CN108573600B - Driver behavior induction and local traffic flow optimization method - Google Patents
Driver behavior induction and local traffic flow optimization method Download PDFInfo
- Publication number
- CN108573600B CN108573600B CN201710164779.4A CN201710164779A CN108573600B CN 108573600 B CN108573600 B CN 108573600B CN 201710164779 A CN201710164779 A CN 201710164779A CN 108573600 B CN108573600 B CN 108573600B
- Authority
- CN
- China
- Prior art keywords
- driver
- driving
- vehicle
- traffic flow
- parameters
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a local traffic flow optimization system based on a multi-vehicle longitudinal following state. Firstly, identifying the character parameters of a driver by adopting a least square method, dividing the driver into an aggressive type, a stable type and a conservative type, and then calibrating the driving behavior of the stable driver to be used as a good following reference. And obtaining the scale of the driver for accepting the suggestion through bisection, and reminding the driver to improve the following behavior, so that the driver is guided to form good driving habits step by step. The invention is based on different following styles of drivers with different characters, provides acceptable driving suggestion scales for specific drivers, suggests the drivers to keep normal driving suggestions, and macroscopically optimizes the traffic flow of local areas by improving the driving behaviors of the drivers.
Description
Technical Field
The invention belongs to the technical field of public transportation, and particularly relates to a multi-vehicle longitudinal following technology for local traffic flow. The invention provides a local area traffic flow optimization method by learning historical driving data of drivers with different character classes and vehicles with different vehicle types stored in a cloud, and the method is suitable for road sections with frequent stop-and-go congestion in traffic flow.
Background
With the continuous and rapid development of economic society, the quantity of automobiles in China continues to be in a rapid growth trend. Meanwhile, with the development of cities, road traffic congestion in local areas (Yangtze river bridges, urban tunnels and the like) is still very severe.
Based on this, it is urgently needed to develop local area traffic flow optimization research. The style of the vehicle is different due to the different characters of the drivers, and the style of the driving car is different, for example, under the condition that the models of the vehicles (large-sized vehicle, medium-sized vehicle and small-sized vehicle) are the same (the models of the front vehicle and the rear vehicle are fixed), the type of the driver of the rear vehicle is: aggressive drivers show too close following and frequent acceleration and deceleration; in order to avoid collision, conservative drivers show too far following the vehicle; under the same working condition (the relation between the speed of the front vehicle and the time) of the front vehicle in the running state, the small vehicle keeps a closer vehicle distance when following the small vehicle, and the small vehicle keeps a relatively larger vehicle distance when following the large vehicle. Whether too far or too close, this can have adverse effects on traffic flow such as reducing road traffic volume, causing stop-and-go traffic flow, and even leading to the formation of large-area congestion.
With the development of the intelligent technology of the automatic driving automobile, the automatic driving automobile not only can share road traffic information, but also can learn by itself. But it ignores the driver's driving style for a particular vehicle model. The individual requirements and the user experience indexes of the driver cannot be guaranteed, and the driver is only taken as a passenger and does not obtain the sense of participation.
In order to fully utilize the automobile driving data and improve the perception of drivers and the traffic flow optimization effect of local areas. The type and historical driving data of the own vehicle and the historical traffic flow data of the specific road section can be saved to a cloud server and can be acquired by other vehicle drivers. The character parameters of the driver of the self vehicle are obtained through the learning of the historical driving data of the self vehicle, the reference prediction model of the traffic flow in a specific time period and the distribution proportion of the vehicle type and the character type of the driver are obtained through counting the historical traffic flow data of a specific road section, and then the corresponding acceptable improvement suggestions are provided, and the optimal solution of the maximum traffic volume or the minimum fuel oil emission and the like is realized through an algorithm. Therefore, congestion in local areas is relieved, and road traffic capacity is improved.
Disclosure of Invention
In order to effectively identify the driver character parameters (following vehicle distance and following speed) of a specific type of vehicle, the driving habits, namely vehicle type-driver character parameters, of a driver with a specific character type under a specific vehicle type under a specific road environment are obtained through the driver type-vehicle type (man-vehicle matching) historical driving data and road information learning of a leading vehicle and a following vehicle. And (3) extracting road environments (gradient, light intensity and the like) with similar cloud ends and the running state of the lead vehicle by combining the current road environment information, and simulating the driving operation of a driver corresponding to the vehicle type under the similar condition. And the optimal following mode (the minimum vehicle speed fluctuation or the minimum oil consumption and the like) in the historical driving data under the same vehicle-environment is extracted through an algorithm, and the vehicle-driver character parameters are analyzed and used as good following reference. And setting optimal driving character parameters under the same type of vehicles-environmental conditions. The driving character parameters of the drivers of the rear vehicles are compared with the optimal driving character parameters, the driving character parameters which can be accepted by the drivers of the rear vehicles are set as references through a dynamic dichotomy, corresponding driving suggestions are provided according to the references to optimize the driving behaviors of the drivers of the following vehicles, and the driving behaviors of the drivers in the traffic flow are optimized through the method, so that the acceptable driving suggestions are provided for each driver in the traffic flow, and finally the purpose of optimizing the traffic flow of the local area is achieved.
The invention is realized by the following technical scheme.
The invention relates to a multi-vehicle longitudinal following method for local area traffic flow optimization, which is characterized in that: the method comprises the following steps:
1) type-specific vehicle-type-specific driver personality parameter acquisition
Deleting traffic flow information in a following state (namely a state that a vehicle is in a lane in front and the following vehicle follows the front vehicle to run) through historical traffic data of each vehicle uploaded to the cloud end, and acquiring the following vehicle distance sdAnd the following velocity vfAccording to the formula sd＝λvf+ L obtains time distance lambda and parking distance L by least square method, classifies the corresponding driver character of each vehicle by following time distance and parking distance, lambda and L are the driver character parameters, and finally obtains the comprehensive parameters under the specific following environment, Yn＝{An，1，An，2，An，3，An，4}，YnRepresenting the combined parameters of the nth vehicle in the fleet, wherein An，1Showing the driving condition of the nth vehicle (namely the speed time relation of the vehicles) in the fleet, An，2Indicates the model of the nth vehicle (classified as a large, medium or small vehicle), An，3Represents a driving character parameter corresponding to the nth vehicle driver, An，4Indicating the road environment information where the driver is located. By acquiring the comprehensive parameters of the (n-1) th vehicle (leading vehicle) and the (n) th vehicle (following vehicle), Y with the parameter consistent with that of the (n-1) th vehicle is selected from the traffic history datan-1Y identical to others except for the driver's personality parametersnComparing the speed of the following vehicleThe volatility and the following performance are the best, and the character parameter of the driver with the minimum speed volatility is selected to be the most optimal driver reference, as shown in the figure 3.
2) Setting a driving style parameter normalization reference table and dynamic good driving style parameters
On the premise of determining the type, the character parameters and the working condition of a front guide vehicle, the driving parameters of drivers meeting different driving styles of following vehicles of the same type (large, medium and small) corresponding to the front guide vehicle are extracted from historical traffic data and are subjected to normalization processing. Determining a corrected driving character parameter which can be accepted by a driver by adopting a dynamic dichotomy through the calibrated driver character parameter and the optimal driver character parameter, wherein the specific measures are as follows:
firstly, selecting a median value of the driving character parameters of the driver and the optimal driving character parameters as character parameters of good driving advice, providing corresponding driving advice according to the median value, and taking the median value as the good driving advice parameters when the driver is willing to accept the advice and does not have unfavorable conflict emotion; if the driving advice is contradicted by the driving advice, recalculating the good driving character parameters on the basis, wherein the new driving character parameters are the median values of the driving parameters and the previous good driving parameters, calculating in sequence until the driver is willing to accept the driving advice, and finally calculating the good driving parameter values, as shown in figure 4.
3) Local traffic flow optimization based on good driver parameter recommendation conditions
When the stop-and-go traffic flow state occurs, the driver compares whether the driving behavior of the driver meets the requirements or not through good driving parameters, and when the driving behavior of the driver does not meet the requirements, corresponding driving suggestions are provided to advise the driver to keep the good driving behavior. If the aggressive driver is judged to be excessively aggressive, the aggressive driver is recommended to keep driving at a proper inter-vehicle distance, namely, the speed fluctuation of the aggressive driver in the driving process is relieved; if a conservative driver judges that the vehicle is far behind, the driver is advised to appropriately reduce the inter-vehicle distance of the following vehicle, namely, the traffic flow per unit time is increased, so that the stop-and-go traffic flow in local areas is relieved. Simultaneously, can know the shared proportion of each lane driver normalization character parameter through high in the clouds, if: the proportion of aggressive drivers in one lane is too large, and the proportion of conservative drivers in the other lane is large, which are not favorable for the normal operation of the traffic flow. The drivers can be properly advised to change lanes, and the reasonable distribution of the character types of the drivers in all lanes is ensured, so that the traffic flow is optimized. The specific sorting and distribution method of the human-vehicle characteristics in the lane is as follows: the magnetic driving method is characterized in that a driver is regarded as an object, the driving character characteristic of the driver is regarded as the magnetic characteristic of the object, wherein the magnetism of an aggressive driver is N, the magnetism of a conservative driver is S, and a steady driver is neutral (nonmagnetic). The magnitude of the repulsive force is related to the number of drivers with the same character and the type of the vehicle, namely, the magnitude of the repulsive force is increased in geometric multiples when the number of the drivers with the same character and the type of the vehicle is increased; and when cars of the same type and with the same driver characters are arranged together, the maximum repulsion force is arranged among large cars, then middle cars and finally small cars. The vehicles with the opposite magnetism are preferentially inserted between the vehicles with the large repulsive force, and when the sequencing of the vehicles with the opposite magnetism is completed, the driver with the neutral magnetism is inserted between the vehicles with the repulsive force, so that the sequencing is completed.
The specific vehicle sequencing embodiment is as follows, and the traffic flow in the following state in the two lanes in the same direction is shown in fig. 5. Wherein the first number in AB is the vehicle type, wherein A represents a large vehicle, B represents a medium vehicle, and C represents a small vehicle; the second number represents the driver personality type, a represents aggressive, B represents heavy and C represents conservative. Such as CC, indicates that conservative drivers drive small vehicles. Because the automobiles can be communicated with the cloud platform, the cloud platform can know the character types of drivers of the vehicles around each automobile, so that the characteristics and the magnitude of the force between the automobiles can be obtained; f (x, y, z, v) wherein x represents the nature of the force as either an attractive force or a repulsive force; y represents the magnitude of the force, which is related to the number of consecutive rows of drivers of the same character type, and the magnitude of the force is anWherein a is a constant of force, a is greater than 1, and n is the number of drivers with the same personality queuing continuously; z denotes resources which can be adjusted around, i.e. drivers in the side lanes can change lanesThe character types are used for reducing the size of repulsive force between the existing vehicles, so that the phenomenon that a plurality of aggressive drivers are arranged together when the drivers with the same character are overlong and continuously arranged on the same lane, and the phenomenon that a certain vehicle stops due to the fact that the rear vehicle decelerates at a higher speed when the front vehicle decelerates at a higher speed is avoided; v represents the maximum number of drivers with the same personality, which is related to the personality type driver proportion and the total number of drivers, when the personality driver proportion is h and the total number of drivers is g, the value of v is 1/h, v is rounded up, and the fact that the personality types of the drivers with the same personality are not concentrated too much is guaranteed. In this way, the speed fluctuation of the traffic flow is reduced. Referring to fig. 5, a vehicle-in-lane ranking rule graph is shown in which the driver personality type of the two front vehicles (AA, BA) in the right lane is aggressive, while the driver of the first vehicle in the left lane is conservative and the second vehicle is heavy. When the cloud platform finds that two vehicles in front of a right lane are repulsive force through an algorithm, vehicles with opposite-sex characteristics are arranged on lanes beside the cloud platform, and due to the action of the repulsive force, a suggestion is provided that a conservative driver in a left lane is recommended to change lanes to enter the right lane and drive between the two vehicles. Thereby avoiding excessive centralized ranking of drivers of the same personality type.
Drawings
FIG. 1 shows a longitudinal multi-car following model
FIG. 2 driver personality parameter normalization
FIG. 3 is a flow chart for forming a good driving behavior reference of a driver
FIG. 4 dichotomy in obtaining good driving behavior advisory parameters acceptable to the driver
FIG. 5 lane vehicle sequencing rule diagram
Detailed Description
The invention is further described below with reference to the accompanying drawings.
The invention relates to local area traffic flow optimization, and a Yangtze river bridge is taken as an optimized road section. When the road section has the traffic flow phenomenon of stop-and-go, the front and the rear vehicles mutually present the following state. First, with GPS information, a historical traffic database may be generated. The historical traffic database contains historical driving records of each vehicle, driving data of following states of the following vehicle and the corresponding front vehicle are extracted, driving style characteristics of the following vehicle can be identified through a least square method, and therefore the following vehicle can be classified, and respective driving characteristics of several common drivers driving the vehicle are obtained. Thereby indicating the driving parameters. Matching the driving parameters of the driver according to the current driving style so as to obtain the man-vehicle characteristics of the type of the vehicle on the Yangtze river bridge, namely the characteristic parameters of the driver; the driver is subjected to parameter positioning through the normalization operation in fig. 2, and driving parameters (the relationship between the following distance and the following speed) of the driving advice which can be accepted by the driver are obtained through the dichotomy in fig. 4, and the driving parameters are used as the standard of good following. And when the driver judges that the vehicle is not following the vehicle, the driver is reminded to drive by adopting correct driving parameters. The method can reduce the fluctuation of the traffic flow on the premise of ensuring the driving experience of the driver, thereby optimizing the traffic flow. Meanwhile, after the driver is accumulated in the day and the month, driving reminding and advising rarely occur, the driver is considered to form driving parameter modeling at the stage, meanwhile, a new good car following standard which can be accepted by the driver is reset, and corresponding reminding advising is performed again. Gradually leading the driver to approach towards the driving parameter direction of the optimal driving, and optimizing the driving operation step by step.
Historical traffic data running on the Yangtze river bridge is extracted through the historical traffic data, and the general rule of traffic flow running in different weather states of all time periods such as Monday to Friday, Saturday, holiday and the like on the Yangtze river bridge can be analyzed through statistical software, so that a reference prediction model, namely the approximate running condition of the traffic flow in the known time period and the known weather state, is generated. And marking the deviation of the traffic flow corresponding to a specific moment and the reference prediction model by introducing a residual error. The distribution ratio of model-driver driving parameters (i.e., the ratio of various human-vehicle characteristics such as aggressive drivers for large-sized vehicles and conservative drivers for small-sized vehicles) constituting the traffic flow is extracted from the reference model and is generally within a certain range. Under the condition that the human-vehicle characteristics in the Yangtze river bridge and the driving parameters (following vehicle distance and following speed characteristics) which can be accepted by each driver can be known, the optimized traffic flow running state can be obtained through simulation. For multiple lanes, it is assumed that all large-vehicle-conservative drivers are in the left lane and all small-vehicle-aggressive drivers are in the right lane. The traffic volume of the left lane is low because the vehicles in the left lane clearly can keep a closer car following distance, but the vehicles keep a too far car following distance; and because the drivers in the vehicles in the right lane are all aggressive, when the current vehicle decelerates, the first vehicle is kept fast and correspondingly, the first vehicle can decelerate with a larger deceleration, and so on, the situation that a certain vehicle decelerates and is increased to stop can occur at the back, so that the fluctuation of the traffic flow is very large, and the normal operation of the traffic flow is not facilitated. Aiming at the problem, on the premise of meeting the driving requirement of the road and knowing the proportion of the human-vehicle characteristics in the traffic flow, the proportion of the human-vehicle characteristics is reasonably distributed to each lane, so that the optimization of the traffic flow can be promoted. The specific rule is as follows: firstly, under a specific road section, different human-vehicle characteristic proportions and different sequencing positions of the human-vehicle characteristic proportions in a motorcade are set to simulate and simulate traffic flow running states under the specific sequencing conditions of the human-vehicle characteristic proportions, so that the optimal sequencing of vehicle drivers in the human-vehicle characteristic proportions is found out. Then, from the human-vehicle characteristic proportion and the sequence in the existing running traffic flow, the human-vehicle characteristic proportion and the sequence in each lane are adjusted by calculation to reach a reasonable proportion so as to optimize the traffic flow. For example, the human-vehicle characteristics in the left lane are substantially all small vehicle aggressive drivers in the co-directional two lanes, while the human-vehicle characteristics in the right lane are substantially all small vehicle conservative drivers. By the combination of the two methods, the condition that the human-vehicle characteristic proportion in each lane of the two lanes is not too high for a certain human-vehicle type proportion through the lane changing behavior, and the traffic flow operation is not facilitated. By making a reassignment of the human-vehicle characteristic ratio and the rank of each lane, the road traffic flow can be optimized.
Furthermore, due to the identification of the driver's person-to-vehicle characteristics, the identification of the vehicle as a new driver can alert to avoid vehicle theft when the new driver drives the vehicle due to the different driving style parameters it maintains. Meanwhile, the driving parameters are identified by analyzing the vehicle operation parameters before the violation of the driver, and only the person with the driving parameters can carry out deduction, so that the driving points of other persons are avoided, and the execution degree of the traffic rules is improved to a certain extent.
Claims (7)
1. A driver behavior induction and local traffic flow optimization method is characterized in that: the method comprises the following steps:
the method comprises the following steps of collecting traffic flow information in the driving process, identifying the character parameters of a driver, and formulating a good driving behavior standard:
deleting the traffic flow information in the following state through the historical traffic data of each vehicle uploaded to the cloud end to obtain the following vehicle distance sdAnd the following velocity vfAccording to the formula sd＝λvf+ L obtains time distance lambda and parking distance L by least square method, classifies the corresponding driver character of each vehicle by following time distance and parking distance, lambda and L are the driver character parameters, and finally obtains the comprehensive parameters under the following environment, Yn＝{An,1，An,2，An,3，An,4}，YnRepresenting the combined parameters of the nth vehicle in the fleet, wherein An,1Indicating the driving condition of the nth vehicle in the fleet, An,2Indicates the model of the nth vehicle, An,3Represents a driving character parameter corresponding to the nth vehicle driver, An,4Information indicating a road environment where a driver is located; the comprehensive parameters of the nth-1 th vehicle and the nth vehicle are respectively obtained as Yn-1And YnAnd deleting Y consistent with the n-1 th vehicle parameter from the traffic historical datan-1And the characteristic parameter A of the driver is deleted from the traffic history datan,3Different but An,1，An,2，An,4All coincident YnComparing the speed fluctuation of the following vehicle, and selecting the character parameter of the driver with the minimum speed fluctuation as the optimal driving behavior standard;
judging whether the driving behavior of the driver is reasonable or not, and determining the corrected driving character parameters accepted by the driver by adopting a dynamic dichotomy through the calibrated driver character parameters and the optimal driver character parameters on the premise of not changing the driving experience of the driver, thereby optimizing the traffic flow and relieving the congestion.
2. The driver behavior induction and local traffic flow optimization method according to claim 1, characterized in that: and the method also comprises the step of carrying out normalization processing on the corresponding driver character parameters of the large, medium and small-sized vehicles.
3. The driver behavior induction and local traffic flow optimization method according to claim 1, characterized in that: the specific steps of the dynamic dichotomy determination of the corrected driving performance parameter for providing driver acceptance include: firstly, selecting a median value of the driving character parameters of the driver and the optimal driving character parameters as character parameters of good driving advice, providing corresponding driving advice according to the median value, and taking the median value as the good driving advice parameters when the driver is willing to accept the advice and does not have unfavorable conflict emotion; if the driving advice is contradicted by the driving advice, recalculating the good driving character parameters on the basis, wherein the new driving character parameters are the median values of the driving parameters and the previous good driving parameters, calculating in sequence until the driver is willing to accept the driving advice, and finally calculating the good driving parameter values.
4. A driver behavior induction and local traffic flow optimization method according to claim 3, characterized in that: by establishing the graded good driving behavior standard, when the driver reaches the driving behavior standard after the suggestion, a new suggestion driving reference is established again, and the driver is gradually induced to keep better driving habits.
5. The driver behavior induction and local traffic flow optimization method according to claim 1, characterized in that: the optimized traffic flow comprises the steps that a driver compares whether own driving behaviors meet requirements through good driving parameters, and when the driving behaviors do not meet the requirements, corresponding driving suggestions are provided to recommend the driver to keep the good driving behaviors: an aggressive driver who is advised to keep the inter-vehicle distance running when it is determined that the aggressive is excessive; a conservative driver who is advised to reduce the following inter-vehicle distance when judging to follow the vehicle too far; the distribution condition of the normalized driver character parameters of each lane is known through the cloud, drivers are advised to change lanes, and reasonable distribution of the character types of the drivers of each lane is guaranteed.
6. The driver behavior induction and local traffic flow optimization method according to claim 5, characterized in that: the method comprises the steps that the distribution condition of normalized driver character parameters of each lane is known through a cloud end, drivers are advised to change lanes, the character types of the drivers in each lane are reasonably distributed, specifically, the drivers are regarded as objects, the driving character characteristics of the drivers are regarded as magnetic characteristics of the objects, the magnetism of aggressive drivers is N, the magnetism of conservative drivers is S, the drivers with stable weight are neutral, and the magnitude of repulsive force is related to the number of the drivers with the same character and the vehicle type, namely, the magnitude of repulsive force is increased in a geometric multiple mode when the number of the drivers with the same character is increased continuously; and when cars of the same type and having the same driver characters are arranged, vehicles with the maximum repulsive force are sorted into large-sized cars, then medium-sized cars and finally small-sized cars, vehicles with opposite magnetism are preferentially inserted between the vehicles with the large repulsive force, and when the sorting of the vehicles with the opposite magnetism is completed, then a driver with neutral magnetism is inserted between the vehicles with the repulsive force, thereby completing the sorting.
7. A driver behavior induction and local traffic flow optimization method according to claim 5 or 6, characterized in that: when the traffic flow is predicted to be congested, the cloud provides an auxiliary driving decision function, and the distribution and the sequencing of the driver character parameters of all vehicles under the maximum traffic flow are calculated and realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710164779.4A CN108573600B (en) | 2017-03-10 | 2017-03-10 | Driver behavior induction and local traffic flow optimization method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710164779.4A CN108573600B (en) | 2017-03-10 | 2017-03-10 | Driver behavior induction and local traffic flow optimization method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108573600A CN108573600A (en) | 2018-09-25 |
| CN108573600B true CN108573600B (en) | 2022-02-08 |
Family
ID=63575847
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710164779.4A Active CN108573600B (en) | 2017-03-10 | 2017-03-10 | Driver behavior induction and local traffic flow optimization method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108573600B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110750877B (en) * | 2019-09-27 | 2024-05-03 | 西安理工大学 | Vehicle following behavior prediction method under Apollo platform |
| JP7176501B2 (en) * | 2019-11-14 | 2022-11-22 | トヨタ自動車株式会社 | Gear stage determination device, method and simulation device |
| CN111968372B (en) * | 2020-08-25 | 2022-07-22 | 重庆大学 | Multi-vehicle type mixed traffic following behavior simulation method considering subjective factors |
| CN112907971B (en) * | 2021-02-04 | 2022-06-10 | 南通大学 | Urban road network short-term traffic flow prediction method based on genetic algorithm optimization space-time residual error model |
| CN116229727A (en) * | 2023-05-10 | 2023-06-06 | 深圳市城市交通规划设计研究中心股份有限公司 | Road congestion induction method and management and control system based on online simulation |
| CN118397831A (en) * | 2024-04-19 | 2024-07-26 | 上海理工大学 | Expressway traffic state prediction method based on behavior feature capture |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202495152U (en) * | 2012-02-27 | 2012-10-17 | 江门市侍卫长汽车防盗有限公司 | Driving habits analysis system based on GPS satellite positioning technology |
| CN102968541A (en) * | 2012-12-11 | 2013-03-13 | 东南大学 | Traffic flow microscopic simulation method based on car following behavior |
| CN103246799A (en) * | 2011-02-09 | 2013-08-14 | 信息移动It股份公司 | Method for characterizing the driving style of vehicle drivers |
| CN103546577A (en) * | 2013-10-31 | 2014-01-29 | 深圳先进技术研究院 | Method and system for achieving safe driving |
| CN104354701A (en) * | 2014-10-29 | 2015-02-18 | 云南大学 | Human-car interaction realization method |
| CN104732785A (en) * | 2015-01-09 | 2015-06-24 | 杭州好好开车科技有限公司 | Driving behavior analyzing and reminding method and system |
| CN104778851A (en) * | 2015-02-16 | 2015-07-15 | 北京交通大学 | Traveling-track-based ecological driving optimization method and system |
| CN105788236A (en) * | 2014-12-26 | 2016-07-20 | 浙江大华技术股份有限公司 | Traffic control method and traffic control device |
| CN105809953A (en) * | 2014-12-27 | 2016-07-27 | 吉林大学 | City traffic flow vehicle and road cooperative control method based on M2M |
| CN106060258A (en) * | 2016-06-08 | 2016-10-26 | 合肥工业大学 | System and method for analyzing driving style of driver based on smartphone |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101211428A (en) * | 2006-12-27 | 2008-07-02 | 厦门雅迅网络股份有限公司 | Driver habit statistical and analytical method |
| DE102008002271A1 (en) * | 2008-06-06 | 2009-12-10 | Robert Bosch Gmbh | Method and device for collecting traffic data for a vehicle |
| CN101929868B (en) * | 2009-06-23 | 2013-08-28 | 神达电脑股份有限公司 | Method for planning navigation route by using navigation equipment of global navigation satellite system |
| US9171409B2 (en) * | 2011-05-04 | 2015-10-27 | GM Global Technology Operations LLC | System and method for vehicle driving style determination |
| GB2499252A (en) * | 2012-02-13 | 2013-08-14 | Jaguar Cars | Driver advice system for a vehicle |
| CN103413359A (en) * | 2013-07-18 | 2013-11-27 | 江苏中科天安智联科技有限公司 | Bad driving behavior analysis evaluation system |
| CN106428015B (en) * | 2016-09-12 | 2019-07-19 | 惠州Tcl移动通信有限公司 | A kind of intelligent travelling crane householder method and device |
-
2017
- 2017-03-10 CN CN201710164779.4A patent/CN108573600B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103246799A (en) * | 2011-02-09 | 2013-08-14 | 信息移动It股份公司 | Method for characterizing the driving style of vehicle drivers |
| CN202495152U (en) * | 2012-02-27 | 2012-10-17 | 江门市侍卫长汽车防盗有限公司 | Driving habits analysis system based on GPS satellite positioning technology |
| CN102968541A (en) * | 2012-12-11 | 2013-03-13 | 东南大学 | Traffic flow microscopic simulation method based on car following behavior |
| CN103546577A (en) * | 2013-10-31 | 2014-01-29 | 深圳先进技术研究院 | Method and system for achieving safe driving |
| CN104354701A (en) * | 2014-10-29 | 2015-02-18 | 云南大学 | Human-car interaction realization method |
| CN105788236A (en) * | 2014-12-26 | 2016-07-20 | 浙江大华技术股份有限公司 | Traffic control method and traffic control device |
| CN105809953A (en) * | 2014-12-27 | 2016-07-27 | 吉林大学 | City traffic flow vehicle and road cooperative control method based on M2M |
| CN104732785A (en) * | 2015-01-09 | 2015-06-24 | 杭州好好开车科技有限公司 | Driving behavior analyzing and reminding method and system |
| CN104778851A (en) * | 2015-02-16 | 2015-07-15 | 北京交通大学 | Traveling-track-based ecological driving optimization method and system |
| CN106060258A (en) * | 2016-06-08 | 2016-10-26 | 合肥工业大学 | System and method for analyzing driving style of driver based on smartphone |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108573600A (en) | 2018-09-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108573600B (en) | Driver behavior induction and local traffic flow optimization method | |
| Ferreira et al. | The impact of driving styles on fuel consumption: A data-warehouse-and-data-mining-based discovery process | |
| Alexander et al. | Assessing the impact of real-time ridesharing on urban traffic using mobile phone data | |
| US10023200B2 (en) | Driver profiling system and method | |
| TWI638328B (en) | Electricity demand prediction device, electricity supply system, method of predicting electricity demand, program , electricity supply menage device | |
| CN108072381B (en) | Path planning method and device | |
| CN106643747B (en) | Navigation method and device | |
| CN107919014B (en) | Taxi running route optimization method for multiple passenger mileage | |
| CN112805762B (en) | System and method for improving traffic condition visualization | |
| CN110395245B (en) | Hybrid electric vehicle energy management system based on fixed route driving information | |
| CN113052405B (en) | Traffic jam prediction and optimization method based on Internet of things and artificial intelligence | |
| CN111932341A (en) | Method and system for determining car pooling order | |
| CN117746640B (en) | Road traffic flow rolling prediction method, system, terminal and medium | |
| CN116772877B (en) | Method, system, device and medium for predicting endurance mileage of new energy automobile | |
| CN108806249B (en) | Passenger trip optimization method based on bus APP software | |
| CN116596380A (en) | Optimization determination method, platform, equipment and medium for expressway construction organization scheme and management and control scheme | |
| CN113673756B (en) | Method and device for determining recommended speed of vehicle and computer equipment | |
| CN112926809B (en) | Flight flow prediction method and system based on clustering and improved xgboost | |
| CN110490365A (en) | A method of based on the pre- survey grid of multisource data fusion about vehicle order volume | |
| CN114492169B (en) | Electric automobile user portraying method and system considering user market response potential | |
| CN113393011B (en) | Method, device, computer equipment and medium for predicting speed limit information | |
| CN109979190B (en) | Road traffic state prediction method and device | |
| CN110021163A (en) | Net based on driving mileage data about bus or train route net occupation rate analysis method | |
| US20240371263A1 (en) | Systems and Methods for Improved Traffic Conditions Visualization | |
| CN113327078B (en) | Method, system and medium for judging parking type of truck loading and unloading vehicle based on LSTM algorithm |
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 |