Vehicle control planning methods and related products

Abstract

The present invention discloses a vehicle control planning method and related products, wherein the method includes: obtaining a planned reference path; calculating an initial value of a lateral control amount based on the reference path, and performing control sampling on the initial value to obtain multiple control sampling points; performing forward recursion based on the lateral control amount of each control sampling point to obtain a pure tracking path corresponding to each control sampling point; performing state sampling on each pure tracking path to obtain multiple corresponding state sampling points; calculating a cost value of the pure tracking path based on the state sampling points of the pure tracking path and the reference path; and selecting the lateral control amount of the control sampling point corresponding to the pure tracking path with the smallest cost value. In an embodiment of the present invention, by performing cost value calculation on multiple pure tracking paths corresponding to the lateral control amounts of the multiple control samples to obtain the lateral control amount corresponding to the pure tracking path with the smallest cost value, a more reasonable lateral control amount can be generated for a vehicle in the presence of errors.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a vehicle control planning method and related products. Background Art

[0002] With the development of artificial intelligence and modern manufacturing, autonomous driving technology has gradually become part of our daily lives, subtly changing the way we travel. Autonomous driving technology can be broadly divided into several aspects: perception, prediction, positioning, decision-making, planning, and control. Control is a key component of autonomous driving.

[0003] Existing path planning methods primarily include search-based and sampling-based planning. Sampling-based planning methods are dynamic programming algorithms. Dynamic programming algorithms perform multi-layer state sampling on a reference path, evaluate all feasible paths, and select the optimal path as the output path. Control methods primarily include model predictive control algorithms, which consist of three steps: 1. Predicting the future state of the system based on the vehicle's current position and model; 2. Solving the optimization problem to find the trajectory with the lowest cost (the optimal solution); and 3. Applying the first control variable of the optimal solution to the system.

[0004] Conventional control methods in the prior art often use a planner to provide a reference path, and a controller to generate control variables to track the reference path. Under the above conditions, the control method lacks the ability to respond to obstacles in real time. In addition, due to various errors, the vehicle state is not completely consistent with the reference state (including position and angle) given by the reference path. In particular, when ensuring that the position error is small, a certain angle error will be generated. The reference path collision check is based on the reference state, so it cannot be guaranteed that the vehicle will be completely collision-free during actual driving along the path.

[0005] The inventors found that the existing path planning method can only detect whether there is a collision at the waypoint status, but cannot determine whether a collision occurs based on the real-time status of the vehicle, especially the collision detection when the vehicle deviates from the path; the model predictive control algorithm is mainly used for trajectory tracking, and has weak obstacle avoidance capabilities. If a longer step-length prediction is performed, solving the optimization problem will be time-consuming and cannot solve the problem of certain position and posture deviations between the actual walking path of the vehicle and the obstacle avoidance path due to factors such as positioning error, tracking error, and system delay. When the distance to the obstacle is particularly close, a collision is likely to occur, causing the vehicle to brake suddenly. Summary of the Invention

[0006] The embodiments of the present invention aim to solve at least one of the above technical problems.

[0007] In a first aspect, an embodiment of the present invention provides a vehicle control planning method, comprising: obtaining a planned reference path; calculating an initial value of a lateral control amount based on the reference path, and performing control sampling on the initial value to obtain a plurality of control sampling points; performing forward recursion based on the lateral control amount of each control sampling point to obtain a pure tracking path corresponding to each control sampling point; performing state sampling on each pure tracking path to obtain a plurality of state sampling points corresponding to the pure tracking path; calculating a cost value of the pure tracking path based on the state sampling points of the pure tracking path and the reference path; and selecting the lateral control amount of the control sampling point corresponding to the pure tracking path with the smallest cost value as the lateral control amount of this vehicle control planning.

[0008] In a second aspect, an embodiment of the present invention provides a vehicle control planning device, comprising: an acquisition sampling module for acquiring a planned reference path, calculating an initial value of a lateral control amount based on the reference path, and performing control sampling on the initial value to obtain a plurality of control sampling points; a forward recursion module for performing forward recursion based on the lateral control amount of each control sampling point to obtain a pure tracking path corresponding to each control sampling point; a state sampling module for performing state sampling on each pure tracking path to obtain a plurality of state sampling points corresponding to the pure tracking path; calculating a cost value of the pure tracking path based on the state sampling points of the pure tracking path and the reference path; and a selection module for selecting the lateral control amount of the control sampling point corresponding to the pure tracking path with the smallest cost value as the lateral control amount of this vehicle control planning.

[0009] In a third aspect, an embodiment of the present invention provides an electronic device comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of the vehicle control planning method of any embodiment of the present invention.

[0010] In a fourth aspect, an embodiment of the present invention provides a storage medium on which a computer program is stored, characterized in that when the program is executed by a processor, the steps of the vehicle control planning method of any embodiment of the present invention are implemented.

[0011] In a fifth aspect, an embodiment of the present invention further provides a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the steps of the vehicle control planning method of any embodiment of the present invention.

[0012] In a sixth aspect, an embodiment of the present invention further provides a mobile tool equipped with a camera, wherein the mobile tool includes the electronic device described in the third aspect, and the camera is communicatively connected to the electronic device.

[0013] In this application, by calculating the cost values ​​of multiple pure tracking paths corresponding to the lateral control quantities of multiple control samples to obtain the lateral control quantity corresponding to the pure tracking path with the smallest cost value, the vehicle can generate a more reasonable lateral control quantity in the presence of errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0015] Figure 1 A flow chart of an embodiment of a vehicle control planning method provided by an embodiment of the present invention;

[0016] Figure 2 A schematic diagram of control sampling of a vehicle control planning execution device provided by one embodiment of the present invention;

[0017] Figure 3 A control schematic diagram of a specific example of a vehicle control planning method provided by one embodiment of the present invention;

[0018] Figure 4 A schematic diagram of a coordinate system for a vehicle control planning method is provided for one embodiment of the present invention;

[0019] Figure 5 A flowchart of another embodiment of a vehicle control planning method provided by one embodiment of the present invention;

[0020] Figure 6 A schematic diagram of a preview process of a preview algorithm of a vehicle control planning method is provided for one embodiment of the present invention;

[0021] Figure 7 A schematic diagram of a prediction model of a vehicle control planning method is provided for one embodiment of the present invention;

[0022] Figure 8 A flowchart of another embodiment of a vehicle control planning method provided by one embodiment of the present invention;

[0023] Figure 9 A reference path diagram of a vehicle control planning method is provided for one embodiment of the present invention;

[0024] Figure 10 A flowchart of another embodiment of a vehicle control planning method provided by one embodiment of the present invention;

[0025] Figure 11 A flowchart of another embodiment of a vehicle control planning method provided by one embodiment of the present invention;

[0026] Figure 12 A state sampling diagram of a vehicle control planning method is provided for one embodiment of the present invention;

[0027] Figure 13 A structural block diagram of a vehicle control planning device provided by one embodiment of the present invention;

[0028] Figure 14 FIG. 1 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. 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 efforts shall fall within the scope of protection of the present invention.

[0030] Those skilled in the art will appreciate that the embodiments of the present application may be implemented as a system, apparatus, device, method, or computer program product. Therefore, the present disclosure may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software.

[0031] For ease of understanding, the technical terms involved in this application are explained below: The "mobile device" referred to in this application includes but is not limited to vehicles with six autonomous driving technology levels L0-L5 as established by the Society of Automotive Engineers International (SAE International) or the Chinese national standard "Automotive Driving Automation Classification".

[0032] In some embodiments, the mobile device may be a vehicle or a robotic device having the following functions:

[0033] (1) Passenger-carrying function, such as family cars and buses;

[0034] (2) Cargo carrying function, such as ordinary trucks, box trucks, trailer trucks, closed trucks, tank trucks, flatbed trucks, container trucks, dump trucks, trucks with special structures, etc.;

[0035] (3) Tool functions, such as logistics delivery vehicles, automated guided vehicles (AGVs), patrol cars, cranes, hoists, excavators, bulldozers, forklifts, rollers, loaders, off-road engineering vehicles, armored engineering vehicles, sewage treatment vehicles, sanitation vehicles, vacuum trucks, floor scrubbers, sprinkler trucks, sweeping robots, food delivery robots, shopping guide robots, lawn mowers, golf carts, etc.;

[0036] (4) Entertainment functions, such as entertainment vehicles, amusement park self-driving devices, balance vehicles, etc.;

[0037] (5) Special rescue functions, such as fire trucks, ambulances, power repair trucks, engineering rescue trucks, etc.

[0038] It should be noted that, unless there is any conflict, the embodiments and features in the embodiments of this application can be combined with each other.

[0039] The present invention may be described in the general context of computer-executable instructions, such as program modules, executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media, including storage devices.

[0040] In the present invention, "module", "device", "system" and the like refer to related entities applied to a computer, such as hardware, a combination of hardware and software, software or software in execution, etc. Specifically, for example, an element can be, but is not limited to, a process running on a processor, a processor, an object, an executable element, an execution thread, a program and / or a computer. In addition, an application or script program running on a server, or a server can all be an element. One or more elements can be in an execution process and / or thread, and an element can be localized on a computer and / or distributed between two or more computers, and can be run by various computer-readable media. An element can also communicate through local and / or remote processes based on a signal having one or more data packets, for example, a signal from a data packet interacting with another element in a local system, a distributed system, and / or a signal from a network on the Internet that interacts with other systems via signals.

[0041] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include" and "comprise" include not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article or device. In the absence of further limitations, the elements defined by the phrase "include..." do not exclude the presence of other identical elements in the process, method, article or device that includes the elements.

[0042] Please refer to Figure 1 , which illustrates a vehicle control planning method provided by an embodiment of the present application.

[0043] like Figure 1 As shown, in step S11, a planned reference path is obtained; an initial value of the lateral control amount is calculated based on the reference path, and control sampling is performed on the initial value to obtain multiple control sampling points;

[0044] In step S12, forward recursion is performed based on the lateral control amount of each control sampling point to obtain a pure tracking path corresponding to each control sampling point;

[0045] In step S13, state sampling is performed on each pure tracking path to obtain a plurality of state sampling points corresponding to the pure tracking path; and the cost value of the pure tracking path is calculated based on the state sampling points of the pure tracking path and the reference path.

[0046] In step S14, the lateral control amount of the control sampling point corresponding to the pure tracking path with the smallest substitution value is selected as the lateral control amount of this vehicle control planning.

[0047] In this embodiment, for step S11, the planned reference path is an obstacle avoidance path given by the planner, wherein the reference path is composed of multiple path points, and the initial value of the lateral control amount can be calculated based on the reference path. Then, control sampling is performed based on the initial value to obtain multiple control sampling points. In a specific example, the initial value of the lateral control amount can be calculated as follows: the path point S closest to the current position A on the reference path is obtained, and the path point S is used as the starting point. In the Frenet coordinate system, a point with a length of preview distance to the starting point is selected as the preview point Y, and then the initial control amount is generated from the current point A to the preview point Y according to the preview algorithm. Other algorithms can also be used to generate initial values, such as traditional control algorithms such as Stanley and PID to generate initial values ​​of the control amount. In another specific example, after obtaining the initial value of the lateral control amount, control sampling is performed at a preset curvature interval (for example, the curvature is 0.01 (1 / m)) through the initial value to obtain multiple control sampling points. For example, assuming the initial value is 0.2, we sample the initial value at intervals of 0.01 to obtain multiple control sampling points, each with a different lateral control amount. For example, if the initial value is 0.2, we sample two points to the left, resulting in sampling points 0.18 and 0.19; and we sample two points to the right, resulting in sampling points 0.21 and 0.22. The corresponding lateral control amounts for the four control sampling points are 0.18, 0.19, 0.21, and 0.22, respectively.

[0048] Then, in step S12, forward recursion is performed based on the lateral control amount of each control sampling point to obtain the pure tracking path corresponding to each control sampling point. In a specific example, forward recursion is performed based on the four control sampling points (0.18, 0.19, 0.21, and 0.22) in the above example to obtain four pure tracking paths.

[0049] Then, in step S13, state sampling is performed on each pure tracking path to obtain multiple state sampling points corresponding to the pure tracking path. A cost value for each pure tracking path is calculated based on the state sampling points of each pure tracking path and the reference path. The cost value for each pure tracking path is calculated by comparing various parameters of each state sampling point on each pure tracking path with various parameters of path points on the reference path.

[0050] Finally, in step S14, after obtaining the cost value for each pure tracking path, the lateral control variable corresponding to the control sampling point of the pure tracking path with the smallest cost value is selected as the lateral control variable for the current vehicle control planning. For example, if the pure tracking path obtained by forward recursion from the control sampling point with a lateral control variable of 0.19 has the smallest cost value, then this lateral control variable of 0.19 can be used as the lateral control variable for this precise control.

[0051] Please refer to Figure 2 and Figure 3 , Figure 2 shows a schematic diagram of control sampling, Figure 3 A control schematic diagram of a specific example of a vehicle control planning method provided in this embodiment of the present application is shown.

[0052] like Figure 2 and Figure 3 As shown, the planner first gives an obstacle avoidance path (consisting of a series of path points), and the precise control module (i.e., the module corresponding to the vehicle control planning method of this application) calculates a reasonable lateral control amount based on the obstacle information perceived by the sensor and the current state of the vehicle given by the locator, and sends it to the controller for precise control.

[0053] In order to make the subsequent description of the embodiments clearer, the basic knowledge used in the embodiments of this application is first introduced:

[0054] Please refer to Figure 4 , which shows the Frenet coordinate system (left figure) and the vehicle coordinate system (right figure) of an embodiment of the present application:

[0055] Among them, in the Frenet coordinate system: a coordinate system composed of the reference path as the coordinate axis, the coordinate axes are the S axis and the L axis, wherein the S axis is the direction in which the reference path increases, and the L axis is the direction perpendicular to the reference path.

[0056] In the vehicle coordinate system: the direction of the vehicle head is the x-axis, and the left side perpendicular to the direction of the vehicle head is the y-axis.

[0057] The embodiment of the present application calculates the cost value of multiple pure tracking paths corresponding to the lateral control quantities obtained from multiple control samples to obtain the lateral control quantity corresponding to the pure tracking path with the smallest cost value, so that the vehicle can generate a more reasonable lateral control quantity in the presence of errors.

[0058] In some optional embodiments, the forward recursion is performed based on the lateral control amount of the control sampling point in the above step S12 to obtain the pure tracking path corresponding to the control sampling point. Specifically, Figure 5 The method flow shown is implemented as follows:

[0059] Step S121: using a preset prediction model, based on the current position of the vehicle and the lateral control amount of the control sampling point, predicting the next frame position point of the current position of the vehicle;

[0060] Step S122: Using the next frame position point as a state sampling point, selecting a preview point on the reference path according to a preset preview distance with the waypoint closest to the state sampling point as a starting point; and using a preset preview algorithm to determine a lateral control amount for the state sampling point based on the state sampling point and the preview point.

[0061] Step S123: using the prediction model, based on the position information of the state sampling point and its lateral control amount, predict the next frame position point of the state sampling point;

[0062] In step S124, the aforementioned steps 2 to 3 are executed based on the next frame position point until a preset stop condition is satisfied, and all state sampling points constituting the pure tracking path are obtained in sequence.

[0063] Therefore, each control sampling point can be forward recursively deduced through the above steps, and a pure tracking path corresponding to each control sampling point can be obtained through a preset preview algorithm and a preset prediction model.

[0064] Please refer to Figure 6 , which shows a schematic diagram of the preview process of the preview algorithm in an embodiment of the present application.

[0065] like Figure 6 As shown in the figure, the preview algorithm is as follows: in the vehicle coordinate system, the current position of the vehicle is known to be C(0,0), the direction of movement is the x-axis, the preview point B(a,b) is selected, and the center of the circle is set to A(0,y). From AB=AC, we can get:

[0066]

[0067]

[0068] Therefore, based on the vehicle's current position C and the preview point B, the lateral control amount δ obtained by the preview algorithm is 1 / R.

[0069] It should be noted that other models can also be used in this application to perform forward recursion of the lateral control quantity of the control sampling point, such as using traditional control algorithms such as Stanley and PID, and the algorithm can be used to perform future trajectory prediction and collision detection later, and this application does not limit this. The reason why the preview algorithm is used for forward recursion in this application is that the initial value of the lateral control quantity is also generated using the preview algorithm. Therefore, when the initial value of the lateral control quantity is obtained using the other algorithms mentioned above, the future trajectory prediction and collision detection are also replaced with other algorithms accordingly, and this application does not limit this.

[0070] Further references Figure 7 , which shows a schematic diagram of the prediction model of an embodiment of the present application.

[0071] Preferably, the preset prediction model may adopt a differential model, which is as follows:

[0072] x k+1 =x k +v k cosθdt

[0073] y k+1 =y k +v k sinθdt

[0074] because:

[0075]

[0076] but:

[0077] θ k+1 =θ k +ωdt=θ k +v k δdt

[0078] Where x and y represent the horizontal and vertical coordinates of the vehicle's position, v represents the speed at the current position, δ represents the lateral control amount at the current position, θ represents the angle, k represents the current frame, k+1 represents the next frame, and R represents the radius.

[0079] In some optional embodiments, in order to further improve the consistency of the lateral control amount, the aforementioned Figure 5 In the process shown in FIG. 1 , determining the lateral control amount of the state sampling point based on the state sampling point and the preview point in step S122 further includes steps S122A and S122B, such as Figure 8 As shown:

[0080] Step S122A, determining whether the difference between the lateral control amount at the state sampling point and the lateral control amount at the previous state sampling point is less than a preset threshold; if less than the preset threshold, executing step S122B; if greater than or equal to the threshold, executing step S123;

[0081] Step S122B: Update the lateral control amount of the state sampling point based on the lateral control amount of the previous state sampling point, and execute step S123. Since the pure tracking path obtained by simply using the preview algorithm + differential model has little difference in lateral control amount for small lateral sampling intervals, in order to make the pure tracking path reflect the difference, when the change in control amount is less than a certain threshold, keep the current control amount unchanged and recursively move forward. For details, please refer to Figure 9 The recursive effect shown.

[0082] The preset threshold is related to the actual vehicle model. The specific model is determined by the vehicle structure. For example, the Ackerman model can be used. The relationship between the left and right wheel speed acceleration under the differential model is as follows: where the left wheel is represented by l and the right wheel is represented by r. For example, if the left wheel speed is v l , the right wheel speed is v r , the average speed is v, the acceleration is a, k represents the current frame, k+1 represents the next frame, d represents the distance between the left and right wheels, and the rate of change of the lateral control amount Δδ is:

[0083] Δδ=δ k+1 -δ k

[0084]

[0085] v k+1 =v k +at

[0086] We can get:

[0087]

[0088] When the threshold is less than This can better balance differences and accuracy. It should be noted that the threshold can be set based on the expected degree of divergence of the pure tracking path. The larger the threshold, the more divergent the path. This is not a limitation of this application. This allows the path to reflect differences while still being consistent with the actual driving path.

[0089] In some optional embodiments, Figure 1 In the method shown in FIG. 1 , after obtaining the pure tracking path corresponding to each control sampling point in step S12, the method further includes step S15, such as Figure 10 As shown, where:

[0090] Step S15: perform collision detection on each pure tracking path respectively, retain the pure tracking paths without collision risk; and execute step S13 based on the pure tracking paths without collision risk.

[0091] In a specific example, for each sampling point, preview is performed, the lateral control amount is calculated, and the next frame position is calculated using a prediction model. Based on the next frame position, preview and prediction are performed again. After looping through a preset N frames, the pure tracking path corresponding to the sampling point is obtained. Collision detection is then performed on the pure tracking path.

[0092] In a further optional embodiment, Figure 10 The method shown further includes step S16, as shown in FIG. Figure 11 As shown:

[0093] If step S15 determines that all pure tracking paths have collision risks, step S16 is executed;

[0094] Step S16: Select the state sampling point closest to the current position of the vehicle in each pure tracking path, and determine the state sampling point farthest from the obstacle from the selected state sampling points; and use the lateral control amount of the control sampling point corresponding to the pure tracking path where the state sampling point farthest from the obstacle is located as the lateral control amount of this vehicle control plan.

[0095] Therefore, when all pure tracking paths have collision risks, the lateral control amount of the control sampling point corresponding to the pure tracking path where the state sampling point farthest from the obstacle is located can be selected as the output control amount.

[0096] In other optional embodiments, the cost value of the pure tracking path is calculated based on the state sampling points of the pure tracking path and the reference path, specifically including: for each state sampling point on the pure tracking path, the cost value of the state sampling point is calculated based on the offset between the state sampling point and the reference path, the difference between the lateral control value of the control sampling point corresponding to the pure tracking path and the lateral control value of the vehicle control plan in the previous frame, and the distance between the state sampling point and the obstacle; and the sum of the cost values ​​of all state sampling points on the pure tracking path is determined as the cost value of the pure tracking path. Therefore, the cost value calculated using the above parameters can better characterize the quality of the pure tracking path, thereby selecting a better pure tracking path and obtaining a more reasonable lateral control value.

[0097] In a specific example, the cost function for calculating the cost value of each state sampling point of the pure tracking path is designed as follows:

[0098] f=k1l 2 +k2(δ k -δ k-1 ) 2 +k3C 2 ;

[0099] Among them, f is the cost value of the state sampling point, k1l 2 Indicates the offset of each state sampling point relative to the reference path in the Frenet coordinate system, k2(δ k -δ k-1 ) 2 Indicates the difference between the lateral control amount of the state sampling point and the lateral control amount of the previous frame, which is used to indicate the smoothness of the path. k3C 2 Indicates the distance from the state sampling point to an obstacle. The default is the distance to the nearest obstacle at that sampling point. The cost of each pure tracking path is the sum of the costs of the state sampling points on it. k1, k2, and k3 are the weights of each term, and are squared to avoid negative values.

[0100] In some other optional embodiments, the process of state sampling can refer to Figure 12 As shown, based on the multiple pure tracking paths generated above, sampling is performed separately, the sampling distance on the reference path is s, N points are sampled, and corresponding points are found on each pure tracking path to obtain state sampling points.

[0101] The vehicle control planning method provided in this application primarily addresses the problem of positional and posture deviations between the vehicle's actual path and the obstacle avoidance path due to factors such as positioning error, tracking error, and system delay. This can easily lead to collisions and sudden braking when the vehicle is very close to an obstacle. Precision control applications involve generating reasonable lateral control measures in the presence of errors, enabling the vehicle to circumvent obstacles and improving the safety of autonomous vehicles.

[0102] like Figure 13 As shown, a vehicle control planning device 900 provided in an embodiment of the present application includes: an acquisition sampling module 910, a forward recursion module 920, a state sampling module 930 and a selection module 940.

[0103] Among them, the acquisition sampling module 910 is used to obtain the planned reference path, calculate the initial value of the lateral control amount based on the reference path, and perform control sampling on the initial value to obtain multiple control sampling points; the forward recursion module 920 is used to perform forward recursion based on the lateral control amount of each control sampling point to obtain the pure tracking path corresponding to each control sampling point; the state sampling module 930 is used to perform state sampling on each pure tracking path to obtain multiple state sampling points corresponding to the pure tracking path; the cost value of the pure tracking path is calculated based on the state sampling points of the pure tracking path and the reference path; the selection module 940 is used to select the lateral control amount of the control sampling point corresponding to the pure tracking path with the smallest cost as the lateral control amount of this vehicle control planning.

[0104] An embodiment of the present application provides a forward recursive module in a vehicle control planning device, which also includes: a first prediction module, a selection and determination module, a second prediction module and an execution module.

[0105] Among them, the first prediction module is used to use a preset prediction model to predict the next frame position point of the current position of the vehicle based on the current position of the vehicle and the lateral control amount of the control sampling point; the selection and determination module is used to use the next frame position point as the state sampling point, and select the preview point on the reference path according to the preset preview distance with the road point closest to the state sampling point on the reference path as the starting point; and use the preset preview algorithm to determine the lateral control amount of the state sampling point based on the state sampling point and the preview point; the second prediction module is used to use the prediction model to predict the next frame position point of the state sampling point based on the position information of the state sampling point and its lateral control amount; the execution module is used to execute the above-mentioned selection and determination module and the second prediction module based on the next frame position point until the preset stop condition is met, and then to all the state sampling points that constitute the pure tracking path. The embodiment of the present application provides a selection and determination module in a vehicle control planning execution device, which also includes: a judgment module and an update module.

[0106] Among them, the judgment module is used to determine whether the difference between the lateral control amount of the state sampling point and the lateral control amount of the previous state sampling point is less than a preset threshold; the update module is used to update the lateral control amount of the state sampling point based on the lateral control amount of the previous state sampling point if it is less than the preset threshold.

[0107] A forward recursive module of a vehicle control planning device provided in an embodiment of the present application further includes: a collision detection module and a state sampling execution module.

[0108] Among them, the collision detection module is used to perform collision detection on each pure tracking path separately and retain the pure tracking paths with no collision risk; the state sampling execution module is used to execute the step of performing state sampling on each pure tracking path separately based on the pure tracking paths with no collision risk to obtain multiple state sampling points corresponding to the pure tracking paths.

[0109] A forward recursive module of a vehicle control planning device provided in an embodiment of the present application further includes: a respective selection module and a lateral control quantity selection module.

[0110] Among them, the selection module is used to select the state sampling point closest to the current position of the vehicle in each pure tracking path if all pure tracking paths have collision risks, and determine the state sampling point farthest from the obstacle from the selected state sampling points; the lateral control amount selection module is used to use the lateral control amount of the control sampling point corresponding to the pure tracking path where the state sampling point farthest from the obstacle is located as the lateral control amount of this vehicle control planning.

[0111] The embodiment of the present application provides a state sampling module in a vehicle control planning device, further comprising: a state sampling point calculation module and a cost value determination module.

[0112] Among them, the state sampling point calculation module is used to calculate the cost value of each state sampling point on the pure tracking path based on the offset between the state sampling point and the reference path, the difference between the lateral control amount of the state sampling point corresponding to the pure tracking path and the lateral control amount of the vehicle control plan in the previous frame, and the distance between the state sampling point and the obstacle; the cost value determination module is used to determine the sum of the cost values ​​of all state sampling points on the pure tracking path as the cost value of the pure tracking path.

[0113] An embodiment of the present invention further provides a non-volatile computer storage medium storing computer-executable instructions, which can execute the vehicle control planning method in any of the above method embodiments; as an implementation manner, the non-volatile computer storage medium of the present invention stores computer-executable instructions, which are configured as follows:

[0114] Get the planned reference path;

[0115] Calculating an initial value of a lateral control amount based on the reference path, and performing control sampling on the initial value to obtain a plurality of control sampling points;

[0116] Perform forward recursion based on the lateral control amount of each control sampling point to obtain the pure tracking path corresponding to each control sampling point;

[0117] Performing state sampling on each pure tracking path to obtain a plurality of state sampling points corresponding to the pure tracking path; calculating a cost value of the pure tracking path based on the state sampling points of the pure tracking path and the reference path;

[0118] The lateral control amount of the control sampling point corresponding to the pure tracking path with the smallest replacement value is selected as the lateral control amount of this vehicle control planning.

[0119] A non-volatile computer-readable storage medium can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the methods described in the embodiments of the present invention. One or more program instructions stored in the non-volatile computer-readable storage medium, when executed by a processor, perform the vehicle control planning method described in any of the above method embodiments.

[0120] An embodiment of the present invention also provides an electronic device, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute a vehicle control planning method.

[0121] In some embodiments, the present invention further provides a mobile device comprising a main body and an electronic device according to any of the preceding embodiments mounted on the main body. The mobile device may be an unmanned vehicle, such as an unmanned sweeper, unmanned floor scrubber, unmanned logistics vehicle, unmanned passenger vehicle, unmanned sanitation vehicle, unmanned minibus / bus, truck, mining vehicle, etc., or a robot.

[0122] In some embodiments, an embodiment of the present invention further provides a computer program product, which, when executed on a computer, enables the computer to execute any one of the methods for vehicle control planning described in the embodiments of the present invention.

[0123] In some embodiments, an embodiment of the present invention also provides a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes any one of the above-mentioned methods based on vehicle control planning.

[0124] Figure 14 This is a hardware structure diagram of an electronic device of a vehicle control planning method provided by another embodiment of the present application, such as Figure 14 As shown, the device includes: one or more processors 1010 and a memory 1020, Figure 14 The apparatus of the vehicle control planning method may further include: an input device 1030 and an output device 1040 .

[0125] The processor 1010, the memory 1020, the input device 1030 and the output device 1040 may be connected via a bus or other means. Figure 14 The bus connection is taken as an example.

[0126] Memory 1020, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the vehicle control planning method in the embodiments of the present application. Processor 1010 executes the non-volatile software programs, instructions, and modules stored in memory 1020 to execute various server functional applications and data processing, thereby implementing the vehicle control planning method in the above-described method embodiment.

[0127] The memory 1020 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data, etc. In addition, the memory 1020 may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 1020 may optionally include a memory remotely located relative to the processor 1010, and these remote memories may be connected to the mobile device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0128] The input device 1030 can receive input digital or character information. The output device 1040 can include a display device such as a display screen.

[0129] The one or more modules are stored in the memory 1020 and, when executed by the one or more processors 1010 , perform the vehicle control planning method in any of the above method embodiments.

[0130] The above-mentioned product can execute the method provided in the embodiment of this application, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in this embodiment, please refer to the method provided in the embodiment of this application.

[0131] The non-volatile computer-readable storage medium may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the device, etc. In addition, the non-volatile computer-readable storage medium may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state memory device. In some embodiments, the non-volatile computer-readable storage medium may optionally include a memory remotely located relative to the processor, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0132] An embodiment of the present invention also provides an electronic device, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of the vehicle control planning method of any embodiment of the present invention.

[0133] The electronic devices of the embodiments of the present application exist in various forms, including but not limited to:

[0134] (1) Mobile communication devices: These devices are characterized by their mobile communication capabilities and their primary purpose is to provide voice and data communications. These terminals include smartphones, multimedia phones, feature phones, and low-end phones.

[0135] (2) Ultra-mobile personal computer devices: These devices fall under the category of personal computers and have computing and processing capabilities, and generally also have mobile Internet access. These terminals include PDAs, MIDs, and UMPC devices, such as tablet computers.

[0136] (3) Portable entertainment devices: These devices can display and play multimedia content. They include audio and video players, handheld game consoles, e-books, smart toys, and portable car navigation devices.

[0137] (4) Other mobile devices with data processing capabilities.

[0138] In this document, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include" and "comprise" include not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article or device. In the absence of further limitations, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device that includes the elements.

[0139] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0140] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A vehicle control planning method, comprising: Get the planned reference path; Calculating an initial value of a lateral control amount based on the reference path, and performing control sampling on the initial value to obtain a plurality of control sampling points; Perform forward recursion based on the lateral control amount of each control sampling point to obtain the pure tracking path corresponding to each control sampling point; Performing state sampling on each pure tracking path respectively to obtain a plurality of state sampling points corresponding to the pure tracking path; Calculating a cost value of the pure tracking path based on the state sampling points of the pure tracking path and the reference path, wherein calculating the cost value of the pure tracking path includes calculating the cost value of each state sampling point on the pure tracking path based on an offset between the state sampling point and the reference path, a difference between a lateral control amount of the state sampling point corresponding to the pure tracking path and a lateral control amount of a vehicle control plan in a previous frame, and a distance between the state sampling point and an obstacle; and determining the sum of the cost values ​​of all state sampling points on the pure tracking path as the cost value of the pure tracking path; Determine the sum of the cost values ​​of all state sampling points on the pure tracking path as the cost value of the pure tracking path; The lateral control amount of the control sampling point corresponding to the pure tracking path with the smallest replacement value is selected as the lateral control amount of this vehicle control planning.

2. The method according to claim 1, characterized in that Based on the lateral control amount of the control sampling point, forward recursion is performed to obtain the pure tracking path corresponding to the control sampling point, which specifically includes: Step 1: Using a preset prediction model, based on the current position of the vehicle and the lateral control amount of the control sampling point, predict the next frame position point of the current position of the vehicle; Step 2: Using the next frame position point as the state sampling point, selecting a preview point on the reference path according to a preset preview distance with the waypoint closest to the state sampling point as the starting point; and using a preset preview algorithm to determine the lateral control amount of the state sampling point based on the state sampling point and the preview point; Step 3: Using the prediction model, based on the position information of the state sampling point and its lateral control amount, predict the next frame position point of the state sampling point. Step 4: Execute the above steps 2 to 3 based on the next frame position point until the preset stop condition is met, and sequentially go to all state sampling points that constitute the pure tracking path.

3. The method according to claim 2, characterized in that The step 2 also includes: Determine whether a difference between the lateral control amount at the state sampling point and the lateral control amount at the previous state sampling point is less than a preset threshold; If it is less than a preset threshold, the lateral control amount of the state sampling point is updated based on the lateral control amount of the previous state sampling point.

4. The method according to claim 1, wherein After obtaining the pure tracking path corresponding to each control sampling point, it also includes: Perform collision detection on each pure tracking path separately and retain the pure tracking paths without collision risk; Based on the pure tracking paths without collision risk, the step of performing state sampling on each pure tracking path to obtain a plurality of state sampling points corresponding to the pure tracking path is performed.

5. The method according to claim 4, characterized in that The method further comprises: If all pure tracking paths have collision risks, select the state sampling point closest to the vehicle's current position in each pure tracking path, and determine the state sampling point farthest from the obstacle from the selected state sampling points; The lateral control amount of the control sampling point corresponding to the pure tracking path where the state sampling point farthest from the obstacle is located is used as the lateral control amount of this vehicle control planning.

6. A vehicle control planning device comprising: Acquisition sampling module, used to obtain the planned reference path; Calculating an initial value of a lateral control amount based on the reference path, and performing control sampling on the initial value to obtain a plurality of control sampling points; A forward recursion module is used to perform forward recursion based on the lateral control amount of each control sampling point to obtain a pure tracking path corresponding to each control sampling point; A state sampling module is used to perform state sampling on each pure tracking path to obtain multiple state sampling points corresponding to the pure tracking path; Calculating a cost value of the pure tracking path based on the state sampling points of the pure tracking path and the reference path, wherein calculating the cost value of the pure tracking path includes calculating the cost value of each state sampling point on the pure tracking path based on an offset between the state sampling point and the reference path, a difference between a lateral control amount of the state sampling point corresponding to the pure tracking path and a lateral control amount of a vehicle control plan in a previous frame, and a distance between the state sampling point and an obstacle; and determining the sum of the cost values ​​of all state sampling points on the pure tracking path as the cost value of the pure tracking path; The selection module is used to select the lateral control amount of the control sampling point corresponding to the pure tracking path with the smallest replacement value as the lateral control amount of this vehicle control planning.

7. An electronic device comprising: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the method according to any one of claims 1 to 5.

8. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer program product, comprising a computer program stored on a non-volatile computer-readable storage medium, wherein the computer program comprises program instructions, which, when executed by a computer, cause the computer to perform the steps of the method according to any one of claims 1 to 5.

10. A mobile tool equipped with a camera, the mobile tool comprising the electronic device according to claim 7, the camera being communicatively connected to the electronic device.

Images