patents.google.com

CN112762954B - A path planning method and system - Google Patents

  • ️Tue Nov 02 2021

CN112762954B - A path planning method and system - Google Patents

A path planning method and system Download PDF

Info

Publication number
CN112762954B
CN112762954B CN202011561630.8A CN202011561630A CN112762954B CN 112762954 B CN112762954 B CN 112762954B CN 202011561630 A CN202011561630 A CN 202011561630A CN 112762954 B CN112762954 B CN 112762954B Authority
CN
China
Prior art keywords
road
unsampled
typical
road section
road segment
Prior art date
2020-12-25
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011561630.8A
Other languages
Chinese (zh)
Other versions
CN112762954A (en
Inventor
兰泽多
芮小平
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hohai University HHU
Original Assignee
Hohai University HHU
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
2020-12-25
Filing date
2020-12-25
Publication date
2021-11-02
2020-12-25 Application filed by Hohai University HHU filed Critical Hohai University HHU
2020-12-25 Priority to CN202011561630.8A priority Critical patent/CN112762954B/en
2021-05-07 Publication of CN112762954A publication Critical patent/CN112762954A/en
2021-11-02 Application granted granted Critical
2021-11-02 Publication of CN112762954B publication Critical patent/CN112762954B/en
2021-11-19 Priority to ZA2021/09285A priority patent/ZA202109285B/en
Status Active legal-status Critical Current
2040-12-25 Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
    • G01C21/3461—Preferred or disfavoured areas, e.g. dangerous zones, toll or emission zones, intersections, manoeuvre types, segments such as motorways, toll roads, ferries
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)
  • Steering Control In Accordance With Driving Conditions (AREA)

Abstract

本发明提供一种路径规划方法及系统，方法包括：首先确定n个典型路段；然后令h＝1；基于模糊推理方法计算第h个未采样路段与各个典型路段的相似度；根据第h个未采样路段与各典型路段的相似度计算第h个未采样路段对应的速度权重；根据第h个未采样路段对应的速度权重计算第h个未采样路段对应的道路阻抗；直到h＝K，其中K为未采样路段的总个数；最后根据各未采样路段对应的道路阻抗规划行驶路径。本发明基于道路阻抗越大，安全性越低的原理有效避免陡坡、视野狭窄的路段，减少安全性差的道路通过机会，从而为驾驶员山区道路安全出行规划行驶路径。

Figure 202011561630

The invention provides a path planning method and system. The method includes: firstly determining n typical road sections; then setting h=1; calculating the similarity between the hth unsampled road section and each typical road section based on a fuzzy inference method; The similarity between the unsampled road section and each typical road section calculates the speed weight corresponding to the hth unsampled road section; calculates the road impedance corresponding to the hth unsampled road section according to the speed weight corresponding to the hth unsampled road section; until h=K, Among them, K is the total number of unsampled road sections; finally, the driving path is planned according to the road impedance corresponding to each unsampled road section. Based on the principle that the larger the road impedance is, the lower the safety is, the invention effectively avoids the road section with steep slope and narrow field of vision, reduces the chance of passing the road with poor safety, thereby planning the driving path for the driver to travel safely on the mountain road.

Figure 202011561630

Description

Path planning method and system

Technical Field

The present invention relates to the field of path planning technologies, and in particular, to a path planning method and system.

Background

In recent years, with the increasing of automobile holding capacity, road traffic accidents caused by motor vehicles in road traffic are increasing, and the road traffic safety situation is becoming more severe. The mountainous area road has complex environment, short protection, rare people and narrow road, and is a main place for traffic accidents. At present, how to plan a safe driving path in a complex environment in a mountainous area becomes a hot point of research in the traffic field.

Disclosure of Invention

The invention aims to provide a path planning method and a system to plan a safe driving path.

In order to achieve the above object, the present invention provides a path planning method, including:

s1: determining n typical road sections;

s2: let h equal to 1;

s3: calculating the similarity between the h-th non-sampled road section and each typical road section based on a fuzzy reasoning method;

s4: calculating the speed weight corresponding to the h-th non-sampled road section according to the similarity of the h-th non-sampled road section and each typical road section;

s5: calculating the road impedance corresponding to the h-th non-sampled road section according to the speed weight corresponding to the h-th non-sampled road section;

s6: judging whether h is smaller than K; if h is less than K, let h be h +1, and return to "S3"; if h is greater than or equal to K, "S7" is performed; k is the total number of the non-sampled road sections;

s7: and planning a driving path according to the road impedance corresponding to each non-sampled road section.

Optionally, the determining n typical road segments specifically includes:

s11: collecting a plurality of sample road sections; the sample road segment comprises m road attribute values and speed weights;

s12: classifying a plurality of sample road sections by using a random forest method and training a prediction model;

s13: calculating first speed weight of each non-sampling road section according to the prediction model;

s14: determining n representative road segments according to the first speed weight of each non-sampled road segment and the speed weights of a plurality of sample road segments.

Optionally, the similarity between the h-th non-sampled road segment and each typical road segment is calculated based on a fuzzy inference method, and a specific formula is as follows:

Figure BDA0002859539320000021

wherein, Pj,hJ-th road attribute value, S, representing h-th unsampled road segmenti,hRepresenting the similarity, k, of the h-th unsampled road segment to the i-th typical road segment1And w1Denotes a correction parameter, Pjt,hAnd j represents the j-th road attribute value of each typical road section corresponding to the h-th unexplored road section, and m is the number of the road attribute values.

Optionally, the speed weight corresponding to the h-th non-sampled road section is calculated according to the similarity between the h-th non-sampled road section and each typical road section, and the specific formula is as follows:

Figure BDA0002859539320000022

wherein, WhRepresents the speed weight corresponding to the h-th non-sampled road section, Si,hRepresents the similarity of the h-th non-sampled road section and the i-th typical road section, Wi,hAnd the speed weight of the ith typical road section corresponding to the h-th unexplored road section is shown.

Optionally, the road impedance corresponding to the h-th non-sampled road section is calculated according to the speed weight corresponding to the h-th non-sampled road section, and the specific formula is as follows:

Figure BDA0002859539320000023

wherein, length* hRepresents the road impedance, length, corresponding to the h-th unsampled road sectionhRepresents the road length, w, corresponding to the h-th unsampled road section* hRepresents the speed limit value W corresponding to the h-th non-sampled road sectionhAnd representing the speed weight corresponding to the h-th non-sampled road section.

Optionally, the planning of the driving path according to the road impedance corresponding to each non-sampled road segment specifically includes:

and selecting the road section with the minimum road impedance corresponding to each non-sampled road section as the driving path.

The invention also provides a path planning system, which comprises:

the typical road section determining module is used for determining n typical road sections;

the assignment module is used for enabling h to be 1;

the similarity determining module is used for calculating the similarity between the h-th non-sampled road section and each typical road section based on a fuzzy reasoning method;

the speed weight determining module is used for calculating the speed weight corresponding to the h-th non-sampling road section according to the similarity of the h-th non-sampling road section and each typical road section;

the road impedance determination module is used for calculating the road impedance corresponding to the h-th non-sampled road section according to the speed weight corresponding to the h-th non-sampled road section;

the judging module is used for judging whether h is smaller than K or not; if h is smaller than K, making h equal to h +1, and returning to the similarity determination module; if h is greater than or equal to K, executing a planning module; k is the total number of the non-sampled road sections;

and the planning module is used for planning the driving path according to the road impedance corresponding to each non-sampled road section.

Optionally, the typical road segment determining module further includes:

the acquisition unit is used for acquiring a plurality of sample road sections; the sample road segment comprises m road attribute values and speed weights;

the training unit is used for classifying the plurality of sample road sections by using a random forest method and training a prediction model;

the first speed weight calculation unit is used for calculating the first speed weight of each non-sampling road section according to the prediction model;

and the comparison unit is used for determining n typical road sections according to the first speed weight of each non-sampling road section and the speed weights of the plurality of sample road sections.

Optionally, the similarity between the h-th non-sampled road segment and each typical road segment is calculated based on a fuzzy inference method, and a specific formula is as follows:

Figure BDA0002859539320000041

wherein, Pj,hJ-th road attribute value, S, representing h-th unsampled road segmenti,hRepresenting the similarity, k, of the h-th unsampled road segment to the i-th typical road segment1And w1Denotes a correction parameter, Pjt,hAnd j represents the j-th road attribute value of each typical road section corresponding to the h-th unexplored road section, and m is the number of the road attribute values.

Optionally, the speed weight corresponding to the h-th non-sampled road section is calculated according to the similarity between the h-th non-sampled road section and each typical road section, and the specific formula is as follows:

Figure BDA0002859539320000042

wherein, WhRepresents the speed weight corresponding to the h-th non-sampled road section, Si,hRepresents the similarity of the h-th non-sampled road section and the i-th typical road section, Wi,hAnd the speed weight of the ith typical road section corresponding to the h-th unexplored road section is shown.

According to the specific embodiment provided by the invention, the invention discloses the following technical effects:

the invention provides a path planning method and a system, wherein the method comprises the following steps: firstly, determining n typical road sections; then h is 1; calculating the similarity between the h-th non-sampled road section and each typical road section based on a fuzzy reasoning method; calculating the speed weight corresponding to the h-th non-sampled road section according to the similarity of the h-th non-sampled road section and each typical road section; calculating the road impedance corresponding to the h-th non-sampled road section according to the speed weight corresponding to the h-th non-sampled road section; until h is equal to K, wherein K is the total number of the non-sampled road sections; and finally planning a driving path according to the road impedance corresponding to each non-sampled road section. The invention effectively avoids steep slopes and road sections with narrow visual fields based on the principle that the higher the road impedance is, the lower the safety is, and reduces the road passing chances with poor safety, thereby planning the driving path for safe trip of the driver on the mountain road.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.

Fig. 1 is a flowchart of a path planning method according to embodiment 1 of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.

The invention aims to provide a path planning method and a system to plan a safe driving path.

In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.

Example 1

Fig. 1 is a flowchart of a path planning method according to embodiment 1 of the present invention, and as shown in fig. 1, the path planning method includes:

s1: n representative road segments are determined.

S2: let h equal to 1.

S3: and calculating the similarity between the h-th non-sampled road section and each typical road section based on a fuzzy inference method.

S4: and calculating the speed weight corresponding to the h-th non-sampled road section according to the similarity of the h-th non-sampled road section and each typical road section.

S5: and calculating the road impedance corresponding to the h-th non-sampled road section according to the speed weight corresponding to the h-th non-sampled road section.

S6: judging whether h is smaller than K; if h is less than K, let h be h +1, and return to "S3"; if h is greater than or equal to K, "S7" is performed; wherein K is the total number of the non-sampled road sections.

S7: and planning a driving path according to the road impedance corresponding to each non-sampled road section.

In the embodiment of the present invention, the determining n typical road segments specifically includes:

s11: collecting a plurality of sample road sections; the sample road segment includes m road attribute values and speed weights. In the embodiment of the present invention, a total of 242 sample road segments are collected, where each sample road segment includes 4 road attribute values, and the road attribute values include: road grade factor, visual field factor, road grade factor and road waviness factor. The samples were taken as in table 1.

TABLE 1

Figure BDA0002859539320000061

S12: and classifying the plurality of sample road sections by using a random forest method and training a prediction model. Wherein the road attribute value is an independent variable and the speed is a dependent variable. A partial sample link data example is shown in table 2.

Table 2 example of partial sample link data selection

Figure BDA0002859539320000062

Figure BDA0002859539320000071

S13: and calculating the first speed weight of each non-sampling road section according to the prediction model.

S14: determining n typical road sections according to the first speed weight of each non-sampling road section and the speed weights of a plurality of sample road sections; specifically, the speed weight of each sample road section is compared with the first speed weight of each non-sampled road section, and each sample road section within a set range is selected as a typical road section.

In the embodiment of the present invention, the similarity between the h-th non-sampled road segment and each typical road segment is calculated based on a fuzzy inference method, and a specific formula is as follows:

Figure BDA0002859539320000072

wherein, Pj,hJ-th road attribute value, S, representing h-th unsampled road segmenti,hRepresenting the similarity, k, of the h-th unsampled road segment to the i-th typical road segment1And w1Denotes a correction parameter, Pjt,hAnd j represents the j-th road attribute value of each typical road section corresponding to the h-th unexplored road section, and m is the number of the road attribute values.

In the embodiment of the present invention, the speed weight corresponding to the h-th non-sampled road section is calculated according to the similarity between the h-th non-sampled road section and each typical road section, and a specific formula is as follows:

Figure BDA0002859539320000081

wherein, WhRepresents the speed weight corresponding to the h-th non-sampled road section, Si,hRepresents the similarity of the h-th non-sampled road section and the i-th typical road section, Wi,hAnd the speed weight of the ith typical road section corresponding to the h-th unexplored road section is shown.

In the embodiment of the present invention, the road impedance corresponding to the h-th non-sampled road section is calculated according to the speed weight corresponding to the h-th non-sampled road section, and the specific formula is as follows:

Figure BDA0002859539320000082

wherein, length* hRepresents the road impedance, length, corresponding to the h-th unsampled road sectionhRepresents the road length, w, corresponding to the h-th unsampled road section* hRepresents the speed limit value W corresponding to the h-th non-sampled road sectionhAnd representing the speed weight corresponding to the h-th non-sampled road section.

In the embodiment of the present invention, the planning of the driving path according to the road impedance corresponding to each non-sampled road segment specifically includes:

and selecting the road section with the minimum road impedance corresponding to each non-sampled road section as the driving path.

Example 2

The invention also provides a path planning system, which comprises:

and the typical road section determining module is used for determining n typical road sections.

And the assignment module is used for enabling h to be 1.

And the similarity determining module is used for calculating the similarity between the h-th non-sampled road section and each typical road section based on a fuzzy reasoning method.

And the speed weight determining module is used for calculating the speed weight corresponding to the h-th non-sampled road section according to the similarity of the h-th non-sampled road section and each typical road section.

And the road impedance determination module is used for calculating the road impedance corresponding to the h-th non-sampled road section according to the speed weight corresponding to the h-th non-sampled road section.

The judging module is used for judging whether h is smaller than K or not; if h is smaller than K, making h equal to h +1, and returning to the similarity determination module; if h is greater than or equal to K, executing a planning module; wherein K is the total number of the non-sampled road sections.

And the planning module is used for planning the driving path according to the road impedance corresponding to each non-sampled road section.

In an embodiment of the present invention, the typical road segment determining module further includes:

the acquisition unit is used for acquiring a plurality of sample road sections; the sample road segment comprises m road attribute values and speed weights;

the training unit is used for classifying the plurality of sample road sections by using a random forest method and training a prediction model;

the first speed weight calculation unit is used for calculating the first speed weight of each non-sampling road section according to the prediction model;

the comparison unit is used for determining n typical road sections according to the first speed weight of each non-sampling road section and the speed weights of a plurality of sample road sections; specifically, the speed weight of each sample road section is compared with the first speed weight of each non-sampled road section, and each sample road section within a set range is selected as a typical road section.

In the embodiment of the present invention, the similarity between the h-th non-sampled road segment and each typical road segment is calculated based on a fuzzy inference method, and a specific formula is as follows:

Figure BDA0002859539320000091

wherein, Pj,hJ-th road attribute value, S, representing h-th unsampled road segmenti,hRepresenting the similarity, k, of the h-th unsampled road segment to the i-th typical road segment1And w1Denotes a correction parameter, Pjt,hAnd j represents the j-th road attribute value of each typical road section corresponding to the h-th unexplored road section, and m is the number of the road attribute values.

In the embodiment of the present invention, the speed weight corresponding to the h-th non-sampled road section is calculated according to the similarity between the h-th non-sampled road section and each typical road section, and a specific formula is as follows:

Figure BDA0002859539320000092

wherein, WhRepresents the speed weight corresponding to the h-th non-sampled road section, Si,hRepresents the similarity of the h-th non-sampled road section and the i-th typical road section, Wi,hAnd the speed weight of the ith typical road section corresponding to the h-th unexplored road section is shown.

The invention mainly analyzes influence factors (road attribute values) influencing the driving safety of the mountainous area road, provides a weight assignment method considering the driving safety based on the principle that the lower the safety is, the higher the road impedance is, and realizes the planning of the mountainous area path according to the road impedance. According to the method, the influence factor data and the safe driving speed data of a typical road section are sampled, the classification mapping relation between the safe driving speed and the influence factors is constructed based on the thought of random forest classification, the problem that a weight assignment function is constructed directly through the influence factors is solved, the fuzzy membership degree of a fuzzy inference method is applied to weight assignment of a non-sampled road section sample, and the result is more accurate and reasonable than that of a direct sampling random forest classification method. Example verification results show that the path recommended by the evaluation method considering the safety weight, provided by the invention, can effectively avoid steep slopes and narrow-view road sections, and reduce the road passing chance with poor safety, so that scientific reference is provided for safe travel of the driver on the mountain road. The invention judges the safety of the driving road section and obtains a more reasonable driving path. The selection of the road attribute value is open, factors influencing the driving safety can be incorporated into the road attribute value according to the actual condition of the research area, and the clearer the analysis of the factors influencing the driving safety of the road is, the safer and more reasonable path can be obtained. And aiming at different types of mountain road characteristics, factors which influence safety more comprehensively are disclosed, and further intensive research is worth.

The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.

The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.

Claims (5)

1.一种路径规划方法，其特征在于，所述路径规划方法包括：1. A path planning method, wherein the path planning method comprises: S1：确定n个典型路段；S1: Determine n typical road segments; S2：令h＝1；S2: let h=1; S3：基于模糊推理方法计算第h个未采样路段与各个典型路段的相似度；具体公式为：S3: Calculate the similarity between the h-th unsampled road segment and each typical road segment based on the fuzzy inference method; the specific formula is:

Figure FDA0003276624910000011

Figure FDA0003276624910000011

 其中，Pj,h表示第h个未采样路段的第j个道路属性值，Si,h表示第h个未采样路段与第i个典型路段的相似度，k1和w1表示修正参数，Pjt,h表示第h个未采路段对应的各典型路段的第j个道路属性值，m为道路属性值的数量；Among them, P j,h represents the jth road attribute value of the hth unsampled road segment, S i,h represents the similarity between the hth unsampled road segment and the ith typical road segment, k 1 and w 1 represent the correction parameters , P jt,h represents the jth road attribute value of each typical road section corresponding to the hth uncollected road section, and m is the number of road attribute values; S4：根据第h个未采样路段与各典型路段的相似度计算第h个未采样路段对应的速度权重；具体公式为：S4: Calculate the speed weight corresponding to the h-th unsampled road segment according to the similarity between the h-th unsampled road segment and each typical road segment; the specific formula is:

Figure FDA0003276624910000012

Figure FDA0003276624910000012

 其中，Wh表示第h个未采样路段对应的速度权重，Si,h表示第h个未采样路段与第i个典型路段的相似度，Wi,h表示第h个未采路段对应的第i个典型路段的速度权重；Among them, W h represents the speed weight corresponding to the h-th unsampled road segment, S i,h represents the similarity between the h-th unsampled road segment and the i-th typical road segment, and Wi ,h represents the h-th unsampled road segment corresponding to The speed weight of the i-th typical road segment; S5：根据第h个未采样路段对应的速度权重计算第h个未采样路段对应的道路阻抗；具体公式为：S5: Calculate the road impedance corresponding to the h-th unsampled road section according to the speed weight corresponding to the h-th unsampled road section; the specific formula is:

Figure FDA0003276624910000013

Figure FDA0003276624910000013

 其中，length* h表示第h个未采样路段对应的道路阻抗，lengthh表示第h个未采样路段对应的道路长度，w* h表示第h个未采样路段对应的限速值，Wh表示第h个未采样路段对应的速度权重；Among them, length * h represents the road impedance corresponding to the h-th unsampled road segment, length h represents the road length corresponding to the h-th unsampled road segment, w * h represents the speed limit value corresponding to the h-th unsampled road segment, and W h represents The speed weight corresponding to the h-th unsampled road segment; S6：判断h是否小于K；如果h小于K，则令h＝h+1，并返回“S3”；如果h大于或等于K，则执行“S7”；其中K为未采样路段的总个数；S6: judge whether h is less than K; if h is less than K, set h=h+1, and return “S3”; if h is greater than or equal to K, execute “S7”; where K is the total number of unsampled road sections ; S7：根据各未采样路段对应的道路阻抗规划行驶路径。S7: Plan a driving route according to the road impedance corresponding to each unsampled road section. 2.根据权利要求1所述的路径规划方法，其特征在于，所述确定n个典型路段，具体包括：2. The route planning method according to claim 1, wherein the determining of n typical road sections specifically comprises: S11：采集多个样本路段；所述样本路段包括m个道路属性值和速度权重；S11: Collect multiple sample road sections; the sample road sections include m road attribute values and speed weights; S12：利用随机森林方法对多个样本路段进行分类并训练预测模型；S12: Use the random forest method to classify multiple sample road segments and train a prediction model; S13：根据所述预测模型计算各未采样路段的第一速度权重；S13: Calculate the first speed weight of each unsampled road segment according to the prediction model; S14：依据各未采样路段的所述第一速度权重与多个样本路段的速度权重确定n个典型路段。S14: Determine n typical road segments according to the first speed weight of each unsampled road segment and the speed weights of a plurality of sample road segments. 3.根据权利要求1所述的路径规划方法，其特征在于，所述根据各未采样路段对应的道路阻抗规划行驶路径，具体为：3. The path planning method according to claim 1, wherein the planning of the driving path according to the road impedance corresponding to each unsampled road section is specifically: 选择各未采样路段对应的道路阻抗最小的路段作为行驶路径。The road section with the smallest road impedance corresponding to each unsampled road section is selected as the driving path. 4.一种路径规划系统，其特征在于，所述路径规划系统包括：4. A path planning system, wherein the path planning system comprises: 典型路段确定模块，用于确定n个典型路段；A typical road segment determination module for determining n typical road segments; 赋值模块，用于令h＝1；Assignment module, used to make h=1; 相似度确定模块，用于基于模糊推理方法计算第h个未采样路段与各个典型路段的相似度；具体公式为：The similarity determination module is used to calculate the similarity between the h-th unsampled road section and each typical road section based on the fuzzy inference method; the specific formula is:

Figure FDA0003276624910000031

Figure FDA0003276624910000031

 其中，Pj,h表示第h个未采样路段的第j个道路属性值，Si,h表示第h个未采样路段与第i个典型路段的相似度，k1和w1表示修正参数，Pjt,h表示第h个未采路段对应的各典型路段的第j个道路属性值，m为道路属性值的数量；Among them, P j,h represents the jth road attribute value of the hth unsampled road segment, S i,h represents the similarity between the hth unsampled road segment and the ith typical road segment, k 1 and w 1 represent the correction parameters , P jt,h represents the jth road attribute value of each typical road section corresponding to the hth uncollected road section, and m is the number of road attribute values; 速度权重确定模块，用于根据第h个未采样路段与各典型路段的相似度计算第h个未采样路段对应的速度权重；具体公式为：The speed weight determination module is used to calculate the speed weight corresponding to the hth unsampled road section according to the similarity between the hth unsampled road section and each typical road section; the specific formula is:

Figure FDA0003276624910000032

Figure FDA0003276624910000032

 其中，Wh表示第h个未采样路段对应的速度权重，Si,h表示第h个未采样路段与第i个典型路段的相似度，Wi,h表示第h个未采路段对应的第i个典型路段的速度权重；Among them, W h represents the speed weight corresponding to the h-th unsampled road segment, S i,h represents the similarity between the h-th unsampled road segment and the i-th typical road segment, and Wi ,h represents the h-th unsampled road segment corresponding to The speed weight of the i-th typical road segment; 道路阻抗确定模块，用于根据第h个未采样路段对应的速度权重计算第h个未采样路段对应的道路阻抗；具体公式为：The road impedance determination module is used to calculate the road impedance corresponding to the h-th unsampled road section according to the speed weight corresponding to the h-th unsampled road section; the specific formula is:

Figure FDA0003276624910000033

Figure FDA0003276624910000033

 其中，length* h表示第h个未采样路段对应的道路阻抗，lengthh表示第h个未采样路段对应的道路长度，w* h表示第h个未采样路段对应的限速值，Wh表示第h个未采样路段对应的速度权重；Among them, length * h represents the road impedance corresponding to the h-th unsampled road segment, length h represents the road length corresponding to the h-th unsampled road segment, w * h represents the speed limit value corresponding to the h-th unsampled road segment, and W h represents The speed weight corresponding to the h-th unsampled road segment; 判断模块，用于判断h是否小于K；如果h小于K，则令h＝h+1，并返回“相似度确定模块”；如果h大于或等于K，则执行“规划模块”；其中K为未采样路段的总个数；The judgment module is used to judge whether h is less than K; if h is less than K, set h=h+1, and return the “similarity determination module”; if h is greater than or equal to K, execute the “planning module”; where K is The total number of unsampled road segments; 规划模块，用于根据各未采样路段对应的道路阻抗规划行驶路径。The planning module is used to plan the driving route according to the road impedance corresponding to each unsampled road section. 5.根据权利要求4所述的路径规划系统，其特征在于，所述典型路段确定模块还包括：5. The route planning system according to claim 4, wherein the typical road segment determination module further comprises: 采集单元，用于采集多个样本路段；所述样本路段包括m个道路属性值和速度权重；a collection unit, configured to collect a plurality of sample road sections; the sample road sections include m road attribute values and speed weights; 训练单元，用于利用随机森林方法对多个样本路段进行分类并训练预测模型；A training unit for classifying multiple sample road segments and training a prediction model using the random forest method; 第一速度权重计算单元，用于根据所述预测模型计算各未采样路段的第一速度权重；a first speed weight calculation unit, configured to calculate the first speed weight of each unsampled road section according to the prediction model; 比较单元，用于依据各未采样路段的所述第一速度权重与多个样本路段的速度权重确定n个典型路段。A comparison unit, configured to determine n typical road segments according to the first speed weight of each unsampled road segment and the speed weights of a plurality of sample road segments.
CN202011561630.8A 2020-12-25 2020-12-25 A path planning method and system Active CN112762954B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202011561630.8A CN112762954B (en) 2020-12-25 2020-12-25 A path planning method and system
ZA2021/09285A ZA202109285B (en) 2020-12-25 2021-11-19 Mountain road safety path planning method and system based on fuzzy random forest algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011561630.8A CN112762954B (en) 2020-12-25 2020-12-25 A path planning method and system

Publications (2)

Publication Number Publication Date
CN112762954A CN112762954A (en) 2021-05-07
CN112762954B true CN112762954B (en) 2021-11-02

Family

ID=75694402

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011561630.8A Active CN112762954B (en) 2020-12-25 2020-12-25 A path planning method and system

Country Status (2)

Country Link
CN (1) CN112762954B (en)
ZA (1) ZA202109285B (en)

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE10314119A1 (en) * 2003-03-28 2004-10-21 Dieter Dr. Bastian Process for determining an integral risk potential for a road user and device for carrying out the process
US8478499B2 (en) * 2010-06-07 2013-07-02 Ford Global Technologies, Llc System and method for vehicle speed monitoring using historical speed data
CN104567898B (en) * 2013-10-17 2017-09-12 中国移动通信集团公司 A kind of traffic route planing method, system and device
CN105808554B (en) * 2014-12-30 2019-09-24 高德软件有限公司 A kind of track data matching process and device
WO2016132395A1 (en) * 2015-02-18 2016-08-25 Hitachi, Ltd. Weight estimation system
CN106932839B (en) * 2015-12-31 2019-01-18 中国石油天然气股份有限公司 Method and device for adjusting rock density and speed curve
US10262530B2 (en) * 2016-12-20 2019-04-16 Cambridge Mobile Telematics Determining customized safe speeds for vehicles
CN107230389A (en) * 2017-07-26 2017-10-03 山西省交通科学研究院 A kind of mountain area winding road safety pre-warning system and method
US10474916B2 (en) * 2017-11-20 2019-11-12 Ashok Krishnan Training of vehicles to improve autonomous capabilities
CN108519095A (en) * 2018-03-08 2018-09-11 杭州后博科技有限公司 A kind of the guidance path danger coefficient computing system and method for combination geographical feature
CN111798039B (en) * 2020-06-12 2022-08-16 河海大学 Student pick-up auxiliary system

Also Published As

Publication number Publication date
ZA202109285B (en) 2022-03-30
CN112762954A (en) 2021-05-07

Similar Documents

Publication Publication Date Title
CN110866677B (en) 2023-04-18 Driver relative risk evaluation method based on benchmark analysis
CN112201038B (en) 2021-09-03 Road network risk assessment method based on risk of bad driving behavior of single vehicle
CN109448369B (en) 2021-08-03 Real-time operation risk calculation method for expressway
CN108430069B (en) 2021-05-18 A V2X Network Performance Test and Comprehensive Evaluation Analysis Method
CN102637357B (en) 2013-11-06 Regional traffic state assessment method
CN111210165B (en) 2023-04-07 Vehicle operation risk assessment system based on risk conduction coupling
CN104200687B (en) 2017-12-12 A kind of driver's speed control behavior monitoring device and monitoring method
CN103895649B (en) 2016-05-25 A kind of driver safety driving warning method
CN106781490A (en) 2017-05-31 Urban highway traffic analysis ＆ appraisement on operation system
CN111428960B (en) 2022-06-03 An automated evaluation method for intelligent vehicle drivability based on fusion of multi-source on-board sensor information
CN114783183A (en) 2022-07-22 Monitoring method and system based on traffic situation algorithm
CN113689071B (en) 2022-11-15 Multi-driver risk evaluation-based active intervention method for bad driving behaviors
CN109635852B (en) 2021-03-23 User portrait construction and clustering method based on multi-dimensional attributes
CN106022561A (en) 2016-10-12 Driving comprehensive evaluation method
CN111563555A (en) 2020-08-21 Driver driving behavior analysis method and system
CN109741599A (en) 2019-05-10 Traffic circulation evaluation method
CN113468670A (en) 2021-10-01 Method for evaluating performance of whole vehicle grade of automatic driving vehicle
CN111080158A (en) 2020-04-28 Urban intersection traffic danger index evaluation method based on composite weight
CN113753059A (en) 2021-12-07 A prediction method of driver's takeover ability under automatic driving system
CN112308136B (en) 2024-06-11 Driving distraction detection method based on SVM-Adaboost
CN116307699A (en) 2023-06-23 Road hidden trouble point segment grading method, device and storage medium based on multi-source data
CN107067729A (en) 2017-08-18 A kind of urban road traffic safety state evaluating method
CN110610326B (en) 2023-04-07 Driving management system based on driving data
CN112762954B (en) 2021-11-02 A path planning method and system
CN109584561A (en) 2019-04-05 Urban highway traffic evaluation of running status method based on floating car data

Legal Events

Date Code Title Description
2021-05-07 PB01 Publication
2021-05-07 PB01 Publication
2021-05-25 SE01 Entry into force of request for substantive examination
2021-05-25 SE01 Entry into force of request for substantive examination
2021-11-02 GR01 Patent grant
2021-11-02 GR01 Patent grant