CN117173911B - Traffic flow allocation method and system suitable for vehicle-road collaboration in intelligent transportation operation - Google Patents

Traffic flow allocation method and system suitable for vehicle-road collaboration in intelligent transportation operation Download PDF

Info

Publication number
CN117173911B
CN117173911B CN202310915156.1A CN202310915156A CN117173911B CN 117173911 B CN117173911 B CN 117173911B CN 202310915156 A CN202310915156 A CN 202310915156A CN 117173911 B CN117173911 B CN 117173911B
Authority
CN
China
Prior art keywords
road
driver
vehicles
calculate
vehicle
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.)
Active
Application number
CN202310915156.1A
Other languages
Chinese (zh)
Other versions
CN117173911A (en
Inventor
梅乐翔
陈智宏
刘旭
高薪
梁超
许进含
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.)
Taiji Computer Corp Ltd
Original Assignee
Taiji Computer Corp Ltd
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.)
Filing date
Publication date
Application filed by Taiji Computer Corp Ltd filed Critical Taiji Computer Corp Ltd
Priority to CN202310915156.1A priority Critical patent/CN117173911B/en
Publication of CN117173911A publication Critical patent/CN117173911A/en
Application granted granted Critical
Publication of CN117173911B publication Critical patent/CN117173911B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Traffic Control Systems (AREA)

Abstract

The invention discloses a traffic flow distribution method and a traffic flow distribution system suitable for intelligent traffic and road cooperation, which relate to the field of intelligent traffic. The road state monitoring module monitors a road by using a camera, recognizes obstacles such as construction, accidents and the like, and calculates a road state index. The demand computing module collects position and destination information of a driver, generates a navigation route and judges whether the driver passes through a road according to the demand degree. The weight calculation module comprehensively considers the number of vehicles, the road state and the demand degree, and calculates the road weight. And the path planning module searches an optimal path from the starting point to the end point according to the weight value, so that the road use efficiency is improved. The intelligent traffic operation and road coordination system realizes intelligent traffic operation and road coordination, comprehensively considers the requirements of drivers, road conditions and traffic requirements, and improves the road use efficiency.

Description

Traffic flow distribution method and system suitable for intelligent traffic operation and road cooperation
Technical Field
The invention relates to the field of intelligent traffic, in particular to a traffic flow distribution method and system suitable for intelligent traffic and road cooperation.
Background
In modern traffic systems, navigation services play a vital role. By providing an optimal travel path, the navigation service can help drivers to effectively plan their journey, avoid traffic congestion, save time and fuel. However, existing navigation services often have problems, particularly in high-density urban road networks.
First, existing navigation systems focus primarily on the driving needs of individual drivers, often ignoring the needs of other drivers. While navigation systems may take into account real-time traffic conditions of the road, such as traffic flow, traffic speed, etc., they typically do not adequately take into account the destination needs of all drivers. In other words, when multiple drivers are all at the same area, existing navigation systems may provide them with the same or similar travel paths, which may result in some roads being too congested, causing traffic congestion.
Secondly, the existing navigation system mainly considers the shortest travel distance or the fastest travel time when providing a travel path for a driver. However, this is not always the best choice. For example, if a road is already very crowded, even if it is the shortest path, it may take a long time for the driver to pass. Also, if a road has poor traffic capacity, such as an accident, a stenosis, or a pothole, the driver may feel uncomfortable even though it is the fastest route.
Therefore, existing navigation services often look frustrating when dealing with large-scale, complex urban traffic problems. In order to improve the use efficiency of the road, reduce traffic jam and improve the driving experience of drivers, a new navigation technical scheme is needed, and the scheme can comprehensively consider the requirements of all drivers, the real-time condition and the traffic capacity of the road so as to provide a better driving path.
Disclosure of Invention
The invention aims to provide a traffic flow distribution method and a traffic flow distribution system suitable for intelligent traffic and road cooperation, so as to solve the problems in the background art.
In order to achieve the above purpose, the invention adopts the following technical scheme:
A traffic flow distribution method suitable for intelligent traffic operation road cooperation comprises the following steps:
S1: the weight of the road ri for any driver a is calculated:
W(ri)＝α/(T(ri)+1)+β×C(ri)+γ×D(ri)+σ/(E(ri)+1)
Wherein:
ri represents the ith road;
T (ri) is the proportion of the actual number of vehicles on the road ri to the vehicles which can be placed on the road ri;
C (ri) represents the passability of the road ri itself, and the better the passability, the greater the C (ri);
D (ri) represents the degree of demand of the road ri for the driver a, the higher the degree of demand is, the greater D (ri);
E (ri) is the superposition of the demands D (ri) of the road ri for all drivers;
Alpha, beta, gamma and sigma are constants greater than 0 respectively;
Wherein, the calculation process of D (ri) corresponding to any driver is as follows:
S1.1: collecting the current position and destination information of the driver through a vehicle internet of things system;
s1.2: generating a plurality of possible navigation routes from the current position to the destination through a navigation algorithm;
s1.3: for each generated navigation route, D (ri) is calculated by judging whether the road ri is traversed or not, and using the following formula:
Wherein m is the number of generated navigation routes, match j (ri) represents an indication function, if the jth navigation route passes through the road ri, match j (ri) =1 is taken, if the jth navigation route does not pass through the road ri, match j(ri)＝0;sj is taken to represent the length of the jth navigation route;
Wherein, α, β, γ, σ are specifically calculated for the road ri and the driver a, specifically: collecting historical data h= { (T1, C1, D1, E1), (T2, C2, D2, E2), … … (Tk, ck, dk, ek) … …, (Tn, cn, dn, en) }, wherein (Tk, ck, dk, ek) represents a kth group of data among a plurality of groups (T (ri), C (ri), D (ri), E (ri)) corresponding to the road ri and the driver a, respectively calculating ((tk+1), 1/Ck,1/Dk, (ek+1)) for each group of data and making it equal to (αk, βk, γk, σk), calculating an average value of αk from 1 to n as α, calculating an average value of βk from 1 to n as β, calculating an average value of γk from 1 to n as γ, and calculating an average value of σk from 1 to n as σ;
s2: taking each road ri as an edge, taking each intersection as a node, and constructing a navigation route map, wherein the weight of the edge ri is W (ri) which corresponds to the driver A and is calculated in the step S1; the following algorithm is then used to find the driver's optimal path from the start point to the end point and send it to driver a:
s2.1: marking a shortest distance value for each node, setting the shortest distance value of a starting point to be 0, and setting the shortest distance values of all other nodes to be infinity;
s2.2: marking all nodes and all edges as unprocessed states;
s2.3: selecting a node N from the untreated nodes according to the shortest distance value;
S2.4: for each untreated adjacent edge H of the node N, calculating W (H) +R (N), if W (H) +R (N) < R (M), updating the shortest distance of M to W (H) +R (N), and marking the edges H and the node N as treated; wherein W (H) is the weight of H, R (N) is the shortest distance of N, M is the other end point of H relative to N; if the unprocessed adjacent edges do not exist for the node N, directly marking the node N as processed;
s2.5: repeating steps S2.3 and S2.4 until the endpoint is marked as processed;
S2.6: starting from the starting point, points marked as processed in turn are found out in time sequence and connected as the shortest path from the starting point to the end point as the optimal path.
Preferably, the calculation process of T (ri) includes the following steps:
a. Setting a plurality of camera devices along a road ri, and monitoring the road ri in real time;
b. Identifying the number of vehicles in each camera device monitoring picture through an image identification technology;
c. adding the number of vehicles monitored by each camera device to obtain the actual number of vehicles on the road ri;
d calculating the number of vehicles which can be placed on the road ri, including measuring the width and length of the road ri, and then estimating the maximum number of vehicles which can be placed with standard vehicle sizes;
e. Dividing the actual number of vehicles obtained in step c by the number of placeable vehicles obtained in step d to obtain T (ri).
Preferably, C (ri) is obtained by:
setting a plurality of camera devices along a road ri, and monitoring the road ri in real time;
identifying road barriers in each camera equipment monitoring picture by an image identification technology, wherein the road barriers at least comprise road barriers caused by construction, accidents and collapse;
Calculating the transverse length of the lane occupied by each obstacle, and if the transverse lengths of a plurality of obstacles are connected, regarding the plurality of obstacles as the same obstacle and calculating the total transverse length of the same obstacle; finally obtaining the transverse lengths L1-LN of N barriers;
Measuring the total transverse length LT of the road ri;
c (ri) is calculated according to the following formula:
Where N is the number of obstacles and Lj is the lateral length of j obstacles.
The invention also discloses a traffic flow distribution system suitable for intelligent traffic and road cooperation, which comprises:
(1) A vehicle number detection module for detecting and calculating an actual vehicle number of each road ri by a sensor device installed on the road, calculating a ratio T (ri) of the actual vehicle number on ri to the road on which the vehicle can be placed;
(2) The road state monitoring module is used for monitoring the road ri in real time through a plurality of camera devices arranged along the road ri, identifying road obstacles in a monitoring picture of each camera device through an image identification technology, including construction, accidents and collapse, and calculating C (ri) according to the identification result by adopting the traffic flow distribution method suitable for intelligent traffic and traffic road cooperation;
(3) The demand calculation module is used for collecting the current position and destination information of a driver through the vehicle internet of things system, generating a plurality of possible navigation routes from the current position to the destination through a navigation algorithm, judging whether each route passes through a road ri or not, and calculating D (ri) and E (ri) according to the traffic flow distribution method suitable for intelligent traffic and road cooperation;
(4) The weight calculation module is used for calculating the weight of each road ri according to the calculated T (ri), C (ri) and D (ri) and the formula W (ri) =alpha/(T (ri) +1) +beta×C (ri) +gamma×D (ri) +sigma/(E (ri) +1), wherein alpha, beta, gamma and sigma are constants larger than 0 calculated according to the traffic flow distribution method suitable for intelligent traffic road cooperation;
(5) The route planning module is used for regarding each road ri as an edge, regarding each intersection as a node, constructing a navigation route map, wherein the weight of the edge ri is W (ri) calculated by the weight calculation module, searching the optimal route from the starting point to the end point of the driver according to the method described in the step S2, and sending the optimal route to the driver;
the vehicle quantity detection module, the road state monitoring module, the demand calculation module, the weight calculation module and the path planning module are mutually connected and communicated.
Preferably, the vehicle number detection module comprises a camera device and an image processing algorithm center, wherein the camera device is used for shooting real-time images of roads, and the image processing algorithm center is used for identifying and calculating the vehicle number.
Preferably, the road state monitoring module comprises a camera device and a deep learning processing unit, wherein the camera device is used for shooting real-time images of roads, and the deep learning processing unit is used for realizing an image recognition function, recognizing road obstacles and calculating the trafficability of the roads.
Preferably, the demand computing module, the weight computing module and the path planning module are all arranged on a high-performance server and a cloud computing platform and are used for processing real-time data and rapidly completing complex computing tasks.
The invention has the advantages compared with the prior art that:
The road use efficiency is improved:
By the weight formula W (ri) =α/(T (ri) +1) +β×c (ri) +γ×d (ri) +σ/(E (ri) +1), the invention considers both the specific needs of each driver and the overall road condition and driver needs. The formula contains both the actual number of vehicles on the road T (ri), the trafficability C (ri) of the road itself, the driver's demand D (ri), and the total demand E (ri) of all drivers for the road. Therefore, road network resources can be utilized more effectively, and the use efficiency of roads is improved.
Optimizing the driving path of the driver: when solving the optimal path of the driver, the invention adopts a weight-based shortest path algorithm. This algorithm calculates weights according to the needs of each driver and the condition of the road, and then determines an optimal path according to these weights. Thus, the driving route which is most suitable for each driver can be provided for each driver, and the driving experience of the driver is improved.
Traffic congestion is reduced: the present invention introduces an attenuation factor of 1/(E (ri) +1) in the weight formula, which means that if the total demand E (ri) of a road is high, the weight of the road is reduced. This can guide the driver away from the high demand roads, thereby reducing the degree of congestion of these roads and reducing traffic congestion.
Self-adaptive adjustment parameters: the weight formula of the invention comprises four parameters alpha, beta, gamma and sigma, and the parameters are automatically adjusted according to historical data. The scheme of the invention can adaptively cope with different road conditions and driver demands, and the use efficiency of the road network is further improved.
Providing personalized navigation services: by fine-calculating the demand D (ri) of each driver, and a demand-based shortest path algorithm, the present invention can provide personalized navigation services for each driver. This can not only improve the driving experience of the driver, but also improve the user satisfaction of the navigation system.
Drawings
FIG. 1 is a schematic flow diagram of the overall process of the present invention;
FIG. 2 is a schematic diagram of the present invention for calculating road weights;
fig. 3 is a schematic diagram of the optimal path algorithm of the present invention.
Detailed Description
The following describes specific embodiments of the present invention with reference to the drawings.
Embodiment 1 of the present invention, specific designs for the system of the present invention are as follows:
(1) The vehicle quantity detection module:
The invention firstly selects proper sensor equipment, such as cameras, magnetic induction type or infrared type vehicle detection sensors, which can be arranged on the curbs at two sides of a road or on the isolation belt at the center of the road, and can be selectively arranged on fixed traffic signs or lamp posts in places such as bridges or overhead roads, which are difficult to directly install. The installation location needs to ensure that the sensor can cover all lanes in order to accurately calculate the number of vehicles at each moment. These sensors send data, either wirelessly or by wire, to a central processing unit, which calculates the number of vehicles on the lane in real time and uses this data for calculating T (ri).
(2) Road state monitoring module:
a plurality of high-resolution camera devices which can be arranged along the road ri, which cameras should be mounted on a street light pole or an ad hoc monitoring pole, as wide as possible over Quan Lu, ensuring that no dead angle exists. The camera transmits image data to the deep learning processing unit in real time through the high-speed optical fiber network, the deep learning processing unit analyzes the image by using a deep learning technology, identifies various road barriers including construction, accidents and collapse, and calculates C (ri) according to the identification result.
(3) The demand calculation module:
The invention collects the current position and destination information of the driver through the vehicle internet of things system, which can be realized through a vehicle-mounted GPS system. After obtaining this information, the module generates a plurality of possible navigation routes using an existing navigation algorithm (e.g., an existing Dijkstra algorithm), and then determines whether each route passes over the road ri, calculating D (ri) and E (ri).
(4) And a weight calculation module:
This module is responsible for calculating the weight of each road ri. It calculates W (ri) from T (ri), C (ri), D (ri), where α, β, γ, σ are constants greater than 0 calculated from the historical data by the coefficient calculation algorithm described later. This module may be implemented based on a high-performance computing server.
(5) And a path planning module:
This module performs path planning based on the results of the weight calculation module. Firstly, each road ri is regarded as an edge, each intersection is regarded as a node, a navigation route map is constructed, then the subsequent optimal route algorithm aiming at the weight is utilized to find an optimal route from a starting point to an end point and send the optimal route to a driver, and the step can be completed through a vehicle-mounted information system or a mobile phone APP.
In order to realize communication between the vehicle and the module, the device of the driver (such as a vehicle-mounted information system or a mobile phone APP) needs to install corresponding software for receiving the result of the path planning module and giving an explicit navigation instruction to the driver.
All of these modules are interconnected and communicate via a high-speed network to transmit and process data in real-time. Considering the real-time requirement of the system, the network should adopt high-speed and low-delay communication technologies such as optical fiber or 5G. Data centers need to have sufficient storage and computing power to process large amounts of image data and to perform complex algorithms.
In practice, the system also needs to take into account fault recovery and redundancy design. For example, backup sensors and camera devices may be deployed in critical locations to prevent data loss due to device failure. At the same time, data centers also need to have backup and failover capabilities to ensure service continuity and data integrity.
In addition, the system requires a management and maintenance module for monitoring the operation status of the system, including equipment status, network status, data processing efficiency, etc., and for maintaining and updating the system periodically. This module can be done jointly by manual and automated tools.
The invention completes the design of an intelligent traffic management system comprising a vehicle quantity detection module, a road state monitoring module, a demand calculation module, a weight calculation module and a path planning module. By adopting the system and the method of the invention in the following embodiment 2, the intelligent management of the urban road traffic flow can be realized, the road utilization rate is improved, the traffic jam is reduced, and the travel efficiency of a driver is improved.
In example 2, the process of the present invention is illustrated. The process of the present invention is schematically illustrated in fig. 1 to 3, wherein fig. 1 is a schematic flow diagram of the overall process of the present invention; FIG. 2 is a schematic diagram of the present invention for calculating road weights; fig. 3 is a schematic diagram of the optimal path algorithm of the present invention.
The method specifically comprises the following steps:
S1: the weight of the road ri for any driver a is calculated:
W(ri)＝α/(T(ri)+1)+β×C(ri)+γ×D(ri)+σ/(E(ri)+1)
Wherein:
ri represents the ith road;
T (ri) is the proportion of the actual number of vehicles on the road ri to the vehicles which can be placed on the road ri;
C (ri) represents the passability of the road ri itself, and the better the passability, the greater the C (ri);
D (ri) represents the degree of demand of the road ri for the driver a, the higher the degree of demand is, the greater D (ri);
E (ri) is the superposition of the demands D (ri) of the road ri for all drivers;
Alpha, beta, gamma and sigma are constants greater than 0 respectively;
Wherein, the calculation process of D (ri) corresponding to any driver is as follows:
S1.1: collecting the current position and destination information of the driver through a vehicle internet of things system;
s1.2: generating a plurality of possible navigation routes from the current position to the destination through a navigation algorithm;
s1.3: for each generated navigation route, D (ri) is calculated by judging whether the road ri is traversed or not, and using the following formula:
Wherein m is the number of generated navigation routes, match j (ri) represents an indication function, if the jth navigation route passes through the road ri, match j (ri) =1 is taken, if the jth navigation route does not pass through the road ri, match j(ri)＝0;sj is taken to represent the length of the jth navigation route;
wherein, the calculation process of T (ri) comprises the following steps:
a. Setting a plurality of camera devices along a road ri, and monitoring the road ri in real time;
b. Identifying the number of vehicles in each camera device monitoring picture through an image identification technology;
c. adding the number of vehicles monitored by each camera device to obtain the actual number of vehicles on the road ri;
d calculating the number of vehicles which can be placed on the road ri, including measuring the width and length of the road ri, and then estimating the maximum number of vehicles which can be placed with standard vehicle sizes;
e. Dividing the actual number of vehicles obtained in step c by the number of placeable vehicles obtained in step d to obtain T (ri).
Wherein, C (ri) is obtained by:
setting a plurality of camera devices along a road ri, and monitoring the road ri in real time;
identifying road barriers in each camera equipment monitoring picture by an image identification technology, wherein the road barriers at least comprise road barriers caused by construction, accidents and collapse;
Calculating the transverse length (perpendicular to the running direction of the vehicle) of the lane occupied by each obstacle, if the transverse lengths of a plurality of obstacles are connected (for example, if two vehicles are transversely connected to occupy the same lane in an accident, the two vehicles are regarded as one obstacle, the transverse length is the lane length), the plurality of obstacles are regarded as the same obstacle, and the total transverse length of the plurality of obstacles is calculated; finally obtaining the transverse lengths L1-LN of N barriers;
Measuring the total transverse length LT of the road ri;
c (ri) is calculated according to the following formula:
Where N is the number of obstacles and Lj is the lateral length of j obstacles.
Furthermore, α, β, γ, σ are calculated specifically for the road ri and the driver a, in particular: collecting historical data h= { (T1, C1, D1, E1), (T2, C2, D2, E2), … … (Tk, ck, dk, ek) … …, (Tn, cn, dn, en) }, wherein (Tk, ck, dk, ek) represents a kth group of data among a plurality of groups (T (ri), C (ri), D (ri), E (ri)) corresponding to the road ri and the driver a, respectively calculating ((tk+1), 1/Ck,1/Dk, (ek+1)) for each group of data and making it equal to (αk, βk, γk, σk), calculating an average value of αk from 1 to n as α, calculating an average value of βk from 1 to n as β, calculating an average value of γk from 1 to n as γ, and calculating an average value of σk from 1 to n as σ; the selection of the coefficient can lead each item in the weights to tend to the same value after being multiplied by the coefficient, thereby avoiding the overlarge proportion of a certain item and balancing the contribution of each item to the weights.
S2: taking each road ri as an edge, taking each intersection as a node, and constructing a navigation route map, wherein the weight of the edge ri is W (ri) which corresponds to the driver A and is calculated in the step S1; the following algorithm is then used to find the driver's optimal path from the start point to the end point and send it to driver a:
s2.1: marking a shortest distance value for each node, setting the shortest distance value of a starting point to be 0, and setting the shortest distance values of all other nodes to be infinity;
s2.2: marking all nodes and all edges as unprocessed states;
s2.3: selecting a node N from the untreated nodes according to the shortest distance value;
S2.4: for each untreated adjacent edge H of the node N, calculating W (H) +R (N), if W (H) +R (N) < R (M), updating the shortest distance of M to W (H) +R (N), and marking the edges H and the node N as treated; wherein W (H) is the weight of H, R (N) is the shortest distance of N, M is the other end point of H relative to N; if the unprocessed adjacent edges do not exist for the node N, directly marking the node N as processed;
s2.5: repeating steps S2.3 and S2.4 until the endpoint is marked as processed;
S2.6: starting from the starting point, points marked as processed in turn are found out in time sequence and connected as the shortest path from the starting point to the end point as the optimal path.
In the following embodiment 3, the optimum path finding after the weight calculation of the present invention is described as an example.
Assume that the invention has 5 nodes, labeled A, B, C, D and E, with A as the start point and E as the end point. The following are the connections between these nodes and the corresponding weights (the distances of the edges are referred to as weights hereinafter):
Weights A to B are 4;
weights A to C are 2;
the weights of B to C are 1;
weights B to D are 5;
The weights of C to D are 8;
Weights C to E are 10;
The weights of D to E are 2;
the invention is to find the shortest path from a to E. Initially, the shortest distance of the node A is set to be 0, and the shortest distance of all other nodes is set to be infinity. Therefore, the present invention has:
Shortest distance of a: 0;
shortest distance of B: infinity;
shortest distance of C: infinity;
shortest distance of D: infinity;
Shortest distance of E: infinity;
The invention then starts the algorithm:
The invention selects the untreated node with the smallest shortest distance, namely A. For each adjacent edge (AB and AC) of a, the total distance from a to the other end node (shortest distance of a plus distance from a to the other end point) is calculated. For AB, the total distance is 0+4; for AC, the total distance is 0+2. Since both total distances are smaller than the current shortest distance of B and C (infinity), the present invention updates the shortest distance of B and C. The invention then marks a as processed.
After updating:
Shortest distance of B: 4, a step of;
Shortest distance of C: 2;
Next, the present invention selects the node with the smallest shortest distance among the unprocessed nodes, i.e., C. Looking at the adjacent sides of C, only the CD and CE are seen, since the AC has been previously processed. For CD, the total distance from a through C to D is 2 (a to C distance) +8 (C to D weight) =10, greater than D current shortest distance (infinity), so the present invention updates D shortest distance. For CE, the total distance from a through C to E is 2 (a to C distance) +10 (C to E weight) =12, which is also less than the current shortest distance of E (infinity), so the present invention updates the shortest distance of E. The invention then marks C as processed.
After updating:
Shortest distance of D: 10;
Shortest distance of E: 12;
Next, the present invention selects B because B's shortest distance is the smallest. The invention then looks at the adjacent edges BC and BD of B, as AB has been previously processed. For BC, the total distance from a through B to C is 4 (a to B distance) +1 (B to C weight) =5, but this is greater than the shortest distance 2 of the current C, so the present invention does not update the shortest distance of C. For BD, the total distance from a through B to D is 4 (a to B distance) +5 (B to D weight) =9, which is less than the current shortest distance of D10, so the present invention updates the shortest distance of D. The invention then marks B as processed.
After updating:
Shortest distance of D: 9
Now, the node with the shortest distance among the unprocessed nodes, namely D, is selected again. D has only one untreated adjacent edge, namely DE. The total distance from a through D to E is 9 (distance a to D) +2 (weight D to E) =11, which is smaller than the current shortest distance 12 of E, so the present invention updates the shortest distance of E. The invention then marks D as processed.
After updating:
shortest distance of E: 11;
Finally, the invention leaves only one unprocessed node, namely E. Because E has no untreated adjacent edges, the present invention marks E as treated directly.
Now all nodes are processed, and time-sequentially A, B, D, E are marked as processed, so the invention finds the shortest path from a to E: a- > B- > D- > E.
The shortest path from the start point to all other nodes can be found with this algorithm and its time complexity is relatively low (O (V2), V being the number of nodes, and if a priority queue or heap is used, the time complexity can be further reduced to O (p+v log V), P being the number of edges), which makes it very useful in practical applications, especially in traffic networks, telecommunication networks, etc.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should be covered by the protection scope of the present invention by making equivalents and modifications to the technical solution and the inventive concept thereof.

Claims (7)

1.一种适用于智能交通运行车路协同的交通流分配方法，其特征在于，包括如下步骤：1. A traffic flow allocation method for intelligent traffic operation vehicle-road collaboration, characterized by comprising the following steps: S1：计算对于任一驾驶者A而言的道路ri的权重：S1: Calculate the weight of road ri for any driver A: W(ri)＝α/(T(ri)+1)+β×C(ri)+γ×D(ri)+σ/(E(ri)+1)W(ri)＝α/(T(ri)+1)+β×C(ri)+γ×D(ri)+σ/(E(ri)+1) 其中：in: ri表示第i条道路；ri represents the i-th road; T(ri)为道路ri上的实际车辆数量占道路ri上可放置车辆的比例；T(ri) is the ratio of the actual number of vehicles on road ri to the number of vehicles that can be placed on road ri; C(ri)表示道路ri自身的可通行能力，可通行能力越好C(ri)越大；C(ri) represents the traffic capacity of road ri itself. The better the traffic capacity, the larger C(ri) is. D(ri)表示道路ri对于驾驶者A的需求程度，需求程度越高D(ri)越大；D(ri) represents the degree of demand for road ri for driver A. The higher the demand, the greater D(ri); E(ri)为道路ri对于所有驾驶者的需求程度D(ri)的叠加；E(ri) is the superposition of the demand degree D(ri) of road ri for all drivers; α、β、γ、σ分别为大于0的常数；α, β, γ, and σ are constants greater than 0; 其中，任一驾驶者对应的D(ri)的计算过程如下：The calculation process of D(ri) corresponding to any driver is as follows: S1.1：通过车辆物联网系统，收集该驾驶者的当前位置和目的地信息；S1.1: Collect the driver’s current location and destination information through the vehicle IoT system; S1.2：通过导航算法生成多条从当前位置到目的地可能的导航路线；S1.2: Generate multiple possible navigation routes from the current location to the destination through a navigation algorithm; S1.3：对于每个生成的导航路线，通过判断是否经过道路ri，并采用如下公式计算D(ri)：S1.3: For each generated navigation route, determine whether it passes through road ri and calculate D(ri) using the following formula: 其中，m是生成的导航路线数量，Matchj(ri)表示指示函数，若第j条导航路线经过道路ri，取Matchj(ri)＝1，若第j条导航路线不经过道路ri，取Matchj(ri)＝0；sj表示第j条导航路线的长度；Wherein, m is the number of generated navigation routes, Match j (ri) represents the indicator function, if the j-th navigation route passes through road ri, Match j (ri) = 1, if the j-th navigation route does not pass through road ri, Match j (ri) = 0; s j represents the length of the j-th navigation route; 其中，α、β、γ、σ针对道路ri和驾驶者A特别计算,具体为：收集历史数据H＝{(T1,C1,D1,E1),(T2,C2,D2,E2),……(Tk,Ck,Dk,Ek)……,(Tn,Cn,Dn,En)}，其中(Tk,Ck,Dk,Ek)表示道路ri以及驾驶者A所对应的多组(T(ri),C(ri),D(ri),E(ri))数据中的第k组数据，对每组数据分别计算((Tk+1),1/Ck,1/Dk，(Ek+1))并令其等于(αk，βk，γk，σk)，计算αk从1～n的均值将其作为α，计算βk从1～n的均值将其作为β，计算γk从1～n的均值将其作为γ，计算σk从1～n的均值将其作为σ；Among them, α, β, γ, σ are specially calculated for road ri and driver A, specifically: collect historical data H = {(T1, C1, D1, E1), (T2, C2, D2, E2), ... (Tk, Ck, Dk, Ek) ..., (Tn, Cn, Dn, En)}, where (Tk, Ck, Dk, Ek) represents the kth group of data in multiple groups (T(ri), C(ri), D(ri), E(ri)) data corresponding to road ri and driver A, calculate ((Tk+1), 1/Ck, 1/Dk, (Ek+1)) for each group of data and set it equal to (αk, βk, γk, σk), calculate the average value of αk from 1 to n and use it as α, calculate the average value of βk from 1 to n and use it as β, calculate the average value of γk from 1 to n and use it as γ, calculate the average value of σk from 1 to n and use it as σ; S2：将每条道路ri看作一个边，每个路口看作一个节点，构建导航路线图，边ri的权重为S1步骤所计算出的对应于驾驶者A的W(ri)；然后，采用以下算法寻找驾驶者从起点到终点的最优路径，并将其发送至驾驶者A：S2: Consider each road ri as an edge and each intersection as a node, and construct a navigation route map. The weight of edge ri is W(ri) corresponding to driver A calculated in step S1; then, the following algorithm is used to find the optimal path from the starting point to the end point of the driver and send it to driver A: S2.1：为每个节点标记一个最短距离值，将起点的最短距离值设为0，其余所有节点的最短距离值设为无穷大；S2.1: Mark a shortest distance value for each node, set the shortest distance value of the starting point to 0, and set the shortest distance values of all other nodes to infinity; S2.2：标记所有节点、所有边为未处理状态；S2.2: Mark all nodes and all edges as unprocessed; S2.3：从未处理节点中按照最短距离值选择一个节点N；S2.3: Select a node N from the unprocessed nodes according to the shortest distance value; S2.4：对于节点N的每一条未处理过的相邻边H，计算W(H)+R(N)，如果W(H)+R(N)＜R(M),则更新M的最短距离为W(H)+R(N)，并标记边H、节点N均为已处理过；其中W(H)是H的权重，R(N)是N的最短距离，M是H相对于N的另一端点；若对于节点N不存在未处理过的相邻边，则直接标记N为已处理；S2.4: For each unprocessed adjacent edge H of node N, calculate W(H)+R(N). If W(H)+R(N)＜R(M), then update the shortest distance of M to W(H)+R(N), and mark edge H and node N as processed; where W(H) is the weight of H, R(N) is the shortest distance of N, and M is the other end point of H relative to N; if there is no unprocessed adjacent edge for node N, directly mark N as processed; S2.5：重复步骤S2.3和S2.4，直到终点被标记为已处理；S2.5: Repeat steps S2.3 and S2.4 until the endpoint is marked as processed; S2.6：从起点开始，按时间顺序找出依次被标记为已处理的点并连接，作为从起点到终点的最短路径作为最优路径。S2.6: Starting from the starting point, find the points marked as processed in chronological order and connect them as the shortest path from the starting point to the end point as the optimal path. 2.根据权利要求1所述适用于智能交通运行车路协同的交通流分配方法，其特征在于，T(ri)的计算过程包括如下步骤：2. The traffic flow allocation method for intelligent traffic operation vehicle-road collaboration according to claim 1 is characterized in that the calculation process of T(ri) includes the following steps: a.沿道路ri设置多个摄像头设备，对道路ri进行实时监控；a. Set up multiple camera devices along the road ri to monitor the road ri in real time; b.通过图像识别技术，识别每个摄像头设备监控画面中的车辆数量；b. Use image recognition technology to identify the number of vehicles in the monitoring image of each camera device; c.将每个摄像头设备监控到的车辆数量相加，得到道路ri上的实际车辆数量；c. Add the number of vehicles monitored by each camera device to obtain the actual number of vehicles on road ri; d计算道路ri可放置车辆的数量，包括测量道路ri的宽度和长度，然后以标准车辆尺寸估算最大可放置车辆数量；d. Calculate the number of vehicles that can be placed on the road ri, including measuring the width and length of the road ri, and then estimating the maximum number of vehicles that can be placed based on the standard vehicle size; e.将步骤c得到的实际车辆数量除以步骤d得到的可放置车辆的数量，得到T(ri)。e. Divide the actual number of vehicles obtained in step c by the number of vehicles that can be placed in step d to obtain T(ri). 3.根据权利要求1所述适用于智能交通运行车路协同的交通流分配方法，其特征在于，C(ri)通过以下步骤获取：3. The traffic flow allocation method for intelligent traffic operation vehicle-road collaboration according to claim 1 is characterized in that C(ri) is obtained by the following steps: 沿道路ri设置多个摄像头设备，对道路ri进行实时监控；Multiple camera devices are set up along the road ri to monitor the road ri in real time; 通过图像识别技术，识别每个摄像头设备监控画面中的道路障碍，至少包括施工、事故、塌方引起的道路障碍；Using image recognition technology, identify road obstacles in the monitoring image of each camera device, including at least road obstacles caused by construction, accidents, and landslides; 计算每个障碍物所占用的车道的横向长度，若多个障碍物的横向长度相连，则将这多个障碍物看做同一个障碍物并计算其总的横向长度；最终得到N个障碍物的横向长度L1～LN；Calculate the lateral length of the lane occupied by each obstacle. If the lateral lengths of multiple obstacles are connected, these multiple obstacles are regarded as one obstacle and their total lateral length is calculated. Finally, the lateral lengths of N obstacles L1 to LN are obtained. 量取道路ri的总横向长度LT；Measure the total lateral length LT of the road ri; 依据如下公式计算C(ri)：C(ri) is calculated according to the following formula: 其中，N为障碍物数量，Lj为j个障碍物的横向长度。Where N is the number of obstacles and Lj is the lateral length of j obstacles. 4.一种适用于智能交通运行车路协同的交通流分配系统，其特征在于，包括：4. A traffic flow distribution system suitable for intelligent traffic operation vehicle-road collaboration, characterized by comprising: (1)车辆数量检测模块，用于通过安装在道路上的传感器设备，检测和计算每条道路ri的实际车辆数量，计算ri上的实际车辆数量占道路可放置车辆的比例T(ri)；(1) A vehicle number detection module is used to detect and calculate the actual number of vehicles on each road ri through sensor devices installed on the road, and calculate the ratio T(ri) of the actual number of vehicles on ri to the number of vehicles that can be placed on the road; (2)道路状态监测模块，通过沿道路ri布置的多个摄像头设备，对道路ri进行实时监控，通过图像识别技术，识别每个摄像头设备监控画面中的道路障碍，包括施工、事故、塌方，并根据识别结果计算权利要求1所述C(ri)；(2) a road status monitoring module, which monitors the road ri in real time through multiple camera devices arranged along the road ri, identifies road obstacles in the monitoring image of each camera device through image recognition technology, including construction, accidents, and landslides, and calculates C(ri) as described in claim 1 based on the recognition results; (3)需求计算模块，用于通过车辆物联网系统，收集驾驶者的当前位置和目的地信息，通过导航算法生成多条从当前位置到目的地可能的导航路线，并判断每条路线是否经过道路ri，以根据权利要求1所述方法计算D(ri)、E(ri)；(3) a demand calculation module, used to collect the driver's current location and destination information through the vehicle Internet of Things system, generate multiple possible navigation routes from the current location to the destination through a navigation algorithm, and determine whether each route passes through the road ri, so as to calculate D(ri) and E(ri) according to the method of claim 1; (4)权重计算模块，用于根据计算出的T(ri)，C(ri)和D(ri)，按照公式W(ri)＝α/(T(ri)+1)+β×C(ri)+γ×D(ri)+σ/(E(ri)+1)计算出每条道路ri的权重，其中α、β、γ、σ为根据权利要求1所述方法由历史数据计算得出的大于0的常数；(4) a weight calculation module, used to calculate the weight of each road ri according to the calculated T(ri), C(ri) and D(ri) according to the formula W(ri)=α/(T(ri)+1)+β×C(ri)+γ×D(ri)+σ/(E(ri)+1), where α, β, γ, and σ are constants greater than 0 calculated from historical data according to the method of claim 1; (5)路径规划模块，用于将每条道路ri看作一个边，每个路口看作一个节点，构建导航路线图，边ri的权重为权重计算模块所计算出的W(ri)，然后根据权利要求1中S2所述方法寻找驾驶者从起点到终点的最优路径，并将其发送至驾驶者；(5) a path planning module, which is used to regard each road ri as an edge and each intersection as a node, to construct a navigation route map, the weight of the edge ri is W(ri) calculated by the weight calculation module, and then find the optimal path from the starting point to the end point of the driver according to the method described in S2 of claim 1, and send it to the driver; 所述车辆数量检测模块、道路状态监测模块、需求计算模块、权重计算模块、路径规划模块相互连接通讯。The vehicle quantity detection module, road status monitoring module, demand calculation module, weight calculation module, and path planning module are interconnected and communicated with each other. 5.根据权利要求4所述系统，其特征在于，所述车辆数量检测模块包括摄像头设备和图像处理算法中心，所述摄像头设备用于拍摄道路的实时图像，所述图像处理算法中心用于识别和计算车辆数量。5. The system according to claim 4 is characterized in that the vehicle quantity detection module includes a camera device and an image processing algorithm center, the camera device is used to capture real-time images of the road, and the image processing algorithm center is used to identify and calculate the number of vehicles. 6.根据权利要求4所述系统，其特征在于，所述道路状态监测模块包括摄像头设备和深度学习处理单元，所述摄像头设备用于拍摄道路的实时图像，所述深度学习处理单元用于实现图像识别功能、识别道路障碍并计算道路的可通行能力。6. The system according to claim 4 is characterized in that the road status monitoring module includes a camera device and a deep learning processing unit, the camera device is used to capture real-time images of the road, and the deep learning processing unit is used to implement image recognition functions, identify road obstacles and calculate the road's traffic capacity. 7.根据权利要求4所述的智能交通运行车路协同的交通流分配系统，其特征在于，所述需求计算模块、权重计算模块、所述路径规划模块均设置于高性能服务器和云计算平台，用于处理实时数据并快速完成复杂的计算任务。7. According to claim 4, the traffic flow distribution system for intelligent traffic operation and vehicle-road collaboration is characterized in that the demand calculation module, the weight calculation module, and the path planning module are all set on a high-performance server and a cloud computing platform to process real-time data and quickly complete complex computing tasks.
CN202310915156.1A 2023-07-25 2023-07-25 Traffic flow allocation method and system suitable for vehicle-road collaboration in intelligent transportation operation Active CN117173911B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310915156.1A CN117173911B (en) 2023-07-25 2023-07-25 Traffic flow allocation method and system suitable for vehicle-road collaboration in intelligent transportation operation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310915156.1A CN117173911B (en) 2023-07-25 2023-07-25 Traffic flow allocation method and system suitable for vehicle-road collaboration in intelligent transportation operation

Publications (2)

Publication Number Publication Date
CN117173911A CN117173911A (en) 2023-12-05
CN117173911B true CN117173911B (en) 2024-11-12

Family

ID=88936473

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310915156.1A Active CN117173911B (en) 2023-07-25 2023-07-25 Traffic flow allocation method and system suitable for vehicle-road collaboration in intelligent transportation operation

Country Status (1)

Country Link
CN (1) CN117173911B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120014831B (en) * 2025-02-26 2025-10-24 浙江大学 A multi-target traffic path guidance method and system based on multi-agent

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103090878A (en) * 2011-10-28 2013-05-08 北京中交兴路信息科技有限公司 Vehicle path planning method, vehicle path planning system and vehicle navigation apparatus
CN109269516A (en) * 2018-08-29 2019-01-25 沈阳理工大学 A kind of dynamic route guidance method based on multiple target Sarsa study

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6615130B2 (en) * 2000-03-17 2003-09-02 Makor Issues And Rights Ltd. Real time vehicle guidance and traffic forecasting system
CN100357987C (en) * 2005-06-02 2007-12-26 上海交通大学 Method for obtaining average speed of city rode traffic low region
EP2973494A4 (en) * 2013-03-15 2016-11-23 Caliper Corp Lane-level vehicle navigation for vehicle routing and traffic management
CN114463977B (en) * 2022-02-10 2023-06-23 北京工业大学 A route planning method based on vehicle-road coordination multi-source data fusion traffic flow prediction

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103090878A (en) * 2011-10-28 2013-05-08 北京中交兴路信息科技有限公司 Vehicle path planning method, vehicle path planning system and vehicle navigation apparatus
CN109269516A (en) * 2018-08-29 2019-01-25 沈阳理工大学 A kind of dynamic route guidance method based on multiple target Sarsa study

Also Published As

Publication number Publication date
CN117173911A (en) 2023-12-05

Similar Documents

Publication Publication Date Title
US20230113298A1 (en) Autonomous vehicle fleet management for reduced traffic congestion
US12562054B2 (en) Autonomous vehicle and center control system (AVCCS) for drone/tele driving or digital twins
Karmakar et al. A smart priority-based traffic control system for emergency vehicles
CN101901546B (en) Intelligent traffic dispatching and commanding and information service method and system based on dynamic information
CN103914988B (en) A kind of traffic road condition data processing method, device and system
KR101034484B1 (en) Driving information providing system that can share camera shooting information
CN109816979B (en) A recommended method for bus routes considering bus arrival frequency and ride comfort
JP5666669B2 (en) A communication-type navigation system that searches for routes by detecting changes in traffic volume
DK201870686A1 (en) Management of multiple autonomous vehicles
CN105489043B (en) Real-time route planing method based on vehicular ad hoc network
CN106530781A (en) Method and system for sharing road condition information based on Internet-of-vehicles
KR102386960B1 (en) Connected Automated Vehicle Road Systems and Methods
CN113532459A (en) Predictive navigation route planning method and system
CN110398254B (en) A method and system for alleviating traffic congestion
CN111405526B (en) Information acquisition method, device, platform, vehicle-mounted equipment and road side equipment
CN101739839A (en) Vehicle dynamic path navigational system
CN106895846B (en) A kind of paths planning method and path planning apparatus
CN117173911B (en) Traffic flow allocation method and system suitable for vehicle-road collaboration in intelligent transportation operation
CN114724372B (en) Intelligent transportation system based on fog calculation
CN114692015A (en) Riding point recommendation method based on density clustering
CN104596534B (en) A kind of method for calculating optimal planning driving path
CN120014849A (en) Vehicle-road collaboration intersection signal light control method, device, medium and product
CN115662134A (en) Dynamic allocation method of space-time resources in urban functional area expressway based on active management and control
EP3605488A1 (en) Management of multiple autonomous vehicles
CN118836882B (en) Online car-hailing route planning method and system based on ARIMA model and SaaS

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
GR01 Patent grant
GR01 Patent grant