CN115454100A

CN115454100A - Global speed planning method, global speed planning device and planning system

Info

Publication number: CN115454100A
Application number: CN202211247742.5A
Authority: CN
Inventors: 杨泽宇; 秦兆博; 秦晓辉; 王龙晓; 王学鹏; 周岩
Original assignee: Weichai Power Co Ltd
Current assignee: Weichai Power Co Ltd
Priority date: 2022-10-12
Filing date: 2022-10-12
Publication date: 2022-12-09

Abstract

The application provides a global speed planning method, a global speed planning device and a planning system. The method comprises a first planning step, wherein a speed planning algorithm is adopted to carry out speed planning on the received total running time, departure time, overall running path and road section speed limit information of the vehicle to obtain an initial overall track; the method comprises the steps of obtaining, controlling a vehicle to run according to an initial global track to obtain the actual running time of the vehicle reaching a target path point; a first comparison step of, in the case of being less than or equal to a predetermined threshold, performing the acquisition step at least once until the vehicle reaches the destination; and a second comparison step, wherein the remaining total running time and the remaining global path are calculated under the condition that the comparison result is greater than the preset threshold value, and the first planning step and the obtaining step are sequentially executed at least once until the vehicle reaches the destination, so that the problem that the global track of the vehicle is difficult to determine through less calculation amount while the on-time reaching requirement of the vehicle is considered in the prior art is solved.

Description

Global speed planning method, global speed planning device and planning system

Technical Field

The present application relates to the field of automatic driving technologies, and in particular, to a global velocity planning method, a global velocity planning apparatus, a computer-readable storage medium, a processor, and a planning system.

Background

The global speed planning is used as a key technology of automatic driving, and mainly determines the speed of traveling along the optimal path according to optimal path information and path segment speed limit information output by the global planning.

In the existing global speed planning scheme, the obtained speed curve is required to meet the acceleration and deceleration performance of a vehicle and the speed limit of a road, and the obtained speed curve is required to be a continuous smooth curve. Most of the determination methods for the smooth speed curve are based on dynamic programming or other heuristic optimization methods, and the methods have the problem of large calculation amount. In addition, in an automatic system such as an intelligent passenger and bus system according to time-sharing scheduling, the performance requirement on the timely arrival of an intelligent vehicle is high, but the performance requirement is rarely considered in the existing global speed planning scheme.

Therefore, there is a high necessity for determining an optimal global speed profile of a vehicle with a small amount of calculation while considering the on-time arrival demand of the vehicle.

Disclosure of Invention

The present application mainly aims to provide a global velocity planning method, a global velocity planning apparatus, a computer-readable storage medium, a processor, and a planning system, so as to solve the problem that it is difficult to determine a global trajectory of a vehicle with a small amount of computation while considering a need for on-time arrival of the vehicle in the prior art.

According to an aspect of an embodiment of the present invention, there is provided a global velocity planning method, including: the method comprises the steps of firstly, performing speed planning on the received total running time of a vehicle, the departure time, the overall running path and the road section speed limit information by adopting a speed planning algorithm to obtain an initial overall track, wherein the initial overall track is used for representing the speed information and the time information of each path point, and the path points are points which are divided on the overall running path according to preset intervals; an obtaining step of controlling the vehicle to run according to the initial global track to obtain an actual running time of the vehicle reaching a target path point, wherein the target path point is one of the path points; a first comparison step, wherein the obtaining step is executed at least once under the condition that the difference value between the actual running time length and the planned time length of the route point is less than or equal to a preset threshold value until the vehicle reaches the destination, and the planned time length of the route point is the running time length of the initially planned target route point; and a second comparison step, namely calculating the remaining total running time and the remaining global path under the condition that the difference value between the actual running time and the planned time of the path point is greater than the preset threshold value, and sequentially executing the first planning step and the obtaining step at least once until the vehicle reaches the destination.

Optionally, a speed planning algorithm is adopted to perform speed planning on the received total running duration, departure time, global driving path and road section speed limit information of the vehicle to obtain an initial global track, and the method includes: dividing the global driving path according to a preset rule to obtain a plurality of path segments, wherein the preset rule is determined according to the forward and backward movement of the vehicle; acquiring at least two key points on each path segment, wherein the key point is one of the path points; preprocessing at least two key points on each path segment to obtain target key points on each path segment; and performing trapezoidal speed planning according to the target key points, the total running time, the departure time, the overall running path and the road section speed limit information on each path segment to obtain the initial overall track of the vehicle.

Optionally, the preprocessing at least two key points on each path segment to obtain a target key point on each path segment includes: for continuous first and second key points on a target path segment, determining a first speed and a second speed of the first key point and a third speed of the second key point, wherein the target path segment is one of the plurality of path segments, and the first and second key points are the key points; if the first speed is greater than the second speed and the second speed is greater than the third speed, calculating a first distance from the second speed to the third speed based on a maximum deceleration, and determining the target keypoint on the target path segment based at least on the first distance; if the second speed is greater than the first speed and the first speed is greater than the third speed, calculating a second distance from the first speed to the third speed based on the maximum deceleration, determining the target keypoints on the target path segment based at least on the second distance.

Optionally, determining the target keypoints on the target path segment according to at least the first distance includes: calculating the distance between the first key point and the second key point to obtain a target key distance; if the first distance is greater than the target key distance, determining the second key point as the target key point, determining a fourth speed of the second key point as the first speed, and deleting the first key point; and determining the first key point and the second key point as the target key point when the first distance is smaller than or equal to the target key distance.

Optionally, determining the target keypoints on the target path segment according to at least the second distance includes: calculating the distance between the first key point and the second key point to obtain a target key distance; if the second distance is greater than the target key distance, determining the second key point as the target key point, determining a fourth speed of the second key point as the first speed, and deleting the first key point; and under the condition that the second distance is smaller than or equal to the target key distance, determining the first key point and the second key point as the target key points.

Optionally, performing trapezoidal speed planning according to the target key point, the total operating time, the departure time, the global travel path, and the road segment speed limit information on each of the path segments to obtain the initial global trajectory of the vehicle, including: a second planning step, wherein the trapezoidal speed planning is carried out on the target key points on each path segment at least according to the road section speed limit information to obtain a global speed curve of the global driving path; a first determination step, wherein the global track duration is determined according to the global speed curve and the global driving path; and a second determination step, determining the initial global track according to the global track time length, the total operation time length and the departure time.

Optionally, determining the initial global trajectory according to the global trajectory duration, the total operation duration, and the departure time includes: under the condition that the overall track duration is longer than the total operation duration, generating first planning failure information, and sending the first planning failure information to a scheduling system; and under the condition that the overall track time length is less than or equal to the total running time length, calculating a difference value between the overall track time length and the total running time length to obtain a target time length difference value, and determining the initial overall track of the vehicle at least according to the target time length difference value and the departure time.

Optionally, determining the initial global trajectory of the vehicle according to at least the target duration difference and the departure time includes: under the condition that the target time length difference is smaller than or equal to a time length difference threshold, adding the speed information and the time information to each path point according to the global speed curve and the departure time to obtain the initial global track of the vehicle; and under the condition that the target time length difference is greater than the time length difference threshold, correcting the speed limit information of the road section according to the target time length difference, and executing the second planning step, the first determining step and the second determining step at least once until the target time length difference is less than or equal to the time length difference threshold.

Optionally, performing the trapezoidal speed planning on the target key point on each path segment according to at least the speed limit information of the road segment to obtain a global speed curve of the global driving path, including: a third planning step, which is to perform kinematic speed planning at least based on the speed information of the target key points on each path segment to obtain a plurality of initial path speed curves, wherein one path segment corresponds to one initial path speed curve; optimizing, namely optimizing each initial path speed curve to obtain an initial global speed curve; and an iteration step, namely performing iteration processing on the initial overall speed curve based on the road section speed limit information to obtain the overall speed curve.

Optionally, performing optimization processing on each initial path speed curve to obtain an initial global speed curve, including: constructing an optimization function at least according to the speed information of two adjacent path points to obtain a plurality of optimization objective functions; and performing optimization solution on the plurality of optimization objective functions by adopting a gradient descent method to obtain the initial global speed curve.

Optionally, based on the speed limit information of the road segment, performing iterative processing on the initial global speed curve to obtain the global speed curve, including: determining the actual path running time of an alternative path point according to the initial global speed curve, wherein the alternative path point is one of the path points; calculating a difference value between the actual path operation time length and a planned path operation time length to obtain a path time length difference value, wherein the planned path operation time length is the operation time length of the planned alternative path point; and under the condition that the difference value of the path time lengths is larger than the preset threshold, correcting the road section speed limit information to which the alternative path point belongs according to a corrected speed limit speed to obtain corrected road section speed limit information, and executing the third planning step, the optimizing step and the iteration step at least once until the difference value of the overall track time length and the total operation time length of the overall speed curve meets a preset range, wherein the corrected speed limit speed is determined at least according to an initial corrected speed limit speed, the actual path operation time length and the planned path operation time length.

According to another aspect of the embodiments of the present invention, there is also provided a global velocity planning apparatus, including: the planning unit is used for performing speed planning on the received total running time, departure time, overall driving path and road section speed limit information of the vehicle by adopting a speed planning algorithm to obtain an initial overall track, wherein the initial overall track is used for representing speed information and time information of each path point, and the path points are points which are divided on the overall driving path according to preset intervals; an obtaining unit, configured to perform an obtaining step to control the vehicle to travel according to the initial global trajectory to obtain an actual running time of the vehicle reaching a target waypoint, where the target waypoint is one of the waypoints; a first comparing unit, configured to perform the obtaining step at least once when a difference between the actual running time and a planned time of a route point is less than or equal to a predetermined threshold value, until the vehicle reaches a destination, where the planned time of the route point is a running time of the initially planned target route point; and the second comparison unit is used for calculating the residual total running time length and the residual global path under the condition that the difference value between the actual running time length and the planned time length of the path point is greater than the preset threshold value in the second comparison step, and sequentially executing the first planning step and the obtaining step at least once until the vehicle reaches the destination.

According to still another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium including a stored program, wherein the program executes any one of the global velocity planning methods.

According to still another aspect of the embodiments of the present invention, there is further provided a processor, where the processor is configured to execute a program, where the program executes any one of the global speed planning methods when running.

According to an aspect of the embodiment of the present invention, there is also provided a planning system, a scheduling system, wherein the scheduling system is configured to send a total operation duration and a departure time to a global speed planning system; the global path planning system is used for sending global driving path and road section speed limit information to the global speed planning system; the global speed planning system comprises a global speed planning device, and the global speed planning device is used for executing any one of the global speed planning methods.

In the embodiment of the invention, in the global speed planning method, firstly, based on a speed planning algorithm, speed planning is carried out on the received total running time length, departure time, global driving path and road section speed limit information of a vehicle to obtain an initial global track; then, acquiring the actual running time of the vehicle reaching the target path point in the process of running the vehicle by the initial global track; then, calculating the difference between the actual running time of the vehicle at the target path point and the planned time of the path point, and if the difference is less than or equal to a preset threshold value, indicating that the vehicle can arrive at the destination on time, so that the vehicle can be continuously controlled to run in the initial global track until the vehicle reaches the destination; and under the condition that the difference value is greater than the preset threshold value, the vehicle cannot arrive at the destination on time, the remaining total running time length and the remaining global path of the vehicle are calculated, and speed planning is performed again according to the remaining total running time length, the remaining global path, the departure time and the road section speed limit information, so that the vehicle arrives at the destination on time. Compared with the method for obtaining the global track of the vehicle through dynamic programming or heuristic optimization in the prior art, the global speed planning method has the advantages that the speed planning algorithm is only needed to be adopted, the speed planning is carried out on the total running time, the starting time, the global driving path and the road section speed limit information of the vehicle, the initial global track of the vehicle is obtained, the calculated amount for determining the initial global track is less, the method does not need to be carried on a vehicle-scale high-calculation-force platform, and the cost of the global speed planning method is lower. In addition, the global speed planning method dynamically adjusts the operation strategy of the vehicle under the influence of dynamic traffic flow by considering the demand of the vehicle on-time arrival, and ensures that the vehicle can arrive at the destination on-time, thereby solving the problem that the prior art is difficult to determine the global track of the vehicle through less calculation amount while considering the demand of the vehicle on-time arrival.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this application, are included to provide a further understanding of the application, and the description of the exemplary embodiments and illustrations of the application are intended to explain the application and are not intended to limit the application. In the drawings:

FIG. 1 shows a flow diagram of a global velocity planning method of an embodiment of the present application;

FIG. 2 is a schematic structural diagram illustrating determination of an initial global trajectory according to an embodiment of the present application;

FIG. 3 illustrates a flow chart of a global velocity planning method of a particular embodiment of the present application;

FIG. 4 illustrates a flow chart of a velocity planning algorithm of a particular embodiment of the present application;

FIGS. 5-13 show schematic diagrams of initial path velocity profiles for a specific embodiment of the present application;

FIG. 14 illustrates a diagram of an initial global velocity profile and a global velocity profile for a particular embodiment of the present application;

fig. 15 shows a schematic structural diagram of a global velocity planning apparatus according to an embodiment of the present application.

Wherein the figures include the following reference numerals:

100. a scheduling system; 200. a global path planning system; 300. a global velocity planning system; 400. an initial global trajectory; 500. an initial global velocity profile; 600. a global velocity profile; 10. a planning unit; 20. an acquisition unit; 30. a first comparing unit; 40. a second comparing unit.

Detailed Description

It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances in order to facilitate the description of the embodiments of the application herein. Moreover, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

As described in the background art, in order to solve the above problems, it is difficult in the prior art to determine a global trajectory of a vehicle with a small amount of calculation while considering a need for a vehicle to arrive on time, and in an exemplary embodiment of the present application, a global velocity planning method, a global velocity planning apparatus, a computer-readable storage medium, a processor, and a planning system are provided.

According to an embodiment of the present application, a global velocity planning method is provided.

Fig. 1 is a flow chart of a global velocity planning method according to an embodiment of the present application. As shown in fig. 1, the global velocity planning method includes the following steps:

step S101, a first planning step, namely performing speed planning on the received total running duration, the departure time, the overall running path and the road section speed limit information of the vehicle by adopting a speed planning algorithm to obtain an initial overall track, wherein the initial overall track is used for representing the speed information and the time information of each path point, and the path points are points which are divided on the overall running path according to preset intervals;

step S102, an obtaining step, in which the vehicle is controlled to run according to the initial global track so as to obtain the actual running time of the vehicle reaching a target waypoint, wherein the target waypoint is one of the waypoints;

step S103, a first comparison step, namely, executing the obtaining step at least once under the condition that the difference value between the actual running time and the planned time of the route point is less than or equal to a preset threshold value until the vehicle reaches the destination, wherein the planned time of the route point is the running time of the initially planned target route point;

and step S104, a second comparison step, namely calculating the residual total running time and the residual global path under the condition that the difference value between the actual running time and the planning time of the path point is greater than the preset threshold value, and sequentially executing the first planning step and the obtaining step at least once until the vehicle reaches the destination.

In the global speed planning method, firstly, based on a speed planning algorithm, speed planning is carried out on the received total running time, departure time, global driving path and road section speed limit information of the vehicle to obtain an initial global track; then, acquiring the actual running time of the vehicle reaching the target path point in the process that the vehicle runs along the initial global track; then, calculating the difference between the actual running time of the vehicle at the target path point and the planned time of the path point, and if the difference is less than or equal to a preset threshold value, indicating that the vehicle can arrive at the destination on time, so that the vehicle can be continuously controlled to run in the initial global track until the vehicle reaches the destination; and under the condition that the difference value is larger than the preset threshold value, the vehicle cannot arrive at the destination on time, the remaining total running time and the remaining global path of the vehicle are calculated, and then the speed planning is carried out again according to the remaining total running time, the remaining global path, the departure time and the road section speed limit information, so that the vehicle arrives at the destination on time. Compared with the method for obtaining the global track of the vehicle through dynamic programming or a heuristic optimization method in the prior art, the method for obtaining the global track of the vehicle only needs to adopt a speed programming algorithm to perform speed programming on the total running time, the departure time, the global driving path and the road section speed limit information of the vehicle to obtain the initial global track of the vehicle, so that the calculation amount for determining the initial global track is less, the method is not required to be carried on a vehicle-scale high-computing-force platform, and the cost of the method for obtaining the global speed is lower. In addition, the global speed planning method dynamically adjusts the operation strategy of the vehicle under the influence of dynamic traffic flow by considering the on-time arrival requirement of the vehicle, so that the vehicle can arrive at the destination on time, and the problem that the global track of the vehicle is difficult to determine through less calculation amount while the on-time arrival requirement of the vehicle is considered in the prior art is solved.

In the actual application process, the road section speed limit information can be adjusted in real time along with different road sections. The total operation time period is a total operation time period required for the vehicle to reach the destination from the start point. The global driving path is decided by a global path planning system. The global travel path is only a path traveled by the vehicle, and does not have speed information and time information. The initial global track obtained in the application is that speed information and time information corresponding to each path point are added on the basis of the global driving path. In addition, in the present application, the time information in the initial global trajectory may be arrival times at which the vehicle arrives at the respective waypoints.

Specifically, the present application does not limit the size of the predetermined threshold, and may flexibly adjust the predetermined threshold according to the actual driving condition of the vehicle.

In a specific embodiment of the present application, as shown in fig. 2, the global velocity planning method of the present application is applied to a global velocity planning system 300. The scheduling system 100 implements the decision of the destination, the departure time, and the total operating time of the vehicle, and the scheduling system 100 sends the destination obtained by the decision to the global path planning system 200. The global path planning system 200 plans a global driving path for a vehicle to reach a destination according to the destination, the starting point positioning information and the high-precision map information, and obtains the road section speed limit information along the global driving path, and the global path planning system 200 sends the global driving path and the road section speed limit information to the global speed planning system 300. For the global speed planning system 300, the total operation duration and departure time sent by the scheduling system 100 are received, and the global driving path and road segment speed limit information sent by the global path planning system 200 is received. The global speed planning system 300 performs speed planning on the received total running time, departure time, global driving path and road section speed limit information by using a speed planning algorithm to obtain a speed curve and a time sequence of the vehicle along the global path, thereby obtaining an initial global track 400 of the vehicle.

In another specific embodiment of the present application, a global velocity planning method is described, and specifically, see fig. 3. The global speed planning method comprises a punctual arrival speed planning part and a global speed rolling planning part in the vehicle running process. And the on-time arrival speed planning part can meet the total running time requirement, the road section speed limit requirement and the vehicle running comfort requirement to obtain an initial global track. If the vehicle strictly follows the initial global track, the destination can be reached on time. And the global speed rolling planning part considers that the influence of dynamic traffic flow in the running process of the vehicle can cause the vehicle to possibly delay or reach a certain target path point in advance in the process of executing the initial global track. If the difference value between the actual running time of the vehicle reaching the target path point and the path point planning running time of the target path point is larger than the preset threshold value, the global speed planning system executes a speed planning algorithm according to the residual total running time requirement, the residual global path and the like in a rolling mode, so that the global track of the vehicle is dynamically adjusted, the corrected global track is obtained, and the vehicle is guaranteed to reach the destination by the waypoint. The method comprises the following specific steps:

s1, receiving total operation time T sent by a scheduling system _d Departure time T _s Receiving a global driving path and road section speed limit information given by a global path planning system;

s2, adopting a speed planning algorithm, and setting the total operation time length T _d Departure time T _s Obtaining an initial global track by the global path and the road section speed limit information, and controlling the vehicle to start executing the initial global track;

s3, calculating the actual running time T of the vehicle reaching the target path point _v (k) The path point planning operation time length T corresponding to the target path point _d (k) Difference value T of _v (k)-T _d (k) .1. The If the difference T _v (k)-T _d (k) Is greater than a predetermined threshold value deltat _max (i.e. | T) _v (k)-T _d (k)|＞ΔT _max ) Then calculate the remaining total running time T _d,r ＝T _d -T _v (k) And intercepting the remaining global path. And calling the speed planning algorithm again to obtain the corrected global track of the rest global path, and starting to execute the corrected global track by the vehicle. If the difference T _v (k)-T _d (k) Is less than or equal to a predetermined threshold value deltat _max (i.e. | T) _v (k)-T _d (k)|≤ΔT _max ) Controlling the vehicle to continue executing the initial global track;

and S4, determining whether the vehicle reaches the destination. If the vehicle accurately arrives at the destination, ending the program; otherwise, the procedure returns to step S3.

It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.

In an embodiment of the present application, a speed planning algorithm is adopted to perform speed planning on the received total running time, departure time, global driving path and road section speed limit information of the vehicle, so as to obtain an initial global track of the vehicle, including: dividing the global travel path according to a predetermined rule to obtain a plurality of path segments, wherein the predetermined rule is determined according to the forward and backward directions of the vehicle; acquiring at least two key points on each path segment, wherein the key point is one of the path points; preprocessing at least two key points on each path segment to obtain target key points on each path segment; and performing trapezoidal speed planning according to the target key points, the total operation time, the departure time, the global driving path and the road section speed limit information on each path segment to obtain the initial global track of the vehicle. In the embodiment, the key points on each path segment are preprocessed according to the speed limit information of the road segment, so that keys which cause planning failure are removed, the obtained target key points can be ensured to be successfully subjected to overall speed planning, and then the target key points on each path segment are adopted, the total operation time, the starting time, the overall driving path and the speed limit information of the road segment are subjected to trapezoidal speed planning to obtain an initial overall track, so that the obtained initial overall track is ensured to be reasonable, and the requirement of arriving at a destination on time can be further met.

Specifically, the predetermined rule is a rule determined according to the forward and backward movement of the vehicle. And the forward and backward movement of the vehicle may be determined according to the direction of the steering wheel of the vehicle.

In practical applications, there may be more than two key points in each path segment, and each two key points may determine a single speed-limiting path segment. For some path segments that cannot meet the requirement of the right-side velocity (i.e., the third velocity) of the second critical point through deceleration, the path segments cannot obtain a feasible planning velocity. Therefore, in another embodiment of the present application, the preprocessing at least two key points on each of the path segments to obtain target key points on each of the path segments includes: determining a first speed and a second speed of a first key point and a third speed of a second key point for continuous first key points and second key points on a target path segment, wherein the target path segment is one of a plurality of path segments, and the first key point and the second key point are both the key points; calculating a first distance from the second speed to the third speed based on a maximum deceleration when the first speed is greater than the second speed and the second speed is greater than the third speed, and determining the target key point on the target route segment based on at least the first distance; and under the condition that the second speed is greater than the first speed and the first speed is greater than the third speed, calculating a second distance from the first speed to the third speed based on the maximum deceleration, and determining the target key point on the target path segment at least according to the second distance, so that the vehicle can be successfully subjected to global speed planning according to the determined target key point.

In particular, the first velocity of the first keypoint may be the left velocity v of the first keypoint ₀ . The second velocity of the first keypoint may be the right velocity v of the first keypoint ₁ . The third speed of the second key point is the right speed v of the second key point ₂ 。

In another embodiment of the present application, determining the target keypoints on the target path segment according to at least the first distance includes: calculating the distance between the first key point and the second key point to obtain a target key distance; determining the second keypoint as the target keypoint and the fourth speed of the second keypoint as the first speed and deleting the first keypoint when the first distance is greater than the target keypoint distance; and determining the first key point and the second key point as the target key point when the first distance is less than or equal to the target key distance. In this embodiment, when the first distance is greater than the target critical distance, it indicates that the requirement of the third speed (i.e. the right speed) of the second critical point cannot be achieved even according to the maximum deceleration, so the fourth speed (i.e. the left speed) of the second critical point can be determined as the first speed (i.e. the left speed) of the first critical point, which ensures that the vehicle can be successfully subjected to the global speed planning according to the target critical point.

In order to further ensure that the vehicle can be successfully subjected to global speed planning according to the target key points. In another embodiment of the present application, determining the target keypoints on the target path segment according to at least the second distance includes: calculating the distance between the first key point and the second key point to obtain a target key distance; determining the second keypoint as the target keypoint and the fourth speed of the second keypoint as the first speed and deleting the first keypoint when the second distance is greater than the target keypoint distance; and determining the first key point and the second key point as the target key point when the second distance is less than or equal to the target key distance.

In practical application, v is assumed to be two key points, namely a first key point and a second key point, on the target path segment ₀ Left side velocity, v, of the first keypoint ₁ Velocity, v, to the right of the first keypoint ₂ The velocity to the right of the second keypoint.

If v is ₀ ＞v ₁ And v is ₁ ＞v ₂ According to the maximum deceleration a _min From v ₁ Is decelerated to v ₂ First distance S _min1 The expression of (a) is:

if the first distance S _min1 If the distance is larger than the target key distance (the distance between the first key point and the second key point), the second key point is determined as the target key point, and the fourth speed (left speed) of the second key point is assigned as v ₀ And deleting the first key point; otherwise, no processing is performed (i.e., the first keypoint and the second keypoint are determined as target keypoints).

If v is ₁ ＞v ₀ And v is ₀ ＞v ₂ According to the maximum deceleration a _min From v ₀ Is decelerated to v ₂ Second distance S _min2 The expression of (c) is:

if the second distance S _min2 If the distance is greater than the target key distance (the distance between the first key point and the second key point), the second key point is determined as the target key point, and the fourth speed (left speed) of the second key point is assigned as v ₀ And deleting the first key point; otherwise, no processing is performed (i.e., the first keypoint and the second keypoint are determined as target keypoints).

In an embodiment of the present application, performing trapezoidal speed planning according to the target key point, the total running time, the departure time, the global driving path, and the road section speed limit information on each of the path segments to obtain the initial global trajectory of the vehicle includes: a second planning step, wherein the trapezoidal speed planning is carried out on the target key points on each path segment at least according to the road section speed limit information to obtain a global speed curve of the global driving path; a first determination step, wherein a global track duration is determined according to the global speed curve and the global driving path; and a second determining step, namely determining the initial global track according to the global track time length, the total running time length and the departure time. In the embodiment, the initial global track is determined according to the global track time length, the total running time length and the departure time, so that the follow-up vehicle can be ensured to run according to the initial global track and arrive at the destination on time.

In particular, the specific method for determining the global trajectory duration according to the global speed curve and the global driving path is not limited in this application, and may be any feasible method in the prior art.

In another embodiment of the present application, determining the initial global trajectory according to the global trajectory duration, the total operation duration, and the departure time includes: under the condition that the overall track time length is longer than the total operation time length, generating first planning failure information and sending the first planning failure information to a scheduling system; and under the condition that the overall track time length is less than or equal to the total running time length, calculating a difference value between the overall track time length and the total running time length to obtain a target time length difference value, and determining the initial overall track of the vehicle at least according to the target time length difference value and the departure time. In this embodiment, when the overall track running duration is longer than the total running duration, it indicates that the vehicle cannot arrive at the destination on time even if the vehicle runs at the speed-limited speed of the road segment, that is, the overall speed planning fails, and the first planning failure information may be sent to the scheduling system, so that the scheduling system may make a decision of the total running duration again. When the global track time length is less than or equal to the total running time length, the initial global track is determined according to the target time length difference, so that the vehicle can be further ensured to arrive at the destination on time.

In order to further ensure that the vehicle can arrive at the destination on time, in another embodiment of the present application, the determining the initial global trajectory of the vehicle according to at least the target time length difference and the departure time includes: adding the speed information and the time information to each path point according to the global speed curve and the departure time under the condition that the target time length difference is less than or equal to a time length difference threshold value to obtain the initial global track of the vehicle; and under the condition that the target time length difference is greater than the time length difference threshold, correcting the speed limit information of the road section according to the target time length difference, and executing the second planning step, the first determining step and the second determining step at least once until the target time length difference is less than or equal to the time length difference threshold.

Specifically, the size of the time length difference threshold is not limited in the present application, and may be flexibly adjusted according to the driving condition of the vehicle.

In a specific embodiment, the present application relates to a method for determining an initial global trajectory of a vehicle, which is specifically shown in fig. 4. The specific steps for determining the initial global trajectory are as follows:

s1, acquiring total operation time length T _d Departure time T _s Global driving path and path speed limit information v _max And the maximum acceleration a of the vehicle meeting the comfort requirement _max And maximum deceleration a _min ；

And S2, dividing the global driving path according to a preset rule (namely a rule for switching forward or backward) to obtain a plurality of path segments. And then respectively carrying out speed planning on each path segment. In the process of speed planning of each path segment, except that the initial speed of the first path segment is the current running speed of the vehicle, the initial speeds and the final speeds of the rest path segments are set to be 0;

and S3, for each path segment, acquiring key points according to the road section speed limit information of each path segment, wherein the number of the key points of each path segment is more than or equal to 2. The information of each key point includes the left speed (or the speed that the vehicle can actually reach) of the key point, the right speed limit, and the serial number in the global path (since the key point is one of the plurality of path points, the serial number of the key point is the serial number of the corresponding path point). Because a single speed-limiting path segment is arranged between two adjacent key points, the starting speed, the ending speed and the speed-limiting value of the path segment are respectively determined by the left speed of the first key point, the right speed of the second key point and the right speed of the first key point;

s4, preprocessing the key points acquired by each path segment to obtain target key points on each path segment, wherein the purpose of preprocessing is to eliminate key points which may cause planning failure;

and s5, performing trapezoidal speed planning according to the target key points, the total operation time, the overall driving path and the road section speed limit information on each path segment to obtain an overall speed curve. And determining the global track duration according to the global speed curve and the global driving path. If the global track duration is longer than the total operation time, generating first planning failure information, and sending the first planning failure information to the scheduling system, so that the scheduling system can make a decision on the total operation duration again; when the overall track time length is less than or equal to the total operation time length, calculating a difference value between the overall track time length and the total operation time length to obtain a target time length difference value;

and S6, under the condition that the target time length difference is larger than the time length difference threshold, correcting the corresponding road section speed limiting information according to the target time length difference, and executing the step S1 again after the corresponding road section speed limiting information is corrected until the target time length difference is smaller than or equal to the time length difference threshold, so as to obtain an initial global track. And under the condition that the target time length difference is smaller than or equal to the time length difference threshold, adding speed information for each path point according to the global speed curve to obtain the initial global track of the vehicle.

In another embodiment of the present application, the obtaining a global speed curve of the global driving path by performing the trapezoidal speed planning on the target key points on each of the path segments according to at least the road section speed limit information includes: a third planning step, which is to perform kinematic speed planning at least based on the speed information of the target key points on each path segment and the corresponding speed limit information of the road section to obtain a plurality of initial path speed curves, wherein one path segment corresponds to one initial path speed curve; optimizing, namely optimizing each initial path speed curve to obtain an initial global speed curve; and an iteration step, namely performing iteration processing on the initial global velocity curve to obtain the global velocity curve. In the embodiment, the obtained multiple initial path speed curves are optimized, so that the obtained initial global speed curve can meet the requirement on the smoothness of the speed curve, and the comfort is better. And then, carrying out iterative processing on the initial global speed curve, thereby ensuring that the obtained global speed curve can meet the demand of on-time arrival.

A particular one of the present applicationIn an embodiment, before performing a kinematic speed planning based on at least speed information of a target key point on each path segment and corresponding road segment speed limit information to obtain a plurality of initial path speed curves, it may be further determined whether the planning of each path segment can be completed. The specific process comprises the following steps: two target key points (namely a first target key point and a second target key point) of a certain path segment are selected, and v is assumed ₀ Left side velocity, v, of the first target keypoint ₁ Velocity, v, to the right of the first target keypoint ₂ The velocity to the right of the second target keypoint. If v is ₁ Not equal to the left speed of the second target key point, the target key points are set incorrectly and planning fails because two different maximum speeds occur between the two target key points. If v is ₀ ＞v ₁ +0.05, then due to v ₀ The right vehicle speed or the actual initial vehicle speed after planning for the previous path segment cannot be greater than the maximum vehicle speed of the path segment, so that the planning fails. If neither of the above conditions is met, the kinematic velocity planning is started.

In another specific embodiment of the present application, the kinematic velocity plan is velocity information of a target key point corresponding to a certain path segment (the velocity information is a left-side velocity v of a first target key point) ₀ Velocity v on the right of the first target keypoint ₁ And the velocity v to the right of the second target keypoint ₂ ) Maximum acceleration a _max And maximum deceleration a _min For input, an initial path velocity profile for the path segment is output. The following is presented in sub-cases:

case 1:

when | v ₀ -v ₁ < 0.01 and v ₂ ≥v ₁ When the path length corresponding to the first target key point is set as S ₀ The path length corresponding to the second target key point is S ₂ In this case, v continues to be maintained ₁ The operation requirement can be met, at the moment, sparse speed path points are generated between two target key points, and v is calculated ₁ The initial path velocity curve obtained as the velocity of this path segment is shown in fig. 5 below.

Case 2:

when | v ₀ -v ₁ < 0.01 and v ₂ ＜v ₁ When the path length corresponding to the first target key point is set as S ₀ The path length corresponding to the second target key point is S ₂ . The distance between two target key points is S ₂ -S ₀ According to the maximum deceleration a _max Can calculate the deceleration to v ₂ Has a shortest distance of S _mind Comprises the following steps:

if S ₂ -S ₀ ＜S _mind If the shortest deceleration distance is not met, the planning fails; if S ₂ -S ₀ ＞S _mind V is to be ₂ As the planned final speed, the vehicle holds v ₁ Run to S ₁ Start to decelerate at the time S ₁ ＝S ₂ -S _mind Then slow down to v ₂ In the process, if s is the length of the path where the vehicle is located at present, the expression for generating sparse speed path points is

Then, the initial path speed curve shown in fig. 6 is obtained according to the first target key point, the second target key point, and the generated sparse speed path points.

Case 3:

case 3 contains two special cases (i) and (ii).

At v ₀ ＜v ₁ And v is ₂ ≥v ₁ When the path length corresponding to the first target key point is set as S ₁ The path length corresponding to the second target key point is S ₃ And S is the length of the current path of the vehicle, the distance between two target key points is S ₃ -S ₁ According to the maximum acceleration a _max The acceleration to v can be calculated ₂ Of (2)Short distance of S _mind Comprises the following steps:

(i) If S ₃ -S ₁ ＞S _mind At this time v ₁ Namely the planned final speed, the vehicle is set to run to S ₂ Start accelerating at the time of treatment, S ₂ ＝S ₃ -S _mind At this time, the expression for generating sparse velocity path points between two target key points is:

then, the initial path speed curve shown in fig. 7 is obtained according to the first target key point, the second target key point, and the generated sparse speed path points.

(ii) If S ₃ -S ₁ ＜S _mind There is a constant acceleration between the two target key points, at which the planned final velocity v is _last The expression of (c) is:

and the expression for generating sparse velocity path points between two target keypoints is:

then, the initial path speed curve shown in fig. 8 is obtained according to the first target key point, the second target key point, and the generated sparse speed path points.

Case 4:

case 4 includes two special cases (i) and (ii).

At v is ₀ ＜v ₁ And v is ₂ ＜v ₁ And v is ₂ ≤v ₀ When the path length corresponding to the first target key point is set as S ₀ The path length corresponding to the second target key point is S ₃ And S is the length of the current path of the vehicle, the distance S between two key points ₃ -S ₀ According to the maximum acceleration a _max The acceleration to v can be calculated ₁ Has a shortest distance of S _acc Comprises the following steps:

according to maximum deceleration a _min Can calculate the deceleration to v ₂ Has a shortest distance of S _dec ：

(i) If (S) _acc +S _dec )＜(S ₃ -S ₀ ) There are path segments that are traveling at a constant speed. At acceleration to v ₁ The expression for generating sparse velocity path points in the process is as follows:

v is constant velocity process ₁ Running at a constant speed; at deceleration to v ₂ The expression for generating sparse velocity path points in the process of (3) is:

then, the initial path velocity curve shown in fig. 9 is obtained according to the first target key point, the second target key point, and the generated sparse velocity path points.

(ii) If (S) _acc +S _dec )≥(S ₃ -S ₀ ) There is no path segment for uniform travel. Let S' be the path length corresponding to the start of deceleration, anAnd the maximum speed that can be accelerated at this time is set as v ', the expression of v' is:

let the acceleration distance be S ₁ ，S ₁ ＝S′-S ₀ Then S is ₁ The expression of (c) is:

the expression for generating sparse velocity path points during acceleration to v' is:

the expression of the sparse speed path points generated in the deceleration process is as follows:

then, the initial path speed curve shown in fig. 10 is obtained according to the first target key point, the second target key point, and the generated sparse speed path points.

Case 5:

case 5 contains three special cases (i), (ii), (iii)

At v ₀ ＜v ₁ And v is ₂ ＜v ₁ And v is ₂ ＞v ₀ When the path length corresponding to the first target key point is set as S ₀ The path length corresponding to the second target key point is S ₃ And S is the length of the current path of the vehicle, the distance between two target key points is (S) ₃ -S ₀ ) According to the maximum acceleration a _max Can calculate from v ₀ Accelerate to v ₁ Has a shortest distance of S _acc Comprises the following steps:

according to the maximum deceleration a _min Can calculate from v ₁ Is decelerated to v ₂ Has a shortest distance of S _dec Comprises the following steps:

then according to the maximum acceleration a _max Can calculate from v ₀ Accelerate to v ₂ The shortest distance S _min Comprises the following steps:

(i) If (S) _acc +S _dec )＜(S ₃ -S ₀ ) Then there is a path segment that is traveling at a constant speed in this case. Is accelerated to v ₁ The expression for generating sparse velocity path points in the process is as follows:

v is constant velocity process ₁ Running at a constant speed; is decelerated to v ₂ The expression for generating sparse velocity path points in the process of (3) is:

the initial path velocity curve shown in fig. 11 is obtained according to the first target keypoint, the second target keypoint, and the generated sparse velocity path point.

(ii) If (S) _acc +S _dec )≥(S ₃ -S ₀ ) In this case, there is no route section that is traveling at a constant speed. Let S' be the path length corresponding to the start of deceleration, and can now do soThe maximum speed to which acceleration is made is set to v ', and the expression for v' is:

setting the acceleration distance S ₁ ，S ₁ ＝S′-S ₀ Then S is ₁ The expression of (c) is:

the expression for generating sparse speed path points in the deceleration process is as follows:

the initial path velocity curve shown in fig. 12 is obtained according to the first target keypoints, the second target keypoints, and the generated sparse velocity path points.

(iii) If S is _min ≥(S ₃ -S ₀ ) Then the acceleration is always in this case. The planned final velocity v at this time _last The expression of (a) is:

the initial path velocity curve shown in fig. 13 is obtained according to the first target keypoints, the second target keypoints, and the generated sparse velocity path points.

In an embodiment of the present application, optimizing each of the initial path speed curves to obtain an initial global speed curve includes: constructing an optimization function at least according to the speed information of two adjacent path points to obtain a plurality of optimization objective functions; and (3) performing optimization solution on a plurality of the optimization objective functions by adopting a gradient descent method to obtain the initial global velocity curve.

In practical application, each initial global speed curve obtained by using the kinematic speed planning method can meet the requirements of the speed limit of the road section of the path segment and the constraints of the maximum acceleration and/or the maximum deceleration. However, the resulting speed variation of the initial global speed profile is not smooth due to the maximum acceleration and/or the maximum deceleration, which has an influence on the driving comfort. In order to improve the driving comfort, in a specific embodiment of the present application, a gradient descent method is adopted to optimize each initial path speed curve. Specifically, an optimal objective function is established and an optimal solution is solved by adopting a gradient descent method, so that a smooth initial global speed curve between path segments is generated.

(1) Establishing an optimized objective function

In order to achieve the purpose of smooth change of speed between each path segment, in a specific embodiment, an optimization objective function is established according to the speed of each adjacent path point in the path segment:

wherein the function f ₁ (v) Function f reflecting the magnitude of the velocity change of adjacent path points ₂ (v) And applying certain constraint on the speed before and after optimization, so that the optimized range of the speed curve is in the adjacent area of the original speed curve. Δ v _i ＝v _i -v _i-1 Is the speed change value, Δ v, of the waypoint i and the adjacent rear waypoint _i+1 ＝v _i+1 -v _i Is the speed variation value, v, of the path point i and the adjacent preceding path point _i，0 The speed before optimization of the path point i, i.e. the speed obtained by the kinematics speed planning, is shown.

(2) Gradient descent method for solving optimal solution

Velocity v is coupled by an objective function for path point i _i Calculating a partial derivative, and calculating a gradient value at the path point, wherein the gradient direction is the direction with the fastest function change, and the target function pair v at the path point i _i The gradient is calculated as:

the velocity after smoothing in the gradient direction is expressed as:

where δ denotes the iteration step in the gradient direction.

In order to further ensure that the vehicle can arrive at the destination on time when traveling along the initial global trajectory, in another embodiment of the present application, the iterative processing is performed on the initial global speed curve to obtain the global speed curve, which includes: determining the actual path running time of an alternative path point according to the initial global speed curve, wherein the alternative path point is one of the path points; calculating a difference value between the actual path operation time length and a planned path operation time length to obtain a path time length difference value, wherein the planned path operation time length is the operation time length of the planned alternative path point; and under the condition that the difference value of the path time lengths is larger than the preset threshold, correcting the road section speed limit information to which the alternative path point belongs according to a corrected speed limit speed to obtain corrected road section speed limit information, and executing the third planning step, the optimizing step and the iteration step at least once until the difference value of the global track time length of the global speed curve and the total operation time length meets a preset range, wherein the corrected speed limit speed is determined at least according to an initial corrected speed limit speed, the actual path operation time length and the planned path operation time length.

In the actual operation process, a smooth initial global speed curve meeting the road section speed limit requirement and the maximum acceleration and/or maximum deceleration constraint of the path segment can be obtained through the trapezoidal speed planning. But the path speed limit information corresponding to the path segment is used as the highest speed upper limit to obtain the global track duration T consumed by the initial global speed curve _v (k) Will be much less than the predetermined threshold T _d (k) I.e., the vehicle will reach an alternative waypoint or destination in advance, is not able to meet the constraints of quasi-point travel. In a specific embodiment of the present application, a global velocity curve satisfying the operating time constraint is planned in a combined iterative manner by a trapezoidal velocity planning and a gradient descent method, and a specific flowchart can be shown in fig. 4.

Specifically, as shown in fig. 14, in the initial global speed curve 500 smoothed by the gradient descent method, the calculation formula of the actual path running time corresponding to the candidate path point is as follows:

wherein s is _i 、v _i Respectively, the path length and speed corresponding to the path point i.

Specifically, the actual path running time T when the alternative path point is available _v (k) With a corresponding planned path run length T _d (k) Is greater than a predetermined threshold value deltat _max Then, the speed limit information v of the road section of the corresponding path segment is subjected to speed limit information v through the initially given corrected speed limit speed delta v _max Correcting to obtain corrected speed limiting information, and calculating corrected speed limiting information v _max The expression of (a) is:

n is the total number of waypoints. And performing trapezoidal speed planning again according to the speed limit information of the corrected road section to obtain the actual path operation time T 'corresponding to the iterated alternative path point' _v (k) In that respect Again according to T' _v (k) And T _d (k) The difference of (d) is iterated over Δ v. Wherein, the iteration step expression of Δ v is:

after obtaining the speed limit information of the corrected section again, the speed planning may be performed again by using the trapezoidal speed planning until the difference between the overall track time length consumed by the planned overall speed curve 600 and the total operation time length satisfies the preset range, and the overall speed curve 600 satisfying the quasi-point operation is obtained as shown in fig. 14.

The embodiment of the present application further provides a global velocity planning apparatus, and it should be noted that the global velocity planning apparatus according to the embodiment of the present application may be used to execute the method for global velocity planning provided by the embodiment of the present application. The global speed planning apparatus provided in the embodiments of the present application is described below.

Fig. 15 is a schematic diagram of a global velocity planning apparatus according to an embodiment of the present application. As shown in fig. 15, the global velocity planning apparatus includes:

a planning unit 10, configured to perform speed planning on the received total running time of the vehicle, the departure time, the global driving path, and the road segment speed limit information by using a speed planning algorithm to obtain an initial global track, where the initial global track is used to represent speed information and time information of each path point, and the path points are points on the global driving path divided at predetermined intervals;

an obtaining unit 20, configured to perform an obtaining step to control the vehicle to travel according to the initial global trajectory, so as to obtain an actual running duration of the vehicle reaching a target waypoint, where the target waypoint is one of the waypoints;

a first comparing unit 30, configured to perform the obtaining step at least once when a difference between the actual operation duration and a route point planning duration is smaller than or equal to a predetermined threshold, until the vehicle reaches a destination, where the route point planning duration is an operation duration of the target route point planned for the first time;

and a second comparing unit 40, configured to calculate a remaining total operating time and a remaining global path in a second comparing step, when a difference between the actual operating time and the planned time of the route point is greater than the predetermined threshold, and execute the first planning step and the obtaining step at least once in sequence until the vehicle reaches the destination.

In the global speed planning device, the planning unit is used for carrying out speed planning on the received total running duration, the departure time, the global driving path and the road section speed limit information of the vehicle based on a speed planning algorithm to obtain an initial global track; the acquiring unit is used for acquiring the actual running time of the vehicle reaching the target path point in the process that the vehicle runs along the initial global track; the first comparison unit is used for calculating the difference between the actual running time of the vehicle at the target path point and the planned time of the path point, and under the condition that the difference is less than or equal to a preset threshold value, the vehicle can arrive at the destination on time, so that the vehicle can be continuously controlled to run in the initial global track until the vehicle arrives at the destination; and the second comparison unit is used for indicating that the vehicle cannot arrive at the target low on time under the condition that the difference value is larger than the preset threshold value, calculating the residual total running time length and the residual global path of the vehicle, and then carrying out speed planning again according to the residual total running time length, the residual global path, the departure time and the road section speed limit information so as to enable the vehicle to arrive at the destination on time. Compared with the scheme of obtaining the global track of the vehicle through dynamic programming or heuristic optimization method in the prior art, the global speed planning device only needs to adopt a speed planning algorithm to carry out speed planning on the total running time, the starting time, the global running path and the road section speed limit information of the vehicle to obtain the initial global track of the vehicle, so that the calculation amount for determining the initial global track is less, the global speed planning device does not need to be carried on a vehicle-scale high-calculation-force platform, and the global speed planning method is lower in cost. In addition, the global speed planning device dynamically adjusts the operation strategy of the vehicle under the influence of dynamic traffic flow by considering the on-time arrival requirement of the vehicle, so that the vehicle can arrive at the destination on time, and the problem that the global track of the vehicle is difficult to determine through less calculation amount while considering the on-time arrival requirement of the vehicle in the prior art is solved.

In the actual application process, the road section speed limit information can be adjusted in real time along with different road sections. The total operation time period is a total operation time period required for the vehicle to reach the destination from the starting point. The global driving path is decided by a global path planning system. The global travel path is only a path traveled by the vehicle, and does not have speed information and time information. The initial global track obtained in the application is that speed information and time information corresponding to each path point are added on the basis of the global driving path. In addition, in the present application, the time information in the initial global trajectory may be arrival times at which the vehicle arrives at the respective waypoints.

In a specific embodiment of the present application, as shown in fig. 2, the global velocity planning method of the present application is applied in a global velocity planning system 300. The scheduling system 100 implements the decision of the destination, the departure time, and the total operating time of the vehicle, and the scheduling system 100 sends the destination obtained by the decision to the global path planning system 200. The global path planning system 200 plans a global driving path for the vehicle to reach the destination according to the destination, the starting point positioning information and the high-precision map information, and obtains the road section speed limit information along the global driving path, and the global path planning system 200 sends the global driving path and the road section speed limit information to the global speed planning system 300. For the global speed planning system 300, the total operation time length and the departure time transmitted by the scheduling system 100 are received, and the global travel path and the section speed limit information transmitted by the global path planning system 200 are received. The global speed planning system 300 performs speed planning on the received total running time, departure time, global driving path and road section speed limit information by using a speed planning algorithm to obtain a speed curve and a time sequence of the vehicle along the global path, thereby obtaining an initial global track 400 of the vehicle.

In another specific embodiment of the present application, a global velocity planning method is described, and specifically, see fig. 3. The global speed planning method comprises a punctual arrival speed planning part and a global speed rolling planning part in the vehicle running process. And the on-time arrival speed planning part can meet the total running time requirement, the road section speed limit requirement and the vehicle running comfort requirement to obtain an initial global track. If the vehicle strictly follows the initial global track, the destination can be reached on time. And the global speed rolling planning part considers that the influence of dynamic traffic flow in the running process of the vehicle can cause the vehicle to possibly delay or reach a certain target path point in advance in the process of executing the initial global track. If the difference value between the actual running time of the vehicle reaching the target path point and the path point planning running time of the target path point is larger than the preset threshold value, the global speed planning system can execute a speed planning algorithm according to the residual total running time requirement, the residual global path and the like in a rolling mode, so that the global track of the vehicle is dynamically adjusted, the corrected global track is obtained, and the vehicle is guaranteed to arrive at the destination through the alignment point. The method comprises the following specific steps:

s3, calculating the target path point reached by the vehicleActual running time length T _v (k) The path point planning operation time length T corresponding to the target path point _d (k) Difference value T of _v (k)-T _d (k) In that respect If the difference value T _v (k)-T _d (k) Is greater than a predetermined threshold value deltat _max (i.e. | T) _v (k)-T _d (k)|＞ΔT _max ) Then calculate the remaining total running time T _d,r ＝T _d -T _v (k) And intercepting the remaining global path. And calling the speed planning algorithm again to obtain the corrected global track of the rest global path, and starting to execute the corrected global track by the vehicle. If the difference value T _v (k)-T _d (k) Is less than or equal to a predetermined threshold value deltat _max (i.e. | T) _v (k)-T _d (k)|≤ΔT _max ) Controlling the vehicle to continue executing the initial global track;

In an embodiment of the present application, the planning unit includes a dividing module, an obtaining module, a preprocessing module, and a planning module, where the dividing module is configured to divide the global driving path according to a predetermined rule to obtain a plurality of path segments, and the predetermined rule is determined according to forward and backward movements of the vehicle; the acquisition module is configured to acquire at least two key points on each of the path segments, where the key point is one of the path points; the preprocessing module is used for preprocessing at least two key points on each path segment to obtain target key points on each path segment; the planning module is configured to perform trapezoidal speed planning according to the target key point, the total operation duration, the departure time, the global travel path, and the road segment speed limit information on each of the path segments to obtain the initial global trajectory of the vehicle. In the embodiment, the key points on each path segment are preprocessed according to the speed limit information of the road segment, so that keys which cause planning failure are removed, the obtained target key points can be ensured to be successfully subjected to overall speed planning, and then the target key points on each path segment are adopted, the total operation time, the starting time, the overall driving path and the speed limit information of the road segment are subjected to trapezoidal speed planning to obtain an initial overall track, so that the obtained initial overall track is ensured to be reasonable, and the requirement of arriving at a destination on time can be further met.

Specifically, the above-described predetermined rule is a rule determined in accordance with the forward and backward movement of the vehicle. And the forward and backward movement of the vehicle may be determined according to the direction of the steering wheel of the vehicle.

In practical applications, there may be more than two key points in each path segment, and each two key points may determine a single speed-limiting path segment. For some required path segments that cannot reach the right speed (i.e., the third speed) of the second critical point by deceleration, the path segments cannot get a feasible planning speed. Therefore, in another embodiment of the present application, the preprocessing module includes a first determining sub-module, a first calculating sub-module, and a second calculating sub-module, where the first determining sub-module is configured to determine, for consecutive first and second keypoints on a target path segment, a first speed and a second speed of the first keypoint, and a third speed of the second keypoint, where the target path segment is one of a plurality of the path segments, and the first keypoint and the second keypoint are both the keypoints; the first calculation submodule is configured to calculate a first distance from the second speed to the third speed based on a maximum deceleration when the first speed is greater than the second speed and the second speed is greater than the third speed, and determine the target keypoint on the target route segment based on at least the first distance; the second calculating submodule is configured to calculate a second distance from the first speed to the third speed based on the maximum deceleration when the second speed is greater than the first speed and the first speed is greater than the third speed, and determine the target keypoints on the target path segment according to at least the second distance, so that it is ensured that the vehicle can be successfully subjected to global speed planning according to the determined target keypoints.

In another embodiment of the present application, the first calculating submodule includes a third calculating submodule, a second determining submodule, and a third determining submodule, where the third calculating submodule is configured to calculate a distance between the first keypoint and the second keypoint to obtain a target keypoint distance; the second determining submodule is configured to determine the second keypoint as the target keypoint, determine a fourth speed of the second keypoint as the first speed, and delete the first keypoint, if the first distance is greater than the target keypoint; the third determining submodule is configured to determine both the first keypoint and the second keypoint as the target keypoint when the first distance is less than or equal to the target keypoint. In this embodiment, when the first distance is greater than the target critical distance, it indicates that the requirement of the third speed (i.e. the right speed) of the second critical point cannot be achieved even according to the maximum deceleration, so the fourth speed (i.e. the left speed) of the second critical point can be determined as the first speed (i.e. the left speed) of the first critical point, which ensures that the vehicle can be successfully subjected to the global speed planning according to the target critical point.

To further ensure that the vehicle can be successfully globally velocity-programmed based on the target key points. In yet another embodiment of the present application, the second calculating submodule includes a fourth calculating submodule, a fourth determining submodule, and a fifth determining submodule, where the fourth calculating submodule is configured to calculate a distance between the first keypoint and the second keypoint to obtain a target keypoint distance; the fourth determining submodule is configured to determine the second keypoint as the target keypoint, determine a fourth speed of the second keypoint as the first speed, and delete the first keypoint, when the second distance is greater than the target keypoint distance; the fifth determining submodule is configured to determine both the first keypoint and the second keypoint as the target keypoint when the second distance is less than or equal to the target keypoint.

In practical application, v is assumed to be two consecutive key points on the target path segment, namely the first key point and the second key point ₀ Left side velocity, v, of the first keypoint ₁ Velocity, v, to the right of the first keypoint ₂ The velocity to the right of the second keypoint.

If v is ₁ ＞v ₀ And v is ₀ ＞v ₂ According to the maximum deceleration a _min From v ₀ Is decelerated to v ₂ Second distance S _min2 The expression of (a) is:

if the second distance S _min2 Greater than the target critical distance (first and second keypoints)Distance between keypoints), the second keypoint is determined to be the target keypoint, and the fourth speed (left speed) of the second keypoint is assigned as v ₀ Deleting the first key point; otherwise, no processing is performed (i.e., the first keypoint and the second keypoint are determined as target keypoints).

In an embodiment of the application, the planning module includes a first planning sub-module, a sixth determining sub-module, and a seventh determining sub-module, where the first planning sub-module is used in a second planning step, and performs the trapezoidal speed planning on the target key point on each path segment according to at least the road segment speed limit information to obtain a global speed curve of the global driving path; the sixth determining submodule is used for the first determining step, and determining the global track duration according to the global speed curve and the global driving path; the seventh determining submodule is configured to perform a second determining step, and determine the initial global trajectory according to the global trajectory duration, the total operation duration, and the departure time. In the embodiment, the initial global track is determined according to the global track time length, the total running time length and the departure time, so that the follow-up vehicle can be ensured to run according to the initial global track and arrive at the destination on time.

In another embodiment of the application, the seventh determining submodule includes a first generating submodule and a fifth calculating submodule, where the first generating submodule is configured to generate first planning failure information and send the first planning failure information to a scheduling system when the global trajectory duration is greater than the total operation duration; the fifth calculating submodule is configured to calculate a difference between the global trajectory duration and the total operation duration to obtain a target duration difference when the global trajectory duration is less than or equal to the total operation duration, and determine the initial global trajectory of the vehicle according to at least the target duration difference and the departure time. In this embodiment, when the global track running duration is longer than the total running duration, it indicates that the vehicle cannot arrive at the destination on time even if the vehicle runs at the speed-limited speed of the road segment, that is, the global speed planning fails, and the first planning failure information may be sent to the scheduling system, so that the scheduling system may make a decision of the total running duration again. When the global track time length is less than or equal to the total running time length, the initial global track is determined according to the target time length difference, so that the vehicle can be further ensured to arrive at the destination on time.

In order to further ensure that the vehicle can arrive at the destination relatively timely, in another embodiment of the present application, the fifth computation submodule includes a second generation submodule and a first modification submodule, where the second generation submodule is configured to, when the target time length difference is less than or equal to a time length difference threshold, add the speed information and the time information to each of the path points according to the global speed curve and the departure time, so as to obtain the initial global trajectory of the vehicle; the first modification submodule is configured to modify the speed limit information of the road segment according to the target duration difference when the target duration difference is greater than the duration difference threshold, and execute the second planning step, the first determining step, and the second determining step at least once until the target duration difference is less than or equal to the duration difference threshold.

and s5, performing trapezoidal speed planning according to the target key points, the total operation time, the overall driving path and the road section speed limit information on each path segment to obtain an overall speed curve. And determining the overall track duration according to the overall speed curve and the overall driving path. If the global track duration is longer than the total operation time, generating first planning failure information, and sending the first planning failure information to the scheduling system, so that the scheduling system can make a decision on the total operation duration again; when the overall track time length is less than or equal to the total operation time length, calculating the difference between the overall track time length and the total operation time length to obtain a target time length difference;

In yet another embodiment of the present application, the first planning submodule includes a second planning submodule, an optimization submodule, and an iterative processing submodule, where the second planning submodule is used in a third planning step, and performs a kinematic speed planning at least based on speed information of the target key point and corresponding speed limit information of the road segment on each of the path segments to obtain a plurality of initial path speed curves, where one of the path segments corresponds to one of the initial path speed curves; the optimization submodule is used for optimizing steps, and optimizing each initial path speed curve to obtain an initial global speed curve; the iteration processing submodule is used for iteration steps, and iteration processing is carried out on the initial global speed curve to obtain the global speed curve. In the embodiment, the obtained multiple initial path speed curves are optimized, so that the obtained initial global speed curve can meet the requirement on the smoothness of the speed curve, and the comfort is good. And then, carrying out iterative processing on the initial global speed curve, thereby ensuring that the obtained global speed curve can meet the demand of on-time arrival.

In a specific embodiment of the present application, before performing a kinematic speed planning based on at least speed information of a target key point on each path segment and corresponding road segment speed limit information to obtain a plurality of initial path speed curves, it may be further determined whether the planning of each path segment can be completed. The specific process is as follows: two target key points (namely a first target key point and a second target key point) of a certain path segment are selected, and v is assumed to be ₀ Left side velocity, v, of the first target keypoint ₁ The velocity to the right of the first target keypoint,v ₂ the velocity to the right of the second target keypoint. If v is ₁ Not equal to the left speed of the second target key point, the target key points are set incorrectly and planning fails because two different maximum speeds occur between the two target key points. If v is ₀ ＞v ₁ +0.05, then due to v ₀ The right vehicle speed or the actual initial vehicle speed after planning for the previous path segment cannot be greater than the maximum vehicle speed of the path segment, so that the planning fails. If neither of the above conditions is met, the kinematic velocity planning is started.

In another specific embodiment of the present application, the kinematic velocity plan is velocity information of a target key point corresponding to a certain path segment (the velocity information is a left-side velocity v of a first target key point) ₀ Velocity v on the right of the first target keypoint ₁ And the velocity v to the right of the second target keypoint ₂ ) Maximum acceleration a _max And maximum deceleration a _min For input, an initial path velocity profile for the path segment is output. The following is presented case by case:

case 1:

Case 2:

when | v ₀ -v ₁ < 0.01 and v ₂ ＜v ₁ When the path length corresponding to the first target key point is set as S ₀ The path length corresponding to the second target key point is S ₂ . The distance between two key points of the target is S ₂ -S ₀ According to the maximum deceleration a _max Can calculate the deceleration to v ₂ Has a shortest distance of S _mind Comprises the following steps:

if S ₂ -S ₀ ＜S _mind If the shortest deceleration distance is not met, the planning fails; if S ₂ -S ₀ ＞S _mind V is to be ₂ As the planned final speed, the vehicle holds v ₁ Run to S ₁ Start to decelerate at the time S ₁ ＝S ₂ -S _mind Then in deceleration to v ₂ In the process, if s is the length of the current path of the vehicle, the expression for generating sparse speed path points is

Case 3:

case 3 contains two special cases (i) and (ii).

At v is ₀ ＜v ₁ And v is ₂ ≥v ₁ When the path length corresponding to the first target key point is set as S ₁ The path length corresponding to the second target key point is S _3，s The distance between two target key points is S according to the length of the current path of the vehicle ₃ -S ₁ According to the maximum acceleration a _max Can calculate the acceleration to v ₂ Has a shortest distance of S _mind Comprises the following steps:

(i) If S ₃ -S ₁ ＞S _mind At this time v ₁ Namely the planned final speed, the vehicle is set to run to S ₂ Start accelerating at the time of treatment, S ₂ ＝S ₃ -S _mind At this time at twoThe expression for generating sparse velocity path points between the target key points is as follows:

(ii) If S ₃ -S ₁ ＜S _mind There is a constant acceleration between the two target key points, at which the planned final velocity v is _last The expression of (a) is:

the expression for generating sparse velocity path points between two target keypoints is:

Case 4:

case 4 includes two special cases (i) and (ii).

according to the maximum deceleration a _min Can calculate the deceleration to v ₂ Has a shortest distance of S _dec ：

(i) If (S) _acc +S _dec )＜(S ₃ -S ₀ ) There is a path segment that is traveling at a constant speed. At acceleration to v ₁ The expression for generating sparse velocity path points in the process is as follows:

v is constant velocity process ₁ Driving at a constant speed; at deceleration to v ₂ The expression for generating sparse velocity path points in the process of (1) is as follows:

(ii) If (S) _acc +S _dec )≥(S ₃ -S ₀ ) There is no path segment for uniform travel. Let S ' be the path length corresponding to the start of deceleration, and the maximum speed to which acceleration can be achieved at this time be v ', then the expression for v ' is:

Case 5:

case 5 contains three special cases (i), (ii), (iii)

At v is ₀ ＜v ₁ And v is ₂ ＜v ₁ And V is ₂ ＞V ₀ When the path length corresponding to the first target key point is set as S ₀ The path length corresponding to the second target key point is S ₃ And S is the length of the current path of the vehicle, the distance between two target key points is (S) ₃ -S ₀ ) According to the maximum acceleration a _max Can calculate the value from v ₀ Accelerate to v ₁ Has a shortest distance of S _acc Comprises the following steps:

according to maximum deceleration a _min Can calculate the value from v ₁ Is decelerated to v ₂ Has a shortest distance of S _dec Comprises the following steps:

(ii) If (S) _acc +S _dec )≥(S ₃ -S ₀ ) In this case, there is no route section that is traveling at a constant speed. Assuming that S ' is a path length corresponding to the start of deceleration and the maximum speed that can be accelerated at this time is set to v ', the expression of v ' is:

the expression for generating sparse velocity path points in the process of accelerating to v' is:

then, the initial path speed curve shown in fig. 12 is obtained according to the first target key point, the second target key point, and the generated sparse speed path points.

In an embodiment of the application, the optimization submodule includes a construction submodule and a solving submodule, where the construction submodule is configured to construct an optimization function according to at least speed information of two adjacent path points, so as to obtain multiple optimization objective functions; and the solving submodule is used for carrying out optimization solving on a plurality of the optimization objective functions by adopting a gradient descent method to obtain the initial global speed curve.

(1) Establishing an optimized objective function

wherein the function f ₁ (v) Function f reflecting the magnitude of the velocity change of adjacent path points ₂ (v) And applying certain constraint on the speed before and after optimization, so that the optimized range of the speed curve is in the adjacent area of the original speed curve. Δ v _i ＝v _i -v _i-1 Is the speed change value, Δ v, of the waypoint i and the adjacent rear waypoint _i+1 ＝v _i+1 -v _i Is the speed variation value, v, of the path point i and the adjacent preceding path point _i，0 The speed before optimization of the path point i, i.e. the speed obtained by the kinematics speed planning, is represented.

(2) Gradient descent method for solving optimal solution

Velocity v through the objective function for path point i _i Calculating the deviation derivative, and calculating the gradient value at the path point, wherein the gradient direction is the direction with the fastest function changeTo, the objective function pair v at the path point i _i The gradient is calculated as:

the smoothed velocity along the gradient direction is expressed as:

where δ represents the iteration step in the gradient direction.

In order to further ensure that the vehicle can arrive at the destination on time when traveling along the initial global trajectory, in another embodiment of the present application, the iteration submodule includes an eighth determining submodule, a sixth calculating submodule and a second modifying submodule, where the eighth determining submodule is configured to determine an actual path operation duration of an alternative path point according to the initial global speed curve, and the alternative path point is one of the plurality of path points; the sixth calculating submodule is configured to calculate a difference between the actual path running time and a planned path running time to obtain a path time difference, where the planned path running time is a running time of the planned alternative path point; the second correction submodule is configured to, when the difference between the path durations is greater than the predetermined threshold, correct the road segment speed limit information to which the alternative path point belongs according to a corrected speed limit speed to obtain corrected road segment speed limit information, and execute the third planning step, the optimizing step, and the iterating step at least once until a difference between a global trajectory duration of the global speed curve and the total operation duration satisfies a preset range, where the corrected speed limit speed is determined at least according to an initial corrected speed limit speed, the actual path operation duration, and the planned path operation duration.

In the actual operation process, the speed limit requirement of the road section and the maximum acceleration and-Or a maximum deceleration constrained smoothed initial global velocity profile. But the path speed limit information corresponding to the path segment is used as the highest speed upper limit to obtain the global track duration T consumed by the initial global speed curve _v (k) Will be much less than the predetermined threshold T _d (k) I.e., the vehicle will reach an alternative waypoint or destination in advance, is not able to meet the constraints of quasi-point travel. In a specific embodiment of the present application, a global velocity curve satisfying the operating time constraint is planned in a combined iterative manner by a trapezoidal velocity planning and a gradient descent method, and a specific flowchart can be shown in fig. 4.

wherein s is _i 、v _i Respectively, the path length and the speed corresponding to the path point i.

Specifically, the actual path running time T when the alternative path point _v (k) With a corresponding planned path run length T _d (k) Is greater than a predetermined threshold value deltat _max Then, the speed limit information v of the road section of the corresponding path segment is subjected to speed limit information v through the initially given corrected speed limit speed delta v _max Correcting to obtain corrected speed limiting information, and calculating corrected speed limiting information v _max The expression of (c) is:

n is the total number of waypoints. And thirdly, performing trapezoidal speed planning according to the speed limit information of the corrected road section to obtain the actual path operation time length T 'corresponding to the iterated alternative path point' _v (k) In that respect Again according to T' _v (k) And T _d (k) The difference of (d) is iterated over Δ v. Wherein the iteration step of Δ vThe expression is as follows:

The global speed planning device comprises a processor and a memory, wherein the planning unit, the obtaining unit, the first comparing unit, the second comparing unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.

The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more, and the problem that the global track of the vehicle is difficult to determine through less calculation amount while the on-time arrival requirement of the vehicle is considered in the prior art is solved by adjusting the kernel parameters.

The memory may include volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), including at least one memory chip.

An embodiment of the present invention provides a computer-readable storage medium, on which a program is stored, where the program, when executed by a processor, implements the above-mentioned global velocity planning method.

The embodiment of the invention provides a processor, which is used for running a program, wherein the global speed planning method is executed when the program runs.

In an exemplary embodiment of the present application, a planning system is further provided, and the planning system includes a scheduling system, a global path planning system, and a global speed planning system. The scheduling system is used for sending the total running time and the departure time to the global speed planning system; the system comprises a global path planning system, a speed limit control system and a speed limit control system, wherein the global path planning system is used for sending global driving path and road section speed limit information to the global speed planning system; the global velocity planning system comprises a global velocity planning apparatus for performing any one of the above-described global velocity planning methods.

The planning system comprises a global velocity planning system comprising a global velocity planning means for performing any of the above-described global velocity planning methods. In the global speed planning method, firstly, based on a speed planning algorithm, speed planning is carried out on the received total running time, departure time, global driving path and road section speed limit information of the vehicle to obtain an initial global track; then, acquiring the actual running time of the vehicle reaching the target path point in the process that the vehicle runs along the initial global track; then, calculating the difference between the actual running time of the vehicle at the target path point and the planned time of the path point, and if the difference is less than or equal to a preset threshold value, indicating that the vehicle can arrive at the destination on time, so that the vehicle can be continuously controlled to run in the initial global track until the vehicle reaches the destination; and under the condition that the difference value is larger than the preset threshold value, the vehicle cannot arrive at the destination on time, the remaining total running time and the remaining global path of the vehicle are calculated, and the speed planning is performed again according to the remaining total running time, the remaining global path, the departure time and the road section speed limit information, so that the vehicle arrives at the destination on time. Compared with the method for obtaining the global track of the vehicle through dynamic programming or a heuristic optimization method in the prior art, the method for obtaining the global track of the vehicle only needs to adopt a speed programming algorithm to perform speed programming on the total running time, the departure time, the global driving path and the road section speed limit information of the vehicle to obtain the initial global track of the vehicle, so that the calculation amount for determining the initial global track is less, the method is not required to be carried on a vehicle-scale high-computing-force platform, and the cost of the method for obtaining the global speed is lower. In addition, the global speed planning method dynamically adjusts the operation strategy of the vehicle under the influence of dynamic traffic flow by considering the demand of the vehicle on-time arrival, and ensures that the vehicle can arrive at the destination on-time, thereby solving the problem that the prior art is difficult to determine the global track of the vehicle through less calculation amount while considering the demand of the vehicle on-time arrival.

An embodiment of the present invention provides an apparatus, where the apparatus includes a processor, a memory, and a program that is stored in the memory and is executable on the processor, and when the processor executes the program, at least the following steps are implemented:

step S101, a first planning step, namely performing speed planning on the received total running time, departure time, overall running path and road section speed limit information of the vehicle by adopting a speed planning algorithm to obtain an initial overall track, wherein the initial overall track is used for representing speed information and time information of each path point, and the path points are points which are divided on the overall running path according to preset intervals;

The device herein may be a server, a PC, a PAD, a mobile phone, etc.

The present application further provides a computer program product adapted to perform a program of initializing at least the following method steps when executed on a data processing device:

In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed technical content can be implemented in other manners. The above-described apparatus embodiments are merely illustrative, and for example, the division of the above-described units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.

The integrated unit may be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as a separate product. Based on such understanding, the technical solution of the present invention, which is substantially or partly contributed by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

From the above description, it can be seen that the above-described embodiments of the present application achieve the following technical effects:

1) In the global speed planning method, firstly, speed planning is carried out on the received total running time length, departure time, global driving path and road section speed limit information of the vehicle based on a speed planning algorithm to obtain an initial global track; then, acquiring the actual running time of the vehicle reaching the target path point in the process of running the vehicle by the initial global track; then, calculating the difference between the actual running time of the vehicle at the target path point and the planned time of the path point, and if the difference is less than or equal to a preset threshold value, indicating that the vehicle can arrive at the destination on time, so that the vehicle can be continuously controlled to run in the initial global track until the vehicle reaches the destination; and under the condition that the difference value is larger than the preset threshold value, the vehicle cannot arrive at the destination on time, the remaining total running time and the remaining global path of the vehicle are calculated, and the speed planning is performed again according to the remaining total running time, the remaining global path, the departure time and the road section speed limit information, so that the vehicle arrives at the destination on time. Compared with the method for obtaining the global track of the vehicle through dynamic programming or a heuristic optimization method in the prior art, the method for obtaining the global track of the vehicle only needs to adopt a speed programming algorithm to perform speed programming on the total running time, the departure time, the global driving path and the road section speed limit information of the vehicle to obtain the initial global track of the vehicle, so that the calculation amount for determining the initial global track is less, the method is not required to be carried on a vehicle-scale high-computing-force platform, and the cost of the method for obtaining the global speed is lower. In addition, the global speed planning method dynamically adjusts the operation strategy of the vehicle under the influence of dynamic traffic flow by considering the demand of the vehicle on-time arrival, and ensures that the vehicle can arrive at the destination on-time, thereby solving the problem that the prior art is difficult to determine the global track of the vehicle through less calculation amount while considering the demand of the vehicle on-time arrival.

2) In the global speed planning device, a planning unit is used for carrying out speed planning on the received total running time length, departure time, global driving path and road section speed limit information of the vehicle based on a speed planning algorithm to obtain an initial global track; the acquiring unit is used for acquiring the actual running time of the vehicle reaching the target path point in the process that the vehicle runs along the initial global track; the first comparison unit is used for calculating the difference between the actual running time of the vehicle at the target path point and the planned time of the path point, and under the condition that the difference is less than or equal to a preset threshold value, the vehicle can arrive at the destination on time, so that the vehicle can be continuously controlled to run along the initial global track until the vehicle arrives at the destination; and the second comparison unit is used for indicating that the vehicle cannot arrive at the destination on time under the condition that the difference value is larger than the preset threshold value, calculating the residual total running time length and the residual global path of the vehicle, and then carrying out speed planning again according to the residual total running time length, the residual global path, the departure time and the road section speed limit information so as to enable the vehicle to arrive at the destination on time. Compared with the scheme of obtaining the global track of the vehicle through dynamic programming or a heuristic optimization method in the prior art, the global speed planning device only needs to adopt a speed planning algorithm to carry out speed planning on the total running time, the starting time, the global driving path and the road section speed limit information of the vehicle to obtain the initial global track of the vehicle, so that the calculation amount for determining the initial global track is less, the device does not need to be carried on a vehicle-scale high-calculation-force platform, and the global speed planning method is lower in cost. In addition, the global speed planning device dynamically adjusts the operation strategy of the vehicle under the influence of dynamic traffic flow by considering the on-time arrival requirement of the vehicle, so that the vehicle can arrive at the destination on time, and the problem that the global track of the vehicle is difficult to determine through less calculation amount while considering the on-time arrival requirement of the vehicle in the prior art is solved.

3) The planning system of the present application comprises a global velocity planning system comprising a global velocity planning apparatus for performing any of the above-described global velocity planning methods. In the global speed planning method, firstly, based on a speed planning algorithm, speed planning is carried out on the received total running duration, the departure time, the global driving path and the road section speed limit information of the vehicle to obtain an initial global track; then, acquiring the actual running time of the vehicle reaching the target path point in the process of running the vehicle by the initial global track; then, calculating the difference between the actual running time of the vehicle at the target path point and the planned time of the path point, and if the difference is less than or equal to a preset threshold value, indicating that the vehicle can arrive at the destination on time, so that the vehicle can be continuously controlled to run in the initial global track until the vehicle reaches the destination; and under the condition that the difference value is larger than the preset threshold value, the vehicle cannot arrive at the destination on time, the remaining total running time and the remaining global path of the vehicle are calculated, and the speed planning is performed again according to the remaining total running time, the remaining global path, the departure time and the road section speed limit information, so that the vehicle arrives at the destination on time. Compared with the method for obtaining the global track of the vehicle through dynamic programming or a heuristic optimization method in the prior art, the method for obtaining the global track of the vehicle only needs to adopt a speed programming algorithm to perform speed programming on the total running time, the departure time, the global driving path and the road section speed limit information of the vehicle to obtain the initial global track of the vehicle, so that the calculation amount for determining the initial global track is less, the method is not required to be carried on a vehicle-scale high-computing-force platform, and the cost of the method for obtaining the global speed is lower. In addition, the global speed planning method dynamically adjusts the operation strategy of the vehicle under the influence of dynamic traffic flow by considering the on-time arrival requirement of the vehicle, so that the vehicle can arrive at the destination on time, and the problem that the global track of the vehicle is difficult to determine through less calculation amount while the on-time arrival requirement of the vehicle is considered in the prior art is solved.

The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A global velocity planning method, comprising:

a first planning step, performing speed planning on the received total running duration, departure time, overall running path and road section speed limit information of the vehicle by adopting a speed planning algorithm to obtain an initial overall track, wherein the initial overall track is used for representing the speed information and time information of each path point, and the path points are points which are divided on the overall running path according to preset intervals;

an obtaining step of controlling the vehicle to run according to the initial global track to obtain an actual running time of the vehicle reaching a target path point, wherein the target path point is one of the path points;

a first comparison step, wherein the obtaining step is executed at least once under the condition that the difference value between the actual running time length and the planned time length of the route point is less than or equal to a preset threshold value until the vehicle reaches the destination, and the planned time length of the route point is the running time length of the initially planned target route point;

and a second comparison step, namely calculating the remaining total running time and the remaining global path under the condition that the difference value between the actual running time and the planned time of the path point is greater than the preset threshold value, and sequentially executing the first planning step and the obtaining step at least once until the vehicle reaches the destination.

2. The global speed planning method according to claim 1, wherein a speed planning algorithm is adopted to perform speed planning on the received total operation duration, departure time, global travel path and road section speed limit information of the vehicle to obtain an initial global track, and the method comprises the following steps:

dividing the global driving path according to a preset rule to obtain a plurality of path segments, wherein the preset rule is determined according to the forward and backward directions of the vehicle;

acquiring at least two key points on each path segment, wherein the key point is one of the path points;

preprocessing at least two key points on each path segment to obtain target key points on each path segment;

and performing trapezoidal speed planning according to the target key points, the total running time, the departure time, the overall running path and the road section speed limit information on each path segment to obtain the initial overall track of the vehicle.

3. The global velocity planning method according to claim 2, wherein preprocessing at least two of the keypoints on each of the path segments to obtain target keypoints on each of the path segments comprises:

for continuous first and second key points on a target path segment, determining a first speed and a second speed of the first key point and a third speed of the second key point, wherein the target path segment is one of the plurality of path segments, and the first and second key points are the key points;

if the first speed is greater than the second speed and the second speed is greater than the third speed, calculating a first distance from the second speed to the third speed based on a maximum deceleration, and determining the target keypoint on the target path segment based at least on the first distance;

if the second speed is greater than the first speed and the first speed is greater than the third speed, calculating a second distance from the first speed to the third speed based on the maximum deceleration, and determining the target keypoint on the target path segment based at least on the second distance.

4. The global velocity planning method according to claim 3, wherein determining the target keypoints on the target path segment based at least on the first distance comprises:

calculating the distance between the first key point and the second key point to obtain a target key distance;

if the first distance is greater than the target key distance, determining the second key point as the target key point, determining a fourth speed of the second key point as the first speed, and deleting the first key point;

and under the condition that the first distance is smaller than or equal to the target key distance, determining the first key point and the second key point as the target key points.

5. The global velocity planning method according to claim 3, wherein determining the target keypoints on the target path segment according to at least the second distance comprises:

if the second distance is greater than the target key distance, determining the second key point as the target key point, determining a fourth speed of the second key point as the first speed, and deleting the first key point;

and under the condition that the second distance is smaller than or equal to the target key distance, determining the first key point and the second key point as the target key points.

6. The global speed planning method according to claim 2, wherein performing trapezoidal speed planning according to the target key point, the total operation duration, the departure time, the global travel path, and the section speed limit information on each of the path segments to obtain the initial global trajectory of the vehicle includes:

a second planning step, wherein the trapezoidal speed planning is carried out on the target key points on each path segment at least according to the road section speed limit information to obtain a global speed curve of the global driving path;

a first determination step, wherein a global track duration is determined according to the global speed curve and the global driving path;

and a second determination step, determining the initial global track according to the global track time length, the total operation time length and the departure time.

7. The global velocity planning method according to claim 6, wherein determining the initial global trajectory based on the global trajectory duration, the total operation duration and the departure time comprises:

under the condition that the overall track duration is longer than the total operation duration, generating first planning failure information, and sending the first planning failure information to a scheduling system;

and under the condition that the overall track time length is less than or equal to the total running time length, calculating a difference value between the overall track time length and the total running time length to obtain a target time length difference value, and determining the initial overall track of the vehicle at least according to the target time length difference value and the departure time.

8. The global velocity planning method of claim 7, wherein determining the initial global trajectory of the vehicle based at least on the target time duration difference and the departure time comprises:

under the condition that the target time length difference is smaller than or equal to a time length difference threshold, adding the speed information and the time information to each path point according to the global speed curve and the departure time to obtain the initial global track of the vehicle;

and under the condition that the target time length difference is greater than the time length difference threshold, correcting the speed limit information of the road section according to the target time length difference, and executing the second planning step, the first determining step and the second determining step at least once until the target time length difference is less than or equal to the time length difference threshold.

9. The global speed planning method according to claim 6, wherein the obtaining of the global speed curve of the global driving path by performing the trapezoidal speed planning on the target key points on each of the path segments according to at least the section speed limit information includes:

a third planning step, performing kinematics speed planning at least based on the speed information of the target key point on each path segment to obtain a plurality of initial path speed curves, wherein one path segment corresponds to one initial path speed curve;

optimizing, namely optimizing each initial path speed curve to obtain an initial global speed curve;

and an iteration step, namely performing iteration processing on the initial overall speed curve based on the road section speed limit information to obtain the overall speed curve.

10. The global velocity planning method according to claim 9, wherein the optimizing each of the initial path velocity profiles to obtain an initial global velocity profile comprises:

constructing an optimization function at least according to the speed information of two adjacent path points to obtain a plurality of optimization objective functions;

and performing optimization solution on the plurality of optimization objective functions by adopting a gradient descent method to obtain the initial global speed curve.

11. The global speed planning method according to claim 9, wherein the iterative processing of the initial global speed profile based on the section speed limit information to obtain the global speed profile comprises:

determining the actual path running time of an alternative path point according to the initial global speed curve, wherein the alternative path point is one of the path points;

calculating a difference value between the actual path operation time length and a planned path operation time length to obtain a path time length difference value, wherein the planned path operation time length is the operation time length of the planned alternative path point;

and under the condition that the difference value of the path time lengths is larger than the preset threshold, correcting the road section speed limit information to which the alternative path point belongs according to a corrected speed limit speed to obtain corrected road section speed limit information, and executing the third planning step, the optimizing step and the iteration step at least once until the difference value of the overall track time length and the total operation time length of the overall speed curve meets a preset range, wherein the corrected speed limit speed is determined at least according to an initial corrected speed limit speed, the actual path operation time length and the planned path operation time length.

12. A global velocity planner, comprising:

the planning unit is used for performing speed planning on the received total running time, departure time, overall driving path and road section speed limit information of the vehicle by adopting a speed planning algorithm to obtain an initial overall track, wherein the initial overall track is used for representing speed information and time information of each path point, and the path points are points which are divided on the overall driving path according to preset intervals;

an obtaining unit, configured to perform an obtaining step to control the vehicle to travel according to the initial global trajectory to obtain an actual running time of the vehicle reaching a target waypoint, where the target waypoint is one of the waypoints;

a first comparing unit, configured to perform the obtaining step at least once when a difference between the actual running time and a route point planning time is less than or equal to a predetermined threshold, until the vehicle reaches a destination, where the route point planning time is a running time of the target route point planned for the first time;

and the second comparison unit is used for calculating the residual total running time length and the residual global path under the condition that the difference value between the actual running time length and the planned time length of the path point is greater than the preset threshold value in the second comparison step, and sequentially executing the first planning step and the obtaining step at least once until the vehicle reaches the destination.

13. A computer-readable storage medium, comprising a stored program, wherein the program performs the global velocity planning method of any of claims 1 to 11.

14. A processor, characterized in that the processor is configured to run a program, wherein the program when running performs the global velocity planning method according to any of claims 1 to 11.

15. A planning system, comprising:

the scheduling system is used for sending the total running time and the departure time to the global speed planning system;

the system comprises a global path planning system, a speed limit control system and a speed limit control system, wherein the global path planning system is used for sending global driving path and road section speed limit information to the global speed planning system;

the global velocity planning system comprises a global velocity planning means for performing the global velocity planning method of any of claims 1 to 11.