method not only considers tracking the vehicle speed issued by the upper planning module, but also takes into account the requirement of arriving at the designated path point on time, and also takes into account acceleration compensation control, which significantly improves ride comfort and longitudinal control accuracy.

[0158] Combined with reference Figure 6, which shows a schematic diagram of longitudinal control provided by one embodiment of the present application. The vehicle compares the planned position with the actual position to obtain a position deviation. The position controller (first PID controller) then outputs a speed compensation based on the position deviation. The speed controller (second PID controller) then outputs an acceleration compensation based on the actual speed, the planned speed, and the speed compensation. Finally, a new acceleration is generated based on the planned acceleration and the acceleration compensation. The braking and throttle variations are then generated based on the new acceleration and vehicle speed. Finally, the vehicle is controlled according to these braking and throttle variations.

[0159] In summary, the technical solution provided in the embodiment of the present application calculates the control amount for vehicle angle control based on lateral control parameters, and then performs lateral control according to the above control amount, which can minimize the steering action of the wheels and greatly improve fuel economy and control robustness; it also calculates the control amount for vehicle longitudinal control based on longitudinal control parameters, not only taking into account the longitudinal position error of the vehicle, but also using the control result of the longitudinal position error of the vehicle as a compensation amount to further control the longitudinal speed error of the vehicle, thereby controlling the acceleration of the vehicle. While considering the speed issued by the upper planning module, it also takes into account the requirement of arriving at the designated path point on time, and also takes into account the compensation control of acceleration, which greatly improves ride comfort and longitudinal control accuracy.

[0160] See also Figure 7 , which shows a structural block diagram of a path tracking device provided in an embodiment of the present application. The device is applied to a vehicle, and the device includes: a first acquisition module 710, a second acquisition module 720, a reference point determination module 730, a reference point search module 740, a parameter determination module 750, and a path tracking module 760.

[0161] The first acquisition module 710 is used to obtain the actual driving parameters of the vehicle, including the vehicle's current position. The second acquisition module 720 is used to obtain path information of the planned path, including the curvature of the target path point in the planned path, which is determined based on the vehicle's current position. The reference point determination module 730 is used to determine a first reference point based on the actual driving parameters and the curvature of the target path point. The reference point search module 740 is used to search for p second reference points in the planned path based on the first reference point, where p is an integer greater than 1, the distance between the i-th second reference point and the first reference point is less than the distance between the i+1-th second reference point and the first reference point, and i is less than or equal to p-1. The parameter determination module 750 is used to determine lateral control parameters and longitudinal control parameters based on the p second reference points. The path tracking module 770 is used to control vehicle driving based on the lateral control parameters and longitudinal control parameters to achieve tracking of the planned path.

[0162] To sum up, the technical solution provided by the embodiment of the present application introduces a curvature term when selecting a reference point, so that the selection of the reference point matches the actual working conditions of the road, and the subsequently calculated lateral deviation and longitudinal deviation also conform to the actual situation, effectively reducing the deviation between the vehicle's driving path and the planned path, and reducing the probability of the vehicle drawing a dragon and turning inward due to unreasonable selection of path reference points, ultimately improving the robustness and stability of the path tracking solution, optimizing the path tracking effect, and improving riding comfort.

[0163] In some embodiments, the parameter determination module 750 is configured to determine a desired reference point based on the p second reference points; determine a lateral control parameter based on the desired reference point; and determine a longitudinal control parameter based on the desired reference point.

[0164] In some embodiments, the current position of the vehicle includes a first horizontal coordinate and a first vertical coordinate, the expected reference point includes a second horizontal coordinate, a second vertical coordinate and a first azimuth angle, and the parameter determination module 750 is used to obtain a first difference between the first horizontal coordinate and the second horizontal coordinate; obtain a second difference between the first vertical coordinate and the second vertical coordinate; determine a lateral control parameter based on the first difference, the second difference and the first azimuth angle; wherein the lateral control parameter and the first difference are negatively correlated, and the lateral control parameter and the second difference are positively correlated.

[0165] In some embodiments, the expected reference point includes a first azimuth angle, and the actual driving parameter of the vehicle includes a second azimuth angle of the vehicle; the parameter determination module 750 is used to obtain a third difference between the second azimuth angle and the first azimuth angle as a longitudinal control parameter.

[0166] In some embodiments, the reference point determination module 730 is configured to determine a preview distance based on the vehicle speed and the curvature parameter; and search for a first reference point on the planned path based on the preview distance.

[0167] In some embodiments, the reference point determination module 730 is used to obtain a vehicle speed gain parameter and a curvature gain parameter; obtain a first product between the vehicle speed gain parameter and the vehicle speed, and a second product between the curvature gain parameter and the curvature parameter; and determine the difference between the first product and the second product as the preview distance.

[0168] In some embodiments, the trajectory tracking module 760 is configured to determine a turning angle control parameter of the vehicle based on the lateral control parameter of the vehicle; and implement lateral control of the vehicle based on the turning angle control parameter.

[0169] In some embodiments, the trajectory tracking module 760 is configured to determine a longitudinal position error, a velocity error, and an acceleration error based on the longitudinal control parameters; and implement longitudinal control of the vehicle based on the longitudinal position error, velocity error, and acceleration error.

[0170] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0171] In several embodiments provided in this application, the coupling between modules may be electrical, mechanical or other forms of coupling.

[0172] In addition, the functional modules in the various embodiments of the present application may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into a single module. The above-mentioned integrated modules may be implemented in the form of hardware or software functional modules.

[0173] See also Figure 8 , which shows that an embodiment of the present application further provides a vehicle 800, which includes: one or more processors 810, a memory 820, and one or more applications. The one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to execute the methods described in the above embodiments.

[0174] The processor 810 may include one or more processing cores. The processor 810 utilizes various interfaces and circuits to connect various components within the battery management system. It executes instructions, programs, code sets, or instruction sets stored in the memory 820, as well as accesses data stored in the memory 820, to perform various functions of the battery management system and process data. Optionally, the processor 810 may be implemented using at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). The processor 810 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; and the modem handles wireless communications. It is understood that the modem may not be integrated into the processor 810 and may be implemented separately via a communication chip.

[0175] The memory 820 may include a random access memory 820 (RAM) or a read-only memory 820 (ROM). The memory 820 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 820 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (e.g., a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the various method embodiments described above, etc. The data storage area may also store data created by the electronic device during use (e.g., a phone book, audio and video data, chat history data), etc.

[0176] See also Figure 9 , which shows that an embodiment of the present application also provides a computer-readable storage medium 900, in which computer program instructions 910 are stored. The computer program instructions 910 can be called by a processor to execute the method described in the above embodiment.

[0177] The computer-readable storage medium 900 may be, for example, a flash memory, an electrically erasable programmable read-only memory (EEPROM), an electrically programmable read-only memory (EPROM), a hard disk, or a read-only memory (ROM). Alternatively, the computer-readable storage medium includes a non-transitory computer-readable storage medium. The computer-readable storage medium 900 has storage space for computer program instructions 910 for executing any of the method steps described above. These computer program instructions 910 can be read from or written to one or more computer program products.

[0178] The above is only a preferred embodiment of the present application and does not constitute any form of limitation to the present application. Although the present application has been disclosed as above with preferred embodiments, it is not intended to limit the present application. Any person skilled in the art can make some changes or modifications to equivalent embodiments using the technical contents disclosed above without departing from the scope of the technical solution of the present application. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present application without departing from the content of the technical solution of the present application are still within the scope of the technical solution of the present application.

Claims

1. A path tracking method, characterized in that: Applied to a vehicle, the method comprises: Acquiring actual driving parameters of the vehicle, wherein the actual driving parameters of the vehicle include a current position of the vehicle; Obtaining path information of a planned path, the path information including a curvature of a target path point in the planned path, the target path point being determined based on a current position of the vehicle; determining a first reference point based on the actual driving parameter and the curvature of the target path point; Searching for p second reference points in the planned path based on the first reference point, where p is an integer greater than 1, a distance between the i-th second reference point and the first reference point is less than a distance between the i+1-th second reference point and the first reference point, and i is less than or equal to p-1; determining a lateral control parameter and a longitudinal control parameter based on the first reference point and the p second reference points, the lateral control parameter being used to characterize a lateral deviation between the actual driving path of the vehicle and the planned path, and the longitudinal control parameter being used to characterize a longitudinal deviation between the actual driving path of the vehicle and the planned path; The vehicle is controlled to travel based on the lateral control parameter and the longitudinal control parameter to achieve tracking of the planned path.

2. The method according to claim 1, characterized in that The determining of a lateral control parameter and a longitudinal control parameter based on the first reference point and the p second reference points includes: determining a desired reference point based on the first reference point and p second reference points; The lateral control parameter is determined based on the desired reference point, and the longitudinal control parameter is determined based on the desired reference point.

3. The method according to claim 2, characterized in that The current position of the vehicle includes a first horizontal coordinate and a first vertical coordinate, the expected reference point includes a second horizontal coordinate, a second vertical coordinate, and a first azimuth angle, and determining the lateral control parameter based on the expected reference point includes: Obtaining a first difference between the first horizontal coordinate and the second horizontal coordinate; Obtaining a second difference between the first ordinate and the second ordinate; The lateral control parameter is determined based on the first difference, the second difference and the first azimuth angle; wherein the lateral control parameter is negatively correlated with the first difference, and the lateral control parameter is positively correlated with the second difference.

4. The method according to claim 2, characterized in that The desired reference point includes a first azimuth angle, and the actual driving parameter of the vehicle includes a second azimuth angle of the vehicle; and determining the longitudinal control parameter based on the desired reference point includes: A third difference between the second azimuth angle and the first azimuth angle is obtained as the longitudinal control parameter.

5. The method according to claim 1, wherein The actual driving parameter of the vehicle includes the speed of the vehicle, and determining the first reference point based on the actual driving parameter and the curvature of the target path point includes: determining a preview distance based on the vehicle speed and the curvature of the target path point; The first reference point is searched for on the planned path based on the preview distance.

6. The method according to claim 5, characterized in that The determining of the preview distance based on the vehicle speed and the curvature of the target path point includes: Obtain vehicle speed gain parameters and curvature gain parameters; Obtaining a first product between the vehicle speed gain parameter and the vehicle speed, and a second product between the curvature gain parameter and the curvature of the target path point; A difference between the first product and the second product is determined as the preview distance.

7. The method according to any one of claims 1 to 6, characterized in that The controlling the vehicle driving based on the lateral control parameter and the longitudinal control parameter to achieve tracking of the planned path includes: determining a steering angle control parameter of the vehicle based on a lateral control parameter of the vehicle; Implementing lateral control of the vehicle based on the turning angle control parameter; determining a longitudinal position error, a velocity error, and an acceleration error based on the longitudinal control parameters; Based on the longitudinal position error, the velocity error, and the acceleration error, longitudinal control of the vehicle is achieved.

8. A path tracking device, characterized in that: The device comprises: A first acquisition module is used to acquire actual driving parameters of the vehicle, wherein the actual driving parameters of the vehicle include the current position of the vehicle; a first determining module, configured to obtain path information of a planned path, the path information including a curvature of a target path point in the planned path, the target path point being determined based on a current position of the vehicle; a reference point determination module, configured to determine a first reference point based on the actual driving parameter and the curvature of the target path point; a reference point search module, configured to search for p second reference points in the planned path based on the first reference point, where p is an integer greater than 1, a distance between the i-th second reference point and the first reference point is less than a distance between the i+1-th second reference point and the first reference point, and i is less than or equal to p-1; a parameter determination module, configured to determine a lateral control parameter and a longitudinal control parameter based on the p second reference points, wherein the lateral control parameter is used to represent a lateral deviation between the actual driving path of the vehicle and the planned path, and the longitudinal control parameter is used to represent a longitudinal deviation between the actual driving path of the vehicle and the planned path; A path tracking module is used to control the vehicle driving based on the lateral control parameters and the longitudinal control parameters to achieve tracking of the planned path.

9. A vehicle, characterized in that: include: one or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by one or more processors, and the one or more applications are configured to execute the path tracking method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer program instructions, which can be called by a processor to execute the path tracking method according to any one of claims 1 to 7.

Images