Unmanned driving target speed planning method, electronic equipment and medium

By determining the road mode according to the curvature and target speed threshold of the path point, and performing deceleration and acceleration smoothing processing, the target speed sudden change of unmanned vehicles between different road modes is solved, and the vehicle stability and safety is improved sex.

CN118584964BActive Publication Date: 2024-11-26CHINA AUTOMOBILE ZHILIAN TECH CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411044816.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-11-26
Estimated Expiration
2044-08-01

AI Technical Summary

Technical Problem

Traditional unmanned vehicles lack target speed transition paths between different road modes, resulting in a sudden change in the target speed, which in turn triggers a sudden change in the vehicle acceleration, affecting stability and safety.

Method used

By determining the road mode according to the curvature and target speed threshold of each path point on the reference path, setting the second target speed threshold, and gradually transitioning to the final target speed through deceleration smoothing processing and acceleration smoothing processing, ensuring that the vehicle is between different road modes smooth transition.

Benefits of technology

It effectively solves the problem of sudden change in target speed between different road modes, improves the stability, safety and ride comfort of the vehicle, and ensures that the vehicle can reach its destination safely and smoothly.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118584964B_ABST
    Figure CN118584964B_ABST
Patent Text Reader

Abstract

The present invention discloses an unmanned driving target speed planning method, electronic device and medium. First, a target speed initial value is set for each path point on a reference path, then the road mode is divided according to the curvature of the path point and the target speed initial value, and finally the target speeds corresponding to the transition sections between different road modes and different modes of roads are determined according to three parameters: road mode, traffic constraint and preset target speed threshold, so as to ensure a smooth transition of the vehicle from a section with a larger target speed threshold to a section with a smaller target speed threshold, or from a section with a smaller target speed threshold to a section with a larger target speed threshold, solve the problem of sudden change in target speed caused by the lack of target speed transition path at the connection of traditional roads with different curvatures, and further provide speed constraints for the vehicle to reach the destination safely and smoothly.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of speed planning, and in particular to an unmanned driving target speed planning method, electronic equipment and medium. Background Art

[0002] Target speed planning is one of the main functions of unmanned vehicles. The unmanned driving system software determines the target speed based on real-time environmental information, and then plans the acceleration required for the vehicle during actual driving based on the real-time environmental information and its own motion state. For different modes of roads (such as long straight roads, curves, etc.), different traffic constraints, the planned target speeds are different. During the movement of the vehicle, if the target speed increases or decreases very quickly, it directly affects the size of the vehicle's acceleration, and further affects the stability and safety of the vehicle. Therefore, a suitable target speed is the basic guarantee to ensure that the vehicle can drive smoothly and safely to the destination.

[0003] The target speed is one of the constraint parameters during vehicle driving. When a vehicle is driving on a specific road section, its speed cannot exceed the target speed specified by the road section. In order to achieve a smooth transition of the vehicle between two sections with different target speeds, it is necessary to reasonably plan the target speed of the road based on the actual situation.

[0004] In view of this, the present invention is proposed. Summary of the invention

[0005] A brief summary of one or more aspects is given below to provide a basic understanding of these aspects. This summary is not an exhaustive overview of all conceived aspects, and is neither intended to identify the key or critical elements of all aspects nor to define the scope of any or all aspects. Its only purpose is to give some concepts of one or more aspects in a simplified form as a prelude to a more detailed description that will be given later.

[0006] The present application provides an unmanned driving target speed planning method, which solves the problem of sudden acceleration or deceleration of the vehicle caused by a sudden change in the target speed, and further ensures the stability, safety and riding comfort of the vehicle during driving.

[0007] In a first aspect, the present invention provides an unmanned driving target speed planning method, comprising the following steps: determining a road pattern of each path point according to a curvature of each path point on a reference path and a first target speed threshold, wherein the first target speed threshold of each path point is determined according to a traffic speed limit regulation;

[0008] According to the road modes of the path points adjacent to the current path point, the road mode of the current path point is modified to filter the noise points in the path points to obtain the filtered path points;

[0009] Setting a second target speed threshold for the waypoint through a configuration file according to the road pattern of the filtered waypoint;

[0010] For each path point, determining a third target speed threshold of the current path point according to the first target speed threshold and the second target speed threshold of the current path point;

[0011] Determine, according to the road mode of the waypoint and / or the third target speed threshold, a first type of waypoint that needs to be decelerated and smoothed, and a second type of waypoint that needs to be accelerated and smoothed;

[0012] Performing a deceleration smoothing process on each path point in the first category according to the speed smoothing distance resolution, the speed smoothing preview distance, and the preset deceleration, and performing an acceleration smoothing process on each path point in the second category according to the preset acceleration, to obtain a final target speed threshold of each path point;

[0013] The final target speed threshold is determined as the planned speed.

[0014] Further, the determining of the road mode of each path point according to the curvature of each path point on the reference path and the first target speed threshold comprises:

[0015] Determine a road mode division reference value based on the following calculation formula, and perform road mode division based on the road mode division reference value to obtain a road mode for each path point;

[0016] RoadMode=Kp×k+Ks×FirstSpeed;

[0017] Among them, RoadMode represents the reference value of road mode division, Kp and Ks represent weight coefficients, Kp+Ks=1, k represents the curvature of the way point, FirstSpeed ​​represents the first target speed threshold of the way point, when FirstSpeed<15km / h, Kp>Ks; when 15km / h<FirstSpeed<30km / h, Kp=Ks; when FirstSpeed>30km / h, Kp<Ks.

[0018] Furthermore, the road mode includes a straight road mode, a small curvature curve mode and a large curvature curve mode;

[0019] The method of modifying the road mode of the current path point according to the road modes of the path points adjacent to the current path point, so as to filter the noise points in each path point to obtain the filtered path point, comprises:

[0020] If the road mode of the current path point is different from the road modes of the path points adjacent to it, and the road modes of the path points adjacent to it are the same, and the length of the road segment composed of the path points adjacent to it with the same road mode is greater than the preset length threshold, then the road mode of the current path point is corrected to be the same as the road mode of the path points adjacent to it;

[0021] Among them, the preset length thresholds corresponding to different road modes are different.

[0022] Furthermore, for each path point, determining a third target speed threshold of the current path point according to the first target speed threshold and the second target speed threshold of the current path point includes:

[0023] If there is only a corresponding first target speed threshold for the current path point, the first target speed threshold is determined as the third target speed threshold for the current path point;

[0024] If there is only a corresponding second target speed threshold for the current path point, the second target speed threshold is determined as the third target speed threshold for the current path point;

[0025] If the current path point has both a corresponding first target speed threshold and a corresponding second target speed threshold, the smaller one of the first target speed threshold and the second target speed threshold is determined as the third target speed threshold of the current path point.

[0026] Further, the determining of the first type of waypoints requiring deceleration smoothing processing according to the road mode of the waypoints and / or the third target speed threshold comprises:

[0027] If the road mode of the current path point is a straight road mode, and the difference between the third target speed threshold of the previous path point adjacent to the current path point and the third target speed threshold of the current path point is greater than the preset speed difference threshold, the path point before the current path point is determined to be a first type of path point that needs to be decelerated and smoothed;

[0028] If the road mode of the current path point is a small curvature curve mode or a large curvature curve mode, and the road mode of the previous path point is different from the road mode of the current path point, the path point before the current path point is determined to be a first type of path point that requires deceleration and smoothing processing.

[0029] Further, performing deceleration smoothing processing on each path point in the first category of path points according to the speed smoothing distance resolution, the speed smoothing preview distance, and the preset deceleration to obtain the final target speed threshold of each path point includes:

[0030] The serial number of the current path point is marked as i, the serial number of the previous path point adjacent to the current path point i is marked as startvalue, startvalue=i-1, the previous path point startvalue adjacent to the current path point i is the first path point to be subjected to deceleration smoothing processing, the serial number of the path point currently subjected to deceleration smoothing processing is marked as j, and if the third target speed threshold of the path point j is less than the third target speed threshold of the path point j+1, then the deceleration smoothing processing flow is exited;

[0031] If the difference between startvalue and j is less than the reference number nprebrake, the third target speed threshold of the waypoint j+1 is determined as the final target speed threshold of the waypoint j, where the reference number nprebrake=speed smoothing preview distance / speed smoothing distance resolution;

[0032] If the difference between startvalue and j is not less than the reference number nprebrake, the reference speed is determined based on the following calculation formula: if the third target speed threshold of the waypoint j is greater than the reference speed, the reference speed is determined as the final target speed threshold of the waypoint j; otherwise, the third target speed threshold of the waypoint j is determined as the final target speed threshold of the waypoint j;

[0033]

[0034]

[0035] in, represents the reference speed, represents the distance between path point j and path point j+1, represents the third target speed threshold of path point j+1, Indicates the brake value. Indicates the preset deceleration, Represents the scaling factor, where the scaling factor of the straight road mode is three times that of other road modes.

[0036] Further, the determining of the first type of path points that need to be decelerated and smoothed, and the second type of path points that need to be accelerated and smoothed, according to the road mode of the path points and / or the third target speed threshold, includes:

[0037] If the difference between the third target speed threshold of a path point after the current path point and the third target speed threshold of the current path point is greater than the preset speed difference threshold, the path point after the current path point is determined as the second type of path point.

[0038] Further, each path point in the second type of path points is accelerated and smoothed according to a preset acceleration to obtain a final target speed threshold of each path point, including:

[0039] The serial number of the current path point is marked as j, and a reference speed is determined based on the following calculation formula. If the third target speed threshold of the path point j+1 is greater than the reference speed, the reference speed is determined as the final target speed threshold of the path point j+1;

[0040]

[0041] in, represents the reference speed, represents the distance between path point j and path point j+1, represents the third target speed threshold of path point j, Indicates the preset acceleration.

[0042] In a third aspect, the present invention further provides an electronic device, the electronic device comprising:

[0043] one or more processors;

[0044] A storage device for storing one or more programs;

[0045] When the one or more programs are executed by the one or more processors, the one or more processors implement the unmanned driving target speed planning method as described above.

[0046] In a fourth aspect, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the unmanned driving target speed planning method as described above.

[0047] The unmanned driving target speed planning method disclosed by the present invention first sets the target speed initial value for each path point on the reference path, then divides the road mode according to the curvature of the path point and the target speed initial value, and finally determines the target speeds corresponding to the transition sections between different road modes and roads of different modes according to three parameters: the road mode, the traffic constraint and the preset target speed threshold, so as to ensure the smooth transition of the vehicle from the section with a larger target speed threshold to the section with a smaller target speed threshold, and ensure that the smaller target speed is immediately executed after entering the section with the smaller target speed threshold, or ensure the smooth transition of the vehicle from the section with a smaller target speed threshold to the section with a larger target speed threshold, and ensure that the larger target speed is immediately executed after entering the section with the larger target speed threshold, so as to solve the problem of sudden change of target speed caused by lack of target speed transition path at the connection of traditional roads with different curvatures, and further provide speed constraints for the vehicle to arrive at the destination safely and smoothly. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0049] Figure 1 A schematic diagram of a process for unmanned driving target speed planning method provided by an embodiment of the present invention Figure 1 ;

[0050] Figure 2 FIG. 4 is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the invention are shown in the accompanying drawings.

[0052] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0053] Figure 1 This is a flow chart of an unmanned driving target speed planning method proposed in this application, which is applicable to speed planning for an autonomous driving vehicle and can be executed by a vehicle controller.

[0054] like Figure 1 As shown, the unmanned driving target speed planning method includes the following steps:

[0055] S110. Determine a road mode of each path point according to a curvature of each path point on a reference path and a first target speed threshold, wherein the first target speed threshold of each path point is determined according to a traffic speed limit regulation.

[0056] Among them, the unmanned vehicle will set the initial value of the target speed, also known as the first target speed threshold, according to the route in the process of making a high-precision map, and the latitude and longitude information and curvature information corresponding to the path points to complete the high-precision map. After that, the unmanned vehicle determines the reference path according to the vehicle starting point and the target point before driving, calculates the curvature information of each path point on the reference path, and comprehensively considers the curvature information and the first target speed threshold to divide the road into three modes, namely, the straight road mode, the small curvature curve mode and the large curvature curve mode, and then sets the second target speed threshold according to different road modes (the second target speed threshold can be set through the configuration file). The setting principle of the second target speed threshold is: the second target speed threshold of the straight road mode is the largest, the second target speed threshold of the large curvature curve mode is the smallest, and the second target speed threshold of the small curvature curve mode is between the two. Then, the first target speed threshold and the second target speed threshold are compared, and the smaller one between the two is used as the third target speed threshold of the path point. Finally, the third target speed threshold is smoothed to obtain the final target speed threshold (unit: km / h). Then, during the vehicle driving process, the final reference target speed of the vehicle is calculated based on the final target speed threshold and combined with the actual vehicle status information and road section information.

[0057] In order to better calculate the final target speed threshold, this method calls the continuous path points of the same road mode a road section. If the two sections before and after correspond to different road modes, the final target speed thresholds of all path points on the same section are not the same, because it involves the transition from high speed to low speed or low speed to high speed. The decision module calculates the vehicle acceleration based on the final target speed threshold and the real-time environmental information around the vehicle, so that the vehicle can arrive at the destination safely and smoothly. The steps of the entire technical solution are as follows:

[0058] Initially, the driverless vehicle collects basic information about the road and creates a high-precision map in the OpenDrive format. The collected information includes the longitude and latitude of the centerline of the road, the heading angle information, and the initial target speed value of some path points (also called the first target speed threshold, in km / h). The vehicle speed cannot exceed the first target speed threshold during driving. The first target speed threshold is the first constraint on the vehicle's driving process. This constraint may be determined by traffic rules, such as a speed limit of 60km / h on a road section or 30km / h on a road section.

[0059] When driving, the global path planning module in the autonomous driving system plans a reference path for the vehicle based on the vehicle's starting point and the target destination, combined with the basic information of the high-precision map, and further calculates the curvature information of each path point on the reference path. The reference path includes the path points from the starting point to the end point (that is, the trajectory points of the vehicle), the curvature of the corresponding points, and the first target speed threshold.

[0060] After the reference path planning is completed, the target speed planning module turns on the target speed planning function according to whether the target speed planning flag switch is turned on. If the target speed planning flag switch is not turned on, the actual vehicle speed planned by the automatic driving decision control module cannot exceed the first target speed threshold. If the target speed planning flag switch is turned on, the target speed planning is further performed.

[0061] If the target speed planning flag switch is turned on, the corresponding road mode initial values ​​will be assigned to the path points with different curvatures on the reference path according to the pre-defined road mode division principle, and the second target speed threshold will be set for the path points of different road modes.

[0062] The road mode division adopts the method of combining curvature and the first target speed threshold weight to solve the problem of road mode mutation caused by simply relying on curvature to divide the road mode.

[0063] Generally, the second target speed threshold should be less than the first target speed threshold, and the second target speed threshold is the target speed corresponding to each road mode during the planned vehicle driving process. Among them, the second target speed threshold, the road mode division rule and the target speed planning flag switch can be modified through the configuration file, so as to meet the needs of adapting to different vehicle models or the same vehicle model to different driving conditions.

[0064] Exemplarily, a road mode division reference value is determined based on the following calculation formula, and road mode division is performed based on the road mode division reference value to obtain a road mode of each path point;

[0065] RoadMode=Kp×k+Ks×FirstSpeed;

[0066] Among them, RoadMode represents the reference value of road mode division, Kp and Ks represent weight coefficients, Kp+Ks=1, k represents the curvature of the way point, FirstSpeed ​​represents the first target speed threshold of the way point, when FirstSpeed<15km / h, Kp>Ks; when 15km / h<FirstSpeed<30km / h, Kp=Ks; when FirstSpeed>30km / h, Kp<Ks.

[0067] Exemplarily, when the first target speed threshold FirstSpeed ​​is less than 15km / h, the weight of the road curvature is increased, considering that it is a curve with large curvature, such as the road curvature weight Kp can be 0.8, and the first target speed threshold weight Ks is 0.2; when the first target speed threshold FirstSpeed ​​is less than 30km / h and greater than 15km / h, the weight Ks of the first target speed threshold is 0.5, and the road curvature weight Kp is 0.5; when the first target speed threshold FirstSpee is greater than 30km / h, the road curvature weight Kp is reduced, and the weight Ks of the first target speed threshold is increased, such as the road curvature weight Kp is 0.3, and the first target speed threshold weight Ks is 0.7, etc. The weight coefficients Kp and Ks can also be configured through XML files to facilitate adaptation to different vehicle models or working conditions.

[0068] S120. Correct the road mode of the current path point according to the road modes of the path points adjacent to the current path point, so as to filter out the noise points in the path points and obtain filtered path points.

[0069] The road mode includes a straight road mode, a small curvature curve mode and a large curvature curve mode; the road mode of the current path point is corrected according to the road mode of the path point adjacent to the current path point to filter the noise points in each path point to obtain the filtered path point, including:

[0070] If the road mode of the current path point is different from the road modes of its front and rear adjacent path points, and the road modes of its front and rear adjacent path points are the same, and the length of the road segment composed of its front and rear adjacent path points with the same road mode is greater than a preset length threshold, then the road mode of the current path point is corrected to be the same road mode as that of its front and rear adjacent path points; wherein the preset length thresholds corresponding to different road modes are different.

[0071] The noise points refer to a section of road with one or several different road modes. The rule for filtering out noise points is: if the road points before and after the noise points are of the same road mode, and the length of the route is greater than a certain threshold (the thresholds for long straight roads, large curvature curves and small curvature curves are different), then the road mode of the noise points is set to the same road mode as the previous and next points. Filtering out noise points is also one of the ways to ensure the final smooth driving of the vehicle, avoiding sudden acceleration or deceleration.

[0072] S130. Setting a second target speed threshold for the waypoint through a configuration file according to the road pattern of the filtered waypoint.

[0073] The setting principle of the second target speed threshold is: the second target speed threshold of the straight road mode is the largest, the second target speed threshold of the large curvature curve mode is the smallest, and the second target speed threshold of the small curvature curve mode is between the two.

[0074] S140. For each path point, determine a third target speed threshold of the current path point according to the first target speed threshold and the second target speed threshold of the current path point.

[0075] Exemplarily, if there is only a corresponding first target speed threshold for the current path point, the first target speed threshold is determined as the third target speed threshold for the current path point;

[0076] If there is only a corresponding second target speed threshold for the current path point, the second target speed threshold is determined as the third target speed threshold for the current path point;

[0077] If the current path point has both a corresponding first target speed threshold and a corresponding second target speed threshold, the smaller one of the first target speed threshold and the second target speed threshold is determined as the third target speed threshold of the current path point.

[0078] S150. Determine, according to the road pattern of the path point and / or the third target speed threshold, a first type of path point that needs to be decelerated and smoothed, and a second type of path point that needs to be accelerated and smoothed.

[0079] Specifically, judgment rule 1: if the road mode of the current path point is a straight road mode, and the difference between the third target speed threshold of the previous path point adjacent to the current path point and the third target speed threshold of the current path point is greater than the preset speed difference threshold, the path point before the current path point is determined to be a first-class path point that needs to be decelerated and smoothed. Judgment rule 2: if the road mode of the current path point is a small curvature curve mode or a large curvature curve mode, and the road mode of the previous path point is different from the road mode of the current path point, the path point before the current path point is determined to be a first-class path point that needs to be decelerated and smoothed.

[0080] Speed ​​smoothing can ensure smooth transition of speed changes and improve the stability and comfort of the vehicle.

[0081] S160, performing deceleration smoothing processing on each path point in the first category according to the speed smoothing distance resolution, the speed smoothing preview distance and the preset deceleration, and performing acceleration smoothing processing on each path point in the second category according to the preset acceleration, to obtain the final target speed threshold of each path point.

[0082] Specifically, the serial number of the current path point is marked as i, the serial number of the previous path point adjacent to the current path point i is marked as startvalue, startvalue=i-1, the previous path point startvalue adjacent to the current path point i is the first path point to be subjected to deceleration smoothing processing, the serial number of the path point currently subjected to deceleration smoothing processing is marked as j, and if the third target speed threshold of the path point j is less than the third target speed threshold of the path point j+1, the deceleration smoothing processing flow is exited;

[0083] If the difference between startvalue and j is less than the reference number nprebrake, the third target speed threshold of path point j+1 is determined as the final target speed threshold of path point j, where the reference number nprebrake=speed smoothing preview distance / speed smoothing distance resolution. If the quotient of speed smoothing preview distance / speed smoothing distance resolution is not an integer, it is rounded up as the value of the reference number nprebrake. For example, if the quotient of speed smoothing preview distance / speed smoothing distance resolution is 90.2, the value of the reference number nprebrake is determined to be 91.

[0084] If the difference between startvalue and j is not less than the reference number nprebrake, the reference speed is determined based on the following calculation formula: if the third target speed threshold of the waypoint j is greater than the reference speed, the reference speed is determined as the final target speed threshold of the waypoint j; otherwise, the third target speed threshold of the waypoint j is determined as the final target speed threshold of the waypoint j;

[0085] (1)

[0086]

[0087] in, represents the reference speed, represents the distance between path point j and path point j+1, represents the third target speed threshold of path point j+1, Indicates the brake value. Indicates the preset deceleration, Represents the scaling factor, where the scaling factor of the straight road mode is three times that of other road modes.

[0088] In other words, the specific steps of the deceleration smoothing process are: if the current point is the first path point on the reference path, no operation is performed; if the current point is not the first path point, determine whether the current point needs to be decelerated and smoothed according to the above-mentioned judgment rules one and two. If necessary, the specific smoothing process is as follows: first calculate the braking value brakea, which is the product of the preset deceleration and the proportional factor. The values ​​set by the proportional factor judgment rule one and judgment rule two are different. Among them, the proportional factor corresponding to the path point that needs to be decelerated and smoothed as determined by judgment rule one is 3 times the proportional factor corresponding to the path point that needs to be decelerated and smoothed as determined by judgment rule two. Because the speed of the straight mode is higher, a larger braking value is required. Smooth changes in speed can be ensured by setting the preset deceleration. The preset deceleration can be configured through an XML file in units of m / s. 2 , increasing the flexibility of vehicle model adaptation and working condition adaptation. The proportional factor is set here to adapt to different vehicle models.

[0089] If the calculated braking value is greater than the set braking threshold, the braking value is assigned to the braking threshold, otherwise the actual calculated value is used. The accuracy of the preset deceleration affects the final vehicle stability. The smaller the value, the smoother the target speed change of the vehicle.

[0090] Calculate the speed smoothing distance resolution: The speed smoothing distance resolution is the distance fdispoint from the current path point to the previous path point. If this distance is less than the sampling accuracy of the GPS sensor, the sampling accuracy of the GPS sensor is determined as the distance from the current path point to the previous path point, that is, the speed smoothing distance resolution is equal to the sampling accuracy of the GPS sensor. With the speed smoothing distance resolution, the number of path points nprebrake required for the actual speed smoothing process can be calculated. nprebrake is equal to the ratio of the speed smoothing preview distance to the speed smoothing distance resolution rounded up to an integer. The speed smoothing preview distance is also divided into two types according to the above-mentioned judgment rules 1 and 2. Usually, the speed smoothing preview distance of the straight road mode is smaller than the speed smoothing preview distance of the non-straight road mode, that is, when the target speed is small, the required speed smoothing preview distance is larger, which can avoid the vehicle's frustration in continuous curves and achieve a smooth transition of speed during the entire driving process.

[0091] The previous path point of the current path point i is recorded as startvalue, that is, startvalue=i-1, and then all the path points before the current path point are decelerated and smoothed in sequence, and j is used to represent the serial number of the path point that needs to be decelerated and smoothed. If the third target speed threshold of path point j is less than the third target speed threshold of path point j+1, the smoothing process is directly exited. If the value of startvalue minus j is less than nprebrake, the third target speed threshold of path point j is set to the third target speed threshold of path point j+1. The purpose is to make the speed of nprebrake path points before path point i the same as the third target speed threshold of path point i, so as to ensure that the vehicle decelerates in advance and further ensure the stability and comfort of the vehicle; continue to perform deceleration and smoothing on the path point j-1 before path point j, until the first path point j (j=0) at the beginning.

[0092] If the value of startvalue minus j is not less than nprebrake, the distance fdis between the current path point j and the next path point j+1 is calculated, and the third target speed threshold of the path point j+1 is converted into a value vpre in meters per second, where vpre is the third target speed threshold of the path point j+1 divided by 3.6. Then, the reference speed of the path point j is calculated according to the calculated brake value brakea, see formula (1). If the value of fspeed is less than the third target speed threshold of the path point j, fspeed is determined as the final target speed threshold of the path point j, otherwise its third target speed threshold is used as its final target speed threshold.

[0093] Performing acceleration and smoothing processing on each of the second-type path points according to a preset acceleration to obtain a final target speed threshold of each path point includes:

[0094] The serial number of the current path point is marked as j, and a reference speed is determined based on the following calculation formula. If the third target speed threshold of the path point j+1 is greater than the reference speed, the reference speed is determined as the final target speed threshold of the path point j+1;

[0095] (2)

[0096] in, represents the reference speed, represents the distance between path point j and path point j+1, represents the third target speed threshold of path point j, Indicates the preset acceleration.

[0097] After the deceleration smoothing process is completed, all path points are further accelerated and smoothed. The acceleration and smoothing process is as follows:

[0098] Smoothing starts from the second path point on the reference path. For a path point i, if the difference between the third target speed threshold of the i+1th path point and the third target speed threshold of the i-th path point is greater than the set threshold, then all path points after the path point i are accelerated and smoothed according to the following process:

[0099] Set acceleration acc + , the minimum is 0.1 (this acceleration value can be written in the XML file and changed at any time according to the vehicle model or working conditions. The unit is m / s 2 ). Calculate the difference between the second target speed threshold of the path point i+1 and the current path point i. If the difference is greater than the threshold, perform smoothing according to the following steps. If it is less than the threshold, determine whether the next path point i needs to be accelerated and smoothed.

[0100] The serial number of the current path point is recorded as j, and the distance fdis between the path point j and the next path point j+1 is calculated. The second target speed threshold of the path point j is converted into a value vpre in meters per second. vpre is the second target speed threshold of the path point j divided by 3.6. According to the value of fdis and the second target speed threshold of the path point j, the acceleration acc is preset. + , predict the reference speed fspeed of path point j+1 according to formula (2). If the third target speed threshold of path point j+1 is greater than fspeed, the reference speed fspeed is used as the final target speed threshold of path point j+1. Otherwise, the third target speed threshold of path point j+1 is used as the final target speed threshold. The acceleration smoothing process of all path points after i is completed in a cycle, and then the value of i is updated. The third target speed threshold of the next path point that needs to be accelerated and smoothed is accelerated and smoothed until the acceleration and smoothing process of all points is completed.

[0101] S170: Perform speed planning with the final target speed threshold as a constraint condition.

[0102] The purpose of this embodiment is to provide a target speed planning method for an unmanned driving system to solve the problem of sudden acceleration or deceleration of a vehicle caused by a sudden change in target speed, and further ensure vehicle safety and the comfort and stability of the ride. The traditional solution that relies solely on curvature to determine straight roads and curves will cause the vehicle to feel frustrated in places with complex scenes such as vehicle test sites. The method proposed in the embodiment of the present application can solve this problem well. In the deceleration smoothing process, the road mode to which the current path point belongs is combined with the speed difference on the straight road to determine whether deceleration smoothing is required. On the curve, the road mode is used to determine whether deceleration smoothing is required, and the deceleration is set. The path point in front of the current path point is decelerated and smoothed. Compared with the traditional method of setting different target speeds based on different road modes, the target speed of the vehicle in the entire reference path changes more smoothly, and there will be no sudden deceleration process. Finally, the acceleration process of the entire reference path point is smoothed by the set acceleration, and the target speed of the subsequent path point is constrained and optimized by the target speed of the previous path point, which solves the problem of target speed mutation caused by optimizing the target speed of the previous path point according to the target speed of the subsequent path point, making the acceleration process smoother.

[0103] Figure 2 Schematic diagram of the structure of an electronic device in the embodiment of the present disclosure. Figure 2 , which shows a structural schematic diagram of an electronic device 500 suitable for implementing the embodiments of the present disclosure. Figure 2 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0104] like Figure 2 As shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage device 508 into a random access memory (RAM) to implement the method of the embodiment described in the present disclosure. In RAM503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, ROM 502, and RAM503 are connected to each other via a bus 504. The I / O interface 505 is also connected to the bus 504. The input device 506, the output device 507, the storage device 508, and the communication device 509 are all connected to the I / O interface 505.

[0105] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart, thereby implementing the unmanned driving target speed planning method as described above. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0106] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0107] The computer-readable medium may be included in the electronic device; or it may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: amends the preset SOC value according to the temperature of the battery cell and / or the service life of the battery to obtain a target SOC value; and controls the vehicle's range extender according to the target SOC value.

[0108] Optionally, when the above one or more programs are executed by the electronic device, the electronic device may also execute other steps described in the above embodiments.

[0109] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0110] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0111] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and its core ideas of this application. The above is only the preferred implementation method of this application. It should be pointed out that due to the limitations of textual expression and the objective existence of infinite specific structures, ordinary technicians in this technical field can make several improvements, modifications or changes without departing from the principles of the present invention, and can also combine the above technical features in an appropriate manner; these improvements, modifications, changes or combinations, or the direct application of the inventive concept and technical solution to other occasions without improvement, should be regarded as the scope of protection of this application.

Claims

1. An unmanned driving target speed planning method, characterized in that: include: Determine the road mode of each path point according to the curvature of each path point on the reference path and a first target speed threshold, wherein the first target speed threshold of each path point is determined according to a traffic speed limit regulation; According to the road modes of the path points adjacent to the current path point, the road mode of the current path point is modified to filter the noise points in the path points to obtain the filtered path points; Setting a second target speed threshold for the waypoint through a configuration file according to the road pattern of the filtered waypoint; For each path point, determining a third target speed threshold of the current path point according to the first target speed threshold and the second target speed threshold of the current path point; Determine, according to the road mode of the waypoint and / or the third target speed threshold, a first type of waypoint that needs to be decelerated and smoothed, and a second type of waypoint that needs to be accelerated and smoothed; Performing a deceleration smoothing process on each path point in the first category according to the speed smoothing distance resolution, the speed smoothing preview distance, and the preset deceleration, and performing an acceleration smoothing process on each path point in the second category according to the preset acceleration, to obtain a final target speed threshold of each path point; Performing speed planning with the final target speed threshold as a constraint condition; The step of determining the road mode of each path point according to the curvature of each path point on the reference path and the first target speed threshold comprises: Determine a road mode division reference value based on the following calculation formula, and perform road mode division based on the road mode division reference value to obtain a road mode for each path point; RoadMode=Kp×k+Ks×FirstSpeed; Among them, RoadMode represents the reference value of road mode division, Kp and Ks represent weight coefficients, Kp+Ks=1, k represents the curvature of the way point, FirstSpeed ​​represents the first target speed threshold of the way point, when FirstSpeed<15km / h, Kp>Ks; when 15km / h<FirstSpeed<30km / h, Kp=Ks; when FirstSpeed>30km / h, Kp<Ks.

2. The unmanned driving target speed planning method according to claim 1, characterized in that: The road mode includes a straight road mode, a small curvature curve mode and a large curvature curve mode; The method of modifying the road mode of the current path point according to the road modes of the path points adjacent to the current path point, so as to filter the noise points in each path point to obtain the filtered path point, comprises: If the road mode of the current path point is different from the road modes of the path points adjacent to it, and the road modes of the path points adjacent to it are the same, and the length of the road segment composed of the path points adjacent to it with the same road mode is greater than the preset length threshold, then the road mode of the current path point is corrected to be the same as the road mode of the path points adjacent to it; Among them, the preset length thresholds corresponding to different road modes are different.

3. The unmanned driving target speed planning method according to claim 1, characterized in that: The step of determining, for each path point, a third target speed threshold of the current path point according to the first target speed threshold and the second target speed threshold of the current path point comprises: If the current path point only has a corresponding first target speed threshold, the first target speed threshold is determined as the third target speed threshold of the current path point; If there is only a corresponding second target speed threshold for the current path point, the second target speed threshold is determined as the third target speed threshold for the current path point; If the current path point has both a corresponding first target speed threshold and a corresponding second target speed threshold, the smaller one of the first target speed threshold and the second target speed threshold is determined as the third target speed threshold of the current path point.

4. The unmanned driving target speed planning method according to claim 1, characterized in that: The determining of the first type of waypoints requiring deceleration smoothing processing according to the road mode of the waypoints and / or the third target speed threshold comprises: If the road mode of the current path point is a straight road mode, and the difference between the third target speed threshold of the previous path point adjacent to the current path point and the third target speed threshold of the current path point is greater than the preset speed difference threshold, the path point before the current path point is determined to be a first type of path point that needs to be decelerated and smoothed; If the road mode of the current path point is a small curvature curve mode or a large curvature curve mode, and the road mode of the previous path point is different from the road mode of the current path point, the path point before the current path point is determined to be a first type of path point that requires deceleration and smoothing processing.

5. The unmanned driving target speed planning method according to claim 4, characterized in that: The step of performing a deceleration and smoothing process on each path point in the first category of path points according to the speed smoothing distance resolution, the speed smoothing preview distance, and the preset deceleration to obtain a final target speed threshold of each path point includes: The serial number of the current path point is marked as i, the serial number of the previous path point adjacent to the current path point i is marked as startvalue, startvalue=i-1, the previous path point startvalue adjacent to the current path point i is the first path point to be subjected to deceleration smoothing processing, the serial number of the path point currently subjected to deceleration smoothing processing is marked as j, and if the third target speed threshold of the path point j is less than the third target speed threshold of the path point j+1, then the deceleration smoothing processing flow is exited; If the difference between startvalue and j is less than the reference number nprebrake, the third target speed threshold of the waypoint j+1 is determined as the final target speed threshold of the waypoint j, where the reference number nprebrake=speed smoothing preview distance / speed smoothing distance resolution; If the difference between startvalue and j is not less than the reference number nprebrake, the reference speed is determined based on the following calculation formula: if the third target speed threshold of the waypoint j is greater than the reference speed, the reference speed is determined as the final target speed threshold of the waypoint j; otherwise, the third target speed threshold of the waypoint j is determined as the final target speed threshold of the waypoint j; in, represents the reference speed, represents the distance between path point j and path point j+1, represents the third target speed threshold of path point j+1, Indicates the brake value. Indicates the preset deceleration, Represents the scaling factor, where the scaling factor of the straight road mode is three times that of other road modes.

6. The unmanned driving target speed planning method according to claim 1, characterized in that: The method of determining the first type of path points that need to be decelerated and smoothed, and the second type of path points that need to be accelerated and smoothed, according to the road mode of the path points and / or the third target speed threshold, comprises: If the difference between the third target speed threshold of a path point after the current path point and the third target speed threshold of the current path point is greater than the preset speed difference threshold, the path point after the current path point is determined as the second type of path point.

7. The unmanned driving target speed planning method according to claim 1, characterized in that: Performing acceleration and smoothing processing on each of the second-type path points according to a preset acceleration to obtain a final target speed threshold of each path point includes: The serial number of the current path point is marked as j, and a reference speed is determined based on the following calculation formula. If the third target speed threshold of the path point j+1 is greater than the reference speed, the reference speed is determined as the final target speed threshold of the path point j+1; in, represents the reference speed, represents the distance between path point j and path point j+1, represents the third target speed threshold of path point j, Indicates the preset acceleration.

8. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the unmanned driving target speed planning method as described in any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the unmanned driving target speed planning method as described in any one of claims 1 to 7 is implemented.