Parallel driving steering track data processing method and device
By annotating and transforming trajectory line equations during parallel driving, vehicle steering trajectory data is plotted, solving the problem of visual misjudgment in remote driving and improving driving safety.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHIDAO NETWORK TECH (BEIJING) CO LTD
- Filing Date
- 2023-02-10
- Publication Date
- 2026-05-29
AI Technical Summary
In parallel driving, remote cockpit drivers, who rely on monitors to observe the vehicle's movement, are prone to misperceptions of distance and misjudgments of the driving trajectory, leading to safety hazards.
By pre-labeling the pixel coordinates of the wheel trajectory images at different steering angles, a first trajectory equation is established, and a second trajectory equation at a preset steering angle is obtained through transformation operations. Combined with the driving warning line curve equation, parallel driving steering trajectory data is drawn and displayed on the monitor.
It effectively reduces the probability of accidents during remote driving and improves the accuracy of the driver's visual perception by displaying the vehicle's driving distance and trajectory lines intuitively.
Smart Images
Figure CN115984416B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of autonomous driving technology, and in particular to a method and apparatus for processing parallel driving steering trajectory data. Background Technology
[0002] With the development of the internet and information technology, transportation tools are becoming increasingly intelligent. In particular, the intelligence of cars is increasingly benefiting ordinary people. Parallel driving has become an essential part of this intelligence. Parallel driving involves the driver issuing control commands in a simulator to remotely control the vehicle's operation.
[0003] Because the vehicle is remotely controlled, the vehicle's driving status can only be observed through a monitor. This may lead to misjudgments of visual distance perception and driving trajectory, causing accidents and posing safety hazards. Summary of the Invention
[0004] This application provides a method and apparatus for processing parallel driving steering trajectory data to provide steering trajectory instructions to drivers in a remote cockpit.
[0005] The embodiments of this application adopt the following technical solutions:
[0006] In a first aspect, embodiments of this application provide a method for processing parallel driving steering trajectory data, wherein the method includes:
[0007] The image pixel coordinates of the trajectory lines of the wheels at different steering angles and corresponding positions in front of the vehicle are pre-marked, and the first trajectory line equation is established for the trajectory lines.
[0008] After performing a preset transformation operation on the first trajectory line equation, a second trajectory line equation under a preset steering angle is obtained.
[0009] Based on the driving warning line curve equation fitted to the target position in front of the vehicle and the second trajectory line equation, the coordinates of the trajectory line at the target position under the preset steering angle are determined, and the target position in front of the vehicle is the driving warning position.
[0010] The parallel driving steering trajectory data is plotted based on the coordinates of the target position and the second trajectory line equation under the preset steering angle.
[0011] In some embodiments, determining the coordinates of the trajectory line at the target position at the preset steering angle based on the driving warning line curve equation fitted to the target position at a distance from the front of the vehicle and the parabolic equation includes:
[0012] Based on the image pixel coordinates of the trajectory line corresponding to the target position in front of the vehicle, polynomial fitting is performed to establish the curve equation at each target position.
[0013] Based on the joint equation system established by the curve equation and the parabola equation at each target position, the coordinates of the trajectory line at the target position under the preset turning angle are calculated.
[0014] In some embodiments, the method further includes:
[0015] Based on the coordinates of the trajectory line at the target position under the preset turning angle and the preset inner line length at the target position, determine the starting point of each of the two inner lines at the target position;
[0016] By combining the straight line equation and the distance equation, the endpoints of the two inner lines at each target location are obtained;
[0017] Connect the starting point and the ending point to obtain the inner line of the parallel driving steering trajectory data.
[0018] In some embodiments, obtaining the parabola equation at a preset turning angle after performing a preset transformation operation on the parabola includes:
[0019] Perform a vertical flip and translation operation on the parabola equation to move the parabola to the positions of the left and right starting points of the pre-marked trajectory line, while keeping the opening direction of the parabola unchanged;
[0020] The tilt angle is calculated based on the pre-marked trajectory line of the wheel with a turning angle of 0 degrees.
[0021] Based on the tilt angle, the parabola that has been rotated to the front position is tilted to obtain the tilt coordinates after rotation, which are used to obtain the parabola equation under the preset steering angle.
[0022] In some embodiments, determining the coordinates of the trajectory line at the target position at the preset steering angle based on the driving warning line curve equation fitted to the target position at a distance from the front of the vehicle and the parabolic equation, wherein the target position at a distance from the front of the vehicle is the driving warning position, includes:
[0023] Establish the relationship between each turning angle θ and the parabolic parameter P, and use a polynomial fitting method to establish the equation between the angle and the parabolic parameter;
[0024] Based on the equation relating the angle and the parabolic parameters, the coordinates of the trajectory line at the target position under the preset turning angle are determined.
[0025] In some embodiments, the parabolic parameter P is obtained in the following manner:
[0026] The parameter P corresponding to the parabola's fit with the marked trajectory line when the right steering angle of the wheel is manually adjusted to different angles is given by the following formula: Where m represents the steering angle of the corresponding wheel, and d is the left and right indicator of the trajectory line.
[0027] In some embodiments, the step of pre-marking the image pixel coordinates of the trajectory line corresponding to the position in front of the vehicle at different steering angles, and representing the trajectory line as a parabola using a parabolic equation, includes:
[0028] Based on the annotation range and interval, the image pixel positions corresponding to multiple locations at distances from the front of the vehicle on the left and right trajectory lines of the wheels at different steering angles in the real scene are pre-annotated, and the annotated physical distances are mapped to the image pixel coordinate positions. Where m represents the steering angle of the corresponding wheel, n represents the marked front position of the vehicle, and d represents the left and right markings of the trajectory line.
[0029] Secondly, embodiments of this application also provide a processing apparatus for parallel driving steering trajectory data, wherein the apparatus includes:
[0030] The annotation module is used to pre-annotate the image pixel coordinates of points on the trajectory line at a preset position in front of the vehicle at different steering angles, and to establish a first trajectory line equation based on the image pixel coordinates of the points on the trajectory line.
[0031] The trajectory line coordinate module is used to obtain the second trajectory line equation under a preset turning angle after the first trajectory line equation undergoes a preset transformation operation.
[0032] The determination module is used to determine the coordinates of the trajectory line at the target distance under the preset steering angle based on the driving warning line curve equation fitted to the target position in front of the vehicle and the second trajectory line equation, wherein the position of the target distance in front of the vehicle is the driving warning position.
[0033] The drawing module is used to draw the parallel driving steering trajectory data based on the coordinates of the target position and the second trajectory line equation under the preset steering angle.
[0034] Thirdly, embodiments of this application also provide an electronic device, including: a processor; and a memory arranged to store computer-executable instructions, which, when executed, cause the processor to perform the above-described method.
[0035] Fourthly, embodiments of this application also provide a computer-readable storage medium that stores one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform the above-described method.
[0036] The at least one technical solution adopted in this application embodiment can achieve the following beneficial effects: by intuitively displaying the vehicle's driving distance and trajectory line on the display, remote drivers can directly drive the vehicle guided by the vehicle's driving trajectory line on the display, avoiding misjudgments of distance and driving trajectory caused by visual perception, and effectively reducing the probability of accidents. This method is simple to implement, achieving the drawing of the vehicle trajectory line through data annotation, manual adjustment, and parameter fitting. Attached Figure Description
[0037] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:
[0038] Figure 1 This is a schematic flowchart of the parallel driving steering trajectory data processing method in the embodiments of this application;
[0039] Figure 2 This is a schematic diagram of the structure of the parallel driving steering trajectory data processing device in the embodiments of this application;
[0040] Figure 3 This is a schematic diagram illustrating the implementation of the parallel driving steering trajectory data processing method in the embodiments of this application.
[0041] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation
[0042] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0043] The inventors discovered during their research that if an autonomous vehicle malfunctions or is involved in an accident during operation, it requires takeover through parallel driving. However, the driver in the parallel cockpit can only remotely take over the autonomous vehicle via a screen to extricate it from trouble or repair the malfunction. This process typically relies solely on the screen in the parallel cockpit, and cannot accurately assess the actual collision risks or perceived distances faced by the autonomous vehicle.
[0044] To address the aforementioned shortcomings, the parallel driving steering trajectory data processing method provided in this application pre-draws and displays the vehicle's driving trajectory and distance on a monitor when the vehicle is remotely controlled to move forward in parallel driving. Furthermore, the driving trajectory line is drawn based on the wheel steering angle, showing the driving trajectory and distance within 5 to 10 meters, and displayed on the parallel cockpit screen. This allows the remote cockpit operator to directly drive the vehicle guided by the driving trajectory line on the monitor, effectively reducing the probability of accidents.
[0045] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.
[0046] This application provides a method for processing parallel driving steering trajectory data, such as... Figure 1 The diagram provided illustrates a method for processing parallel driving steering trajectory data in an embodiment of this application. The method includes at least the following steps S110 to S140:
[0047] Step S110: Pre-label the image pixel coordinates of points on the trajectory line at a preset position in front of the vehicle's front at different steering angles of the wheel, and establish a first trajectory line equation based on the image pixel coordinates of the points on the trajectory line. The wheel is the wheel of a vehicle in a real-world scenario. During pre-labeling, the image pixel positions corresponding to the preset positions of the left and right trajectory line points are obtained at different steering angles of the wheel. Steering trajectory data is usually divided into left and right trajectory lines, and appears simultaneously as a set of trajectory data.
[0048] The trajectory points of the wheels at different steering angles and at each preset position in front of the vehicle are pre-marked. Then, the combination of the obtained trajectory points is mapped to an image pixel coordinate system. Based on the image pixel coordinate system, the first trajectory equation is then established.
[0049] To facilitate subsequent rotation and translation, the equation of the trajectory is expressed using a parabola equation. For example, the parabola formula is: y 2 =2px.
[0050] Step S120: After performing a preset transformation operation on the first trajectory line equation, obtain the second trajectory line equation under a preset steering angle.
[0051] Since the marked position is the wheel position, the first trajectory equation needs to be rotated to the front of the car. To meet the steering requirements of the trajectory data, the parabolic equation under the preset steering angle is then obtained. In other words, the second trajectory equation corresponding to a given angle can be determined.
[0052] Preferably, the above process also requires manually labeling the parabola parameters and solving for the relationship between the parabola parameters and the preset turning angle.
[0053] Step S130: Based on the driving warning line curve equation fitted to the target position in front of the vehicle and the second trajectory line equation, determine the coordinates of the trajectory line at the target distance under the preset steering angle, and the position of the target distance in front of the vehicle is the driving warning position.
[0054] After obtaining the equation of the second trajectory line under the preset steering angle, it is necessary to further determine the driving warning positions at different distances on the trajectory line, so as to obtain the coordinates of the trajectory line under the preset steering angle at the target position.
[0055] Step S140: Draw the parallel driving steering trajectory data based on the coordinates of the target position and the second trajectory line equation under the preset steering angle.
[0056] The steering trajectory data required for parallel driving is drawn based on the coordinates of the target position and the equation of the second trajectory line under the preset steering angle.
[0057] Since vehicles can turn left or right, they can be considered symmetrical about the centerline of the vehicle's straight-line direction. Based on this principle, after finding the axis of symmetry, the left turn direction can be considered as the mirror image of the right turn direction about this axis of symmetry. Mirroring the right-turn parabola about the axis of symmetry yields the pixel coordinates for the left turn. Finally, draw the two left and right turning trajectory lines and four inner lines for either the left or right turn direction onto the image.
[0058] In one embodiment of this application, determining the coordinates of the trajectory line at the target distance under the preset steering angle based on the driving warning line curve equation fitted according to the target distance in front of the vehicle and the parabolic equation includes: performing polynomial fitting based on the image pixel coordinate positions corresponding to the trajectory line at the target distance in front of the vehicle to establish a curve equation at each target position; and calculating the coordinates of the trajectory line at the target position under the preset steering angle based on the joint equation system established by the curve equation at each target position and the parabolic equation.
[0059] Based on the pre-labeled wheel steering data, establish curve equations for multiple trajectory lines at all labeled angles, representing distances from the target position in front of the vehicle. Polynomial fitting can be used to fit these curve equations.
[0060] Then, based on the joint equation system established by the curve equation and the parabola equation at each target position, the coordinates of the trajectory line at the target position under the preset turning angle are calculated.
[0061] It should be noted that the required distance from the target position in front of the vehicle can be determined based on actual needs.
[0062] For example, the pixel coordinates of the left and right trajectory lines can be marked at a position of 10m: The pixel coordinates of the left and right trajectory lines marked at the 5m position: Four driving warning line curve equations were established. Then, a joint system of equations was created by combining the driving warning line curve equations and the parabolic equations to solve for the pixel coordinates of the intersections at 10m and 5m. The 10m intersection point represents the line length of the parabola representing the trajectory and the 10m warning position. The 5m intersection point represents the 5m warning position.
[0063] In one embodiment of this application, the method further includes: determining the starting point of each of the two inner lines at the target position based on the coordinates of the trajectory line at the target position under the preset steering angle and the preset inner line length of the target position; obtaining the ending point of each of the two inner lines at the target position by combining the straight line equation and the distance equation; and connecting the starting point and the ending point to obtain the inner line of the parallel driving steering trajectory data.
[0064] To draw the line segment (inner line) at the warning location, it is necessary to determine the endpoint and starting point of the line segment. In practice, the lengths of the 10m and 5m inner lines can be set as D1 and D2 respectively, and the equations of the two inner line lines are the lines connecting the starting points on the corresponding 10m and 5m trajectory lines. Therefore, the endpoint positions of the two 10m and 5m inner lines can be obtained by combining the line equations and distance equations, and connecting the corresponding starting and ending points gives the inner line.
[0065] In one embodiment of this application, obtaining the parabolic equation at a preset steering angle after performing a preset transformation operation on the parabola includes: performing a vertical flip and translation operation on the parabolic equation to move the parabola to the positions of the left and right starting points of a pre-marked trajectory line, while keeping the opening direction of the parabola unchanged; calculating the tilt angle based on the pre-marked trajectory line with a wheel turning angle of 0 degrees; and tilting the parabola that has been rotated to the front position of the vehicle based on the tilt angle to obtain the rotated tilt coordinates, which are used to obtain the parabolic equation at the preset steering angle.
[0066] The parabola equation is vertically flipped and translated, so that the parabola's x-axis coordinates are the starting points, and it is moved to the positions of the marked starting points on the left and right sides of the trajectory line, without changing the orientation of the parabola's opening. Considering that the trajectory line is tilted on the image, the tilt angle needs to be calculated. Based on the marked trajectory line at a wheel rotation angle of 0 degrees, the tilt angle can be calculated. Using the tilt angle calculated in the previous step, the parabola, now rotated to the front position, is tilted again, and the rotated tilt coordinates are obtained.
[0067] In one embodiment of this application, determining the coordinates of the trajectory line at the target position at the preset steering angle based on the driving warning line curve equation fitted to the target position in front of the vehicle and the parabolic equation, wherein the target position in front of the vehicle is the driving warning position, includes: establishing the relationship between each steering angle θ and the parabolic parameter P; using a polynomial fitting method to establish the equation between the angle and the parabolic parameter; and determining the coordinates of the trajectory line at the target position at the preset steering angle based on the equation between the angle and the parabolic parameter.
[0068] The process of manually adjusting parameter P involves manually adjusting the parameter p value of the labeled trajectory line that corresponds to the parabola when the vehicle's wheel steering angles are 0 degrees, 10 degrees, 20 degrees, 30 degrees, and 40 degrees in a real-world scenario. A relationship can be established between each steering angle θ and the parabolic parameter p, for example, using a polynomial fitting method to establish an equation between the angle and the parabolic parameter, and then solving it using an objective function. The solution is the parabolic equation for the corresponding angle.
[0069] In one embodiment of this application, the parabolic parameter P is obtained as follows: the parameter P corresponding to the parabola matching the marked trajectory line when the right steering angle of the wheel is manually adjusted to different angles, and the formula for the parameter P is as follows: Where m represents the steering angle of the corresponding wheel, and d is the left and right indicator of the trajectory line.
[0070] Manually adjust parameter values: Where m∈[0, 10, 20, 30, 40] represents the steering angle of the corresponding wheel. d∈[L, R] are the left and right indicators of the trajectory line.
[0071] In one embodiment of this application, the step of pre-marking the image pixel coordinates of the trajectory lines of the wheel at different steering angles relative to the position in front of the vehicle, and representing the trajectory lines as parabolas using a parabolic equation, includes: pre-marking multiple image pixel positions corresponding to the position in front of the vehicle at different steering angles of the wheel in a real scene, according to the marking range and interval degrees, and mapping the marked physical distances to the image pixel coordinates. Where m represents the steering angle of the corresponding wheel, n represents the marked front position of the vehicle, and d represents the left and right markings of the trajectory line.
[0072] The image pixel positions corresponding to 10m, 7.5m, 5m, 2.5m, and 0m on the left and right trajectory lines are marked with a range of 0 to 40 degrees, with an interval of 10 degrees. It can be understood that 10m, 7.5m, 5m, 2.5m, and 0m are selected or determined according to actual needs; of course, distances that are too far usually do not require a warning.
[0073] For example, the labeled physical distance is mapped to image pixel coordinates: Where m∈[0, 10, 20, 30, 40] represents the steering angle of the corresponding wheel, in degrees. n∈[0, 2.5, 5, 7.5, 10] represents the marked position in front of the vehicle, in meters, and 0 represents the 0m position where the vehicle front meets the ground. Where d∈[L, R] are the left and right markers of the trajectory line.
[0074] This application embodiment also provides a parallel driving steering trajectory data processing device 200, such as... Figure 2 The diagram shows a schematic representation of a parallel driving steering trajectory data processing device according to an embodiment of this application. The parallel driving steering trajectory data processing device 200 includes at least: a labeling module 210, a trajectory line coordinate module 220, a determination module 230, and a drawing module 240, wherein:
[0075] In one embodiment of this application, the annotation module 210 is specifically used to: pre-annotate the image pixel coordinates corresponding to points on the trajectory line at a preset position in front of the vehicle's front at different steering angles of the wheel, and establish a first trajectory line equation based on the image pixel coordinates corresponding to the points on the trajectory line. The wheel is the wheel of a vehicle in a real scene. During pre-annotation, the image pixel positions corresponding to the preset positions of the left and right trajectory lines are obtained at different steering angles of the wheel. The steering trajectory data is usually divided into left and right trajectory lines, and appears simultaneously as a set of trajectory data.
[0076] The trajectory lines of the wheels at each corresponding position in front of the front of the vehicle when the wheels are turning in different directions are pre-labeled, and then the obtained trajectory lines are mapped to image pixel coordinate groups.
[0077] To facilitate subsequent rotation and translation, the trajectory is represented by a parabola using the equation of a parabola. For example, the formula for a parabola is: y 2 =2px.
[0078] In one embodiment of this application, the trajectory line coordinate module 220 is specifically used to: obtain a second trajectory line equation under a preset turning angle after performing a preset transformation operation on the established first trajectory line equation.
[0079] Since the marked position is the wheel position, the parabola needs to be rotated to the front of the car. To meet the steering requirements of the trajectory data, the equation of the parabola under the preset steering angle is then obtained. In other words, the equation of the parabola corresponding to a given angle can be determined.
[0080] Preferably, the above process also requires manually labeling the parabola parameters and solving for the relationship between the parabola parameters and the preset turning angle.
[0081] In one embodiment of this application, the determining module 230 is specifically used to: determine the coordinates of the trajectory line at the target distance under the preset steering angle based on the driving warning line curve equation fitted to the target position in front of the vehicle and the second trajectory line equation, wherein the position of the target distance in front of the vehicle is the driving warning position.
[0082] After obtaining the parabolic equation at the preset steering angle, it is necessary to further determine the driving warning positions at different distances along the trajectory. The coordinates of the trajectory at the target position obtained from this determination can then be used to determine the vehicle's driving position.
[0083] In one embodiment of this application, the drawing module 240 is specifically used to: draw the parallel driving steering trajectory data according to the coordinates of the target position and the second trajectory line equation under the preset steering angle.
[0084] The steering trajectory data required for parallel driving is drawn based on the coordinates of the target location and the parabolic equation under the preset steering angle.
[0085] Since vehicles can turn left or right, they can be considered symmetrical about the centerline of their straight-line direction. Based on this principle, after finding the axis of symmetry, the left turn direction can be considered as the mirror image of the right turn direction about the axis of symmetry. The right turn pixel coordinate set, after being mirrored based on the axis of symmetry, becomes the left turn pixel coordinate set. Finally, draw the two left and right turning trajectory lines and four inner lines for either the left or right turn direction onto the image.
[0086] It is understood that the above-mentioned parallel driving steering trajectory data processing device can implement each step of the parallel driving steering trajectory data processing method provided in the foregoing embodiments. The relevant explanations of the parallel driving steering trajectory data processing method are applicable to the parallel driving steering trajectory data processing device, and will not be repeated here.
[0087] Figure 3 This is a schematic diagram illustrating the implementation of the parallel driving steering trajectory data processing method in this application embodiment, which specifically includes the following steps:
[0088] Step S1: Mark the image pixel positions corresponding to 10m, 7.5m, 5m, 2.5m, and 0m on the left and right trajectory lines at the right steering angle of the wheel. The marking range is 0-40 degrees, with intervals of 10 degrees. The physical distances obtained after marking are mapped to image pixel coordinates:
[0089] Where m∈[0, 10, 20, 30, 40] represents the steering angle of the corresponding wheel, in degrees. n∈[0, 2.5, 5, 7.5, 10] represents the marked position in front of the vehicle, in meters, and 0 represents the 0m position where the vehicle's front meets the ground. Where d∈[L, R] are the left and right markers of the trajectory line.
[0090] Step S2: Express the turning trajectory in parabolic equation form. Since there are two trajectory lines, left and right, two parabolic equations can be solved. The formula for solving a single parabola is as follows:
[0091] The formula for a parabola is: y 2 =2px
[0092] Step S3: Perform a vertical flip and translation operation on the parabola equation, using the x-axis coordinates as the starting point, and move the parabola to the positions of the left and right starting points of the marked trajectory line, without changing the orientation of the parabola's opening. The formula is as follows:
[0093] Let the starting position of the parabola be (0, 0);
[0094] Let the pixel coordinates on the left and right parabolas be respectively: i∈R represents the i-th coordinate on the trajectory line.
[0095] Pixel coordinates after parabolic rotation:
[0096] Where H represents the height of the image or video frame, This indicates the starting position of the vehicle's front coordinates on the left and right trajectory lines.
[0097] Step S4: Since the trajectory line is represented at an angle on the image, the angle of inclination needs to be calculated. The angle of inclination can be calculated based on the trajectory line at a wheel rotation angle of 0 degrees. The formula is as follows:
[0098] Tilt angle:
[0099] in, This represents the coordinates of any two points on each trajectory line of the left and right tracks when the wheel turns right at an angle of 0.
[0100] Step S5: Using the tilt angle calculated in the previous step, tilt the parabola that has been rotated to the front position. The tilt coordinates after rotation are calculated using the following formula:
[0101] Equation of rotation:
[0102] in, The new coordinates are those of the parabola after rotation.
[0103] Step S6: Manually adjust the parameter p value corresponding to the parabolic trajectory line matching the marked trajectory line at right steering angles of 0, 10, 20, 30, and 40 degrees. The formula is as follows:
[0104] Manually adjust parameter values: Where m∈[0, 10, 20, 30, 40] represents the steering angle of the corresponding wheel. d∈[L, R] is the left and right indicator of the trajectory line.
[0105] Step S7: Establish the relationship between each turning angle θ and the parabolic parameter p. Use a polynomial fitting method to establish the equation between the angle and the parabolic parameter. The formula is as follows:
[0106] Establish the coordinate relationship between the steering angle and parabolic parameters:
[0107] The polynomial formula is:
[0108] Sample input method:
[0109] Based on the coordinate data, the fitting function H(x) is given, and the residual is: r i =H(x) i )-y i Using L2 regularization, solve for H(x) = w0 + w1x + w2x 2 +…+w n x n .
[0110] The objective function is: The solution method is to minimize the objective function. Since there are two trajectory lines, left and right, two polynomial equations can be fitted.
[0111] Step S8: Substitute the input right steering angle θ′ of the wheel into the polynomial equation obtained in step 7 to obtain the parabola parameter p = P(θ′). Then, substitute it into the parabola equation to obtain the parabola equation at the corresponding angle.
[0112] Step S9: Based on the data marked in Step 1, establish the curve equations for the 10m and 5m lines at all marked angles. Use a polynomial fitting method to fit the curve equations; the fitting method is the same as in Step 7.
[0113] The specific formula is as follows:
[0114] The pixel coordinates of the left and right trajectory lines marked at the 10m position: The pixel coordinates of the left and right trajectory lines marked at the 5m position: A total of four curve equations were established.
[0115] Step S10: Establish a joint system of equations for the driving warning line curve equation and the parabola equation, and solve for the pixel coordinates of the intersection points at 10m and 5m. The 10m intersection point represents the line length when the parabola represents the trajectory line and the 10m warning position. The 5m intersection point represents the 5m warning position. The formula is as follows:
[0116] Combined equations of the driving warning line curve and the parabola equation:
[0117] The solution retains the valid and satisfactory roots. This allows us to obtain the coordinates of the two trajectory lines at 10m and 5m, under the right turn angle θ′ of the wheel:
[0118] Step S11: Set the lengths of the 10m and 5m inner lines to D1 and D2 respectively. The equations of the two inner line straight lines are also the lines connecting the starting points on the corresponding 10m and 5m trajectory lines. Therefore, the endpoint positions of the two inner lines for each of the 10m and 5m can be obtained by combining the straight line equations and the distance equations. The formula is as follows:
[0119] Given: a trajectory line point approximately 10m long Track points approximately 5m Based on the equation of the straight line y=kx+b, the slope of the corresponding line k∈[k 10m k 5m ], bias b∈[b 10m b 5m ].
[0120] Joint parametric equations:
[0121] Where n′∈[5, 10], D∈[D1, D2].
[0122] The joint parametric equation can be transformed into a quadratic equation in one variable. In practice, the equation has two real roots. The valid root of the solution located between the two trajectory lines is retained; this is the x-coordinate of the endpoint. Substituting this root into the equation of the straight line yields the y-coordinate. The coordinates of the endpoints corresponding to the four inner lines are then obtained. Connecting the corresponding starting and ending points gives the inner lines.
[0123] Step S12, when the vehicle turns left or right, it can be considered as symmetrical to the centerline of the vehicle's straight-line direction. Based on this principle, after finding the axis of symmetry, the left turn direction can be considered as the mirror image of the right turn direction about the axis of symmetry. The right turn pixel coordinate set, after being mirrored and flipped based on the axis of symmetry, becomes the left turn pixel coordinate set.
[0124] Step S13: Finally, draw the left and right turning trajectory lines and the four inner lines on the image for the left or right turn direction.
[0125] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 4 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.
[0126] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.
[0127] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.
[0128] The processor reads the corresponding computer program from non-volatile memory into main memory and then executes it, forming a parallel driving steering trajectory data processing device at the logical level. The processor executes the program stored in memory and specifically performs the following operations:
[0129] The image pixel coordinates of the trajectory lines of the wheels at different steering angles and corresponding positions in front of the vehicle are pre-marked, and the trajectory lines are represented by a parabola equation to obtain a parabola.
[0130] The image pixel coordinates of the points on the trajectory line at a preset position in front of the vehicle at different steering angles are pre-marked, and a first trajectory line equation is established based on the image pixel coordinates of the points on the trajectory line.
[0131] After performing a preset transformation operation on the first trajectory line equation, a second trajectory line equation under a preset steering angle is obtained.
[0132] Based on the driving warning line curve equation fitted to the target position in front of the vehicle and the second trajectory line equation, the coordinates of the trajectory line at the target distance under the preset steering angle are determined, and the position of the target distance in front of the vehicle is the driving warning position.
[0133] The parallel driving steering trajectory data is plotted based on the coordinates of the target position and the second trajectory line equation under the preset steering angle.
[0134] The above is as stated in this application. Figure 1 The method executed by the parallel driving steering trajectory data processing device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.
[0135] The electronic device can also perform Figure 1 A method for processing parallel driving steering trajectory data in a device, and implementation of the parallel driving steering trajectory data processing device in... Figure 1 The functions of the embodiments shown are not described in detail here.
[0136] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by an electronic device including multiple applications, enable the electronic device to perform... Figure 1 The method executed by the parallel driving steering trajectory data processing device in the illustrated embodiment is specifically used to perform:
[0137] The image pixel coordinates of the points on the trajectory line at a preset position in front of the vehicle at different steering angles are pre-marked, and a first trajectory line equation is established based on the image pixel coordinates of the points on the trajectory line.
[0138] After performing a preset transformation operation on the first trajectory line equation, a second trajectory line equation under a preset steering angle is obtained.
[0139] Based on the driving warning line curve equation fitted to the target position in front of the vehicle and the second trajectory line equation, the coordinates of the trajectory line at the target distance under the preset steering angle are determined, and the position of the target distance in front of the vehicle is the driving warning position.
[0140] The parallel driving steering trajectory data is plotted based on the coordinates of the target position and the second trajectory line equation under the preset steering angle.
[0141] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0142] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0143] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0144] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0145] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0146] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0147] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media do not include transient computer-readable media, such as modulated data signals and carrier waves.
[0148] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0149] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0150] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.
Claims
1. A method for processing parallel driving steering trajectory data, wherein, The method includes: The image pixel coordinates of the points on the trajectory line at a preset position in front of the vehicle at different steering angles are pre-marked, and a first trajectory line equation is established based on the image pixel coordinates of the points on the trajectory line. The image pixel coordinates corresponding to the trajectory lines of the wheels at different steering angles and at a preset position in front of the vehicle are pre-marked, and the trajectory lines are represented by a parabola equation to obtain a parabola, including: Based on the annotation range and interval, the image pixel positions corresponding to multiple locations at distances from the front of the vehicle on the left and right trajectory lines of the wheels at different steering angles in the real scene are pre-annotated, and the annotated physical distances are mapped to the image pixel coordinate positions. Where m represents the steering angle of the corresponding wheel, n represents the marked front position of the vehicle, and d represents the left and right markings of the trajectory line; After performing a preset transformation operation on the first trajectory line equation, a second trajectory line equation under a preset steering angle is obtained. The step of obtaining the parabolic equation at a preset turning angle after performing a preset transformation operation on the first trajectory equation includes: Perform a vertical flip and translation operation on the parabola equation to move the parabola to the positions of the left and right starting points of the pre-marked trajectory line, while keeping the opening direction of the parabola unchanged; The tilt angle is calculated based on the pre-marked trajectory line of the wheel with a turning angle of 0 degrees. Based on the tilt angle, the parabola that has been rotated to the front position is tilted to obtain the tilt coordinates after rotation, which are used to obtain the parabola equation under the preset steering angle. Based on the driving warning line curve equation fitted to the target position in front of the vehicle and the parabolic equation, the coordinates of the trajectory line at the target position under the preset steering angle are determined. The target position in front of the vehicle is the driving warning position, including: Establish each steering angle To determine the relationship between the angle and the parabola parameter P, a polynomial fitting method is used to establish the equation between the angle and the parabola parameter P. Based on the equation between the angle and the parabolic parameters, determine the coordinates of the trajectory line at the target position under the preset turning angle; Based on the driving warning line curve equation fitted to the target position in front of the vehicle and the second trajectory line equation, the coordinates of the trajectory line at the target distance under the preset steering angle are determined, and the position of the target distance in front of the vehicle is the driving warning position. The parallel driving steering trajectory data is plotted based on the coordinates of the target position and the second trajectory line equation under the preset steering angle.
2. The method as described in claim 1, wherein, The step of determining the coordinates of the trajectory line at the target distance under the preset steering angle by using the driving warning line curve equation fitted based on the target position in front of the vehicle and the second trajectory line equation includes: Based on the image pixel coordinates of the trajectory line corresponding to the target distance in front of the vehicle, polynomial fitting is performed to establish the curve equation at each target position. Based on the joint equation set established by the curve equation at each target position and the second trajectory equation, the coordinates of the trajectory at the target position under the preset turning angle are calculated.
3. The method as described in claim 2, wherein, The method further includes: Based on the coordinates of the trajectory line at the target position under the preset turning angle and the preset inner line length at the target position, determine the starting point of each of the two inner lines at the target position; By combining the straight line equation and the distance equation, the endpoints of the two inner lines at each target location are obtained; Connect the starting point and the ending point to obtain the inner line of the parallel driving steering trajectory data.
4. The method as described in claim 1, wherein, The parabolic parameter P is obtained in the following way: The parameter P corresponding to the parabola's fit with the marked trajectory line when the right steering angle of the wheel is manually adjusted to different angles is given by the following formula: ,in This indicates the steering angle of the corresponding wheel, and d represents the left and right indicators of the trajectory line.
5. A device for processing parallel driving steering trajectory data, wherein, The device includes: The annotation module is used to pre-annotate the image pixel coordinates of points on the trajectory line at a preset position in front of the vehicle at different steering angles, and to establish a first trajectory line equation based on the image pixel coordinates of the points on the trajectory line. The image pixel coordinates corresponding to the trajectory lines of the wheels at different steering angles and their distance from the front of the vehicle are pre-marked, and the trajectory lines are represented by a parabola equation to obtain a parabola, including: Based on the annotation range and interval, the image pixel positions corresponding to multiple locations at distances from the front of the vehicle on the left and right trajectory lines of the wheels at different steering angles in the real scene are pre-annotated, and the annotated physical distances are mapped to the image pixel coordinate positions. Where m represents the steering angle of the corresponding wheel, n represents the marked front position of the vehicle, and d represents the left and right markings of the trajectory line; The trajectory line coordinate module is used to obtain the second trajectory line equation under a preset turning angle after the first trajectory line equation is established through a preset transformation operation. The step of obtaining the parabolic equation at a preset turning angle after performing a preset transformation operation on the first trajectory equation includes: Perform a vertical flip and translation operation on the parabola equation to move the parabola to the positions of the left and right starting points of the pre-marked trajectory line, while keeping the opening direction of the parabola unchanged; The tilt angle is calculated based on the pre-marked trajectory line of the wheel with a turning angle of 0 degrees. Based on the tilt angle, the parabola that has been rotated to the front position is tilted to obtain the tilt coordinates after rotation, which are used to obtain the parabola equation under the preset steering angle. Based on the driving warning line curve equation fitted to the target position in front of the vehicle and the parabolic equation, the coordinates of the trajectory line at the target position under the preset steering angle are determined. The target position in front of the vehicle is the driving warning position, including: Establish each steering angle To determine the relationship between the angle and the parabola parameter P, a polynomial fitting method is used to establish the equation between the angle and the parabola parameter P. Based on the equation between the angle and the parabolic parameters, determine the coordinates of the trajectory line at the target position under the preset turning angle; The determination module is used to determine the coordinates of the trajectory line at the target distance under the preset steering angle based on the driving warning line curve equation fitted to the target position in front of the vehicle and the second trajectory line equation, wherein the position of the target distance in front of the vehicle is the driving warning position. The drawing module is used to draw the parallel driving steering trajectory data based on the coordinates of the target position and the second trajectory line equation under the preset steering angle.
6. An electronic device, comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the method of any one of claims 1 to 4.
7. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform the method of any one of claims 1 to 4.