CN114529088A - Driving path planning method and system based on accident risk cost - Google Patents
Driving path planning method and system based on accident risk cost Download PDFInfo
- Publication number
- CN114529088A CN114529088A CN202210157771.6A CN202210157771A CN114529088A CN 114529088 A CN114529088 A CN 114529088A CN 202210157771 A CN202210157771 A CN 202210157771A CN 114529088 A CN114529088 A CN 114529088A
- Authority
- CN
- China
- Prior art keywords
- accident
- path
- accident risk
- risk cost
- index
- Prior art date
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 78
- 206010039203 Road traffic accident Diseases 0.000 claims abstract description 45
- 238000011156 evaluation Methods 0.000 claims abstract description 43
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 28
- 238000011002 quantification Methods 0.000 claims abstract description 16
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 230000015654 memory Effects 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 2
- 238000011160 research Methods 0.000 description 13
- 238000004364 calculation method Methods 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 6
- 230000006399 behavior Effects 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 230000006698 induction Effects 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 3
- 125000002015 acyclic group Chemical group 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000012847 principal component analysis method Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004424 eye movement Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 231100000518 lethal Toxicity 0.000 description 1
- 230000001665 lethal effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a driving path planning method and a system based on accident risk cost, which comprises the following steps: acquiring historical traffic accident data, and preprocessing the data; establishing an accident risk cost evaluation index system according to historical traffic accident data; determining the weight of each index, and determining the accident risk cost of each road section according to the accident risk quantification model; and constructing an example network, and obtaining an optimal path by adopting a K shortest path solving algorithm based on the starting point, the end point, the accident risk cost of each path section and the travel time of each path section. According to the traffic accident data, a risk evaluation system is constructed from accident characteristics, an accident risk quantification model based on an entropy weight method is established, and a path planning algorithm comprehensively considering risk cost and transit time is designed so as to guide a driver to go out and improve driving safety.
Description
Technical Field
The invention relates to the technical field of path planning, in particular to a driving path planning method and system based on accident risk cost.
Background
The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.
The advanced driving assistance system can provide route planning and intelligent guidance for a driver, and is one of important means for improving the running efficiency of a traffic network, relieving traffic jam of urban roads and avoiding travel risks. However, conventional route planning mostly takes the minimum driving distance or driving time as an optimization target, and relatively few researches are made on the basis of the road accident risk cost.
In recent years, the research results on accident risks are many, and can be broadly divided into two categories:
1) on the basis of traffic accident data, road traffic safety evaluation research is developed by methods such as a Bayesian network and an accident rate method;
2) and (3) establishing an index evaluation system based on characteristics of people, vehicles, roads, environment and the like, and carrying out traffic accident risk evaluation research by combining methods such as an Analytic Hierarchy Process (AHP), an entropy weight method and a fuzzy evaluation method.
The road traffic safety aspect is researched by using traffic accident data, and Anthony and the like predict the accident rate by using a model combining Delphi technology and a Bayesian network based on the road traffic accident data, and evaluate the national road traffic safety; the Chu utilizes the ordered logit model to carry out accident cause analysis on serious accidents of a large bus running on a highway for a long distance, and researches show that factors such as fatigue driving, no fastening of a safety belt by a driver or a passenger, drunk driving and the like have obvious influence on the severity of the accidents; mohan et al evaluated urban traffic safety by using an accident rate method based on lethal traffic accident data of 6 cities, and found that most of the death people in traffic accidents are vulnerable traffic groups (pedestrians, bicycles, electric vehicles and motorcycle users); eusofe et al, Gomes et al, evaluate road traffic safety from the traffic management layer based on traffic accident data. An accident risk evaluation index aspect is constructed based on characteristics of people, vehicles, roads, environment and the like, an evaluation index system of road dangerous goods transportation risk is determined by document research and expert consultation of Li and the like, Zhao and the like, and a risk condition of dangerous goods transportation is evaluated by an Analytic Hierarchy Process (AHP); fernandez J.J. and the like use a questionnaire survey mode to rank and score factor indexes (such as bad driving behaviors of drivers, traffic sign mastering degree, distracted driving and the like) influencing road accidents by 535 manila drivers, and determine the weight of each index by combining an Analytic Hierarchy Process (AHP), wherein the results show that the bad driving behaviors of the drivers are main reasons for the traffic accidents; the method comprises the steps that a road safety evaluation index system is established by Temrungsie and the like according to a United nations road safety white paper, 100 experts engaged in traffic related industries are investigated to score indexes, an Analytic Hierarchy Process (AHP) is utilized to analyze road traffic safety influence factors, and the execution of traffic regulations is enhanced when traffic management is found to be disordered; the Cai and the like establish a road traffic safety risk estimation index system based on vehicle driving behavior data, provide a road traffic safety entropy calculation method based on an entropy weight method, and divide road traffic safety risk levels by utilizing K-means clustering; guo et al collect driver eye movement state and vehicle running state data through driving simulation experiments, construct a driver behavior index system, simplify indexes by adopting a principal component analysis method, and finally calculate characteristic index weight by utilizing an entropy weight method to evaluate the influence of driver behavior on traffic safety.
Most of the influencing factors about path selection in the existing path planning research are focused on minimizing the driving distance and the travel time, but the factors such as the character characteristics, the travel purpose and the road environment of a driver are rarely considered. The criteria for the driver to select the travel route are not fixed, so the meaning of "optimal" is also narrow, and the route recommended by the model does not necessarily meet the driver's expectation. Thus, many scholars incorporate into the path planning model factors that influence driver selection: the GRANTHAM trains historical route data of a driver by using a fuzzy neural network method, reflects the trip preference of the driver and provides guidance for the trip route selection of the vehicle-mounted navigation equipment; and the LEE estimates delay of the driver caused by poor travel behaviors through discrete selection analysis, and then compares travel time of different paths to recommend a more reliable path for the driver. However, there are many factors influencing the travel selection of drivers, wherein the route guidance considering traffic safety is increasingly emphasized by learners, and KARIM establishes a shortest path model fusing the travel time and the safety of the route by analyzing the relationship between traffic conflicts and collisions; PAYYANADAN, accident risk indexes such as left turn, turning around and travel distance of the old driver are quantified by using collision accident data of the old driver, and the safety degree of the driving path is evaluated based on the accident risk indexes, so that the old driver is assisted to select a safer traveling path, and the accident risk of the old driver is reduced; according to parameters such as traffic volume, traffic capacity and the like, a prediction model of path travel time and accident risk cost is established, and a path planning algorithm of drivers with different risk tendencies is designed from the perspective of generalized travel expenses.
From the above, it can be seen that many scholars have made a lot of research on accident risk and path planning, but there still exist certain disadvantages:
1) the method has the advantages that the road traffic safety evaluation research based on the traffic accident data utilizes the statistical data after the accident occurs, the road traffic safety state after the accident occurs can be evaluated, but the prevention and the pre-control before the accident occur are more important, and the method lacks the risk estimation before the accident occurs;
2) the road transportation risk research of an index system is established according to physical characteristics of people, vehicles, roads, environment and the like, and the risk state is mostly evaluated through questionnaire survey, expert scoring and a hierarchical analysis model by combining objective analysis and subjective evaluation. However, the questionnaire survey mode has high subjectivity, is greatly influenced by the risk preference and experience of scoring experts, has strong subjectivity, and is lack of data support, so that the obtained evaluation is not accurate and objective.
In the aspect of path planning research, the conventional path guidance system usually takes the minimum driving mileage or travel time as an optimal target, and although there is a path guidance research considering driver selection preference and driving safety, the research of constructing a path guidance model based on the road accident risk cost is still less.
Disclosure of Invention
In order to solve the defects of the prior art, the invention provides a driving path planning method and a driving path planning system based on accident risk cost; according to the traffic accident data, a risk evaluation system is constructed from accident characteristics, an accident risk quantification model based on an entropy weight method is established, and a path planning algorithm comprehensively considering risk cost and transit time is designed so as to guide a driver to go out and improve driving safety.
In a first aspect, the invention provides a driving path planning method based on accident risk cost;
the driving path planning method based on the accident risk cost comprises the following steps:
acquiring historical traffic accident data, and preprocessing the data;
establishing an accident risk cost evaluation index system according to historical traffic accident data;
determining the weight of each index, and determining the accident risk cost of each road section according to the accident risk quantification model;
and constructing an example network, and obtaining an optimal path by adopting a K shortest path solving algorithm based on the starting point, the end point, the accident risk cost of each path section and the travel time of each path section.
In a second aspect, the invention provides a driving path planning system based on accident risk cost;
driving path planning system based on accident risk cost includes:
an acquisition module configured to: acquiring historical traffic accident data, and preprocessing the data;
an evaluation index system creation module configured to: establishing an accident risk cost evaluation index system according to historical traffic accident data;
an accident risk cost determination module configured to: determining the weight of each index, and determining the accident risk cost of each road section according to the accident risk quantification model;
an optimal path solving module configured to: and constructing an example network, and obtaining an optimal path by adopting a K shortest path solving algorithm based on the starting point, the end point, the accident risk cost of each path section and the travel time of each path section.
In a third aspect, the present invention further provides an electronic device, including:
a memory for non-transitory storage of computer readable instructions; and
a processor for executing the computer readable instructions,
wherein the computer readable instructions, when executed by the processor, perform the method of the first aspect.
In a fourth aspect, the present invention also provides a storage medium storing non-transitory computer readable instructions, wherein the non-transitory computer readable instructions, when executed by a computer, perform the instructions of the method of the first aspect.
In a fifth aspect, the invention also provides a computer program product comprising a computer program for implementing the method of the first aspect when run on one or more processors.
Compared with the prior art, the invention has the beneficial effects that:
the method comprises the steps of establishing an accident risk evaluation system based on traffic accident data, constructing an accident risk cost quantification model based on human-vehicle-road-environment multifactor, calculating each index weight by using an entropy weight method, and determining accident risk of a road section; then, a path planning model comprehensively considering risk cost and transit time is designed based on the improved K shortest path algorithm. The conclusion of the invention is as follows:
1) a risk index evaluation system is constructed based on historical accident data, index weight is calculated by adopting an entropy weight method, and an accident risk cost calculation model is provided, so that objective quantification of vehicle driving risk is realized, and the defect that the subjectivity of the traditional risk evaluation method is too high is overcome.
2) A path induction model meeting multiple constraints is designed based on an improved K shortest path algorithm, the model comprehensively considers the path risk cost and the travel time, selects an optimal travel path with low risk and short travel time for a driver, and has theoretical and practical application values in the aspects of road transportation risk assessment and accident prevention.
3) According to the invention, the accident risk of the road section is quantized, and the route guidance model based on the accident risk cost is designed, so that a travel route with higher safety is provided for a driver, the traffic accident risk can be effectively reduced, and the driving safety is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a flowchart of a method according to a first embodiment;
FIG. 2 is a schematic diagram of an exemplary network according to the first embodiment;
fig. 3 is a diagram illustrating a path selection result according to the first embodiment.
Detailed Description
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular is intended to include the plural unless the context clearly dictates otherwise, and furthermore, it should be understood that the terms "comprises" and "comprising," 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.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
All data are obtained according to the embodiment and are legally applied on the data on the basis of compliance with laws and regulations and user consent.
In recent years, the holding amount of automobiles is continuously increased, and the imbalance between road traffic demand and supply brings about serious traffic jam and traffic safety problems. In order to reduce the travel risk of a driver, the invention provides a driver path planning method based on traffic accident risk cost. Firstly, establishing an accident risk evaluation system based on traffic accident data, and constructing an accident risk cost quantification model based on human-vehicle-road-environment multifactor; secondly, calculating the weight of each index by using an entropy weight method, and determining the accident risk of the road section under the human-vehicle-road-environment multi-factor condition; then, a path planning model is established, a solving algorithm based on K shortest paths is designed, the accident risk cost and the path travel time are comprehensively considered, and the optimal path is solved. The results show that: an accident risk cost calculation model established based on historical accident data can quantify the vehicle driving risk; the path planning method based on the accident risk cost can assist a driver to select an optimal travel path with low risk and short travel time, and is beneficial to improving the driving safety and efficiency of the driver.
In order to realize path planning based on accident risk, firstly, the accident risk of a road section needs to be quantized, the traffic accident data is used, physical characteristic indexes such as people, vehicles, roads, environments and the like which can influence the accident severity in a data set are screened out to construct a risk evaluation system, an accident risk cost quantization model is established, and an entropy weight method is used for calculating index weight. Based on the method, real-time risks of the road sections are calculated, the travel time of the road sections is loaded, and a calculation example network is constructed. And then, improving the K shortest path algorithms for limiting loop-free, taking the accident risk cost as a main target, comprehensively considering the path travel time, and searching the optimal path in the example network. The technical route of the invention is shown in figure 1.
Example one
The embodiment provides a driving path planning method based on accident risk cost;
as shown in fig. 1, the driving path planning method based on accident risk cost includes:
s101: acquiring historical traffic accident data, and preprocessing the data;
s102: establishing an accident risk cost evaluation index system according to historical traffic accident data;
s103: determining the weight of each index, and determining the accident risk cost of each road section according to the accident risk quantification model;
s104: and constructing an example network, and obtaining an optimal path by adopting a K shortest path solving algorithm based on the starting point, the end point, the accident risk cost of each path section and the travel time of each path section.
Further, the step S101: acquiring historical traffic accident data; wherein the historical traffic accident data comprises: state description of personnel, vehicles, environment and the like when an accident occurs, and data of accident type, casualty conditions and the like; such as: the driver's age, sex, whether the driver is distracted, tired, speeding, whether the vehicle is off lane, vehicle type, whether the vehicle is transporting dangerous goods, road section where accident occurs, road type, road alignment, road surface condition, time, whether it is a working day, day or night, weather and light conditions, etc.
Further, preprocessing the data; the method specifically comprises the following steps:
cleaning the data to delete abnormal values;
because the data set comprises a plurality of tables, each data is in different tables, and the data tables need to be uniformly combined according to accident numbers.
Further, S102: establishing an accident risk cost evaluation index system according to historical traffic accident data; wherein the evaluation index comprises: the age of the driver; whether the driver is distracted; whether fatigue driving is present; whether the operation is not appropriate for deviating from the lane; whether the vehicle is running at overspeed; the number of drunk driving persons; whether safety equipment in the vehicle is used (such as a safety belt and a safety seat); the gender of the driver; driver certification conditions; recording vehicle accidents; whether the accident involves a large vehicle; whether the vehicle carries dangerous goods; a road type; whether the road has an intersection or not; road line shape; road surface condition; traffic control measures; accident occurrence is weekday/weekend; day/night; weather conditions; lighting conditions;
determination process of evaluation index: according to four elements of the traffic system, namely people, vehicles, roads and environment, and accident data, indexes which belong to the four elements of the traffic system and influence the severity of the traffic accident are screened out.
Further, S103: determining the weight of each index, and determining the accident risk cost of each road section according to the accident risk quantification model; the weight of each evaluation index is determined in the following mode:
and calculating the weight of each evaluation index by adopting an entropy weight method.
Further, the weight of each evaluation index is calculated by adopting an entropy weight method; the method specifically comprises the following steps:
s1031: for n traffic accident samples, m indexes are xijThe value of the j index of the i sample;
s1032: normalization processing of indexes: heterogeneous indexes are homogenized;
the forward direction index is as follows:
negative direction index:
s1033: calculating the proportion of the ith sample value in the j index:
s1034: calculating the entropy value of the j index:
wherein k is 1/ln (n) > 0, and satisfies ej≥0；
S1035: computing information entropy redundancy (difference):
dj＝1-ej,j＝1,…,m (5)
s1036: calculating the weight of each index:
wherein x isijIs normalized data.
It should be understood that, for the index weight calculation, there are an entropy weight method, an analytic hierarchy process, a principal component analysis method, and the like, where the entropy weight method is an objective weighting method and has higher reliability and accuracy relative to subjective weighting. According to the explanation of the basic principle of information theory, information is a measure of the degree of system order, entropy is a measure of the degree of system disorder, and according to the definition of information entropy, for a certain index, the dispersion degree of the certain index can be judged by using an entropy value, and the smaller the information entropy value is, the greater the dispersion degree of the index is, the greater the influence (namely weight) of the index on comprehensive evaluation is. The method is more suitable for describing the influence of abnormal values in indexes such as people, vehicles, roads, environment and the like on the severity of the accident. For example, for several different traffic accidents, if a certain index value changes greatly and other index values do not change basically, it indicates that the index causes the difference of the accidents, and a larger weight can be taken.
It should be noted that the entropy weight method can calculate the index weight value, but there is a problem that the zero-value index entropy value cannot be calculated in the practical application process, so when some index value has zero, all the evaluation index data of the group is increased by 0.00001, and the addition of the small increment does not discard the group of data and ensures that the difference of each index is less influenced.
Further, S103: determining the weight of each index, and determining the accident risk cost of each road section according to the accident risk quantification model; the method specifically comprises the following steps:
wherein Z isiAccident risk cost for the ith sample; dijReal data corresponding to the j index for the ith sample; w is ajIs the jth index weight.
In a traffic system, the mutual influence among human, vehicle, road and environment elements is comprehensively considered when an accident occurs, and the time-space change of the state of each element can influence the occurrence of the traffic accident and the severity of the accident at any time. In the prior art, traffic safety analysis is performed mostly by a method for constructing a risk index system, but subjective assumption is more for screening indexes and determining weights. The invention screens risk evaluation indexes from the traffic accident data set, calculates index weight, calculates comprehensive score according to real-time data, defines the comprehensive score as accident risk and can reflect the influence of each element on the accident risk.
Further, S104: constructing an example network, and obtaining an optimal path by adopting a K shortest path solving algorithm based on a starting point, an end point, the accident risk cost of each path section and the travel time of each path section; the method specifically comprises the following steps:
s1041: initializing a traffic network, and determining a starting point s, an end point t and a number K of alternative paths of a path;
s1042: loading the accident risk cost of each road section and the travel time of each road section into a traffic network;
s1043: aiming at accident risk cost, Dijkstra is used for solving the shortest path p from s to t by using Dijkstra algorithmk；
S1044: if K is larger than or equal to K, turning to S1047;
if k is<K, then the shortest path pkAll nodes v except the end point tiAll the nodes are regarded as deviating nodes, and the total number of the nodes is x (i is more than or equal to 0 and less than or equal to x);
s1045: traversing all the deviated nodes to obtain each deviated node viShortest path to end point t, pkFrom the starting point s to viAnd the obtained viThe shortest route phase concatenation to end point t is stored as a candidate route in the set P'kPerforming the following steps;
s1046: candidate Path set P'kIf the status is empty, go to S1047; if not, calculating the travel time of each candidate path to obtain the path p with the shortest fulfillment timek+1Will path pk+1From set P'kRemoving from the collection, putting into the collection PkIn, return to S1044;
s1047: and screening the optimal path with the minimum path travel time from the K candidate paths to obtain a result.
And a plurality of paths are arranged between the starting point and the end point, and each path is connected in sequence by a plurality of road sections.
It should be understood that, in the conventional path guidance algorithm, weights of edges in a network graph are added to find the shortest path, and a K shortest path problem (KSP) is a variation of the shortest path problem, and unlike the conventional shortest path problem, the KSP problem aims to find multiple alternative optimized paths between a starting point and an ending point in the graph to form a shortest path group, so as to meet selection requirements of users on different paths to the greatest extent. Based on the improvement of the K shortest path algorithm, the invention designs the path induction algorithm meeting multiple constraints, namely, in the K shortest path set obtained by calculating the accident cost, the path with the minimum path travel time T is the optimal path.
K shortest path problem (K short paths, KSP): let G ═ V, E denote a network graph, where V is a set of n nodes and E is a set of m edges. E each edge EkRepresented by a node pair, i.e. ek＝(i,j)，ci,jIndicating the length of the edge. Assuming that s and t are two nodes in graph G, the path p from s to t in the graph is represented by a sequence of nodes, i.e. p ═ v1＝s,v2,…,vhT), s and t are called the initial node and the terminal node of p, respectively. The length c (p) of p is the sum of the lengths of all sides on p, i.e. c (p) ═ Σ(i,j)∈pcij。
For the collection of paths from s to t, PstIt is shown that the shortest path problem is to find the path p with the smallest length from s to t*I.e. determining p*∈PstSo that for any other P (P ∈ P)st,p≠p*) All have c (p)*) C (p) is less than or equal to c. The KSP problem is an extension to the shortest path problem, and it is to determine a secondary short path and a third short path in addition to the shortest path until the kth short path is found. By pkRepresenting the kth short path from s to t, the KSP problem is to determine a set of paths PK＝{p1,p2,…,pk}∈PstSo that the following 3 conditions are satisfied:
(1) the K paths are generated in order, i.e. p for all i (i ═ 1,2, …, K-1), piIs at piDetermined before + 1;
(2) the K paths are arranged in lengths from small to large, i.e. for all i (i ═ 1,2, …, K-1) there is c (p)i)<c(pi+1)；
(3) The K paths are shortest, i.e. for all P ∈ Pst-PKAll have c (p)K)<c(p)。
The KSP problem is generally divided into two categories according to path restriction conditions: the KSP problem in general and the problem of defining acyclic KSP. The KSP problem in general has no restrictions on the path; the constraint of the loop-free KSP problem requires that the path to be solved is a simple path and cannot contain loops. The network map of the present invention does not contain rings and therefore only analyzes the KSP problem that is defined as ring-free.
The invention adopts the deviation path algorithm to calculate and limit the problem of the acyclic KSP, and the core of the deviation path algorithm is how to utilize the p which is obtained1,p2,…,pkIs found for the shortest deviation path pk+1First, the Dijkstra algorithm is used to find the shortest path from s to t and treat it as p1Put into Path set PkIn (3), k paths { p) before obtaining1,p2,…,pkAfter that, p is calculatedk+1The process of (2) is as follows:
(1) get pkOf each node v except the terminating nodeiAs possible departure nodes, calculate viShortest path to node t, from node v in order to avoid duplication with previously found pathsiThe dropped edge cannot be connected to the shortest path p found before1,p2,…,pkFrom v to viThe separated edges are the same;
(2) the slave v to be foundiShortest path to node t and current path pkFrom s to viIs formed by path splicing ofk+1And stores it in the candidate route set P'kPerforming the following steps;
(3) from candidate Path set P'kThe shortest one of them is selected as pk+1And put it into the path set PkPerforming the following steps;
repeating the steps until K paths are obtained.
The invention uses the 2019 traffic accident data counted by the national highway traffic safety administration of a country, and the data set covers the detailed data of the traffic accidents occurring in 2019, including the state description of personnel, vehicles, environment and the like, the accident type, casualty conditions and other data when the accidents occur. According to four elements of a traffic system: people, vehicles, roads and environments systematically screen risk factors in the data sets, including 22 indexes (see table 1) such as the time of an accident, the sex of a driver, the road alignment and the weather, which have different influences on the severity of the accident.
TABLE 1 Accident cost impact factor index set
(A _ D15_ 20: young drivers of age 15-20; A _ D65 PLS: elderly drivers of age > 65; A _ DIST: distracted driving; A _ DROWSY: fatigue driving; A _ RELRD: mishandling off-lanes; A _ SPCRA: speeding; DRYNK _ DR: drunk driving population; REST _ USE: in-vehicle safety, Sex: driver gender; A _ LIC _ S: driver status; PREV _ ACC: accident recording; A _ LT: large vehicle; HAZ _ INV: dangerous cargo; A _ RU: road type; A _ INTESC: road intersection; VALIGN: road alignment; VSURCOND: road status; VTFCRAON: traffic control facility; A _ DOW: working day/weekend; A _ TOLGD: day/night; WEATHER: CON: light condition)
The data set has complex structure, numerous indexes and large sample size, so that the abnormal data needs to be cleaned and deleted. And then screening influence factor indexes, distributing the influence factors in a plurality of data tables, connecting the screened data tables according to accident numbers for facilitating subsequent data processing, and combining the screened data tables into one data table (see table 2), wherein the processed data table totally comprises 26218 accident data and 22 accident cost influence factors.
Table 2 partial results after data preprocessing
Quantifying the accident risk cost: an entropy weight method is realized by using Python, and objective weighting is carried out on the indexes, wherein the index entropy value and the weight are shown in a table 3.
TABLE 3 Accident cost impact factor index weight calculation results
In combination with equation (7), the calculation formula of the accident risk cost of the vehicle running on a certain road section is as follows:
Zi＝0.026981dij+0.034764dij+…+0.039489dij+0.068413dij (8)
in the formula: z is a linear or branched memberiAccident risk cost for the ith road segment; dijReal-time data of j index of the ith road section; 1, …, n; j is 1, …, m.
Route induction example analysis: the road network adopted by the calculation example consists of 10 nodes and 14 road segments, and is particularly shown in fig. 2 and 3. The corresponding attribute of each road section is given by assuming the real-time people, vehicles, roads, environment and other parameters of the road network, and the accident risk cost of each road section is calculated according to a formula (8) on the basis of the attribute, and the result is shown in a table 4.
TABLE 4 network characteristic parameters
Python is used for realizing a path induction model algorithm, network parameters are input, K is set to be 3 (namely 3 candidate paths are calculated), and v is solved by a Dijkstra algorithm by taking risk cost as a target1To v10Shortest path p of1＝(v1,v3,v4,v5,v9,v10) Path risk cost ∑ Zi＝6.19，p2The detailed calculation steps are as follows:
TABLE 5 off-path Algorithm
Obtaining four candidate paths after traversing each deviated node, and respectively calculating the travel time of each candidate path as follows: 31, 31, 29, 33. Selecting the path with the shortest path travel time as p2Thus, the second path of the output is: p is a radical of2＝(v1,v3,v4,v8,v9,v10)。
Similarly, the third path of the model output is: p is a radical of3＝(v1,v2,v4,v5,v9,v10) Referring to Table 6, the path having the minimum travel time is selected as the optimal path, p1,p2The path travel times are all 29, but p1Lower risk cost, therefore p1＝(v1,v3,v4,v5,v9,v10) A path is optimized for the network.
Table 6 shortest path list
According to the path selection result, the following steps are known: the model takes path accident risk cost as a main target to comprehensively consider path travel time to realize multi-constraint path induction, and the selected optimal path meets the requirement of shorter travel time on the basis of lower risk cost, so that the path accident risk cost and the optimal path travel time are kept in a relatively balanced state.
Example two
The embodiment provides a driving path planning system based on accident risk cost;
driving path planning system based on accident risk cost includes:
an acquisition module configured to: acquiring historical traffic accident data, and preprocessing the data;
an evaluation index system creation module configured to: establishing an accident risk cost evaluation index system according to historical traffic accident data;
an accident risk cost determination module configured to: determining the weight of each index, and determining the accident risk cost of each road section according to the accident risk quantification model;
an optimal path solving module configured to: and constructing an example network, and obtaining an optimal path by adopting a K shortest path solving algorithm based on the starting point, the end point, the accident risk cost of each path section and the travel time of each path section.
It should be noted here that the acquiring module, the evaluation index system establishing module, the accident risk cost determining module and the optimal path solving module correspond to steps S101 to S104 in the first embodiment, and the modules are the same as the corresponding steps in the implementation example and application scenario, but are not limited to the disclosure in the first embodiment. It should be noted that the modules described above as part of a system may be implemented in a computer system such as a set of computer-executable instructions.
In the foregoing embodiments, the descriptions of the embodiments have different emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
The proposed system can be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the above-described modules is merely a logical division, and in actual implementation, there may be other divisions, for example, multiple modules may be combined or integrated into another system, or some features may be omitted, or not executed.
EXAMPLE III
The present embodiment also provides an electronic device, including: one or more processors, one or more memories, and one or more computer programs; wherein, a processor is connected with the memory, the one or more computer programs are stored in the memory, and when the electronic device runs, the processor executes the one or more computer programs stored in the memory, so as to make the electronic device execute the method according to the first embodiment.
It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and so on. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may include both read-only memory and random access memory, and may provide instructions and data to the processor, and a portion of the memory may also include non-volatile random access memory. For example, the memory may also store device type information.
In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software.
The method in the first embodiment may be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor. The software modules may be located in ram, flash, rom, prom, or eprom, registers, among other storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor. To avoid repetition, it is not described in detail here.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
Example four
The present embodiments also provide a computer-readable storage medium for storing computer instructions, which when executed by a processor, perform the method of the first embodiment.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, 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 invention should be included in the protection scope of the present invention.
Claims (10)
1. The driving path planning method based on accident risk cost is characterized by comprising the following steps:
acquiring historical traffic accident data, and preprocessing the data;
establishing an accident risk cost evaluation index system according to historical traffic accident data;
determining the weight of each index, and determining the accident risk cost of each road section according to the accident risk quantification model;
and constructing an example network, and obtaining an optimal path by adopting a K shortest path solving algorithm based on the starting point, the end point, the accident risk cost of each path section and the travel time of each path section.
2. The accident risk cost-based driving path planning method according to claim 1, wherein each index weight is determined, and the accident risk cost of each road section is determined according to an accident risk quantification model; the weight of each evaluation index is determined in the following mode:
and calculating the weight of each evaluation index by adopting an entropy weight method.
3. The accident risk cost-based driving path planning method according to claim 2, wherein the weight of each evaluation index is calculated by using an entropy weight method; the method specifically comprises the following steps:
(11): for n traffic accident samples, m indexes are xijThe value of the j index of the ith sample;
(12): normalization processing of indexes: heterogeneous indexes are homogenized;
the forward direction index is as follows:
negative direction index:
(13): calculating the proportion of the ith sample value in the j index:
(14): calculating the entropy value of the j index:
wherein k is 1/ln (n) > 0, and satisfies ej≥0；
(15): calculating the information entropy redundancy:
dj＝1-ej,j＝1,…,m (5)
(16): calculating the weight of each index:
wherein x isijIs normalized data.
4. The accident risk cost-based driving path planning method of claim 1,
determining the weight of each index, and determining the accident risk cost of each road section according to the accident risk quantification model; the method specifically comprises the following steps:
wherein Z isiAccident risk cost for the ith sample; dijReal data corresponding to the j index for the ith sample; w is ajIs the jth index weight.
5. The driving path planning method based on accident risk cost according to claim 1, wherein an example network is constructed, and an optimal path is obtained by adopting K shortest path solving algorithms based on a starting point, a destination point, the accident risk cost of each road section and the travel time of each road section; the method specifically comprises the following steps:
(21): initializing a traffic network, and determining a starting point s, an end point t and a number K of alternative paths of a path;
(22): loading the accident risk cost of each road section and the travel time of each road section into a traffic network;
(23): aiming at accident risk cost, Dijkstra is used for solving the shortest path p from s to t by using Dijkstra algorithmk；
(24): if K is more than or equal to K, turning to (27);
if k is<K, then the shortest path pkAll nodes v except the end point tiAll the nodes are regarded as deviating nodes, x are counted, and i is more than or equal to 0 and less than or equal to x;
(25): traversing all the deviated nodes to obtain each deviated node viShortest path to end point t, pkFrom the starting point s to viAnd the obtained viThe shortest route phase concatenation to end point t is stored as a candidate route in the set P'kPerforming the following steps;
(26): candidate Path set P'kIf the signal is empty, turning to (27); if not, calculating the travel time of each candidate path to obtain the path p with the shortest fulfillment timek+1Will path pk+1From set P'kRemoving from the collection, putting into the collection PkIn (5), returning to (24);
(27): and screening the optimal path with the minimum path travel time from the K candidate paths to obtain a result.
6. The accident risk cost-based driving path planning method of claim 1, wherein historical traffic accident data is obtained; wherein the historical traffic accident data comprises: description of personnel, vehicles and environment states, accident type and casualty condition when an accident occurs.
7. The accident risk cost-based driving path planning method of claim 1,
establishing an accident risk cost evaluation index system according to historical traffic accident data; wherein, the evaluation index comprises: the age of the driver; whether distracted driving is performed; whether fatigue driving is present; whether the operation is not appropriate for deviating from the lane; whether the vehicle runs at an overspeed; the number of drunk drivers; whether safety facilities in the vehicle are used or not; the sex of the driver; driver certification conditions; recording vehicle accidents; whether the accident involves a large vehicle; whether the vehicle carries dangerous goods; a road type; whether the road has an intersection or not; road line shape; the condition of the road surface; traffic control measures; accident occurrence is weekday/weekend; day/night; weather conditions; lighting conditions;
determination process of evaluation index: according to four elements of the traffic system, namely people, vehicles, roads and environment, and accident data, indexes which belong to the four elements of the traffic system and influence the severity of the traffic accident are screened out.
8. Driving path planning system based on accident risk cost, characterized by includes:
an acquisition module configured to: acquiring historical traffic accident data, and preprocessing the data;
an evaluation index system creation module configured to: establishing an accident risk cost evaluation index system according to historical traffic accident data;
an incident risk cost determination module configured to: determining the weight of each index, and determining the accident risk cost of each road section according to the accident risk quantification model;
an optimal path solving module configured to: and constructing an example network, and obtaining an optimal path by adopting a K shortest path solving algorithm based on the starting point, the end point, the accident risk cost of each path section and the travel time of each path section.
9. An electronic device, comprising:
a memory for non-transitory storage of computer readable instructions; and
a processor for executing the computer readable instructions,
wherein the computer readable instructions, when executed by the processor, perform the method of any of claims 1-7.
10. A storage medium storing non-transitory computer-readable instructions, wherein the non-transitory computer-readable instructions, when executed by a computer, perform the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210157771.6A CN114529088A (en) | 2022-02-21 | 2022-02-21 | Driving path planning method and system based on accident risk cost |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210157771.6A CN114529088A (en) | 2022-02-21 | 2022-02-21 | Driving path planning method and system based on accident risk cost |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114529088A true CN114529088A (en) | 2022-05-24 |
Family
ID=81625183
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210157771.6A Pending CN114529088A (en) | 2022-02-21 | 2022-02-21 | Driving path planning method and system based on accident risk cost |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114529088A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115115318A (en) * | 2022-07-27 | 2022-09-27 | 山东大学 | Dangerous goods transportation network planning method and system considering user path selection behavior |
| CN115169996A (en) * | 2022-09-06 | 2022-10-11 | 天津所托瑞安汽车科技有限公司 | Road risk determination method, apparatus and storage medium |
| CN115994689A (en) * | 2023-03-22 | 2023-04-21 | 交通运输部水运科学研究所 | Management method and device for safe transportation of dangerous goods in intelligent dock and harbor district |
| CN116910853A (en) * | 2023-06-28 | 2023-10-20 | 深圳市蕾奥规划设计咨询股份有限公司 | Pedestrian travel simulation method and device for TOD three-dimensional slow-going space |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105634954A (en) * | 2016-01-08 | 2016-06-01 | 烽火通信科技股份有限公司 | Shortest path calculation method by considering light damage based on WSON |
| CN112037513A (en) * | 2020-09-01 | 2020-12-04 | 清华大学 | Real-time traffic safety index dynamic comprehensive evaluation system and construction method thereof |
| CN112116136A (en) * | 2020-09-04 | 2020-12-22 | 上海汽车集团股份有限公司 | Shortest path generation method and related device |
| CN112201038A (en) * | 2020-09-28 | 2021-01-08 | 同济大学 | Road network risk assessment method based on risk of bad driving behavior of single vehicle |
| CN112232682A (en) * | 2020-07-22 | 2021-01-15 | 同济大学 | Method and system for determining and grading environmental risk degree of automatic driving open test road |
| CN112419719A (en) * | 2020-11-18 | 2021-02-26 | 济南北方交通工程咨询监理有限公司 | Method and system for evaluating traffic operation safety of highway |
| CN112446538A (en) * | 2020-11-23 | 2021-03-05 | 合肥工业大学 | Optimal path obtaining method based on personalized risk avoidance |
| CN112565082A (en) * | 2020-12-25 | 2021-03-26 | 鹏城实验室 | Service chain mapping method based on hybrid network, intelligent terminal and storage medium |
| CN113361997A (en) * | 2021-06-04 | 2021-09-07 | 南京大学 | Dangerous waste transportation path real-time planning method based on risk minimization |
-
2022
- 2022-02-21 CN CN202210157771.6A patent/CN114529088A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105634954A (en) * | 2016-01-08 | 2016-06-01 | 烽火通信科技股份有限公司 | Shortest path calculation method by considering light damage based on WSON |
| CN112232682A (en) * | 2020-07-22 | 2021-01-15 | 同济大学 | Method and system for determining and grading environmental risk degree of automatic driving open test road |
| CN112037513A (en) * | 2020-09-01 | 2020-12-04 | 清华大学 | Real-time traffic safety index dynamic comprehensive evaluation system and construction method thereof |
| CN112116136A (en) * | 2020-09-04 | 2020-12-22 | 上海汽车集团股份有限公司 | Shortest path generation method and related device |
| CN112201038A (en) * | 2020-09-28 | 2021-01-08 | 同济大学 | Road network risk assessment method based on risk of bad driving behavior of single vehicle |
| CN112419719A (en) * | 2020-11-18 | 2021-02-26 | 济南北方交通工程咨询监理有限公司 | Method and system for evaluating traffic operation safety of highway |
| CN112446538A (en) * | 2020-11-23 | 2021-03-05 | 合肥工业大学 | Optimal path obtaining method based on personalized risk avoidance |
| CN112565082A (en) * | 2020-12-25 | 2021-03-26 | 鹏城实验室 | Service chain mapping method based on hybrid network, intelligent terminal and storage medium |
| CN113361997A (en) * | 2021-06-04 | 2021-09-07 | 南京大学 | Dangerous waste transportation path real-time planning method based on risk minimization |
Non-Patent Citations (1)
| Title |
|---|
| 李丰军等: "煤矿水害风险评价与防治决策***研究", 30 April 2012, 中国地质大学出版社, pages: 70 - 72 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115115318A (en) * | 2022-07-27 | 2022-09-27 | 山东大学 | Dangerous goods transportation network planning method and system considering user path selection behavior |
| CN115169996A (en) * | 2022-09-06 | 2022-10-11 | 天津所托瑞安汽车科技有限公司 | Road risk determination method, apparatus and storage medium |
| CN115169996B (en) * | 2022-09-06 | 2022-12-13 | 天津所托瑞安汽车科技有限公司 | Road risk determination method, apparatus and storage medium |
| CN115994689A (en) * | 2023-03-22 | 2023-04-21 | 交通运输部水运科学研究所 | Management method and device for safe transportation of dangerous goods in intelligent dock and harbor district |
| CN116910853A (en) * | 2023-06-28 | 2023-10-20 | 深圳市蕾奥规划设计咨询股份有限公司 | Pedestrian travel simulation method and device for TOD three-dimensional slow-going space |
| CN116910853B (en) * | 2023-06-28 | 2024-05-17 | 深圳市蕾奥规划设计咨询股份有限公司 | Pedestrian travel simulation method and device for TOD three-dimensional slow-going space |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114529088A (en) | Driving path planning method and system based on accident risk cost | |
| CN112700072B (en) | Traffic condition prediction method, electronic device, and storage medium | |
| Dogan et al. | A corridor selection for locating autonomous vehicles using an interval-valued intuitionistic fuzzy AHP and TOPSIS method | |
| US20220222556A1 (en) | Road traffic jam early warning method and system | |
| Quattrone et al. | Random and fuzzy utility models for road route choice | |
| JP4796167B2 (en) | Event judgment device | |
| Owczarzak et al. | Design of passenger public transportation solutions based on autonomous vehicles and their multiple criteria comparison with traditional forms of passenger transportation | |
| Dakic et al. | On the modeling of passenger mobility for stochastic bi-modal urban corridors | |
| Huang et al. | Investigation of bimodal macroscopic fundamental diagrams in large-scale urban networks: empirical study with GPS data for Shenzhen city | |
| CN111667693B (en) | Method, apparatus, device and medium for determining estimated time of arrival | |
| Shoman et al. | Deep learning framework for predicting bus delays on multiple routes using heterogenous datasets | |
| CN113988705A (en) | Traffic safety risk assessment method and device | |
| CN112884235A (en) | Travel recommendation method, and training method and device of travel recommendation model | |
| CN113628446B (en) | Traffic information acquisition and analysis method and system based on Internet of things | |
| Ghoul et al. | Real-time safest route identification: Examining the trade-off between safest and fastest routes | |
| CN113408833A (en) | Public traffic key area identification method and device and electronic equipment | |
| Rodrigues et al. | Hybrid context-aware multimodal routing | |
| Liao et al. | Driver route planning method based on accident risk cost prediction | |
| Shrivastava et al. | Deep-learning-based model for prediction of crowding in a public transit system | |
| CN111047167B (en) | Line data processing method, device, equipment and storage medium | |
| Huang et al. | Analysing taxi customer-search behaviour using Copula-based joint model | |
| CN112729329A (en) | Safe driving route recommendation method, device and equipment | |
| Cortés et al. | A recursive stochastic transit equilibrium model estimated using passive data from Santiago, Chile | |
| Ekhlakov et al. | Multicriteria Assessment Method for Network Structure Congestion Based on Traffic Data Using Advanced Computer Vision | |
| Zhao et al. | Modeling and analysis of vehicle path dispersion at signalized intersections using explainable backpropagation neural networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |