Turn-around path planning method, device, equipment and medium

Abstract

The invention discloses a U-turn path planning method and device, equipment and a medium, and relates to the technical field of automatic driving, and the method comprises the steps: carrying out the U-turn path planning through taking the current position of a vehicle as a starting point and taking the target position of each lane in an opposite road as a terminal point when the vehicle is driven to a preset U-turn road section if the road edge of the opposite road can be recognized at present, calculating the calculation overhead of each U-turn path, then taking the U-turn path with the minimum calculation overhead as the final U-turn path, and judging that the path planning is successful, so as to complete the U-turn control of the own vehicle by utilizing the final U-turn path; and if the path planning fails, controlling the own vehicle to steer and move to the preset road edge position at the intersection position of the current lane at the maximum steering wheel angle, and completing the turn-round control of the own vehicle at the preset road edge position by adopting a gear switching mode. According to the invention, the optimal U-turn path can be generated when the vehicle has the U-turn demand, and the U-turn efficiency of the vehicle is improved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a U-turn path planning method, device, equipment and medium. Background Art

[0002] In the development of autonomous driving technology, the autonomous navigation capability of vehicles in various traffic scenarios is key. As one of the common driving operations, U-turns at intersections place high demands on the path planning capabilities of autonomous driving vehicles. In existing technologies, autonomous driving vehicles often have problems such as unreasonable path planning, low U-turn efficiency, and insufficient safety when making U-turns at intersections.

[0003] The usual method of turning around at an intersection usually includes one or more of the following features: Figure 1 Turn the steering wheel in the opposite direction as shown in the figure to seek more turning space. Figure 2 , as shown in the figure, to avoid the target lane curb and Figure 3 The gear switching operation is shown. Each feature has its advantages and disadvantages. For the first one, it rarely invades the turning space of the opposite lane and can realize the U-turn at the intersection at once, but it needs to invade the space of the adjacent lane, and it is not applicable to the situation where the straight and left turns are green at the same time; for the second one, it does not invade the space of the adjacent lane, and the situation where the straight and left turns are green at the same time is not affected, but because the vehicle must move to the intersection first, it is not applicable to the situation where the intersection is narrow and the opposite lane turns at the same time. In addition, these two schemes require the width of the target lane to be as large as possible, otherwise it will increase its own intrusion distance. For the third scheme, it does not need to occupy the space of other lanes, and can realize U-turns at any intersection. There is no requirement for the width of the target lane, but its U-turn time is longer, and it includes a gear switch, which has higher requirements for planning.

[0004] In summary, how to generate the optimal U-turn path when the vehicle has a U-turn demand to improve the vehicle U-turn efficiency is a problem that needs to be solved. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide a U-turn path planning method, device, equipment and medium, which can generate an optimal U-turn path when a vehicle has a U-turn requirement, so as to improve the U-turn efficiency. The specific scheme is as follows:

[0006] In a first aspect, the present application discloses a U-turn path planning method, comprising:

[0007] When driving to the preset U-turn section, if the curb of the opposite road can be currently identified, the U-turn path is planned with the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point, and the calculation cost of each U-turn path is calculated, and then the U-turn path with the smallest calculation cost is used as the final U-turn path, and the path planning is determined to be successful, so as to complete the U-turn control of the vehicle using the final U-turn path;

[0008] If the path planning fails, the vehicle is controlled to steer to a preset curb position at the intersection of the current lane with the maximum steering wheel angle, and a gear shift is performed at the preset curb position to complete the U-turn control of the vehicle;

[0009] The U-turn path planning is performed with the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point, including:

[0010] Acquire lane information in the oncoming road; wherein the lane information includes the total number of lanes and the starting point of the intersection of each lane;

[0011] The position of each lane in the opposite road at a preset distance from the starting point of the corresponding intersection is determined as the target position, and a U-turn path is planned with the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point to obtain a plurality of U-turn paths.

[0012] Optionally, the calculating of the computational overhead of each U-turn path includes:

[0013] Determine a first cost model for each of the U-turn paths constructed based on a preset maximum lateral acceleration, a preset maximum longitudinal acceleration, a minimum lateral distance between the vehicle and other vehicles, and a minimum longitudinal distance;

[0014] Determine a second cost model constructed based on the farthest lateral distance between each of the U-turn paths and the current position of the vehicle and the lateral distance between each lane and the current position of the vehicle;

[0015] The computational cost of each U-turn path is calculated based on the first cost model and the second cost model.

[0016] Optionally, controlling the vehicle to steer to a preset curb position at the intersection of the current lane with the maximum steering wheel angle includes:

[0017] Determine whether there is an obstacle between the intersection position of the current lane and the preset curb position;

[0018] If there is no obstacle between the intersection position of the current lane and the preset curb position, determine the current first optimal speed, and use the current first optimal speed to control the vehicle to turn and move from the intersection position to the preset curb position at the maximum steering wheel angle;

[0019] If there is an obstacle between the intersection position of the current lane and the preset curb position, the current second optimal speed and the current optimal trajectory are determined, and the current second optimal speed and the current optimal trajectory are used to control the vehicle to turn from the intersection position to the preset curb position at the maximum steering wheel angle.

[0020] Optionally, determining the current first optimal speed includes:

[0021] Calculating the computational costs at different preset speeds using a third cost model constructed based on the preset maximum lateral acceleration, the minimum longitudinal distance and the obstacle position, and taking the speed corresponding to the minimum value of the computational cost as the current first optimal speed;

[0022] The determining of the current second optimal speed and the current optimal trajectory comprises:

[0023] A fourth cost model constructed based on the first cost model and the target distance between the center point of the vehicle body and the corner point of the vehicle body is used to calculate the computational cost at different speeds and different trajectories, and the speed and trajectory corresponding to the minimum computational cost are determined as the current second optimal speed and the current optimal trajectory.

[0024] Optionally, the U-turn control of the vehicle is completed by switching gears at the preset curb position, including:

[0025] After switching to the preset reverse gear at the preset curb position, the steering movement of the vehicle is controlled with the maximum reverse turning angle corresponding to the maximum steering wheel turning angle, and the steering movement is stopped after the body position of the vehicle meets the preset conditions, and then the process jumps to the step of U-turn path planning with the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point.

[0026] Optionally, the process of determining whether the position of the vehicle body meets a preset condition includes:

[0027] A target circle is drawn with the current front direction of the vehicle and the center point of the vehicle body as tangents and a preset minimum turning radius. If the curb starting point of the opposite road is within the target circle and the distance between the curb starting point and the circle boundary meets the preset distance condition, it is determined that the vehicle body position meets the preset condition.

[0028] Optionally, the U-turn path planning method further includes:

[0029] If the curb of the opposite road is not currently identified, the vehicle is controlled to steer and move at the maximum steering wheel angle;

[0030] If the curb of the oncoming road is identified during the turning movement, the process jumps to the step of performing U-turn path planning with the current position of the vehicle as the starting point and the target position of each lane in the oncoming road as the end point;

[0031] If the curb of the oncoming road is not identified during the turning movement, and the vehicle has currently entered any target lane in the oncoming road, path planning is performed with the current position of the vehicle as the starting point and the target position in the target lane as the end point.

[0032] In a second aspect, the present application discloses a U-turn path planning device, comprising:

[0033] A first U-turn control module is used for, when driving to a preset U-turn section, if the curb of the opposite road can be currently identified, taking the current position of the vehicle as a starting point and the target position of each lane in the opposite road as an end point to perform U-turn path planning, and calculating the calculation cost of each U-turn path, and then taking the U-turn path with the smallest calculation cost as the final U-turn path, and determining that the path planning is successful, so as to complete the U-turn control of the vehicle using the final U-turn path;

[0034] A second U-turn control module is used for controlling the vehicle to steer to a preset curb position at the intersection of the current lane with the maximum steering wheel angle if the path planning fails, and completing the U-turn control of the vehicle by shifting gears at the preset curb position;

[0035] Wherein, the first U-turn control module specifically includes:

[0036] An information acquisition unit, configured to acquire lane information in the oncoming road; wherein the lane information includes the total number of lanes and the starting point of the intersection of each lane;

[0037] The path planning unit is used to determine the position of each lane in the opposite road at a preset distance from the starting point of the corresponding intersection as the target position, and to perform U-turn path planning with the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point to obtain a plurality of U-turn paths.

[0038] In a third aspect, the present application discloses an electronic device, comprising:

[0039] Memory, used to store computer programs;

[0040] The processor is used to execute the computer program to implement the steps of the U-turn path planning method disclosed above.

[0041] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the steps of the aforementioned disclosed U-turn path planning method are implemented.

[0042] It can be seen that when the present application drives to a preset U-turn section, if the curb of the opposite road can be currently identified, the current position of the vehicle is used as the starting point, and the target position of each lane in the opposite road is used as the end point to perform U-turn path planning, and the computational overhead of each U-turn path is calculated, and then the U-turn path with the smallest computational overhead is used as the final U-turn path, and the path planning is determined to be successful, so as to complete the U-turn control of the vehicle using the final U-turn path; if the path planning fails, the vehicle is controlled to steer to the preset curb position at the intersection position of the current lane with the maximum steering wheel angle, and the U-turn control of the vehicle is completed by switching gears at the preset curb position. Among them, the U-turn path planning is performed with the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point, including: obtaining lane information in the opposite road; wherein the lane information includes the total number of lanes and the intersection starting point of each lane; determining the position of each lane in the opposite road at a preset distance from the corresponding intersection starting point as the target position, and performing U-turn path planning with the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point to obtain a plurality of U-turn paths.

[0043] Beneficial effect: In the present application, when the vehicle is traveling to the preset U-turn section, if the curb of the opposite road can be currently identified, the current position of the vehicle is used as the starting point, and the target position of each lane in the opposite road is used as the end point to plan the U-turn path, and the computational cost of each U-turn path is calculated. It can be understood that there are usually multiple lanes in the opposite road. By obtaining the total number of lanes in the opposite road and the starting point of the intersection of each lane, and then using the position of each lane at a preset distance from the starting point of the intersection as the target position for U-turn path planning, multiple U-turn paths can be obtained. Therefore, the present application needs to calculate the computational cost of the U-turn path corresponding to each lane, and then use the U-turn path with the smallest computational cost as the final U-turn path, so as to use the final U-turn path to complete the U-turn control of the vehicle. In this way, as long as the curb of the opposite road can be currently identified, the U-turn path planning can be started quickly, and the optimal U-turn path can be generated, which reduces the computational cost and improves the vehicle U-turn efficiency. In addition, if the path planning fails, that is, the final U-turn path cannot be output according to the above steps, the planning is considered to have failed. In this case, the vehicle is controlled to steer to the preset curb position at the intersection of the current lane with the maximum steering wheel angle, and the gear is switched at the preset curb position to complete the U-turn control of the vehicle. That is, if the above path planning fails, the gear switching method is required to complete the U-turn control. Through the above scheme, the present application can generate the most suitable and optimal U-turn path in combination with the vehicle position, road information, etc. to control the vehicle to complete the U-turn operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0045] Figure 1 This is a schematic diagram of the first U-turn path disclosed in this application;

[0046] Figure 2 This is a schematic diagram of the second U-turn path disclosed in this application;

[0047] Figure 3 This is a schematic diagram of the third U-turn path disclosed in this application;

[0048] Figure 4 A flow chart of a U-turn path planning method disclosed in this application;

[0049] Figure 5 A flow chart of path planning for a U-turn at an intersection disclosed in this application;

[0050] Figure 6 A schematic diagram of the position between a vehicle and a road disclosed in the present application;

[0051] Figure 7 A specific U-turn path planning method flow chart disclosed in this application;

[0052] Figure 8 A schematic diagram of a vy coordinate system disclosed in this application;

[0053] Fig. 9 A schematic diagram of a yx coordinate system disclosed in this application;

[0054] Fig.10 A schematic diagram of a vyx coordinate system disclosed in this application;

[0055] Fig.11 This is a schematic diagram of the structure of a U-turn path planning device disclosed in this application;

[0056] Fig.12 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0058] Currently, when autonomous vehicles turn around at intersections, there are often problems such as unreasonable path planning, low turn efficiency, and insufficient safety. Figure 1 and Figure 2 The U-turn solution shown in the figure requires the target lane width to be as large as possible, otherwise the intrusion distance will increase. Figure 3 The U-turn solution shown does not need to occupy other lane spaces and can be turned around at any intersection, and has no requirements for the width of the target lane, but it takes a long time to turn around and includes a gear switch, which requires higher planning. To this end, the embodiment of the present application discloses a U-turn path planning method, device, equipment and medium, which can generate an optimal U-turn path when a vehicle has a U-turn requirement to improve the U-turn efficiency.

[0059] See also Figure 4 and Figure 5 As shown, the embodiment of the present application discloses a U-turn path planning method, the method comprising:

[0060] Step S11: When driving to a preset U-turn section, if the curb of the opposite road can be currently identified, a U-turn path is planned with the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point, and the computational cost of each U-turn path is calculated, and then the U-turn path with the smallest computational cost is taken as the final U-turn path, and the path planning is determined to be successful, so as to use the final U-turn path to complete the U-turn control of the vehicle.

[0061] In this embodiment, when the vehicle is driving to the preset U-turn section, it needs to determine whether the curb of the opposite road can be identified. It can be understood that the application first needs to detect whether there is a curb (or boundary) on the adjacent opposite road. Under normal circumstances, the boundary is identifiable. When there is extreme weather or the road is too wide, the boundary cannot be identified. Figure 6 As shown in Figure 6 When the road segment shown in is detected, it will be determined whether the boundary of the opposite road can be identified at present, i.e. Figure 6 The leftmost black line.

[0062] When the boundary can be identified, the current position of the vehicle is used as the starting point, and the target position of each lane in the opposite road is used as the end point to plan the U-turn path, and the computational cost of each U-turn path is calculated. It can be understood that there are usually multiple lanes in the opposite road, so this application needs to use each lane as the lane where the U-turn path is located, and calculate the corresponding computational cost, and then use the U-turn path with the smallest computational cost as the final U-turn path. At this time, the path planning is also determined to be successful, so that the U-turn control of the vehicle is completed using the final U-turn path. In this way, as long as the curb of the opposite road can be identified at present, the U-turn path planning can be started quickly, and the optimal U-turn path can be generated, which reduces the computational cost and improves the vehicle U-turn efficiency.

[0063] In a specific implementation, the U-turn path planning is performed with the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point, including: obtaining lane information in the opposite road; wherein the lane information includes the total number of lanes and the intersection starting point of each lane; determining the position of each lane in the opposite road at a preset distance from the corresponding intersection starting point as the target position, and performing U-turn path planning with the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point, so as to obtain a plurality of U-turn paths.

[0064] That is, if it is determined that the roadside of the oncoming road can be identified, the lane information of the oncoming road is further obtained, that is, the total number of lanes in the oncoming road and the starting point of the intersection of each lane are obtained. Figure 6As shown, the preset distance is recorded as x, where x is a calibrable parameter value, and the position of each lane in the opposite road corresponding to the intersection starting point x is determined as the target position. It should also be pointed out that the embodiment of the present application uses the center point of the vehicle to represent the current position of the vehicle, such as Figure 6 Therefore, the current position P of the vehicle is taken as the starting point, and the position of each lane in the opposite road corresponding to the starting point x of the intersection is taken as the end point for U-turn path planning to obtain a number of U-turn paths.

[0065] It should be noted that there are still cases where path planning fails during the planning process. For example, when a vehicle or pedestrian stops on the planned trajectory, the planning module may not be able to plan a trajectory from the start point to the end point, so the path planning fails. When planning fails suddenly during the planning process, such as a pedestrian intruding the vehicle trajectory, the planned end point is changed to h meters away from the original trajectory of the pedestrian intruding vehicle. h is a constant, which can be 0.5. At the same time, the speed of the planning end point is changed to 0. At this time, a trajectory that slowly stops can be started.

[0066] In addition, the above method also includes: if the curb of the opposite road is not currently identified, the maximum steering wheel angle is used to control the steering movement of the vehicle; if the curb of the opposite road is identified during the steering movement, jump to the step of taking the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point to perform U-turn path planning; if the curb of the opposite road is not identified during the steering movement, and the vehicle has currently entered any target lane in the opposite road, the current position of the vehicle is used as the starting point and the target position in the target lane is used as the end point to perform path planning. It can be understood that when the boundary of the opposite road is not identified, the vehicle is directly moved at the maximum steering wheel angle. If the boundary of the opposite road is identified during the steering movement, the step of taking the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point to perform U-turn path planning is executed again, and the trajectory is output when it is determined that the path planning is successful. If the road is too wide and there are too many lanes, resulting in the curb of the oncoming road not being recognized during the turning process, and the current vehicle has entered any target lane in the oncoming road, the path planning is performed with the current position of the vehicle as the starting point and the target position in the target lane as the end point.

[0067] Step S12: If the path planning fails, the vehicle is controlled to steer to a preset curb position at the intersection of the current lane with the maximum steering wheel angle, and the vehicle is turned around by switching gears at the preset curb position.

[0068] In this embodiment, if the path planning fails, that is, the final U-turn path cannot be output according to the above steps, it is considered that the planning has failed. In this case, the vehicle is controlled to turn to the preset curb position at the intersection position P1 of the current lane with the maximum steering wheel angle. It should be pointed out that under this condition, the lane closest to the boundary is selected for planning, and the U-turn control of the vehicle is completed by switching gears when reaching the preset curb position. That is, if the current path planning fails, the U-turn control needs to be completed by switching gears. Through the above scheme, the present application can generate the most suitable and optimal U-turn path in combination with the vehicle position, road information, etc. to control the vehicle to complete the U-turn operation.

[0069] In a specific embodiment, the above-mentioned method of switching gears at the preset curb position to complete the U-turn control of the vehicle includes: after switching to the preset reverse gear at the preset curb position, controlling the steering movement of the vehicle with the maximum reverse angle corresponding to the maximum steering wheel angle, stopping the steering movement after the vehicle body position meets the preset conditions, and then jumping to the step of planning the U-turn path with the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point. That is, when the preset curb position is reached, first switch to the preset reverse gear, then control the steering movement of the vehicle with the maximum reverse angle corresponding to the maximum steering wheel angle, and stop the steering movement after the vehicle body position meets the preset conditions. After stopping the movement, the U-turn path is planned with the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point. Among them, the preset curb position refers to the distance between the center of the vehicle and the starting point of the curb of the opposite road. Less than the calibration value K, where the value of K needs to be greater than the distance d1 between the center point of the vehicle and the corner point of the vehicle. The schematic diagram of d1 is as follows Figure 6 It should be noted that in this case the planned path is as follows Figure 3 The U-turn path shown in .

[0070] Among them, the process of determining that the position of the vehicle body meets the preset conditions includes: using the current front direction of the vehicle and the center point of the vehicle body as tangents, and drawing a target circle with a preset minimum turning radius. If the starting point of the curb of the opposite road is located within the target circle, and the distance between the starting point of the curb and the circle boundary meets the preset distance condition, then the position of the vehicle body meets the preset conditions. That is, during the real-time movement of the vehicle, using the current front direction of the vehicle and the center point of the vehicle body as tangents, and drawing a circle with a preset minimum turning radius, if the starting point of the curb of the opposite road is located within the target circle and the distance between the starting point of the curb and the circle boundary meets the preset distance condition, then the position of the vehicle body meets the preset conditions, that is, the corresponding Figure 5 The target in is reachable; the preset distance condition specifically refers to the distance from the starting point of the road edge to the circle boundary Where is a calibrable parameter.

[0071] It should be pointed out that when there is an obstacle during the movement and the obstacle has been on the current moving path for a long time, for example, it has been on the current moving path for 5 seconds, it is necessary to pause the movement first; wherein, whether there is an obstacle can be predicted based on the information collected by the sensor; then at this time, it is necessary to turn the steering wheel again and switch to the forward gear to continue moving forward, and repeat the above steps of judging whether the position of the vehicle body meets the preset conditions during the movement, until it is determined that the position of the vehicle body meets the preset conditions, then stop moving, and then perform subsequent path planning.

[0072] It can be seen that in this application, when the vehicle is driving to the preset U-turn section, if the curb of the opposite road can be currently identified, the current position of the vehicle is used as the starting point, and the target position of each lane in the opposite road is used as the end point to plan the U-turn path, and the calculation cost of each U-turn path is calculated. It can be understood that there are usually multiple lanes in the opposite road. By obtaining the total number of lanes in the opposite road and the starting point of the intersection of each lane, and then using the position of each lane at a preset distance from the starting point of the intersection as the target position for U-turn path planning, multiple U-turn paths can be obtained. Therefore, this application needs to calculate the calculation cost of the U-turn path corresponding to each lane, and then use the U-turn path with the smallest calculation cost as the final U-turn path, so as to use the final U-turn path to complete the U-turn control of the vehicle. In this way, as long as the curb of the opposite road can be identified at present, the U-turn path planning can be started quickly, and the optimal U-turn path can be generated, which reduces the calculation cost and improves the vehicle U-turn efficiency. In addition, if the path planning fails, that is, the final U-turn path cannot be output according to the above steps, the planning is considered to have failed. In this case, the vehicle is controlled to steer to the preset curb position at the intersection of the current lane with the maximum steering wheel angle, and the gear is switched at the preset curb position to complete the U-turn control of the vehicle. That is, if the above path planning fails, the gear switching method is required to complete the U-turn control. Through the above scheme, the present application can generate the most suitable and optimal U-turn path in combination with the vehicle position, road information, etc. to control the vehicle to complete the U-turn operation.

[0073] See also Figure 7 As shown, the embodiment of the present application discloses a specific U-turn path planning method. Compared with the previous embodiment, this embodiment further illustrates and optimizes the technical solution. Specifically, it includes:

[0074] Step S21: When driving to a preset U-turn section, if the curb of the oncoming road can be currently identified, then the lane information of the oncoming road is obtained; wherein the lane information includes the total number of lanes and the starting point of the intersection of each lane.

[0075] Step S22: The position of each lane in the opposite road at a preset distance from the starting point of the corresponding intersection is determined as the target position, and a U-turn path is planned with the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point to obtain a plurality of U-turn paths.

[0076] Step S23: Determine a first cost model for each of the U-turn paths constructed based on a preset maximum lateral acceleration, a preset maximum longitudinal acceleration, a minimum lateral distance and a minimum longitudinal distance between the vehicle and other vehicles, and determine a second cost model constructed based on the farthest lateral distance between each of the U-turn paths and the current position of the vehicle and the lateral distance between each lane and the current position of the vehicle.

[0077] In this embodiment, the total computational cost model C is constructed as follows:

[0078] C=f+f1;

[0079] Wherein, f is the first overhead model, f1 is the second overhead model;

[0080]

[0081] ;

[0082] in, , i=1, 2, …, n, is the proportional coefficient, which is used to adjust the influence of each weight on the final output. and Indicates the currently planned lateral and longitudinal accelerations. and Indicates the calibrated preset maximum longitudinal acceleration and preset maximum lateral acceleration. Indicates the minimum longitudinal distance between the vehicle and other vehicles. Indicates the minimum lateral distance between the vehicle and other vehicles, which can be obtained by the sensor. represents the maximum lateral distance between the planned U-turn path and the current position of the vehicle, that is, the starting position p. represents the lateral distance between each lane and the starting position p, , All of them are calibrable constant parameters.

[0083] The role of model f is to ensure that the vehicle passes the intersection at a steady speed, and the role of model f1 is to ensure that the planned trajectory maintains as little deviation as possible when entering the target lane.

[0084] Step S24: Calculate the computational cost of each U-turn path based on the first cost model and the second cost model, then use the U-turn path with the smallest computational cost as the final U-turn path, and determine that the path planning is successful, so as to use the final U-turn path to complete the U-turn control of the vehicle.

[0085] In this embodiment, the total cost model constructed based on the first cost model and the second cost model calculates the computational cost of each U-turn path, and then the U-turn path with the smallest computational cost is used as the final U-turn path to complete the U-turn control of the vehicle using the final U-turn path.

[0086] The following is a detailed description of the above path planning process:

[0087] Step 1: Establish the vyx coordinate system, where v represents the speed, y represents the direction of the front of the vehicle, and x represents the direction perpendicular to the front of the vehicle. The (0, 0, 0) position of the vyx coordinate system is the position of the particle when the speed of the vehicle is 0.

[0088] Step 2: If Figure 8 As shown, points are scattered in the vyx coordinate system. Points in the vyx space coordinate system have the following rules: when the points are projected to the vy coordinate system, the lower the speed, the denser the points (for a single t, the lower the speed, the shorter the distance that can be traveled, so the denser the points). When the point jumps from l1 to s1 (same for jumping to s2), the vehicle deceleration logic is triggered, so the vehicle deceleration can be represented by the slope of the arrow. In addition, Fig. 9 As shown, the yx coordinate system represents the lateral motion of the vehicle, and the principle of projecting its points onto the yx plane is similar to that of the vy plane. The slope from l2 to point s3 or s4 can be expressed as lateral acceleration.

[0089] Step 3: Select the end point and mark it in the vyx coordinate system.

[0090] Step 4: Pick a point in space. According to the description of step 2, considering the vehicle dynamics constraints, within a single step, the point that the vehicle can pick in the next step is in the plane, such as Fig.10 After selecting the point on the plane, take this point as the origin and continue to select points on the next plane until the end point is selected.

[0091] Step 5: There are multiple ways to reach the end point. Find the optimal trajectory based on the minimum computational cost.

[0092] Step 6: Output the trajectory with the lowest computational cost.

[0093] It should be pointed out that in the above planning process, the final planned path is as follows: Figure 1 or Figure 2 U-turn path shown.

[0094] Step S25: If the path planning fails, the vehicle is controlled to steer to a preset curb position at the intersection of the current lane with the maximum steering wheel angle, and the vehicle is turned around by switching gears at the preset curb position.

[0095] In this embodiment, the above-mentioned controlling the vehicle to steer and move to a preset curb position at the intersection position of the current lane with the maximum steering wheel angle includes: judging whether there is an obstacle between the intersection position of the current lane and the preset curb position; if there is no obstacle between the intersection position of the current lane and the preset curb position, determining the current first optimal speed, and using the current first optimal speed to control the vehicle to steer and move from the intersection position to the preset curb position with the maximum steering wheel angle; if there is an obstacle between the intersection position of the current lane and the preset curb position, determining the current second optimal speed and the current optimal trajectory, and using the current second optimal speed and the current optimal trajectory to control the vehicle to steer and move from the intersection position to the preset curb position with the maximum steering wheel angle.

[0096] That is, when the vehicle is controlled to turn and move to the preset curb position at the maximum steering wheel angle, there are mainly two situations. One is that there is no obstacle in the trajectory between the intersection position of the current lane and the preset curb position, and the other is that there is an obstacle in the trajectory between the intersection position of the current lane and the preset curb position. When there is no obstacle on the trajectory of driving at the maximum steering wheel angle, the planning under this condition does not include trajectory planning, because the vehicle always drives at the maximum steering wheel angle, but it includes speed planning, so it is necessary to determine the current first optimal speed under this condition, and use the current first optimal speed to control the vehicle to turn and move from the intersection position to the preset curb position at the maximum steering wheel angle. When there is an obstacle on the trajectory of driving at the maximum steering wheel angle, both speed planning and trajectory planning need to be considered under this condition, and the end point of the planning is set as follows: Figure 6 In the green area shown, if there is an obstacle in the area, the area where the obstacle is located is removed. That is, in this working condition, it is necessary to determine the current second optimal speed and the current optimal trajectory, and use the current second optimal speed and the current optimal trajectory to control the vehicle to turn from the intersection position to the preset roadside position with the maximum steering wheel angle.

[0097] In a specific implementation, the above-mentioned determination of the current first optimal speed includes: using a third cost model constructed based on the preset maximum lateral acceleration, the minimum longitudinal distance and the obstacle position to calculate the computational cost under different preset speeds, and taking the speed corresponding to the minimum value of the computational cost as the current first optimal speed.

[0098] The expression of the third cost model C1 is as follows:

[0099]

[0100] Where v is the input preset speed, d is the position of the obstacle closest to the vehicle on the current trajectory, is the proportional coefficient, which is used to adjust the influence of each weight on the final output. i It is a constant used to adjust the influence of the speed v interval.

[0101] Through the above formula, the speed corresponding to the minimum calculated cost is finally used to control the vehicle to turn from the intersection position to the preset curb position with the maximum steering wheel angle.

[0102] In a specific implementation, the above-mentioned determination of the current second optimal speed and the current optimal trajectory includes: using a fourth cost model constructed based on the first cost model and the target distance between the center point of the vehicle body and the corner point of the vehicle body to calculate the computational cost under different speeds and different trajectories, and determining the speed and trajectory corresponding to the minimum computational cost as the current second optimal speed and the current optimal trajectory.

[0103] The expression of the fourth cost model C2 is as follows:

[0104] ;

[0105] in, is the distance from the center point of the vehicle to the starting point of the boundary.

[0106] Through the above formula, the speed and trajectory corresponding to the minimum cost are finally used to control the vehicle to move from the intersection position to the preset curb position with the maximum steering wheel angle.

[0107] It can be seen that the above schemes need to consider the computational overhead in different situations, so as to select the path with the least computational overhead to implement planning. In this process, the optimal U-turn path can be generated by comprehensively considering the vehicle's real-time position, speed, high-precision map information and surrounding traffic environment, thereby improving the U-turn efficiency. In addition, obstacle recognition and exception handling mechanisms are fully considered in the path planning process to ensure safety during the U-turn process. This scheme can be applied to different types of intersections and traffic environments, and has strong adaptability and practicality.

[0108] See also Fig.11 As shown, the embodiment of the present application discloses a U-turn path planning device, which includes:

[0109] The first U-turn control module 11 is used for, when driving to a preset U-turn section, if the curb of the opposite road can be currently identified, taking the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point to perform U-turn path planning, and calculating the calculation cost of each U-turn path, and then taking the U-turn path with the smallest calculation cost as the final U-turn path, and determining that the path planning is successful, so as to complete the U-turn control of the vehicle using the final U-turn path;

[0110] A second U-turn control module 12 is used to control the vehicle to steer to a preset curb position at the intersection of the current lane with the maximum steering wheel angle if the path planning fails, and to complete the U-turn control of the vehicle by means of gear switching at the preset curb position;

[0111] Wherein, the first U-turn control module 11 specifically includes:

[0112] An information acquisition unit, configured to acquire lane information in the oncoming road; wherein the lane information includes the total number of lanes and the starting point of the intersection of each lane;

[0113] The path planning unit is used to determine the position of each lane in the opposite road at a preset distance from the starting point of the corresponding intersection as the target position, and to perform U-turn path planning with the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point to obtain a plurality of U-turn paths.

[0114] In this application, when the vehicle is traveling to the preset U-turn section, if the curb of the opposite road can be currently identified, the current position of the vehicle is used as the starting point, and the target position of each lane in the opposite road is used as the end point to perform U-turn path planning, and the computational overhead of each U-turn path is calculated. It can be understood that there are usually multiple lanes in the opposite road. By obtaining the total number of lanes in the opposite road and the starting point of the intersection of each lane, and then using the position of each lane at a preset distance from the starting point of the intersection as the target position for U-turn path planning, multiple U-turn paths can be obtained. Therefore, this application needs to calculate the computational overhead of the U-turn path corresponding to each lane, and then use the U-turn path with the smallest computational overhead as the final U-turn path to complete the U-turn control of the vehicle using the final U-turn path. In this way, as long as the curb of the opposite road can be currently identified, the U-turn path planning can be quickly started, and the optimal U-turn path can be generated, reducing the computational overhead, thereby improving the vehicle U-turn efficiency. In addition, if the path planning fails, that is, the final U-turn path cannot be output according to the above steps, the planning is considered to have failed. In this case, the vehicle is controlled to steer to the preset curb position at the intersection of the current lane with the maximum steering wheel angle, and the gear is switched at the preset curb position to complete the U-turn control of the vehicle. That is, if the above path planning fails, the gear switching method is required to complete the U-turn control. Through the above scheme, the present application can generate the most suitable and optimal U-turn path in combination with the vehicle position, road information, etc. to control the vehicle to complete the U-turn operation.

[0115] Since the embodiments of the device part correspond to the embodiments of the method part, the embodiments of the device part refer to the description of the embodiments of the method part, which will not be described here. In addition, the invention has the same beneficial effects as the U-turn path planning method mentioned above.

[0116] Fig.12 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Specifically, it may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the U-turn path planning method performed by the electronic device disclosed in any of the aforementioned embodiments.

[0117] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0118] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0119] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon include an operating system 221, a computer program 222 and data 223, etc. The storage method can be temporary storage or permanent storage.

[0120] Among them, the operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device 20, so as to realize the operation and processing of the massive data 223 in the memory 22 by the processor 21, which can be Windows, Unix, Linux, etc. In addition to including a computer program that can be used to complete the U-turn path planning method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks. In addition to data received by the electronic device and transmitted from an external device, the data 223 can also include data collected by its own input and output interface 25, etc.

[0121] Furthermore, an embodiment of the present application also discloses a computer-readable storage medium, in which a computer program is stored. When the computer program is loaded and executed by a processor, the steps of the U-turn path planning method disclosed in any of the aforementioned embodiments are implemented.

[0122] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0123] Those skilled in the art may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0124] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a compact disc read-only memory (CD-ROM), or any other form of storage medium known in the art.

[0125] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0126] The above is a detailed introduction to a U-turn path planning method, device, equipment and storage medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for a general technician in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A U-turn path planning method, characterized in that: include: When driving to the preset U-turn section, if the curb of the opposite road can be currently identified, the U-turn path is planned with the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point, and the calculation cost of each U-turn path is calculated, and then the U-turn path with the smallest calculation cost is used as the final U-turn path, and the path planning is determined to be successful, so as to complete the U-turn control of the vehicle using the final U-turn path; If the path planning fails, the vehicle is controlled to steer to a preset curb position at the intersection of the current lane with the maximum steering wheel angle, and a gear shift is performed at the preset curb position to complete the U-turn control of the vehicle; The U-turn path planning is performed with the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point, including: Acquire lane information in the oncoming road; wherein the lane information includes the total number of lanes and the starting point of the intersection of each lane; The position of each lane in the opposite road at a preset distance from the starting point of the corresponding intersection is determined as the target position, and a U-turn path is planned with the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point to obtain a plurality of U-turn paths.

2. The U-turn path planning method according to claim 1, characterized in that: The calculation cost of calculating each U-turn path includes: Determine a first cost model for each of the U-turn paths constructed based on a preset maximum lateral acceleration, a preset maximum longitudinal acceleration, a minimum lateral distance between the vehicle and other vehicles, and a minimum longitudinal distance; Determine a second cost model constructed based on the farthest lateral distance between each of the U-turn paths and the current position of the vehicle and the lateral distance between each lane and the current position of the vehicle; The computational cost of each U-turn path is calculated based on the first cost model and the second cost model.

3. The U-turn path planning method according to claim 2, characterized in that: The controlling the vehicle to steer and move to a preset curb position at the intersection of the current lane with the maximum steering wheel angle includes: Determine whether there is an obstacle between the intersection position of the current lane and the preset curb position; If there is no obstacle between the intersection position of the current lane and the preset curb position, determine the current first optimal speed, and use the current first optimal speed to control the vehicle to turn and move from the intersection position to the preset curb position at the maximum steering wheel angle; If there is an obstacle between the intersection position of the current lane and the preset curb position, the current second optimal speed and the current optimal trajectory are determined, and the current second optimal speed and the current optimal trajectory are used to control the vehicle to turn from the intersection position to the preset curb position at the maximum steering wheel angle.

4. The U-turn path planning method according to claim 3, characterized in that: The determining of the current first optimal speed comprises: Calculating the computational costs at different preset speeds using a third cost model constructed based on the preset maximum lateral acceleration, the minimum longitudinal distance and the obstacle position, and taking the speed corresponding to the minimum value of the computational cost as the current first optimal speed; The determining of the current second optimal speed and the current optimal trajectory comprises: A fourth cost model constructed based on the first cost model and the target distance between the center point of the vehicle body and the corner point of the vehicle body is used to calculate the computational cost at different speeds and different trajectories, and the speed and trajectory corresponding to the minimum computational cost are determined as the current second optimal speed and the current optimal trajectory.

5. The U-turn path planning method according to claim 1, characterized in that: The method of switching gears to complete the U-turn control of the vehicle at the preset curb position includes: After switching to the preset reverse gear at the preset curb position, the steering movement of the vehicle is controlled with the maximum reverse turning angle corresponding to the maximum steering wheel turning angle, and the steering movement is stopped after the body position of the vehicle meets the preset conditions, and then the process jumps to the step of U-turn path planning with the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point.

6. The U-turn path planning method according to claim 5, characterized in that: The process of determining whether the vehicle body position meets the preset conditions includes: A target circle is drawn with the current front direction of the vehicle and the center point of the vehicle body as tangents and a preset minimum turning radius. If the curb starting point of the opposite road is within the target circle and the distance between the curb starting point and the circle boundary meets the preset distance condition, it is determined that the vehicle body position meets the preset condition.

7. The U-turn path planning method according to any one of claims 1 to 6, characterized in that: Also includes: If the curb of the opposite road is not currently identified, the vehicle is controlled to steer and move at the maximum steering wheel angle; If the curb of the oncoming road is identified during the turning movement, the process jumps to the step of performing U-turn path planning with the current position of the vehicle as the starting point and the target position of each lane in the oncoming road as the end point; If the curb of the oncoming road is not identified during the turning movement, and the vehicle has currently entered any target lane in the oncoming road, path planning is performed with the current position of the vehicle as the starting point and the target position in the target lane as the end point.

8. A U-turn path planning device, characterized in that: include: A first U-turn control module is used for, when driving to a preset U-turn section, if the curb of the opposite road can be currently identified, taking the current position of the vehicle as a starting point and the target position of each lane in the opposite road as an end point to perform U-turn path planning, and calculating the calculation cost of each U-turn path, and then taking the U-turn path with the smallest calculation cost as the final U-turn path, and determining that the path planning is successful, so as to complete the U-turn control of the vehicle using the final U-turn path; A second U-turn control module is used for controlling the vehicle to steer to a preset curb position at the intersection of the current lane with the maximum steering wheel angle if the path planning fails, and completing the U-turn control of the vehicle by shifting gears at the preset curb position; Wherein, the first U-turn control module specifically includes: An information acquisition unit, configured to acquire lane information in the oncoming road; wherein the lane information includes the total number of lanes and the starting point of the intersection of each lane; The path planning unit is used to determine the position of each lane in the opposite road at a preset distance from the starting point of the corresponding intersection as the target position, and to perform U-turn path planning with the current position of the vehicle as the starting point and the target position of each lane in the opposite road as the end point to obtain a plurality of U-turn paths.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor is used to execute the computer program to implement the steps of the U-turn path planning method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store computer programs; wherein, when the computer program is executed by a processor, the steps of the U-turn path planning method as described in any one of claims 1 to 7 are implemented.

Images