Speed ​​planning method, device, electronic device and storage medium

Abstract

The present invention discloses a speed planning method, device, electronic device and storage medium, wherein the method comprises: obtaining current scene information; determining the speed planning objective function and preset constraints corresponding to the current scene information; calculating the maximum value of the speed constraint corresponding to the current scene information, updating the preset constraints according to the calculation result, and obtaining the updated constraints; solving the minimum value of the objective function according to the updated constraints, and obtaining the speed planning parameters at each time point; generating a speed planning scheme based on the speed planning parameters at each time point. The present invention can avoid the phenomenon of the vehicle turning too fast, decelerating too fast, and accelerating in advance when exiting a curve, improves the control accuracy of the vehicle when passing through a curve, is conducive to improving the safety and comfort of the vehicle when passing through a curve, and improves the riding experience.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a speed planning method, device, electronic device and storage medium. Background Art

[0002] Speed ​​planning is a key technology for autonomous driving. It mainly determines the speed of the vehicle along the route based on the optimal trajectory information output by the vehicle's trajectory planning. Since we want to change the speed on the route, what we really need to choose is a series of speeds related to the waypoints on the route. Inappropriate target speeds and accelerations will exceed the limit conditions of vehicle movement and affect the safety and comfort of the driver and passengers.

[0003] The existing speed planning method is a solution to a quadratic objective function with multiple constraints, where the objective function is:

[0004]

[0005] The constraints are

[0006]

[0007]

[0008]

[0009]

[0010]

[0011]

[0012] Among them, s i , are the position, velocity, acceleration, and jerk at the i-th moment respectively. Maximum velocity constraint Related to the curvature of the current road, the larger the curvature, the The smaller.

[0013] According to the above constraints, solve the minimum value f of the objective function f min , and the corresponding position, velocity, acceleration, and jerk at each moment.

[0014] Since the speed constraint is the maximum Related to the current road curvature, when an autonomous driving vehicle turns, the speed will drop suddenly, and it is impossible to drop to the target value immediately. As a result, the turning speed will be too fast and the deceleration will be too fast, which will reduce the control accuracy and produce a poor riding experience.

[0015] Some solutions in the prior art improve this defect by adding a single-point preview method in front, but the speed planning method using this method will cause premature acceleration when about to exit a curve, which will still cause reduced control accuracy and a poor riding experience when exiting a curve.

[0016] Therefore, it is necessary to improve the existing cornering speed control method to improve the safety, comfort and driving experience of the vehicle when passing through a curve, and improve the user experience. Summary of the invention

[0017] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the first aspect of the present invention proposes a speed planning method, comprising:

[0018] Get current scene information;

[0019] Determine the speed planning objective function and preset constraints corresponding to the current scene information;

[0020] Calculating the maximum speed constraint value corresponding to the current scene information, and updating the preset constraint condition according to the calculation result to obtain an updated constraint condition;

[0021] Solving the minimum value of the objective function according to the updated constraint conditions to obtain speed planning parameters at each time point; the speed planning parameters include position, speed, acceleration and jerk;

[0022] A speed planning scheme is generated based on the speed planning parameters at each time point.

[0023] Further, the calculating the maximum value of the constraint speed corresponding to the current scene information includes:

[0024] Get the current vehicle speed;

[0025] Obtaining the number of rear-aiming path points, the curvature proportionality coefficient, the speed proportionality coefficient, and the minimum number of forward-aiming path points corresponding to the current scene information;

[0026] Calculate the maximum value of the speed constraint corresponding to each of the forward aiming path point, the current path point and the backward aiming path point according to the current vehicle speed, the number of the backward aiming path points, the curvature proportionality coefficient, the speed proportionality coefficient and the minimum number of the forward aiming path points;

[0027] Traversing the maximum value of the speed constraint corresponding to each path point among the forward aiming path point, the current path point and the backward aiming path point, and obtaining a minimum value of the maximum value of the speed constraint;

[0028] The preset speed constraint maximum value in the preset constraint condition is replaced with the minimum value of the speed constraint maximum value to obtain an updated constraint condition.

[0029] Further, the calculating the maximum speed constraint value corresponding to the current path point according to the current vehicle speed, the number of rear-aiming path points, the curvature proportionality coefficient, the speed proportionality coefficient and the minimum number of front-aiming path points includes:

[0030] Calculate the number of forward aiming path points according to the current vehicle speed, the speed proportional coefficient and the minimum number of forward aiming path points;

[0031] The maximum value of the speed constraint corresponding to the current path point is calculated according to the number of forward aiming path points, the number of backward aiming path points and the curvature proportionality coefficient.

[0032] Furthermore, the method for calculating the number of forward aiming path points according to the current vehicle speed, the speed proportional coefficient and the minimum number of forward aiming path points is as follows:

[0033] q=[k v *cur_speed]+b,(k v > 0, cur_speed ≥ 0, b∈N + ) where q is the number of points on the forward aiming path;

[0034] cur_speed is the current speed of the autonomous driving vehicle, cur_speed ≥ 0;

[0035] k v is the speed proportionality coefficient, k v >0;

[0036] b is the minimum number of forward aiming path points, b∈N + .

[0037] Furthermore, the method for calculating the maximum value of the speed constraint according to the number of forward aiming path points, the number of backward aiming path points and the curvature proportionality coefficient is as follows:

[0038]

[0039] in, is the maximum value of speed constraint;

[0040] k is the curvature proportionality coefficient;

[0041] p is the number of back-aiming path points, p>0;

[0042] i is the current path point, ip≥0;

[0043] q is the number of points on the forward aiming path, q>b;

[0044] N is the number of global path points.

[0045] Furthermore, before obtaining the number of rear-aiming path points, the curvature proportionality coefficient, the speed proportionality coefficient and the minimum number of forward-aiming path points corresponding to the current scene information, the method further includes:

[0046] Obtaining user driving preference information corresponding to the current scene;

[0047] The curvature scaling factor and the speed scaling factor corresponding to the current scene information are adjusted according to the user driving preference.

[0048] Furthermore, the obtaining of current scene information includes:

[0049] Obtain global path information, environmental perception information and real-time positioning information;

[0050] The current scene information is determined according to the global path information, the environmental perception information and the real-time positioning information.

[0051] A second aspect of the present invention provides a speed planning device, comprising:

[0052] A scene acquisition module is used to obtain current scene information;

[0053] A determination module, used to determine the speed planning objective function and preset constraints corresponding to the current scene information;

[0054] A constraint condition updating module, used to calculate the maximum value of the speed constraint corresponding to the current scene information, and update the preset constraint condition according to the calculation result to obtain an updated constraint condition;

[0055] A speed planning parameter solving module, used to solve the minimum value of the objective function according to the updated constraint conditions to obtain the speed planning parameters at each time point; the speed planning parameters include position, speed, acceleration and jerk;

[0056] A scheme generating module is used to generate a speed planning scheme based on the speed planning parameters at each time point.

[0057] The third aspect of the present invention proposes an electronic device, characterized in that the electronic device includes a processor and a memory, the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the speed planning method described in the first aspect of the present invention.

[0058] The fourth aspect of the present invention proposes a computer-readable storage medium, characterized in that the storage medium stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement the speed planning method described in the first aspect of the present invention.

[0059] It can be seen from the embodiments of the speed planning method, device, electronic device or storage medium provided by the present invention that the embodiments of the present invention can avoid the phenomenon of the vehicle turning too fast, decelerating too fast, and accelerating prematurely when exiting a curve, thereby improving the control accuracy of the vehicle when passing through a curve, which is beneficial to improving the safety and comfort of the vehicle when passing through a curve and improving the riding experience.

[0060] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0062] Figure 1 is a flow chart of a speed planning method provided by an embodiment of the present invention;

[0063] Figure 2 is a flow chart of calculating the maximum value of the constraint speed corresponding to the current scene information provided by an embodiment of the present invention;

[0064] Figure 3 is a flowchart of step S203 provided by an embodiment of the present invention;

[0065] Figure 4 It is a structural block diagram of a speed planning device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Examples of the embodiments are shown in the drawings, where the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions.

[0067] Example

[0068] In view of the problem that when an autonomous driving vehicle turns, the current speed planning method will cause reduced control accuracy and produce a poor riding experience, the present invention proposes a speed planning method based on front and rear multi-point preview. Figure 1 It is a flow chart of a speed planning method provided by an embodiment of the present invention. This specification provides method operation steps such as the embodiment or flow chart, but may include more or fewer operation steps based on conventional or non-creative labor. The order of steps listed in the embodiment is only one way of executing the steps among many orders, and does not represent the only order of execution. When the actual system or server product is executed, it can be executed in sequence or in parallel according to the method shown in the embodiment or the accompanying drawings (for example, in a parallel processor or multi-threaded processing environment). Specifically, Figure 1 As shown, the method may include the following steps:

[0069] S101: Acquire current scene information;

[0070] In one embodiment, obtaining current scene information includes: obtaining global path information, environmental perception information, real-time positioning information and real-time autonomous driving information of the ego vehicle; determining the association between the ego vehicle and the autonomous driving scene based on the global path information, environmental perception information, real-time positioning information and real-time autonomous driving information, and determining the current scene information.

[0071] S102: Determine the speed planning objective function and preset constraints corresponding to the current scene information;

[0072] Specifically, the scene information is stored in association with the speed planning objective function and the preset conditions, and the speed planning objective functions corresponding to different scene information may be the same or different.

[0073] For example, the speed planning objective function may be a quadratic objective function with multiple constraints provided by the prior art, where the objective function is:

[0074]

[0075] The constraints are

[0076]

[0077]

[0078]

[0079]

[0080]

[0081]

[0082] Among them, s i , are the position, velocity, acceleration and jerk at the i-th moment respectively;

[0083] is the minimum value of the speed constraint, is the maximum value of speed constraint;

[0084] is the minimum value of acceleration constraint, is the maximum value of acceleration constraint;

[0085] is the minimum value of the jerk constraint, is the maximum value of the jerk constraint;

[0086] k is the curvature scale coefficient; curve is the curvature.

[0087] According to the above constraints, solve the minimum value f of the objective function f min , and the corresponding position, velocity, acceleration, and jerk at each moment.

[0088] S103: Calculate the maximum value of the speed constraint corresponding to the current scene information, and update the preset constraint condition according to the calculation result to obtain the updated constraint condition;

[0089] Figure 2 is a flowchart of calculating the maximum value of the constraint speed corresponding to the current scene information provided by an embodiment of the present invention, specifically as follows Figure 2 As shown, calculating the maximum value of the constraint speed corresponding to the current scene information includes the following steps:

[0090] S201: Obtain current vehicle speed;

[0091] Specifically, the current vehicle speed may be a vehicle speed measured by a speed measuring device on the vehicle, or may be a vehicle speed measured by a navigation and positioning system of the vehicle.

[0092] S202: Obtain the number of rear-aiming path points, curvature proportionality coefficient, speed proportionality coefficient and minimum number of front-aiming path points corresponding to the current scene information;

[0093] Regarding the number of preview points to be selected, compared to the traditional preview-based control method which can only select one preview point, the embodiment of the present invention adopts a multi-point preview method. Compared with a single preview point, multiple preview points can predict a longer number of steps and distances, and can take into account the tracking error of the entire path, thereby improving the tracking accuracy. At the same time, it also ensures comfort during the control process and does not produce sudden changes in the control amount.

[0094] However, too many or too few rear-aiming path points and front-aiming path points will affect the vehicle's cornering speed. To ensure driving safety and a good riding experience, the embodiment of the present invention sets the rear-aiming path points and the minimum front-aiming path points to fixed values, thereby limiting the speed planning parameter values ​​calculated based on the preview points to an acceptable range.

[0095] For example, in one embodiment, the value of the number of backward aiming path points is 10, and it is necessary to preview 10 path points backward from the current path. In other embodiments, the number of backward aiming path points can also be other values, such as 5, 8, 14, etc., and this embodiment is not limited thereto.

[0096] The minimum forward aiming point number is the forward aiming path point number when the current speed of the autonomous driving vehicle is 0. The minimum forward aiming path point number is a fixed value. For example, in one embodiment, the minimum forward aiming path point number is 8. At this time, it is necessary to preview at least 8 path points forward from the current path point. In other embodiments, the minimum forward aiming path point number can also be other values, such as 3, 12, etc., and this embodiment is not limited thereto.

[0097] Specifically, the values ​​of the curvature proportional coefficient and the speed proportional coefficient are adjustable, and users can set them according to their needs, so that the driving style of the vehicle entering and exiting a curve meets the user's personal preferences.

[0098] In one embodiment, the step S202 further includes the following steps:

[0099] Obtain the user's driving preference information corresponding to the current scene;

[0100] The curvature scaling factor and speed scaling factor corresponding to the current scene information are adjusted according to the user's driving preferences.

[0101] S203: Calculating the maximum value of the speed constraint corresponding to each of the forward aiming path point, the current path point and the backward aiming path point according to the current vehicle speed, the number of backward aiming path points, the curvature ratio coefficient, the speed ratio coefficient and the minimum number of forward aiming path points;

[0102] In one embodiment, the number of rearward aiming path points is 10, and the number of forward aiming path points is 8. The rearward aiming path points can be determined by: starting from the current path point, taking v(t)ΔT as the search distance, searching 10 path points backward as the rearward aiming path points; starting from the current path point, taking v(t)ΔT as the search distance, searching 8 path points forward as the forward aiming path points. Here, "forward" should be understood as the direction of vehicle travel, and "backward" is the opposite.

[0103] Figure 3 is a flowchart of step S203 provided in an embodiment of the present invention, and the specific example is as follows Figure 3 As shown, step S203 includes the following steps:

[0104] S2031: Calculate the number of forward aiming path points according to the current vehicle speed, the speed proportionality coefficient and the minimum number of forward aiming path points;

[0105] In one embodiment, a method for calculating the number of forward aiming path points according to the current vehicle speed, the speed proportionality coefficient and the minimum forward aiming path points is as follows:

[0106] q=[k v *cur_speed]+b,(k v > 0, cur_speed ≥ 0, b∈N + ) where q is the number of points on the forward aiming path;

[0107] cur_speed is the current speed of the autonomous driving vehicle, cur_speed ≥ 0;

[0108] k v is the speed proportionality coefficient, k v >0;

[0109] b is the minimum number of forward aiming path points, b∈N + .

[0110] S2032: Calculate the maximum value of the speed constraint corresponding to the current path point according to the number of forward aiming path points, the number of backward aiming path points and the curvature proportionality coefficient.

[0111] In one embodiment, a method for calculating the maximum value of the speed constraint according to the number of forward aiming path points, the number of backward aiming path points and the curvature proportionality coefficient is as follows:

[0112]

[0113] in, is the maximum value of speed constraint;

[0114] k is the curvature proportionality coefficient;

[0115] p is the number of back-aiming path points, p>0;

[0116] i is the current path point, ip≥0;

[0117] q is the number of points on the forward aiming path, q>b;

[0118] N is the number of global path points.

[0119] S204: traversing the maximum value of the speed constraint corresponding to each path point among the forward aiming path point, the current path point and the backward aiming path point, and obtaining the minimum value of the maximum value of the speed constraint;

[0120] S205: Replace the preset speed constraint maximum value in the preset constraint condition with the minimum value of the speed constraint maximum value to obtain an updated constraint condition.

[0121] For example, the minimum speed constraint and the maximum speed constraint in the preset constraints are Speed ​​Constraints The maximum speed constraint corresponding to the current scene information is V 3 , updating the preset constraint conditions according to the calculation results specifically means replacing the maximum speed constraint value in the preset constraint conditions with the maximum speed constraint value V corresponding to the current scene information 3 , thus obtaining the speed constraint corresponding to the current scene information

[0122] S104: solving the minimum value of the objective function according to the updated constraint conditions to obtain the speed planning parameters at each time point;

[0123] Specifically, the speed planning parameters include position, speed, acceleration and jerk.

[0124] S105: Generate a speed planning solution based on the speed planning parameters at each time point.

[0125] The autonomous driving control scheme includes trajectory planning and speed planning. The trajectory planning module receives global path, environmental perception, and real-time positioning information, and obtains the trajectory planning result through the built-in local path planning method; the speed planning module receives global path, environmental perception, and real-time positioning information, and obtains the speed planning result through the built-in speed planning method, and inputs the trajectory planning result and speed planning result into the autonomous driving control module, so as to build the vehicle's autonomous driving control scheme.

[0126] It should be noted that the embodiments of the present invention are not limited by the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously.

[0127] Figure 4 is a structural block diagram of a speed planning device provided by an embodiment of the present invention, specifically as follows Figure 4As shown, an embodiment of the present invention further provides a speed planning device, which includes the following modules:

[0128] A scene acquisition module 301 is used to acquire current scene information;

[0129] A determination module 302 is used to determine a speed planning objective function and preset constraints corresponding to the current scene information;

[0130] The constraint condition updating module 303 is used to calculate the maximum value of the speed constraint corresponding to the current scene information, and update the preset constraint condition according to the calculation result to obtain the updated constraint condition;

[0131] The speed planning parameter solving module 304 is used to solve the minimum value of the objective function according to the updated constraint conditions to obtain the speed planning parameters at each time point; the speed planning parameters include position, speed, acceleration and jerk;

[0132] The scheme generating module 305 is used to generate a speed planning scheme based on the speed planning parameters at each time point.

[0133] It should be noted that, without departing from the scope of the present disclosure, the speed planning method provided by the embodiment of the present invention can be applied to the automatic driving control of trucks, sport utility vehicles, vans, RVs or any other type of vehicles.

[0134] An embodiment of the present invention also provides an electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by the processor to implement a speed planning method as described in the method embodiment.

[0135] An embodiment of the present invention also provides a storage medium, which can be set in a server to store at least one instruction, at least one program, code set or instruction set related to the speed planning method in the method embodiment. The at least one instruction, the at least one program, the code set or instruction set is loaded and executed by the processor to implement the speed planning method provided in the above-mentioned method embodiment.

[0136] Optionally, in this embodiment, the storage medium may be located in at least one of the multiple network servers of the computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0137] It can be seen from the embodiments of the speed planning method, device, electronic device or storage medium provided by the present invention that the embodiments of the present invention determine the speed planning objective function and constraints according to the scene, update the constraints based on the front and rear multi-point preview to make them adapt to the scene, and solve the speed planning parameters at each time point based on the speed planning objective function and the updated constraints. The obtained speed planning scheme can avoid the phenomenon of the vehicle turning too fast, decelerating too fast, and accelerating in advance when exiting the curve, thereby improving the control accuracy of the vehicle when passing through the curve, which is beneficial to improving the safety and comfort of the vehicle when passing through the curve, and improving the riding experience.

[0138] It should be noted that the sequence of the embodiments of the present invention described above is for description only and does not represent the advantages and disadvantages of the embodiments. The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0139] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and server embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0140] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0141] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A speed planning method, characterized in that: include: Obtain current scene information, including: global path information, environmental perception information and real-time positioning information; Determine the speed planning objective function and preset constraints corresponding to the current scene information; Get the current vehicle speed; Obtaining the number of rear-aiming path points, the curvature proportionality coefficient, the speed proportionality coefficient, and the minimum number of forward-aiming path points corresponding to the current scene information; Calculate the maximum value of the speed constraint corresponding to each of the forward aiming path point, the current path point and the backward aiming path point according to the current vehicle speed, the number of the backward aiming path points, the curvature proportionality coefficient, the speed proportionality coefficient and the minimum number of the forward aiming path points; Traversing the maximum value of the speed constraint corresponding to each path point among the forward aiming path point, the current path point and the backward aiming path point, and obtaining a minimum value of the maximum value of the speed constraint; Replacing the preset speed constraint maximum value in the preset constraint condition with the minimum value of the speed constraint maximum value to obtain an updated constraint condition; Solving the minimum value of the objective function according to the updated constraint conditions to obtain speed planning parameters at each time point; the speed planning parameters include position, speed, acceleration and jerk; Generate a speed planning scheme based on the speed planning parameters at each time point; The calculating the maximum speed constraint value corresponding to the current path point according to the current vehicle speed, the number of rear-aiming path points, the curvature proportionality coefficient, the speed proportionality coefficient and the minimum number of front-aiming path points includes: Calculate the number of forward aiming path points according to the current vehicle speed, the speed proportional coefficient and the minimum number of forward aiming path points; Calculating the maximum value of the speed constraint corresponding to the current path point according to the number of forward aiming path points, the number of backward aiming path points and the curvature proportionality coefficient; The method for calculating the number of forward aiming path points according to the current vehicle speed, the speed proportional coefficient and the minimum number of forward aiming path points is as follows: q=[kv*cur_speed]+b Wherein, q is the number of points on the forward aiming path; cur_speed is the current speed of the autonomous driving vehicle, cur_speed ≥ 0; kv is the speed proportional coefficient, kv>0; b is the minimum number of forward aiming path points, b∈N+; The method for calculating the maximum value of the speed constraint according to the number of forward aiming path points, the number of backward aiming path points and the curvature proportionality coefficient is as follows: in, is the maximum value of speed constraint; k is the curvature proportionality coefficient, >0; p is the number of back-aiming path points, p>0; i is the current path point, ip≥0; q is the number of points on the forward aiming path, q>b, ; N is the number of global path points.

2. The speed planning method according to claim 1, characterized in that: Before obtaining the number of rear-aiming path points, the curvature proportionality coefficient, the speed proportionality coefficient and the minimum number of forward-aiming path points corresponding to the current scene information, the method further includes: Obtaining user driving preference information corresponding to the current scene; The curvature scaling factor and the speed scaling factor corresponding to the current scene information are adjusted according to the user driving preference.

3. The speed planning method according to claim 1, characterized in that: The obtaining of current scene information includes: Obtain global path information, environmental perception information and real-time positioning information; The current scene information is determined according to the global path information, the environmental perception information and the real-time positioning information.

4. A speed planning device, characterized in that: include: The scene acquisition module is used to obtain the current scene information, including global path information, environmental perception information and real-time positioning information; A determination module, used to determine the speed planning objective function and preset constraints corresponding to the current scene information; The current vehicle speed acquisition module is used to obtain the current vehicle speed; A parameter acquisition module, used to obtain the number of rear-aiming path points, curvature proportional coefficient, speed proportional coefficient and minimum forward-aiming path points corresponding to the current scene information; A constraint condition updating module is used to calculate the maximum value of the speed constraint corresponding to each of the forward aiming path point, the current path point and the backward aiming path point according to the current vehicle speed, the number of the backward aiming path points, the curvature proportional coefficient, the speed proportional coefficient and the minimum number of the forward aiming path points; traverse the maximum value of the speed constraint corresponding to each of the forward aiming path point, the current path point and the backward aiming path point to obtain the minimum value of the maximum value of the speed constraint; replace the preset maximum value of the speed constraint in the preset constraint condition with the minimum value of the maximum value of the speed constraint to obtain the updated constraint condition; A speed planning parameter solving module, used to solve the minimum value of the objective function according to the updated constraint conditions to obtain the speed planning parameters at each time point; the speed planning parameters include position, speed, acceleration and jerk; A scheme generating module, used for generating a speed planning scheme based on the speed planning parameters at each time point; The constraint update module includes: Calculate the number of forward aiming path points according to the current vehicle speed, the speed proportional coefficient and the minimum number of forward aiming path points; Calculating the maximum value of the speed constraint corresponding to the current path point according to the number of forward aiming path points, the number of backward aiming path points and the curvature proportionality coefficient; The method for calculating the number of forward aiming path points according to the current vehicle speed, the speed proportional coefficient and the minimum number of forward aiming path points is as follows: q=[kv*cur_speed]+b Wherein, q is the number of points on the forward aiming path; cur_speed is the current speed of the autonomous driving vehicle, cur_speed ≥ 0; kv is the speed proportional coefficient, kv>0; b is the minimum number of forward aiming path points, b∈N+; The method for calculating the maximum value of the speed constraint according to the number of forward aiming path points, the number of backward aiming path points and the curvature proportionality coefficient is as follows: in, is the maximum value of speed constraint; k is the curvature proportionality coefficient, >0; p is the number of back-aiming path points, p>0; i is the current path point, ip≥0; q is the number of points on the forward aiming path, q>b, ; N is the number of global path points.

5. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the speed planning method as described in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that: The storage medium stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the speed planning method as described in any one of claims 1-3.

Images