Gradient Determination Method, Device, Vehicle and Storage Medium in High-Speed Curve Scenarios

Abstract

The present invention provides a method, device, vehicle and storage medium for determining a slope in a high-speed curve scenario, belonging to the technical field of vehicle autonomous driving. The method includes: obtaining a plurality of position points of an autonomous driving vehicle in a high-speed curve driving scenario, and determining the turning radius at the position points; the plurality of position points include a plurality of actual position points and a plurality of predicted position points; determining an objective function based on the position points and the turning radius, the objective function including a smoothness cost function, a distance cost function and an offset cost function; determining the constraint conditions of the objective function, and fitting the plurality of actual position points and the plurality of predicted position points based on the objective function and the constraint conditions to obtain a slope line, and determining the slope based on the slope line. The present invention improves the determination efficiency and accuracy of the slope.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle autonomous driving, and particularly to a method, device, vehicle and storage medium for determining a slope in a high-speed curve scenario. Background Art

[0002] The slope design on a curve is crucial for ensuring the driving safety and comfort of a highway. The road slope has a significant impact on aspects such as the driving performance, fuel efficiency, braking distance, and driving safety of a vehicle.

[0003] Currently, there are mainly two methods for obtaining the road slope: sensor-based and vehicle longitudinal dynamics-based. The sensor-based identification method is to directly measure the slope angle by installing sensors on the vehicle, such as using an inclination displacement sensor, an inertial navigator, and a GPS. However, the signal frequency of the sensor is low, there is a positioning error, and in special areas (such as continuous tunnels in mountainous areas) during continuous positioning, there are problems of signal non-reception or large signal deviation, and the cumulative error of the slope on the curve will gradually increase. The identification method based on vehicle longitudinal dynamics or kinematics is to use the vehicle's longitudinal dynamics model plus the data obtained from the vehicle CAN bus to estimate unknown system parameters. Although there are many methods in this regard, a common difficulty lies in the decoupling of the changes in vehicle own parameters (such as mass) and external resistance (such as slope), resulting in inaccurate estimation of the slope. In addition, the time-varying nature of the road also increases the complexity of the estimation process.

[0004] Therefore, there is an urgent need to provide a method, device, vehicle and storage medium for determining a slope in a high-speed curve scenario to improve the accuracy and efficiency of the determined slope. Summary of the Invention

[0005] In view of this, it is necessary to provide a method, device, vehicle and storage medium for determining a slope in a high-speed curve scenario to solve the technical problem of low efficiency and accuracy in determining the slope in the prior art.

[0006] On the one hand, to solve the above technical problem, the present invention provides a method for determining a slope in a high-speed curve scenario, including:

[0007] Obtain multiple position points of an autonomous driving vehicle in a high-speed curve driving scenario, and determine the turning radius at the position points; the multiple position points include multiple actual position points and multiple predicted position points;

[0008] Determine an objective function based on the position points and the turning radius, where the objective function includes a smoothness cost function, a distance cost function, and an offset cost function;

[0009] Determine the constraint conditions of the objective function, and fit the multiple actual position points and the multiple predicted position points based on the objective function and the constraint conditions to obtain a slope line, and determine the slope based on the slope line.

[0010] In a possible implementation manner, the objective function is:

[0011]

[0012]

[0013]

[0014]

[0015] In the formula, is the objective function; is the smoothness cost function; is the distance cost function; is the offset cost function; and are the X-axis coordinate and Z-axis coordinate of the i-th position point respectively; and are the X-axis coordinate and Z-axis coordinate of the (i - 1)-th position point respectively; and are the X-axis coordinate and Z-axis coordinate of the (i + 1)-th position point respectively; is the turning radius of the i-th position point; , and are the X-axis coordinate, Y-axis coordinate and Z-axis coordinate of the road center point corresponding to the i-th position point respectively.

[0016] In a possible implementation manner, the constraint conditions include a continuous slope offset constraint and a curvature radius constraint; the continuous slope offset constraint is:

[0017]

[0018] The curvature radius constraint is:

[0019]

[0020] In the formula, is the distance between the i-th position point and the center of the rolling sphere on the slope line; , and are the X-axis coordinate, Y-axis coordinate and Z-axis coordinate of the center of the rolling sphere on the slope line respectively; is the minimum distance; , , is the Y-axis coordinate of the i-th position point, the (i - 1)-th position point, and the (i + 1)-th position point; is the average length between the multiple position points; is the maximum curvature approximation.

[0021] In a possible implementation, the obtaining of multiple position points of the autonomous vehicle in a high-speed curve driving scenario includes:

[0022] Obtain the historical driving trajectory of the autonomous vehicle in the high-speed curve scenario, and determine the multiple actual position points based on the historical driving trajectory;

[0023] Obtain the vehicle driving state data of the autonomous vehicle at each of the actual position points, and input the vehicle driving state data and the multiple actual position points into a position prediction model to obtain the multiple predicted position points.

[0024] In a possible implementation, if the vehicle driving state data includes the vehicle speed, before obtaining the historical driving trajectory of the autonomous vehicle in the high-speed curve scenario, it further includes:

[0025] Determine a position prediction distance based on the vehicle speed, and determine the number of the multiple predicted position points based on the position prediction distance.

[0026] In a possible implementation, before determining the objective function based on the position points and the turning radius, it further includes:

[0027] Determine the maximum turning radius, and determine whether the turning radius at each position point is greater than the maximum turning radius;

[0028] When the turning radius at the position point is greater than the maximum turning radius, remove the position point.

[0029] In a possible implementation, the method further includes:

[0030] Generate a speed control command for controlling the vehicle speed of the autonomous vehicle based on the slope;

[0031] Obtain the vehicle speed change trend of the autonomous vehicle under the control of the speed control command;

[0032] Verify the accuracy of the slope based on the vehicle speed change trend.

[0033] On the other hand, the present invention also provides a slope determination device in a high-speed curve scenario, including:

[0034] A position and turning radius determination unit, configured to obtain multiple position points of an autonomous vehicle in a high-speed curve driving scenario, and determine the turning radius at the position points; the multiple position points include multiple actual position points and multiple predicted position points;

[0035] An objective function determination unit, configured to determine an objective function based on the position points and the turning radius, the objective function including a smoothness cost function, a distance cost function, and an offset cost function;

[0036] A slope determination unit, configured to determine the constraint conditions of the objective function, and fit the multiple actual position points and the multiple predicted position points based on the objective function and the constraint conditions to obtain a slope line, and determine the slope based on the slope line.

[0037] On the other hand, the present invention also provides an autonomous vehicle, including a memory and a processor, wherein,

[0038] The memory is configured to store a program;

[0039] The processor is coupled to the memory and configured to execute the program stored in the memory to implement the steps in the slope determination method in the high-speed curve scenario in any of the above possible implementation manners.

[0040] On the other hand, the present invention also provides a computer-readable storage medium, on which a program or an instruction is stored, and when the program or the instruction is executed by a processor, the steps in the slope determination method in the high-speed curve scenario in any of the above possible implementation manners are implemented.

[0041] The beneficial effects of the present invention are as follows: The slope determination method in the high-speed curve scenario provided by the present invention can determine the slope by obtaining multiple position points of an autonomous vehicle in a high-speed curve driving scenario and the turning radius at the position points. Compared with the method of determining the slope by a sensor in the prior art, the technical problem of low sensor signal frequency can be solved. Compared with the method of determining the slope by the vehicle longitudinal dynamics, it is not necessary to decouple the vehicle's own parameters and external resistance, which reduces the difficulty of slope determination and improves the accuracy of the determined slope. Moreover, the determination process of the present invention is simple, thereby improving the slope determination efficiency.

[0042] Further, in the process of determining the slope, the present invention simultaneously considers the curve and the slope, and generates an objective function including a smoothness cost function, a distance cost function, and an offset cost function based on the curve and the slope, that is: the objective function takes into account the safety, comfort, and economy of driving at the same time.

[0043] Furthermore, the present invention determines the slope based on the position points and the turning radius. By setting the position points to include actual position points and predicted position points, the prediction of the slope can be achieved, and no sensors are required. Therefore, the problem that signals cannot be received or the signal deviation is large during continuous positioning in special areas (such as continuous tunnels in mountainous areas) in the prior art is solved, and the robustness of the slope determination method is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention, and those skilled in the art can obtain other drawings based on these drawings without creative efforts.

[0045] Figure 1 Schematic flowchart of an embodiment of the slope determination method in a high-speed curve scenario provided by the present invention;

[0046] Figure 2 Schematic diagram of the construction principle of the smoothness cost function provided by the present invention;

[0047] Figure 3 Schematic diagram of the construction principle of the continuous slope offset constraint provided by the present invention;

[0048] Figure 4 Schematic diagram of the construction principle of the curvature radius constraint provided by the present invention;

[0049] Figure 5 For the present invention Figure 1 Schematic flowchart of an embodiment of determining multiple position points in step S101 of the present invention;

[0050] Figure 6 Schematic flowchart of an embodiment of verifying the accuracy of the determined slope provided by the present invention;

[0051] Figure 7 Schematic structural diagram of an embodiment of the slope determination device in a high-speed curve scenario provided by the present invention;

[0052] Figure 8 Schematic structural diagram of an embodiment of an autonomous driving vehicle provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0054] It should be understood that the schematic drawings are not drawn to scale. The flowcharts used in the present invention illustrate the operations implemented according to some embodiments of the present invention. It should be understood that the operations of the flowchart may not be implemented in sequence, and steps without logical context relationships may be reversed or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart or remove one or more operations from the flowchart under the guidance of the content of the present invention. Some of the block diagrams shown in the drawings are functional entities, which do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor systems and / or microcontroller systems.

[0055] Reference to "embodiment" herein means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0056] The present invention provides a method, apparatus, vehicle, and storage medium for determining a slope in a high-speed curve scenario, which will be described separately below.

[0057] Figure 1 It is a schematic flowchart of an embodiment of the method for determining a slope in a high-speed curve scenario provided by the present invention. As Figure 1 shown, the method for determining a slope in a high-speed curve scenario includes:

[0058] S101. Obtain multiple position points of an autonomous vehicle in a high-speed curve driving scenario, and determine the turning radius at the position points; the multiple position points include multiple actual position points and multiple predicted position points;

[0059] S102. Determine an objective function based on the position points and the turning radius, where the objective function includes a smoothness cost function, a distance cost function, and an offset cost function;

[0060] S103. Determine the constraint conditions of the objective function, and fit the multiple actual position points and the multiple predicted position points based on the objective function and the constraint conditions to obtain a slope line, and determine the slope based on the slope line.

[0061] Among them, the specific method for determining the turning radius at the determined position point in step S101 is as follows: The idea of forming a circle with three points is adopted to determine the turning radius, that is, an inscribed circle is determined based on the current position point and two adjacent position points adjacent to the current position point, and the radius of the inscribed circle is the turning radius.

[0062] Compared with the prior art, the slope determination method in the high-speed bend scenario provided by the embodiment of the present invention can determine the slope by obtaining multiple position points and the turning radius at the position points of the autonomous driving vehicle in the high-speed bend driving scenario. Compared with the method of determining the slope by sensors in the prior art, the technical problem of low sensor signal frequency can be solved. Compared with the method of determining the slope by the vehicle longitudinal dynamics method, there is no need to decouple the vehicle's own parameters and external resistance, which reduces the difficulty of slope determination and improves the accuracy of the determined slope. Moreover, the determination process of the present invention is simple, thus improving the determination efficiency of the slope.

[0063] Furthermore, in the process of determining the slope in the embodiment of the present invention, the bend and the slope are considered simultaneously, and an objective function including a smoothness cost function, a distance cost function, and an offset cost function is generated based on the bend and the slope, that is, the objective function takes into account the safety, comfort, and economy of driving at the same time.

[0064] Even further, the embodiment of the present invention determines the slope based on the position point and the turning radius. By setting the position point to include the actual position point and the predicted position point, the prediction of the slope can be realized, and sensors are not required. Therefore, the problem that signals cannot be received or the signal deviation is large during continuous positioning in special areas (such as continuous tunnels in mountainous areas) in the prior art is solved, and the robustness of the slope determination method is improved.

[0065] It should be understood that the specific principle that the objective function can take into account the safety, comfort, and economy of driving at the same time by setting the smoothness cost function, the distance cost function, and the offset cost function is as follows:

[0066] Power demand: When going uphill, the vehicle needs more power to overcome the influence of gravity; when going downhill, gravity helps the vehicle accelerate, but at the same time, more braking force is required to control the speed.

[0067] Fuel efficiency: When going uphill, driving usually results in a decrease in fuel efficiency because the vehicle needs more energy to overcome gravity.

[0068] Braking distance: When going downhill, the braking distance of the vehicle may increase because the vehicle has greater kinetic energy and more braking force is required to decelerate.

[0069] It can be seen from this that by determining the slope, the vehicle driving parameters can be controlled according to the slope to ensure that the vehicle power meets the current slope and ensure the optimal fuel efficiency and optimal braking force under the current slope, that is, taking into account the safety, comfort and economy of driving.

[0070] In some embodiments of the present invention, the objective function is:

[0071]

[0072]

[0073]

[0074]

[0075] In the formula, is the objective function; is the ride comfort cost function; is the distance cost function; is the offset cost function; and are the X-axis coordinate and Z-axis coordinate of the i-th position point respectively; and are the X-axis coordinate and Z-axis coordinate of the (i - 1)-th position point respectively; and are the X-axis coordinate and Z-axis coordinate of the (i + 1)-th position point respectively; is the turning radius of the i-th position point; 、 and are the X-axis coordinate, Y-axis coordinate and Z-axis coordinate of the road center point corresponding to the i-th position point respectively.

[0076] In some embodiments of the present invention, the constraint conditions include continuous slope offset constraint and curvature radius constraint; the continuous slope offset constraint is:

[0077]

[0078] The curvature radius constraint is:

[0079]

[0080] In the formula, is the distance between the i-th position point and the center of the rolling sphere on the slope line; 、 and are the X-axis coordinate, Y-axis coordinate and Z-axis coordinate of the center of the rolling sphere on the slope line respectively; is the minimum distance; 、 , is the Y-axis coordinate of the i-th position point, the (i-1)-th position point, and the (i+1)-th position point; is the average length between multiple position points; is the maximum curvature.

[0081] It should be noted that: the X-axis, Y-axis, and Z-axis in the embodiments of the present invention refer to the three coordinate axes of the vehicle coordinate system. Among them, the origin of the vehicle coordinate system coincides with the centroid of the autonomous vehicle, the X-axis is parallel to the ground and points to the front of the vehicle, the Z-axis passes through the vehicle centroid and points upward, and the Y-axis points to the left of the driver.

[0082] In a specific embodiment of the present invention, the construction principle of the ride comfort cost function is as Figure 2 shown. The length of the vector represents the square of the modulus of the new vector formed by adding the vectors and the vector . That is, . If these three points are on a straight line, is the smallest. That is, the larger the angle between the vector and the vector , the closer the curve is to being straight, indicating that under the premise that the curve is satisfied, the slope does not change much either. At this time, the slope of the curve during autonomous driving on the curve is smoother, and the driving is smoother. Among them, the distance cost function represents the sum of the squares of the distances between adjacent position points on the curve. The offset cost function represents the sum of the squares of the offset distances of the position points from the center line of the road.

[0083] Among them, the continuous slope offset constraint is to ensure that the change in the road slope does not suddenly change violently. As

[0084] shown, a sphere rolls along the slope line with its center of the sphere. The solid curve in the figure is the slope line, and the distance between the center of the sphere and the position point should be less than a certain value. Figure 3 Among them, the principle of the curvature radius constraint is as

[0085] shown. Assuming that Figure 4 the three points , and are located on the same circle. When is relatively small, the moduli of the vectors and the vector are approximately equal to the arc length. Then there is:

[0086]

[0087] According to the geometric relationship of the isosceles triangle, there is:

[0088]

[0089] Since , C is the midpoint of, there is relationship, and we get:

[0090]

[0091] According to the geometric relationship of right triangles, there are:

[0092]

[0093] Substitute into and we get:

[0094]

[0095] Substitute and we get:

[0096]

[0097]

[0098] Substitute and we get:

[0099]

[0100] Among them, when the autonomous vehicle is going uphill or downhill, it satisfies the constraint of the kinematic minimum turning radius, that is

[0101]

[0102] That is to say:

[0103]

[0104] In a specific embodiment of the present invention, as Figure 5 shown, obtaining multiple position points of the autonomous vehicle in the high-speed curve driving scenario in step S101 includes:

[0105] S501. Obtain the historical driving trajectory of the autonomous vehicle in the high-speed curve scenario, and determine multiple actual position points based on the historical driving trajectory;

[0106] S502. Obtain the vehicle driving state data of the autonomous vehicle at each actual position point, and input the vehicle driving state data and multiple actual position points into the position prediction model to obtain multiple predicted position points.

[0107] Among them, the historical driving trajectory includes, but is not limited to, the three-dimensional coordinates of each driving position, and the vehicle driving state data includes, but is not limited to, the IMU data obtained by the inertial sensor and the vehicle speed.

[0108] It should be understood that in existing autonomous vehicles, a trajectory prediction model is set up to predict the vehicle's driving trajectory for the next few seconds to achieve vehicle trajectory prediction. Among them, the trajectory prediction model can be obtained through training, testing, and verification based on historical trajectory data. The model structure of the trajectory prediction model includes, but is not limited to, the LSTM model, etc.

[0109] To ensure the accuracy of the predicted position points and thus the accuracy of the determined slope, in some embodiments of the present invention, before step S501, it further includes:

[0110] Determine the position prediction distance based on the vehicle speed, and determine the number of predicted position points based on the position prediction distance.

[0111] In the embodiments of the present invention, by determining the position prediction distance through the vehicle speed, it is possible to predict the position within a shorter distance when the vehicle speed is high, and predict the position within a longer distance when the vehicle speed is low. The position prediction distance can be adaptively adjusted according to the different vehicle speeds to ensure the accurate determination of the predicted position points within the position prediction distance.

[0112] Specifically, the number of predicted position points can be determined by the position prediction distance and a preset interval distance.

[0113] Since when the turning radius is too large, safety problems will occur. To further ensure the driving safety of autonomous vehicles in high-speed curved road scenarios, in some embodiments of the present invention, before step S102, it further includes:

[0114] Determine the maximum turning radius, and determine whether the turning radius at each position point is greater than the maximum turning radius;

[0115] When the turning radius at the position point is greater than the maximum turning radius, the position point is removed.

[0116] In the embodiments of the present invention, by removing the position points with a turning radius greater than the maximum turning radius, the driving safety of all position points can be ensured.

[0117] Among them, the maximum turning radius is:

[0118]

[0119] In the formula, is the driving speed, is the minimum acceleration, which is an empirical value.

[0120] To verify the accuracy of the slope determined in the embodiments of the present invention, in some embodiments of the present invention, such as Figure 6 shown, the slope determination method in the high-speed curve scenario further includes:

[0121] S601. Generate a speed control command for controlling the speed of the autonomous vehicle based on the slope;

[0122] S602. Obtain the speed change trend of the autonomous vehicle under the control of the speed control command;

[0123] S603. Verify the accuracy of the slope based on the speed change trend.

[0124] Specifically, when the slope is an uphill slope, the speed control command is to accelerate driving. After the command is issued, if the determined speed change trend is to accelerate and the acceleration degree is greater than the acceleration threshold, it indicates that the determined slope is incorrect, and the current slope should be a downhill slope or a flat slope. On the contrary, the determined slope is correct. This is because: during the uphill process of the vehicle, part of the vehicle power needs to be used to overcome gravity, and the speed change trend can be deceleration, uniform speed or slight acceleration, but it cannot be a large increase in speed. When there is a large increase in speed, it indicates that the slope is not an uphill slope. The same applies to other situations and will not be elaborated one by one here.

[0125] To better implement the slope determination method in the high-speed curve scenario in the embodiments of the present invention, correspondingly, based on the slope determination method in the high-speed curve scenario, the embodiments of the present invention further provide a slope determination device in the high-speed curve scenario, such as Figure 7 shown, the slope determination device 700 in the high-speed curve scenario includes:

[0126] A position and turning radius determination unit 701, configured to obtain multiple position points of the autonomous vehicle in the high-speed curve driving scenario and determine the turning radius at the position points; the multiple position points include multiple actual position points and multiple predicted position points;

[0127] A target function determination unit 702, configured to determine a target function based on the position points and the turning radius, and the target function includes a smoothness cost function, a distance cost function, and an offset amount cost function;

[0128] A slope determination unit 703, configured to determine the constraint conditions of the target function, and fit the multiple actual position points and the multiple predicted position points based on the target function and the constraint conditions to obtain a slope line, and determine the slope based on the slope line.

[0129] The slope determination device 700 in the above embodiments can implement the technical solutions described in the method embodiments for slope determination in the high-speed curve scenario. The specific implementation principles of the above modules or units can be referred to the corresponding content in the method embodiments for slope determination in the high-speed curve scenario, which will not be elaborated here.

[0130] As Figure 8 shown, the present invention also correspondingly provides an autonomous vehicle 800. The autonomous vehicle 800 includes a processor 801, a memory 802, and a display 803. Figure 8 Only some components of the autonomous vehicle 800 are shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented.

[0131] In some embodiments, the processor 801 can be a central processing unit (CPU), a microprocessor, or other data processing chips, and is used to run the program code stored in the memory 802 or process data, such as the method for slope determination in the high-speed curve scenario of the present invention.

[0132] In some embodiments of the present invention, the processor 801 can be a single server or a server group. The server group can be centralized or distributed. In some embodiments, the processor 801 can be local or remote. In some embodiments, the processor 801 can be implemented on a cloud platform. In one embodiment, the cloud platform can include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination of the above.

[0133] In some embodiments, the memory 802 can be an internal storage unit of the autonomous vehicle 800, such as the hard disk or memory of the autonomous vehicle 800. In some other embodiments, the memory 802 can also be an external storage device of the autonomous vehicle 800, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the autonomous vehicle 800.

[0134] Furthermore, the memory 802 can also include both the internal storage unit and the external storage device of the autonomous vehicle 800. The memory 802 is used to store the application software installed in the autonomous vehicle 800 and various types of data.

[0135] The display 803 may be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. in some embodiments. The display 803 is used to display information of the autonomous vehicle 800 and to display a visualized user interface. Components 801 - 803 of the autonomous vehicle 800 communicate with each other via a system bus.

[0136] In some embodiments of the present invention, when the processor 801 executes the slope determination program in the high-speed curve scenario in the memory 802, the following steps can be achieved:

[0137] Obtain multiple position points of the autonomous vehicle in the high-speed curve driving scenario, and determine the turning radius at the position points; the multiple position points include multiple actual position points and multiple predicted position points;

[0138] Determine an objective function based on the position points and the turning radius, and the objective function includes a smoothness cost function, a distance cost function, and an offset cost function;

[0139] Determine the constraint conditions of the objective function, and fit the multiple actual position points and the multiple predicted position points based on the objective function and the constraint conditions to obtain a slope line, and determine the slope based on the slope line.

[0140] It should be understood that when the processor 801 executes the slope determination program in the high-speed curve scenario in the memory 802, in addition to the above functions, other functions can also be achieved. For specific details, please refer to the description of the corresponding method embodiments above.

[0141] Furthermore, the embodiments of the present invention do not specifically limit the type of the autonomous vehicle 800 mentioned. The autonomous vehicle 800 may be a portable autonomous vehicle such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of the portable autonomous vehicle include, but are not limited to, portable autonomous vehicles equipped with IOS, android, microsoft, or other operating systems. The above portable autonomous vehicles may also be other portable autonomous vehicles. It should also be understood that in some other embodiments of the present invention, the autonomous vehicle 800 may not be a portable autonomous vehicle, but a desktop computer with a touch-sensitive surface (such as a touch panel).

[0142] Accordingly, an embodiment of the present invention further provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the programs or instructions are executed by a processor, the steps or functions in the slope determination method in the above-mentioned high-speed curve scenarios provided by each method embodiment can be implemented.

[0143] Those skilled in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware (such as a processor, a controller, etc.) through a computer program. The computer program can be stored in a computer-readable storage medium. Among them, the computer-readable storage medium is a disk, an optical disc, a read-only memory, or a random access memory, etc.

[0144] The above has introduced in detail a slope determination method, device, autonomous driving vehicle, and storage medium in a high-speed curve scenario provided by the present invention. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for determining a slope in a high-speed curved road scenario, characterized in that, Including: Obtaining multiple position points of an autonomous driving vehicle in a high-speed curved road driving scenario, and determining the turning radius at the position points; the multiple position points include multiple actual position points and multiple predicted position points; Determining an objective function based on the position points and the turning radius, the objective function including a smoothness cost function, a distance cost function, and an offset cost function; Determining the constraint conditions of the objective function, and fitting the multiple actual position points and the multiple predicted position points based on the objective function and the constraint conditions to obtain a slope line, and determining a slope based on the slope line; The objective function is: In the formula, is the objective function; is the smoothness cost function; is the distance cost function; is the offset cost function; and are the X-axis coordinate and Z-axis coordinate of the i-th position point respectively; and are the X-axis coordinate and Z-axis coordinate of the (i - 1)-th position point respectively; and are the X-axis coordinate and Z-axis coordinate of the (i + 1)-th position point respectively; is the turning radius of the i-th position point; , and are the X-axis coordinate, Y-axis coordinate and Z-axis coordinate of the road center point corresponding to the i-th position point respectively.

2. The slope determination method in a high-speed curve scenario according to claim 1, wherein, The constraint conditions include a continuous slope offset constraint and a curvature radius constraint; the continuous slope offset constraint is: The curvature radius constraint is: Wherein, is the distance between the i-th position point and the center of the rolling sphere on the slope line; , and are respectively the X-axis coordinate, Y-axis coordinate and Z-axis coordinate of the center of the rolling sphere on the slope line; is the minimum distance; , , are the Y-axis coordinates of the i-th position point, the i-1-th position point and the i+1-th position point; is the average length between the multiple position points; is the maximum curvature.

3. The slope determination method in a high-speed curve scenario according to claim 1, characterized in that, The obtaining multiple position points of an autonomous driving vehicle in a high-speed curved road driving scenario includes: Obtaining the historical driving trajectory of the autonomous driving vehicle in the high-speed curved road scenario, and determining the multiple actual position points based on the historical driving trajectory; Obtaining the vehicle driving state data of the autonomous driving vehicle at each of the actual position points, and inputting the vehicle driving state data and the multiple actual position points into a position prediction model to obtain the multiple predicted position points.

4. The slope determination method in the high-speed bend scenario according to claim 3, characterized in that The vehicle driving state data includes a vehicle speed, and before obtaining the historical driving trajectory of the autonomous driving vehicle in the high-speed curved road scenario, it further includes: Determining a position prediction distance based on the vehicle speed, and determining the number of the multiple predicted position points based on the position prediction distance.

5. The slope determination method in a high-speed curve scenario according to claim 1, wherein Before determining the objective function based on the position points and the turning radius, it further includes: Determining a maximum turning radius, and determining whether the turning radius at each of the position points is greater than the maximum turning radius; When the turning radius at the position point is greater than the maximum turning radius, removing the position point.

6. The slope determination method in a high-speed curve scenario according to claim 1, characterized in that The method further includes: Generating a speed control instruction for controlling the vehicle speed of the autonomous driving vehicle based on the slope; Obtaining the vehicle speed change trend of the autonomous driving vehicle under the control of the speed control instruction; Verifying the accuracy of the slope based on the vehicle speed change trend.

7. A slope determination device for a high-speed curve scenario, characterized in that, Including: A position and turning radius determination unit, configured to obtain multiple position points of an autonomous driving vehicle in a high-speed curved road driving scenario, and determine the turning radius at the position points; the multiple position points include multiple actual position points and multiple predicted position points; An objective function determination unit, configured to determine an objective function based on the position points and the turning radius, the objective function including a smoothness cost function, a distance cost function, and an offset cost function; A slope determination unit, configured to determine the constraint conditions of the objective function, and fitting the multiple actual position points and the multiple predicted position points based on the objective function and the constraint conditions to obtain a slope line, and determining a slope based on the slope line; The objective function is: In the formula, is the objective function; is the smoothness cost function; is the distance cost function; is the offset cost function; and are the X-axis coordinate and Z-axis coordinate of the i-th position point respectively; and are the X-axis coordinate and Z-axis coordinate of the (i - 1)-th position point respectively; and are the X-axis coordinate and Z-axis coordinate of the (i + 1)-th position point respectively; is the turning radius of the i-th position point; , and are the X-axis coordinate, Y-axis coordinate and Z-axis coordinate of the road center point corresponding to the i-th position point respectively.

8. An autonomous vehicle, characterized in that, Including a memory and a processor, wherein, The memory is configured to store programs; The processor, which is coupled to the memory, is configured to execute the program stored in the memory to implement the steps in the slope determination method in the high-speed curve scenario according to any one of claims 1 to 6 above.

9. A computer-readable storage medium, characterized in that, A program or instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, the steps in the slope determination method in the high-speed curve scenario according to any one of 1 to 6 are implemented.

Images