Path generation method, device and electronic equipment based on automatic driving

Abstract

The embodiment of the application relates to the technical field of automatic driving, and discloses a path generation method based on automatic driving, which comprises the following steps: determining current heading information of a current position of a vehicle and target heading information of a terminal point; calculating a deviation amount between the current heading information and the target heading information; if the deviation amount is greater than a preset value, generating a plurality of predicted driving tracks corresponding to the current vehicle; selecting a target point of the current vehicle on the predicted driving tracks according to a positional relationship between the predicted driving tracks and the terminal point; continuously generating a next target point based on a deviation amount between the target point and the terminal point until the target point coincides with the terminal point; and generating a path through a plurality of segments of tracks formed among the current position, the plurality of target points and the terminal point. The application generates an optimal path returning to the original point through the plurality of segments of tracks among the target points, reduces driving time of the vehicle returning to the original point, and thus improves demonstration efficiency of an examination subject.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of automatic driving, in particular to a path generation method and device based on automatic driving and electronic equipment. BACKGROUND

[0002] In the traditional driving school teaching process, in order to teach students, the coach needs to personally drive the coach car to demonstrate, but the coach's energy is limited, and it is difficult to repeatedly drive the coach car for demonstration in a short time, so that students can only obtain a few times of demonstration teaching when learning.

[0003] In order to improve the teaching efficiency, the existing coach car can be modified by adding an automatic driving system to realize automatic driving demonstration of the driving school examination project. In the automatic driving demonstration process of the driving school examination project, the existing coach car needs to start from the starting point of each project for complete automatic driving demonstration each time.

[0004] However, the vehicle may not be in a suitable position when the student starts the automatic driving demonstration, and if the vehicle still drives according to the predetermined demonstration route, the vehicle may not be able to drive according to the demonstration route due to a large position deviation, causing demonstration failure and other dangers. Therefore, if the vehicle is not at the original position, it needs to be manually driven to the starting position, or automatically driven back to the starting position. Due to the narrow space, the existing vehicle needs to try different paths multiple times to automatically drive back to the original position, which consumes a lot of time and causes low demonstration efficiency. SUMMARY

[0005] To solve the above problems, embodiments of the present application provide a path generation method and device based on automatic driving and electronic equipment, which can improve the accuracy of path generation and thus improve the demonstration efficiency of the vehicle.

[0006] In a first aspect, the present application provides a path generation method based on automatic driving, applied to an electronic device, the method comprising:

[0007] determining current heading information of a current position of a vehicle and target heading information of a terminal point, the current heading information and the target heading information comprising positioning coordinate parameters and vehicle heading corresponding heading parameters;

[0008] calculating a deviation amount between the current heading information and the target heading information;

[0009] if the deviation amount is greater than a preset value, generating a plurality of predicted driving trajectories corresponding to the current vehicle;

[0010] selecting a target point of the current vehicle on the predicted driving trajectory according to the positional relationship between the predicted driving trajectory and the terminal point.

[0011] continuing to generate a next target point based on the deviation between the target point and the end point until the target point coincides with the end point;

[0012] generating a path based on a plurality of segments formed by the current position, the target points and the end point.

[0013] In an embodiment, the predicted driving trajectory includes a predicted driving trajectory in a forward direction of the vehicle and a predicted driving trajectory in a backward direction of the vehicle.

[0014] In an embodiment, the generating a plurality of predicted driving trajectories of the current vehicle includes:

[0015] obtaining a vehicle model, the vehicle model including a wheelbase and a maximum steering angle of the vehicle;

[0016] obtaining a minimum turning radius of the vehicle in the forward direction and the backward direction according to the vehicle model;

[0017] obtaining a plurality of predicted driving trajectories in the forward direction and the backward direction based on different steering angles according to the minimum turning radius of the vehicle.

[0018] In an embodiment, the calculating the deviation between the current heading information and the target heading information includes:

[0019] if a heading parameter of the current heading information is a heading parameter of the target heading information is

[0020] calculating obtaining a heading difference between the current heading information and the target heading information;

[0021] determining whether the heading difference is less than 180 degrees;

[0022] if the heading difference is less than 180 degrees, the heading included angle is otherwise, the heading included angle is

[0023] if the deviation is greater than a preset value, generating a plurality of predicted driving trajectories corresponding to the current vehicle includes:

[0024] determining whether the heading included angle is greater than a maximum steering angle of the vehicle; if the heading included angle is greater than the maximum steering angle of the vehicle, generating the plurality of predicted driving trajectories corresponding to the current vehicle according to the heading included angle and

[0025]

[0026] ​​​In an embodiment, the target point of the current vehicle is selected on the predicted driving track according to the positional relationship between the predicted driving track and the terminal point, and the method comprises:

[0027] determining the relative distance between each predicted driving track and the terminal point;

[0028] retrieving the point on the predicted driving track with the minimum relative distance as the target point of the current vehicle.

[0029] In an embodiment, the path is generated through the multi-segment track formed by the current position, the target points and the terminal point, and the method comprises:

[0030] obtaining the preset acceleration values in different vehicle states, and the driving time of each segment from the current position to the target point, from the target point to the target point, and from the target point to the terminal point;

[0031] calculating the multi-segment track from the current position to the target point, from the target point to the target point, and from the target point to the terminal point based on a quintic polynomial according to the acceleration values and the driving time;

[0032] splicing the multi-segment track to obtain the total path from the current position to the terminal point.

[0033] In a second aspect, the application further discloses an automatic driving-based path generation device, which comprises:

[0034] an information determination module configured to determine the current heading information of the current position of the vehicle and the target heading information of the terminal point, wherein the current heading information and the target heading information comprise positioning coordinate parameters and vehicle heading parameters corresponding to the heading parameters;

[0035] a calculation module configured to calculate the deviation between the current heading information and the target heading information;

[0036] a predicted driving track generation module configured to generate a plurality of predicted driving tracks corresponding to the current vehicle if the deviation is greater than a preset value;

[0037] a target point selection module configured to select the target point of the current vehicle on the predicted driving track according to the positional relationship between the predicted driving track and the terminal point, and continue to generate the next target point based on the deviation between the target point and the terminal point until the target point coincides with the terminal point;

[0038] a path generation module configured to generate the path through the multi-segment track formed by the current position, the target points and the terminal point.

[0039] In an embodiment, the predicted driving track comprises a predicted driving track in the forward direction of the vehicle and a predicted driving track in the backward direction of the vehicle;

[0040] The predicted driving trajectory generation module is specifically used for:

[0041] Obtain a vehicle model, which includes the vehicle wheelbase and maximum steering angle;

[0042] The minimum turning radius of the vehicle in the forward and reverse directions is obtained based on the vehicle model.

[0043] Based on the vehicle's minimum turning radius, several predicted driving trajectories are obtained in the forward and reverse directions under different steering angles.

[0044] In one embodiment, the predicted driving trajectory generation module is specifically used for:

[0045] Determine the relative distance between each of the predicted driving trajectories and the destination;

[0046] The point on the predicted driving trajectory with the smallest relative distance is selected as the target point of the current vehicle.

[0047] Thirdly, this application also provides an electronic device, which includes a processor and a memory, wherein the processor and the memory are electrically connected.

[0048] The memory stores a computer program, and the processor executes the path generation method based on autonomous driving as described above by calling the computer program stored in the memory.

[0049] This autonomous driving-based path generation method, device, and electronic device determines the deviation between the current heading information and the target heading information. If the deviation is greater than a preset value, several predicted driving trajectories are generated. By generating several predicted driving trajectories and based on the positional relationship between different predicted driving trajectories and the destination, several target points for smoothing the trajectories are generated. Then, the optimal path back to the origin is generated through multiple trajectories between the target points, reducing the vehicle's travel time back to the origin and thus improving the demonstration efficiency of the examination subject. Attached Figure Description

[0050] Figure 1 This is a flowchart illustrating the implementation of the path generation method based on autonomous driving provided in an embodiment of this application.

[0051] Figure 2 This is an application scenario diagram of the path generation method based on autonomous driving provided in the embodiments of this application.

[0052] Figure 3 The flowchart illustrates the implementation of selecting target points in an embodiment of this application.

[0053] Figure 4This is a schematic diagram of the structure of the path generation device based on autonomous driving provided in an embodiment of this application.

[0054] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the specific technical solutions of this application will be further described in detail below with reference to the accompanying drawings of the embodiments of this application. The following embodiments are used to illustrate this application, but are not intended to limit the scope of this application.

[0056] Please see Figure 1 The figure illustrates the implementation flow of the path generation method based on autonomous driving provided in an embodiment of this application.

[0057] like Figure 1 As shown, the path generation method based on autonomous driving may include the following implementation steps.

[0058] 101. Determine the current heading information of the vehicle's current location and the target heading information of the destination.

[0059] The current heading information and target heading information include positioning coordinate parameters and heading parameters corresponding to the vehicle's orientation.

[0060] The positioning coordinates can be obtained through the device's built-in positioning device, such as positioning coordinates obtained through GPS, Beidou or other satellite navigation, or positioning coordinates of the internal site obtained through Bluetooth, WIFI or other means. The positioning coordinates can be obtained using common methods in the field, and this application does not limit them.

[0061] The heading parameters corresponding to the vehicle's orientation can be obtained through methods such as gyroscope, magnetic induction, and inertial positioning. These parameters correspond to the azimuth parameters when the vehicle is traveling in the forward direction.

[0062] In one embodiment, the target heading information of the destination can be obtained from an origin point pre-set at the test or training ground that meets the requirements of the test or training, i.e., an ideal starting point for the vehicle when starting during the test or training. The current heading information of the vehicle can be obtained through a positioning device installed on the vehicle. Both the target heading information and the current heading information of the destination include positioning coordinate parameters and heading parameters.

[0063] Specifically, each project (parallel parking, reversing into a parking space, right-angle turn, and curved driving) defines an origin. The origin is, in principle, the starting position at the entrance of each project, with the initial heading being the direction the vehicle normally travels. Based on the vehicle's location information, it is first determined which project the vehicle is in, and then the predefined origin and heading for that project are selected as the endpoint and target heading of the trajectory.

[0064] It is understandable that the origin (i.e., the vehicle's destination) and target heading may differ in different test items and different venues, and can be determined according to the actual situation.

[0065] 102. Calculate the deviation between the current heading information and the target heading information.

[0066] The deviation may include the angle difference between the heading parameters between the endpoint and the current position, and / or the distance deviation obtained from the positioning coordinate parameters between the endpoint and the current position.

[0067] In one embodiment, the deviation can be set based on a vehicle model and a site model. For example, the vehicle model may include data such as the vehicle's wheelbase, length, width, and maximum steering angle, while the site model may include the positioning coordinates of each boundary point of the site. The position of each boundary of the site can be determined based on the positioning coordinates of each boundary point.

[0068] It can be seen that by using the data information of the vehicle model and the site model, it can be determined whether the vehicle can reach the destination from the current position in one step when driving normally. If it is known from the parameters provided by the current heading information and the target heading information that the vehicle cannot reach the destination in one step, it can be confirmed that several target points need to be generated to smooth its path so that the vehicle can reach the destination by achieving the target heading parameters.

[0069] Furthermore, a preset deviation can be used to determine whether a target point needs to be generated. For example, the deviation could include whether the angle difference between the heading parameters of the endpoint and the current position is greater than the vehicle's turning radius. If it is, it can be determined that the vehicle cannot reach the endpoint in one trip. This deviation setting can be determined based on the site model and vehicle model to determine whether a target point needs to be generated.

[0070] In one embodiment, calculating the deviation between the current heading information and the target heading information may include:

[0071] If the heading parameter of the current heading information is The heading parameters of the target heading information are: calculate Obtain the heading difference between the current heading information and the target heading information; determine if the heading difference is less than 180 degrees; if it is less than 180 degrees, then determine the heading angle. Otherwise

[0072] Using the above method, the deviation of the heading parameters between the current heading information and the target heading information can be calculated.

[0073] 103. Determine if the deviation is greater than the preset value. If yes, generate several predicted driving trajectories for the current vehicle; otherwise, end this step.

[0074] At this point, the vehicle's current heading information and the target heading information can be compared with corresponding preset values. Understandably, these preset values ​​can be determined based on actual conditions. The method for determining the deviation can be implemented using techniques available in this field.

[0075] 104. If the deviation is greater than the preset value, several predicted driving trajectories corresponding to the current vehicle will be generated.

[0076] Specifically, it can determine the heading angle. Is it greater than the vehicle's maximum steering angle? If so, then based on the heading angle... as well as Generate several predicted driving trajectories corresponding to the current vehicle. It can be seen that, through the included angle... as well as Generating a predicted driving trajectory can improve the accuracy of the predicted driving trajectory, thereby increasing the success rate and efficiency of the vehicle returning to its origin.

[0077] The predicted driving trajectory can include the predicted driving trajectory of the vehicle at different steering angles. For example, if the steering angle of the outer wheel of the vehicle is 40° and the steering angle of the inner wheel is 33.5°, then the predicted driving trajectory at various angles within that steering angle can be generated by taking into account the size of the steering angle.

[0078] In one embodiment, the generated predicted driving trajectory may include multiple predicted driving trajectories spaced 1° apart by steering angle. If the maximum steering angle of the vehicle is 38°, then predicted driving trajectories are generated at each angle of 1°, 2°...38°.

[0079] In another embodiment, the predicted driving trajectory may include not only the predicted driving trajectory in the forward direction of the vehicle, but also the predicted driving trajectory in the reverse direction. Of course, if the predicted driving trajectory is in the forward direction, it is generated according to the maximum steering angle in the forward direction; if the predicted driving trajectory is in the reverse direction, it is generated according to the maximum steering angle in the reverse direction.

[0080] Understandably, the maximum steering angle for the forward and reverse directions of a vehicle is slightly different, which can be achieved based on the actual vehicle model for each vehicle.

[0081] Furthermore, the vehicle's predicted driving trajectory is also related to the scene model. The vehicle's predicted driving trajectory generally does not exceed the boundary position of the scene, and the width and length of the predicted driving trajectory are related to the width and length of the vehicle, in order to avoid the vehicle going beyond the site boundary or even colliding with objects outside the boundary during automatic driving.

[0082] 105. Based on the positional relationship between the predicted driving trajectory and the destination, select the target point of the current vehicle on the predicted driving trajectory.

[0083] The positional relationship between the predicted driving trajectory and the destination can include the distance or orientation between various points on the predicted driving trajectory and the destination. This positional relationship can be related to the predicted time and predicted distance between various points on the predicted driving trajectory and the destination. If there is a point on the predicted driving trajectory with the shortest driving distance to the destination, or with the fewest subsequent target points, then that point can be used as the target point.

[0084] In one embodiment, the positional relationship between the predicted driving trajectory and the destination can be determined by calculating the distance from the predicted driving trajectory to the destination. If a certain point on a predicted driving trajectory is the closest to the destination, then that point can be set as the next target point for the vehicle on the predicted driving trajectory.

[0085] Furthermore, the target point can be a point on the predicted driving trajectory in the forward direction of the vehicle or a point on the predicted driving trajectory in the backward direction of the vehicle. The target point can be determined by comprehensively retrieving the positional relationship between the predicted driving trajectory and the destination in both directions simultaneously or separately.

[0086] By selecting the target point of the current vehicle based on the positional relationship between the predicted driving trajectory and the destination, the point with the highest driving efficiency can be effectively selected as the optimal node passed through during the vehicle's return to the origin, thereby minimizing the vehicle's trajectory distance and number of attempts and improving the efficiency of the vehicle's return to the origin.

[0087] 106. Based on the deviation between the target point and the endpoint, continue to generate the next target point until the target point and the endpoint coincide.

[0088] Once the target point is determined, the predicted heading information of the vehicle when it reaches that target point can be obtained, that is, the position coordinate parameters and heading parameters of the vehicle after it reaches the target point. The heading information of the target point is used to recalculate the deviation of the heading information between the target point and the destination, and the deviation is used to generate several predicted driving trajectories of the vehicle at the target point. The predicted driving trajectories are then used to determine the position of the next target point.

[0089] Of course, the implementation method of generating the next target point based on the deviation between the target point and the endpoint can refer to the steps in 103-105, which will not be repeated here.

[0090] If the next target point coincides with the destination, that is, the distance between the next target point and the destination is 0, and the heading parameters are the same, then it can be considered that the vehicle can travel to the destination in one step from the current target point. At this time, it can be determined that no further target points will be generated, and the trajectory generation is completed.

[0091] 107. Generate a path by using the multiple trajectories formed by the current location, several target points, and the endpoint.

[0092] After generating several target points, the points corresponding to the current location, the destination, and the predicted driving trajectories between the generated points can be strung together to form the overall path, thus completing the path generation.

[0093] At this point, to achieve a better autonomous driving experience, the multiple trajectory segments can be further smoothed. Specifically, the step of generating a path using the multiple trajectory segments formed by the current position, several target points, and the destination can include the following steps.

[0094] Obtain the acceleration values ​​under different preset vehicle states, as well as the travel time for each segment from the current position to the target point, from the target point to the target point, and from the target point to the destination; based on the acceleration values ​​and travel time, calculate multiple trajectories from the current position to the target point, from the target point to the target point, and from the target point to the destination using a fifth-order polynomial; stitch the multiple trajectories together to obtain the total path from the current position to the destination.

[0095] The acceleration value can be determined based on the vehicle's acceleration capability and the force analysis of the occupants, according to the actual situation. The travel time for each segment can be estimated based on the actual travel distance from the current location to the target point, from the target point to the target point, and from the target point to the destination, as well as the acceleration value.

[0096] By smoothing with a fifth-order polynomial, we can obtain the data information corresponding to the actual path used for autonomous driving trajectory, which can then be used for autonomous driving navigation to return the vehicle to its origin.

[0097] Specifically, you can refer to the following formula to achieve smoothing:

[0098] q(t) = a0 + a1(t-t0) + a2(t-t0) 2 +a3(t-t0) 3 +a4(t-t0) 4 +a5(t-t0) 5

[0099] Where q is the position, a is the acceleration, and t-t0 is the time between the two points.

[0100] In some embodiments, during autonomous driving, the vehicle follows a series of tracks, moving forward or backward accordingly. Based on the deviation between the current vehicle position and the target track, vehicle tracking algorithms, including but not limited to PID, are used to continuously track the steering wheel angle. The vehicle eventually travels along the track, and after straightening the vehicle to reach the starting position (i.e., the endpoint of this operation), the autonomous driving demonstration can continue.

[0101] Combination Figure 2 The figure shows an application scenario of the path generation method based on autonomous driving in this application.

[0102] In such Figure 2 In the scenario shown, the current position is Q1, and the destination is Q4. If the vehicle at Q1 is pointing directly to the right, and the vehicle at the destination Q4 is also pointing directly to the right, the deviation between Q1 and Q4 is determined. Based on the vehicle model and the terrain model, a predicted driving trajectory at Q1 is generated, yielding the target point Q2 and a trajectory D1 in the backward direction relative to Q1. Then, a predicted driving trajectory is generated based on Q2, yielding the target point Q3 and a trajectory D2 in the forward direction relative to Q2. Finally, a trajectory D3 in the backward direction relative to Q3 is generated based on Q3 to reach the destination Q4.

[0103] The trajectories D1, D2, and D3 can all be smoothed using the aforementioned fifth-order polynomials, and then spliced ​​together to form a smoothed path D1-D3 for autonomous driving.

[0104] As can be seen from the above, by judging the deviation between the current heading information and the target heading information, if the deviation is greater than the preset value, several predicted driving trajectories are generated. By generating several predicted driving trajectories and based on the positional relationship between different predicted driving trajectories and the destination, several target points for smoothing the trajectory are generated. Then, the optimal path back to the origin is generated through multiple trajectories between the target points, reducing the vehicle's travel time back to the origin and thus improving the demonstration efficiency of the test subject.

[0105] Please refer to Figure 3 The figure shows a flowchart of the implementation of selecting target points provided in an embodiment of this application.

[0106] likeFigure 3 As shown, the process of selecting the target point can further include the following steps.

[0107] 201. Obtain the vehicle model, which includes the vehicle wheelbase and maximum steering angle.

[0108] The vehicle's wheelbase and maximum steering angle can both be obtained from the factory data of different vehicles. This vehicle model can be stored in the vehicle's autonomous driving system or set in a pre-set database in the cloud; this application does not limit the specific storage method.

[0109] In one embodiment, the vehicle model may further include information related to the length and width of the vehicle, which may also be obtained by actual measurement of the vehicle.

[0110] In another embodiment, to determine the vehicle's current location, a positioning point can be set on the vehicle. This positioning point can be used to receive positioning signals to achieve positioning. By determining the installation position of the positioning point on the vehicle and its relative position in the vehicle model, the vehicle's current specific location can be determined, thereby improving the accuracy of the algorithm in generating paths and in the autonomous driving process.

[0111] 202. Based on the vehicle model, obtain the minimum turning radius of the vehicle in the forward and backward directions.

[0112] Specifically, based on the vehicle's wheelbase and maximum steering angle, the minimum turning radius of the vehicle is calculated using the formula R = L / 2(sin X) (where R is the minimum turning radius, L is the wheelbase, and X is the maximum steering angle).

[0113] Of course, different vehicles have different length and width specifications, as well as different maximum steering angles in the forward or reverse direction. The minimum turning radius of the vehicle can be calculated based on the actual maximum steering angle, thereby achieving a more accurate calculation of the predicted driving trajectory.

[0114] 203. Based on the vehicle's minimum turning radius, obtain several predicted driving trajectories in the forward and reverse directions under different steering angles.

[0115] In one embodiment, the generated predicted driving trajectory may include multiple predicted driving trajectories spaced 1° apart by steering angle. If the maximum steering angle of the vehicle is 38°, then predicted driving trajectories are generated at each angle of 1°, 2°...38°.

[0116] Of course, in addition to the example interval of 1°, different intervals of steering angle can be set according to actual computing power to ensure that the generated predicted driving trajectory is as close as possible to the actual situation.

[0117] By using the above-mentioned method to generate the predicted driving trajectory, the accuracy of the predicted driving trajectory can be improved, thereby improving the accuracy of the subsequent target point and path generation.

[0118] 204. Determine the relative distance between each predicted driving trajectory and the destination.

[0119] In one embodiment, the positional relationship between the predicted driving trajectory and the destination can be determined by calculating the distance from the predicted driving trajectory to the destination. If a certain point on a predicted driving trajectory is the closest to the destination, then that point can be set as the next target point for the vehicle on the predicted driving trajectory.

[0120] Furthermore, the target point can be a point on the predicted driving trajectory in the forward direction of the vehicle or a point on the predicted driving trajectory in the backward direction of the vehicle. The target point can be determined by comprehensively retrieving the positional relationship between the predicted driving trajectory and the destination in both directions simultaneously or separately.

[0121] 205. Select the point on the predicted driving trajectory with the smallest relative distance as the target point of the current vehicle.

[0122] By selecting the target point of the current vehicle based on the distance between the predicted driving trajectory and the destination, the point with the highest driving efficiency can be effectively selected as the optimal node passed through during the vehicle's return to the origin, thereby minimizing the vehicle's trajectory distance and number of attempts and improving the efficiency of the vehicle's return to the origin.

[0123] As can be seen from the above, the generation of the predicted driving trajectory, by combining it with the vehicle model and using the distance relationship between the predicted driving trajectory and the destination to select and determine the target point, can improve the accuracy of target point selection, thereby improving the efficiency of the vehicle returning to the origin.

[0124] Please refer to Figure 4 The figure shows the structure of a path generation device based on autonomous driving provided in an embodiment of this application.

[0125] like Figure 4 As shown, the autonomous driving-based path generation device 10 includes:

[0126] The information determination module 11 is used to determine the current heading information of the vehicle's current position and the target heading information of the destination. The current heading information and the target heading information include positioning coordinate parameters and heading parameters corresponding to the vehicle's orientation.

[0127] The current heading information and target heading information include positioning coordinate parameters and heading parameters corresponding to the vehicle's orientation.

[0128] The positioning coordinates can be obtained through the device's built-in positioning device, such as positioning coordinates obtained through GPS, Beidou or other satellite navigation, or positioning coordinates of the internal site obtained through Bluetooth, WIFI or other means. The positioning coordinates can be obtained using common methods in the field, and this application does not limit them.

[0129] The heading parameters corresponding to the vehicle's orientation can be obtained through methods such as gyroscope, magnetic induction, and inertial positioning. These parameters correspond to the azimuth parameters when the vehicle is traveling in the forward direction.

[0130] The calculation module 12 is used to calculate the deviation between the current heading information and the target heading information.

[0131] The deviation may include the angle difference between the heading parameters between the endpoint and the current position, and / or the distance deviation obtained from the positioning coordinate parameters between the endpoint and the current position.

[0132] In one embodiment, the deviation can be set based on a vehicle model and a site model. For example, the vehicle model may include data such as the vehicle's wheelbase, length, width, and maximum steering angle, while the site model may include the positioning coordinates of each boundary point of the site. The position of each boundary of the site can be determined based on the positioning coordinates of each boundary point.

[0133] It can be seen that by using the data information of the vehicle model and the site model, it can be determined whether the vehicle can reach the destination from the current position in one step when driving normally. If it is known from the parameters provided by the current heading information and the target heading information that the vehicle cannot reach the destination in one step, it can be confirmed that several target points need to be generated to smooth its path so that the vehicle can reach the destination by achieving the target heading parameters.

[0134] The predicted driving trajectory generation module 13 is used to generate several predicted driving trajectories corresponding to the current vehicle if the deviation is greater than a preset value.

[0135] Specifically, it can determine the heading angle. Is it greater than the vehicle's maximum steering angle? If so, then based on the heading angle... as well as Generate several predicted driving trajectories corresponding to the current vehicle. It can be seen that, through the included angle... as well as Generating a predicted driving trajectory can improve the accuracy of the predicted driving trajectory, thereby increasing the success rate and efficiency of the vehicle returning to its origin.

[0136] The predicted driving trajectory can include the predicted driving trajectory of the vehicle at different steering angles. For example, if the steering angle of the outer wheel of the vehicle is 40° and the steering angle of the inner wheel is 33.5°, then the predicted driving trajectory at various angles within that steering angle can be generated by taking into account the size of the steering angle.

[0137] The target point selection module 14 is used to select the target point of the current vehicle on the predicted driving trajectory based on the positional relationship between the predicted driving trajectory and the destination; and to continue to generate the next target point based on the deviation between the target point and the destination until the target point coincides with the destination.

[0138] The positional relationship between the predicted driving trajectory and the destination can include the distance or orientation between various points on the predicted driving trajectory and the destination. This positional relationship can be related to the predicted time and predicted distance between various points on the predicted driving trajectory and the destination. If there is a point on the predicted driving trajectory with the shortest driving distance to the destination, or with the fewest subsequent target points, then that point can be used as the target point.

[0139] In one embodiment, the positional relationship between the predicted driving trajectory and the destination can be determined by calculating the distance from the predicted driving trajectory to the destination. If a certain point on a predicted driving trajectory is the closest to the destination, then that point can be set as the next target point for the vehicle on the predicted driving trajectory.

[0140] Once the target point is determined, the predicted heading information of the vehicle when it reaches that target point can be obtained, that is, the position coordinate parameters and heading parameters of the vehicle after it reaches the target point. The heading information of the target point is used to recalculate the deviation of the heading information between the target point and the destination, and the deviation is used to generate several predicted driving trajectories of the vehicle at the target point. The predicted driving trajectories are then used to determine the position of the next target point.

[0141] Of course, the implementation method of generating the next target point based on the deviation between the target point and the endpoint can refer to the steps in 103-105, which will not be repeated here.

[0142] The path generation module 15 is used to generate a path from the current position, several target points and the endpoint, which form multiple trajectories.

[0143] After generating several target points, the points corresponding to the current location, the destination, and the predicted driving trajectories between the generated points can be strung together to form the overall path, thus completing the path generation.

[0144] As can be seen from the above, the device generates several predicted driving trajectories and, based on the positional relationship between different predicted driving trajectories and the destination, generates several target points for smoothing the trajectories. Then, it generates the optimal path back to the origin through multiple trajectories between the target points, thereby reducing the vehicle's travel time back to the origin and improving the demonstration efficiency of the examination subject.

[0145] In one embodiment, the predicted driving trajectory includes a predicted driving trajectory in the forward direction of the vehicle and a predicted driving trajectory in the reverse direction of the vehicle. The predicted driving trajectory generation module is specifically used for:

[0146] Obtain a vehicle model, which includes the vehicle wheelbase and maximum steering angle;

[0147] The minimum turning radius of the vehicle in the forward and reverse directions is obtained based on the vehicle model;

[0148] Based on the vehicle's minimum turning radius, several predicted driving trajectories are obtained in the forward and reverse directions under different steering angles.

[0149] In one embodiment, the predicted driving trajectory generation module is specifically used for:

[0150] Determine the relative distance between each predicted driving trajectory and the destination, and select the point on the predicted driving trajectory with the smallest relative distance as the target point of the current vehicle.

[0151] The aforementioned predicted driving trajectory generation module can combine with the vehicle model and use the distance relationship between the predicted driving trajectory and the destination to select and determine the target point, thereby improving the accuracy of target point selection and thus improving the efficiency of the vehicle returning to the origin.

[0152] The specific implementation method of this device can be referenced as follows: Figures 1-3 The path generation method based on autonomous driving will not be described in detail in this application.

[0153] Please see Figure 5 The figure shows a structural diagram of the electronic device provided in an embodiment of this application.

[0154] like Figure 5 As shown, the electronic device can be a general vehicle terminal, such as an in-vehicle entertainment terminal or a vehicle-mounted system. Alternatively, it can be a portable terminal, such as a smartphone, tablet, laptop, or desktop computer. It can also be an electronic interactive system with specific functions, such as an in-vehicle entertainment system, or other electronic devices that can interact with the user, sending location information and generated route information by connecting to the in-vehicle entertainment terminal or vehicle-mounted system.

[0155] The electronic device includes a processor 21 and a memory 22, which are electrically connected. The memory 22 stores a computer program, and the processor 21 executes the path generation method based on autonomous driving mentioned in any of the above embodiments by calling the computer program stored in the memory 22. For example:

[0156] The system determines the current heading information of the vehicle's current position and the target heading information of the destination, wherein the current heading information and the target heading information include positioning coordinate parameters and heading parameters corresponding to the vehicle's orientation; it calculates the deviation between the current heading information and the target heading information; if the deviation is greater than a preset value, it generates several predicted driving trajectories corresponding to the current vehicle; based on the positional relationship between the predicted driving trajectory and the destination, it selects a target point for the current vehicle on the predicted driving trajectory; based on the deviation between the target point and the destination, it continues to generate the next target point until the target point coincides with the destination; and it generates a path through the multiple trajectories formed by the current position, several target points, and the destination.

[0157] The processor 21 may be a Central Processing Unit (CPU). The processor 21 can perform various appropriate actions and processes based on a program stored in the memory 22, that is, a program stored in read-only memory (ROM) or a program loaded from the memory into random access memory (RAM), such as executing the methods described in the above embodiments. The RAM also stores various programs and data required for system operation. The processor 21 and memory 22 are interconnected via a bus 23. An input / output (I / O) interface 24 is also connected to the bus 23.

[0158] In some embodiments, the following components may be connected to the I / O interface 24: an input section 25 including a keyboard, mouse, etc.; an output section 26 including a liquid crystal display (LCD) and speakers, etc.; a storage section including a hard disk, etc.; and a communication section 27 including a network interface card such as a LAN (Local Area Network) card and a modem, etc. The communication section 27 performs communication processing via a network such as the Internet.

[0159] In the embodiments of this application, the electronic device and the path generation device based on autonomous driving are of the same concept as the path generation method based on autonomous driving in the above embodiments. Any method step provided in the embodiments of the path generation method based on autonomous driving can be run on the electronic device and the path generation device based on autonomous driving. For details of its implementation process, please refer to the embodiments of the path generation method based on autonomous driving. It can be combined in any way to form optional embodiments of this application, which will not be repeated here.

[0160] The aforementioned electronic device determines the deviation between the current heading information and the target heading information. If the deviation is greater than a preset value, it generates several predicted driving trajectories. By generating several predicted driving trajectories and based on the positional relationship between different predicted driving trajectories and the destination, it generates several target points for smoothing the trajectories. Then, it generates the optimal path back to the origin through multiple trajectories between the target points, reducing the vehicle's travel time back to the origin and thus improving the demonstration efficiency of the examination subject.

[0161] As used herein, the term "module" can refer to a software or hardware object that executes on the computing system. The various components, modules, engines, and services described herein can be implementations on the computing system. The apparatuses and methods described herein can be implemented in software or hardware, both of which are within the scope of this application.

[0162] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0163] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection, an electrical connection, or a connection that allows communication between them; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication between two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0164] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made based on the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A path generation method based on autonomous driving, applied to electronic devices, characterized in that, The method includes: Determine the current heading information of the vehicle's current position and the target heading information of the destination. The current heading information and the target heading information include positioning coordinate parameters and heading parameters corresponding to the vehicle's orientation. Calculate the deviation between the current heading information and the target heading information; If the deviation is greater than a preset value, then several predicted driving trajectories corresponding to the current vehicle are generated. Based on the positional relationship between the predicted driving trajectory and the destination, a target point for the current vehicle is selected on the predicted driving trajectory; Based on the deviation between the target point and the endpoint, the next target point is generated until the target point and the endpoint coincide. A path is generated by using the current location, several target points, and the endpoint to form multiple trajectory segments, including: Obtain acceleration values ​​under different preset vehicle states, as well as travel times for each segment from the current position to the target point, from the target point to the target point, and from the target point to the destination; Based on the acceleration value and travel time, multiple trajectories from the current position to the target point, from the target point to the target point, and from the target point to the destination are calculated using a fifth-order polynomial. By splicing together multiple trajectory segments, the total path from the current position to the destination can be obtained; The predicted driving trajectory includes a predicted driving trajectory in the forward direction of the vehicle and a predicted driving trajectory in the backward direction of the vehicle; generating several predicted driving trajectories for the current vehicle includes: Obtain a vehicle model, which includes the vehicle wheelbase and maximum steering angle; The minimum turning radius of the vehicle in the forward and reverse directions is obtained based on the vehicle model. Based on the vehicle's minimum turning radius, several predicted driving trajectories are obtained in the forward and reverse directions under different steering angles.

2. The path generation method based on autonomous driving as described in claim 1, characterized in that: The calculation of the deviation between the current heading information and the target heading information includes: If the heading parameter of the current heading information is The heading parameters of the target heading information are: ; calculate To obtain the heading difference between the current heading information and the target heading information; Determine if the heading difference is less than 180 degrees; If it is less than 180 degrees, then the heading angle = Otherwise =360- ; If the deviation is greater than a preset value, then several predicted driving trajectories corresponding to the current vehicle are generated, including: Determine the heading angle Is it greater than the vehicle's maximum steering angle? If so, then based on the heading angle as well as , Generate several predicted driving trajectories for the current vehicle.

3. The path generation method based on autonomous driving as described in claim 2, characterized in that, The step of selecting a target point for the current vehicle on the predicted driving trajectory based on the positional relationship between the predicted driving trajectory and the destination includes: Determine the relative distance between each of the predicted driving trajectories and the destination; The point on the predicted driving trajectory with the smallest relative distance is selected as the target point of the current vehicle.

4. A path generation device based on autonomous driving, characterized in that, include: The information determination module is used to determine the current heading information of the vehicle's current position and the target heading information of the destination. The current heading information and the target heading information include positioning coordinate parameters and heading parameters corresponding to the vehicle's orientation. The calculation module is used to calculate the deviation between the current heading information and the target heading information; The predicted driving trajectory generation module is used to generate several predicted driving trajectories corresponding to the current vehicle if the deviation is greater than a preset value. The target point selection module is used to select a target point of the current vehicle on the predicted driving trajectory based on the positional relationship between the predicted driving trajectory and the destination. Based on the deviation between the target point and the endpoint, the next target point is generated until the target point and the endpoint coincide. The path generation module is used to generate a path from multiple trajectories formed by the current location, several target points, and the destination, including: Obtain acceleration values ​​under different preset vehicle states, as well as travel times for each segment from the current position to the target point, from the target point to the target point, and from the target point to the destination; Based on the acceleration value and travel time, multiple trajectories from the current position to the target point, from the target point to the target point, and from the target point to the destination are calculated using a fifth-order polynomial. By splicing together multiple trajectory segments, the total path from the current position to the destination can be obtained; The predicted driving trajectory includes a predicted driving trajectory in the forward direction of the vehicle and a predicted driving trajectory in the backward direction of the vehicle; generating several predicted driving trajectories for the current vehicle includes: Obtain a vehicle model, which includes the vehicle wheelbase and maximum steering angle; The minimum turning radius of the vehicle in the forward and reverse directions is obtained based on the vehicle model. Based on the vehicle's minimum turning radius, several predicted driving trajectories are obtained in the forward and reverse directions under different steering angles.

5. The path generation device based on autonomous driving as described in claim 4, characterized in that, The predicted driving trajectory generation module is specifically used for: Determine the relative distance between each of the predicted driving trajectories and the destination; The point on the predicted driving trajectory with the smallest relative distance is selected as the target point of the current vehicle.

6. An electronic device, characterized in that, The electronic device includes a processor and a memory, and the processor and the memory are electrically connected. The memory stores a computer program, and the processor executes the path generation method based on autonomous driving as described in any one of claims 1-3 by calling the computer program stored in the memory.

Images