CN115731708B - Real-time vehicle track lane change point monitoring method based on Bayesian theory - Google Patents
Real-time vehicle track lane change point monitoring method based on Bayesian theory Download PDFInfo
- Publication number
- CN115731708B CN115731708B CN202211428816.5A CN202211428816A CN115731708B CN 115731708 B CN115731708 B CN 115731708B CN 202211428816 A CN202211428816 A CN 202211428816A CN 115731708 B CN115731708 B CN 115731708B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- time
- lane change
- moment
- change point
- 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
- 230000008859 change Effects 0.000 title claims abstract description 72
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000012544 monitoring process Methods 0.000 title claims abstract description 22
- 238000005070 sampling Methods 0.000 claims description 11
- 230000006399 behavior Effects 0.000 abstract description 23
- 238000004364 calculation method Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 5
- 230000001133 acceleration Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Abstract
The invention discloses a real-time vehicle track lane change point monitoring method based on Bayesian theory, which comprises the steps of acquiring a running track data set of a vehicle, taking generated track data and historical vehicle statistical data as priori information, considering the influence of traffic environment indexes on lane change behaviors of a driver, providing a self-adaptive risk function calculation method based on a two-term logic regression model, and finally obtaining the t-position of the vehicle according to the Bayesian theory n Time of dayPosterior predictive distribution of (c) to obtain the vehicle at t n Time of dayPosterior predictive probability of (c) when the vehicle is at t n When the time posterior prediction probability is larger than a preset threshold value, the vehicle t is considered to generate a lane change point; the method not only considers the influence of the driving habit, the driving skill and the like of the driver, but also considers the influence of the traffic environment index on the lane changing behavior of the driver, and the final result can guide and standardize the driving behavior, thereby reducing the occurrence of accidents and improving the driving safety.
Description
Technical Field
The invention belongs to the technical field of safe driving of vehicles, and particularly relates to a real-time vehicle track lane change point monitoring algorithm based on a Bayesian theory.
Background
The identification and prediction of vehicle lane change behavior is one of the main research contents in the field of automobile development nowadays. Following and lane changing are two basic states of vehicle operation. The lane change behavior more easily causes interactions with the vehicle than the following behavior. It has been found that if the lane change behavior can be detected before the vehicle passes over the centerline, the accident rate will be significantly reduced. Therefore, the lane changing behavior of the vehicle can be timely identified, understood and predicted, and traffic accidents can be effectively avoided.
With further development of the internet of vehicles and vehicle road coordination technology, traffic system monitors can obtain unprecedented individualized, high-precision and high-dimensional vehicle track data. The running track of the vehicle is formed when the driver performs a series of driving operations, and is the result of the combined actions of physiological factors, environmental factors, unobservable psychological factors and the like. Generally, only if a lane change trend is generated by a driver and a lane change condition is met by a target lane, lane change points are possibly generated; therefore, the method is not only limited by low data quality and high cost, but also is easily and actively removed or damaged, thus severely restricting the development of channel-changing behavior monitoring technology. And the method has the defects of difficult observation of driving behaviors, high cost of monitoring equipment, low precision and the like.
Disclosure of Invention
The invention provides an algorithm which has high accuracy of a prediction result and can monitor lane changing behavior of a vehicle in real time, and aims to solve the problems that the driving behavior is difficult to observe, the cost of monitoring equipment is high and the accuracy is low.
The invention adopts the following technical scheme:
the real-time vehicle track lane change point monitoring method based on the Bayesian theory comprises the following steps of, aiming at a vehicle on a target road section, monitoring lane change conditions of the vehicle on the target road section at the current moment:
step A: aiming at a vehicle on a target road section, acquiring t in a historical time period based on a preset sampling time interval 0 To t n The preset track data of the vehicle i running at each sampling moment form a running track data set of the vehicle i wherein ,tn At the current moment, n is more than or equal to 2;
and (B) step (B): vehicle i-based trajectory data setObtaining the sampling time t of the vehicle i θ To t n Longitudinal position coordinate time series within the time period of (2)> wherein tθ Is the distance t n The generation time of the latest lane change point satisfies the condition that t is more than or equal to 0 θ ＜t n ；
Step C: for vehicles on the target road segment, steps C1-C3 are performed to construct vehicle i at t n Time of day vertical position coordinatesPosterior predictive distribution of->Further judge that the vehicle i is on the target road section t n Whether a lane change point is generated at the moment, and monitoring the lane change condition of the vehicle i on the target road section at the current moment:
step C1: first, a run-length function is constructed by the following formula
In the formula, when the vehicle i is at t T When the track is changed at the moment, thenIs 0, i.e. vehicle i is at t T Generating a lane change point at moment; when the vehicle i is at t T When the track is not changed at any time, then/>Is->Is a priori information of (2);
step C2: based on the vehicle i at t θ To t n-1 Time series of ordinate in time periodVehicle i is constructed at t by the following formula n Time ordinate +.>Posterior predictive distribution of->
in the formula ,representation->UPM prediction of (c);
representing run +.>Posterior predictive distribution of (2) belonging to->Is a priori information of (2);
step C3: based on the vehicle i at t n Time of dayLongitudinal position coordinatesPosterior predictive distribution of->Obtaining posterior predictive probability P if vehicle i is at t n Time->If the posterior prediction probability P of the vehicle i is larger than the preset threshold U, predicting the vehicle i at t n Generating a lane change point at moment; if the vehicle i is at t n Time->If the posterior prediction probability P of (a) is smaller than or equal to the preset threshold U, predicting the vehicle i at t n The lane change point is not generated at the moment.
As a preferred embodiment of the present invention, in the step C2,UPM prediction of (c)I.e. < ->Obtained by the following formula:
in the vehicle i longitudinal position coordinate time seriesObeying normal distribution alpha, the super parameter is +.> and />Alpha 'represents the conjugate index distribution of alpha, and the superparameters of alpha' are +.> and /> and />According to the preset-> and />And gradually and iteratively updating to obtain the product.
In the step C2, as a preferred embodiment of the present invention, the run lengthPosterior predictive distribution of (a)I.e. < ->The method comprises the following steps of: time series based on the ordinate of the vehicle i>Constructing +.> and />Is a joint probability distribution of (1)
in the formula ,representation->About-> and />UPM prediction of (c);
is t n-1 Priori information of the time lane change point, which is expressed based on t n-2 Time lane change situation vehicle i is at t n-1 The probability of channel change at the moment is obtained by a risk function; />Representing a preset +.> and />Is a joint probability of (2);
step 2: based on and />Is->Constructing +.>Posterior predictive distribution of->
As a preferable embodiment of the present invention, the preset threshold U is 0.001.
As a preferable technical scheme of the invention, the super parameter is and />The initial value is preset as wherein />Representing the time series of the ordinate>Is set to the start value of (1).
As a preferable technical scheme of the invention, the super-parameter and />Obtained according to the following formula:
in the formula ：indicating that the vehicle is at t m The ordinate of the moment.
As a preferred embodiment of the present invention, in step 2, the following is adoptedThe risk function is obtained by a risk function, and the specific formula of the risk function is as follows:
as a preferred embodiment of the present invention, in step 2, the following is adoptedThe value of (2) is set by the following formula:
where λ represents the average time interval between adjacent lane change points.
As a preferred embodiment of the present invention, the risk functionIs constructed by the following formula:
in the formula ,indicating that vehicle i is at t n-1 Probability of changing channels at the moment; />Indicating that vehicle i is at t n-1 The time is a vector composed of traffic environment indexes, wherein the traffic environment indexes comprise t n-1 Preset track data of a vehicle i at the moment and preset track data of front and rear vehicles adjacent to the same lane of the vehicle i; beta k Representing the parameter vector, obeying normal distribution, and Q represents the total number of traffic environment indexes.
As a preferred embodiment of the present invention, the risk function may be set as
The beneficial effects of the invention are as follows: the invention provides a real-time vehicle track lane change point monitoring method based on Bayesian theory, which comprises the steps of acquiring a running track data set of a vehicle, taking generated track data and historical vehicle statistical data as priori information, considering the influence of traffic environment indexes on lane change behaviors of a driver, providing a self-adaptive risk function calculation method based on a two-term logic regression model, considering the influence of driving habit, driving skill and the like of the driver, and finally obtaining the t of the vehicle according to the Bayesian theory n Time of dayPosterior predictive distribution of (2) and thus obtain the vehicle +.>Posterior predictive probability of (c) when the vehicle is at t n When the time posterior prediction probability is greater than a preset threshold value, then the method is consideredFor vehicle t n Generating a lane change point at moment; and when the surrounding conditions do not meet the channel changing conditions, the risk function is reduced, the variable point identification result is affected, and the monitoring result is more accurate. The method not only considers the influence of the driving habit, the driving skill and the like of the driver, but also considers the influence of the traffic environment index on the lane changing behavior of the driver, and the final result can guide and standardize the driving behavior, thereby reducing the occurrence of accidents and improving the driving safety.
Drawings
FIG. 1 is a schematic diagram of a vehicle track acquisition simulation provided by an embodiment of the present invention;
fig. 2 is a diagram of a NGSIM straight-ahead vehicle running track applied in an embodiment of the present invention;
fig. 3 is a diagram of a moving track of an NGSIM lane-changing vehicle according to an embodiment of the present invention;
FIG. 4 is a diagram of a lane change vehicle motion trajectory according to an embodiment of the present invention;
fig. 5 is a diagram of a detection result of a lane change point of a vehicle running track according to an embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples will provide those skilled in the art with a more complete understanding of the invention, but are not intended to limit the invention in any way.
The vehicle trajectory is dynamically changed due to the influence of people, vehicles, roads and environments. The differences in factors such as risk perception of individual drivers, driving experience, driving skill, lane keeping ability, etc., cause the average value around which the vehicle track may fluctuate up and down within a certain range. When the vehicle is turned from the straight course to the lane change course, the vehicle trajectory may deviate from the average. Defining the starting point of the vehicle from the following process to the lane changing process as the lane changing point. For the running track of the vehicle, the lane change point and the change point of the corresponding track correspond to two running states of the vehicle respectively at two sides of the change point. Therefore, the invention provides a vehicle real-time lane change behavior monitoring method based on the Bayesian theory, which is used for detecting the lane change behavior of the vehicle in real time based on the acquired vehicle track data.
The real-time vehicle track lane change point monitoring method based on the Bayesian theory comprises the following steps of, aiming at a vehicle on a target road section, monitoring lane change conditions of the vehicle on the target road section at the current moment:
step A: data are collected, and t in a historical time period is obtained based on a preset sampling time interval aiming at vehicles on a target road section 0 To t n The track data of the vehicle i running at each sampling moment are preset to form a running track data set of the vehicle i wherein ,tn At the current moment, n is more than or equal to 2; the running trace data set comprises sampling moments, namely t 0 To t n Presetting track data of a vehicle i corresponding to each moment respectively, wherein the preset track data comprise speed, longitudinal position coordinates, transverse position coordinates, acceleration, speed of a front vehicle in a same lane, longitudinal position coordinates of the front vehicle in the same lane, transverse position coordinates of the front vehicle in the same lane and acceleration of the front vehicle in the same lane; the technical method for acquiring the data comprises the following steps: beidou positioning technology, vehicle-mounted radar, road side detection equipment and the like; as shown in fig. 1, the coordinate axis is the positive direction of the Y axis with the initial position of the vehicle on the target road section as the origin, and the X axis is perpendicular to the Y axis; along the X-axis, i.e. expressed as a longitudinal variation; the horizontal position coordinates refer to the vehicle advancing direction, and the vertical position coordinates refer to the distribution direction of the lanes, namely the X-axis changing direction; the vehicle abscissa refers to the vehicle running direction, the vehicle ordinate refers to the distribution direction of the lanes, and whether the lane change generating point occurs can be judged through the variation range of the vehicle ordinate. Based on the acquired data, a running track data set of the vehicle on the target road section can be obtained>The vehicle running track data set comprises a time sequence corresponding to each track data, wherein the time sequence of the longitudinal position coordinates of the vehicle is presetWherein i denotes a vehicleAnd (5) a vehicle.
In the embodiment, the invention adopts the track data of the U.S. published vehicle track data set NGSIM, which comprises the speed, longitudinal and transverse position coordinates, acceleration, head distance and head time distance of the vehicle; the vehicle transverse position coordinate refers to the vehicle running direction local_x, the vertical position coordinate refers to the distribution direction local_y of the lane, and whether a lane change generation point occurs can be judged through the change amplitude of the vehicle vertical position coordinate; the trajectories of 330 straight vehicles and 300 lane change vehicles are extracted from the NGSIM trajectory data set, respectively, as shown in fig. 2 and 3.
And (B) step (B): vehicle i-based trajectory data setObtaining the sampling time t of the vehicle i θ To t n Longitudinal position coordinate time series within the time period of (2)> wherein tθ Is the distance t n The generation time of the latest lane change point satisfies the condition that t is more than or equal to 0 θ ＜t n . And obtaining the sampling time t of the vehicle i 0 To t n Longitudinal position coordinate time series within the time period of (2)>
Step C: steps C1-C3 are performed for vehicles on the target road segment, the trajectory of which is shown in fig. 4 for vehicle i; building vehicle i at t n Time of day vertical position coordinatesPosterior predictive distribution of->Further judge that the vehicle i is on the target road section t n And monitoring whether a lane change point is generated at the moment and monitoring the lane change condition of the vehicle at the current moment on the target road section.
Taking vehicle i as an exampleExtracting the vehicle i at t 0 To t n Time series of vehicle longitudinal position coordinates in time period, if vehicle i is at t 0 To t n If a plurality of lane change points exist, the distance t is the following distance n-1 The latest lane change point t at moment θ For starting point, constructing the vertical position coordinate of each vehicle i at t n Time of dayPosterior predictive distribution of->Further judge that each vehicle i is on the target road section t n Time->Whether the track is a track changing point or not; t is more than or equal to 0 θ ＜t n . θ is a known value, if the vehicle i is at t 0 To t n-1 If no lane change point exists, t θ Take the value t n-1 。
Step C1: first, a run-length function is constructed by the following formula
In the formula, when the vehicle i is at t T When the track is changed at the moment, thenIs 0, i.e. vehicle i is at t T Generating a lane change point at moment; when the vehicle i is at t T When the channel is not changed at all, then +.>Is->Is a priori information about (a). t is t 0 ≤t T ＜t n Said t T Time->The distribution of (2) can be expressed as +.>
Step C2: based on the vehicle i at t θ To t n-1 Time series of ordinate in time periodVehicle i is constructed at t by the following formula n Time ordinate +.>Posterior predictive distribution of->
in the formula ,representation->UPM (Underlying probabilistic model) prediction of (2); />Representing run +.>Posterior predictive distribution of (2) belonging to->Is a priori information about (a). To calculate->Value, step 1 to step 2 can be performed; to calculate->Step 3 may be performed.
Vehicle i tour Cheng i,t-1 Posterior distribution of (2)The method is constructed by the following steps:
step 1: based on the time series of the vehicle i longitudinal position coordinates according to the probability chain lawConstructing +.> and />Is->
in the formula ,representation->About-> and />UPM prediction of (c);
is t n-1 Priori information of the time lane change point, which is expressed based on t n-2 Time lane change situation vehicle i is at t n-1 The probability of channel change at the moment is obtained by a risk function; />Representing a preset +.> and />Is used to determine the joint probability of (1).
The saidCan be defined by a risk function H (gamma i,t-2 +1) is obtained by the following formula:
the risk functionIs constructed by the following formula:
in the formula ,indicating that vehicle i is at t n-1 Probability of changing channels at the moment; />Indicating that vehicle i is at t n-1 The time is a vector composed of traffic environment indexes, wherein the traffic environment indexes comprise t n-1 Preset track data of a vehicle i at the moment and preset track data of front and rear vehicles adjacent to the same lane of the vehicle i; presetting each track data comprising speed, longitudinal position coordinates, transverse position coordinates, acceleration, headstock distance and headstock time distance information; beta k Representing the parameter vector, representing the regression coefficient of the variable, and Q representing the total number of traffic environment indexes.
In addition, the risk function can also be directly set asλ represents the average time interval between adjacent lane-change points, i.e. represents the average time interval between adjacent lane-change points over a historical period of time, in this embodiment λ is 1000s.
Step 2: based on the longitudinal position coordinate time sequence of the vehicle i according to the Bayesian theoryAnd and />Is->Constructing +.>Posterior predictive distribution of->
In addition, the risk function H (gamma i,t-2 +1), can also be constructed by the following formula:
where λ represents the average time interval between adjacent lane-change points, and λ is 1000s.
Step 3:UPM prediction->I.e. < ->Obtained by the following formula:
in the method, a time sequence of the longitudinal position coordinates of the vehicle i is presetObeying normal distribution alpha, the super parameter is +.>Andalpha 'represents the conjugate index distribution of alpha, and the superparameters of alpha' are +.> and /> and />According to the preset-> and />And gradually and iteratively updating to obtain the product.
The super parameter is and />The initial value is preset to +.> wherein />Representing the time series of the ordinate>Is set to the start value of (1). Said superparameter-> and />Obtained according to the following formula:
in the formula ：indicating that the vehicle is at t m The ordinate of the moment.
Step C3: based on the vehicle i at t n Time of day vertical position coordinatesPosterior predictive distribution of->Obtaining posterior predictive probability P if vehicle i is at t n Time->If the posterior prediction probability of the vehicle i is larger than a preset threshold U, predicting that the vehicle i generates a lane change point at the time t; if the vehicle i is at t n Time->If the posterior prediction probability of (a) is less than or equal to the preset threshold U, predicting that the vehicle i is at t n The lane change point is not generated at the moment. In this embodiment, the preset threshold U is 0.001, and the detection result is shown in fig. 5.
The trajectory of the vehicle is easier to observe and capture than complex driving behaviors. Thus, it would be a new approach to solve the bottleneck problem to study difficult to observe, complex driving behavior using simple, readily available vehicle trajectory data. The method provided by the invention can realize real-time and online monitoring of the lane change behavior of the vehicle, and overcomes the defects that the driving behavior is difficult to observe, the cost of monitoring equipment is high and the accuracy is low; the invention is oriented to the future vehicle cooperative application scene, uses the generated track data and the historical vehicle statistical data as priori information, predicts the posterior distribution at the current moment according to Bayesian inference, and the prediction result can be updated gradually along with the change of time; generally, only if a lane change trend is generated by a driver and a lane change condition is met by a target lane, lane change points are possibly generated; compared with the traditional method, the method is based on the consideration of the influence of the Bayesian vehicle lane change point detection algorithm on the aspects of driving habit, driving skill and the like of the driver on the one hand, and the influence of the traffic environment index on the lane change behavior of the driver on the other hand. In addition, the method can guide and standardize driving behaviors of the final result from the perspective of a bicycle, reduce accidents and improve driving safety.
Although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that the foregoing embodiments may be modified or equivalents substituted for some of the features thereof. All equivalent structures made by the content of the specification and the drawings of the invention are directly or indirectly applied to other related technical fields, and are also within the scope of the invention.
Claims (2)
1. A real-time vehicle track lane change point monitoring method based on Bayesian theory is characterized by comprising the following steps: for a vehicle on a target road segment, the following steps are executed, and the channel changing condition of the vehicle on the target road segment at the current moment is monitored:
step A: aiming at a vehicle on a target road section, acquiring t in a historical time period based on a preset sampling time interval 0 To t n The preset track data of the vehicle i running at each sampling moment form a running track data set of the vehicle i wherein ,tn At the current moment, n is more than or equal to 2;
and (B) step (B): vehicle i-based trajectory data setObtaining the sampling time t of the vehicle i θ To t n Longitudinal position within a time period of (2)Coordinate time series-> wherein tθ Is the distance t n The generation time of the latest lane change point satisfies t 0 ≤t θ ＜t n ；
Step C: for vehicles on the target road segment, steps C1-C3 are performed to construct vehicle i at t n Time of day vertical position coordinatesPosterior predictive distribution of->Further judge that the vehicle i is on the target road section t n Whether a lane change point is generated at the moment, and monitoring the lane change condition of the vehicle i on the target road section at the current moment:
step C1: constructing a run-length function by the following formula
In the formula, when the vehicle i is at t T When the track is changed at the moment, thenIs 0, i.e. vehicle i is at t T Generating a lane change point at moment; when the vehicle i is at t T When the channel is not changed at all, then +.> Is->Is a priori information of (2);
step C2: based on the vehicle i at t θ To t n-1 Time series of ordinate in time periodVehicle i is constructed at t by the following formula n Time ordinate +.>Posterior predictive distribution of->
in the formula ,representation->UPM prediction of (c);
representing run +.>Posterior predictive distribution of (2) belonging to->Is a priori information of (2);
wherein ,UPM prediction->I.e. < ->Obtained by the following formula:
in the vehicle i longitudinal position coordinate time seriesObeying normal distribution alpha, the super parameter is +.> and />Alpha 'represents the conjugate index distribution of alpha, and the superparameters of alpha' are +.> and /> and />According to the preset-> and />Gradually and iteratively updating to obtain the product; /> and />The initial value is preset to +.> wherein />Representing a time series of ordinate positionsA start value of (2);
wherein , and />Obtained according to the following formula:
in the formula ：indicating that the vehicle is at t m An ordinate of time;
wherein, the run lengthPosterior predictive distribution of->I.e. < ->Obtained by the following steps 1 to 2:
step 1: time series based on vehicle i longitudinal position coordinatesConstructing +.> and />Is->
in the formula ,representation->About-> and />UPM prediction of (c);is t n-1 Priori information of the time lane change point, which is expressed based on t n-2 Time lane change situation vehicle i is at t n-1 The probability of channel change at the moment is obtained by a risk function; />Representing a preset +.> and />Is a joint probability of (2);the value of (2) is set by the following formula:
wherein λ represents an average time interval between adjacent lane change points;
the saidThe specific formula obtained from the risk function is as follows:
the risk functionIs constructed by the following formula:
in the formula ,indicating that vehicle i is at t n-1 Probability of changing channels at the moment; />Indicating that vehicle i is at t n-1 The time is a vector composed of traffic environment indexes, wherein the traffic environment indexes comprise t n-1 Preset track data of a vehicle i at the moment and preset track data of front and rear vehicles adjacent to the same lane of the vehicle i; beta k Representing a parameter vector, obeying normal distribution, and Q represents the total number of traffic environment indexes;
the risk function may be set to
Step 2: based on and />Is->Build by the following formulaPosterior predictive distribution of->
Step C3: based on the vehicle i at t n Time of day vertical position coordinatesPosterior predictive distribution of->Obtaining posterior predictive probability P if vehicle i is at t n Time->If the posterior prediction probability P of the vehicle i is larger than the preset threshold U, predicting the vehicle i at t n Generating a lane change point at moment; if the vehicle i is at t n Time->If the posterior prediction probability P of (a) is smaller than or equal to the preset threshold U, predicting the vehicle i at t n The lane change point is not generated at the moment.
2. The method for monitoring the lane change point of the vehicle track in real time based on the Bayesian theory according to claim 1, wherein the method comprises the following steps: the preset threshold U is 0.001.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211428816.5A CN115731708B (en) | 2022-11-15 | 2022-11-15 | Real-time vehicle track lane change point monitoring method based on Bayesian theory |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211428816.5A CN115731708B (en) | 2022-11-15 | 2022-11-15 | Real-time vehicle track lane change point monitoring method based on Bayesian theory |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115731708A CN115731708A (en) | 2023-03-03 |
| CN115731708B true CN115731708B (en) | 2023-10-17 |
Family
ID=85295808
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211428816.5A Active CN115731708B (en) | 2022-11-15 | 2022-11-15 | Real-time vehicle track lane change point monitoring method based on Bayesian theory |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115731708B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108387242A (en) * | 2018-02-07 | 2018-08-10 | 西南交通大学 | Automatic Pilot lane-change prepares and executes integrated method for planning track |
| WO2018220418A1 (en) * | 2017-06-02 | 2018-12-06 | Toyota Motor Europe | Driving assistance method and system |
| CN110705388A (en) * | 2019-09-16 | 2020-01-17 | 清华大学 | Target vehicle lane change identification method for auxiliary driving based on prediction feedback |
| CN111079834A (en) * | 2019-12-16 | 2020-04-28 | 清华大学 | Intelligent vehicle safety situation assessment method considering multi-vehicle interaction |
| CN111086514A (en) * | 2018-10-08 | 2020-05-01 | 现代摩比斯株式会社 | Apparatus for notifying driving lane and control method thereof |
| CN112053589A (en) * | 2020-08-18 | 2020-12-08 | 北京航空航天大学 | Target vehicle lane changing behavior adaptive identification model construction method |
| CN112347567A (en) * | 2020-11-27 | 2021-02-09 | 青岛莱吉传动系统科技有限公司 | Vehicle intention and track prediction method |
| CN112819845A (en) * | 2021-02-26 | 2021-05-18 | 华南理工大学 | Flexible packaging substrate contour, line width and line distance defect detection method, medium and equipment |
| CN113096379A (en) * | 2021-03-03 | 2021-07-09 | 东南大学 | Driving style identification method based on traffic conflict |
| CN113178097A (en) * | 2020-01-09 | 2021-07-27 | 大陆汽车有限责任公司 | Method for establishing probability map of unoccupied space comprising static target and dynamic target |
| US11151880B1 (en) * | 2020-08-21 | 2021-10-19 | Toyota Motor Engineering & Manufacturing North America, Inc. | Systems and methods for providing guidance to vehicle drivers regarding predicted lane-change behavior of other vehicle drivers |
| DE102020214203A1 (en) * | 2020-11-11 | 2022-05-12 | Volkswagen Aktiengesellschaft | Method for determining a lane change intention of another motor vehicle located in the immediate vicinity of a motor vehicle, and assistance system |
| CN115018016A (en) * | 2022-08-03 | 2022-09-06 | 苏州大学 | Method and system for identifying lane changing intention of manually-driven vehicle |
| CN115056798A (en) * | 2022-05-30 | 2022-09-16 | 天津大学 | Automatic driving vehicle lane change behavior vehicle-road cooperative decision algorithm based on Bayesian game |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11836585B2 (en) * | 2020-03-02 | 2023-12-05 | Uatc, Llc | Systems and methods for training probabilistic object motion prediction models using non-differentiable prior knowledge |
-
2022
- 2022-11-15 CN CN202211428816.5A patent/CN115731708B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018220418A1 (en) * | 2017-06-02 | 2018-12-06 | Toyota Motor Europe | Driving assistance method and system |
| CN108387242A (en) * | 2018-02-07 | 2018-08-10 | 西南交通大学 | Automatic Pilot lane-change prepares and executes integrated method for planning track |
| CN111086514A (en) * | 2018-10-08 | 2020-05-01 | 现代摩比斯株式会社 | Apparatus for notifying driving lane and control method thereof |
| CN110705388A (en) * | 2019-09-16 | 2020-01-17 | 清华大学 | Target vehicle lane change identification method for auxiliary driving based on prediction feedback |
| CN111079834A (en) * | 2019-12-16 | 2020-04-28 | 清华大学 | Intelligent vehicle safety situation assessment method considering multi-vehicle interaction |
| CN113178097A (en) * | 2020-01-09 | 2021-07-27 | 大陆汽车有限责任公司 | Method for establishing probability map of unoccupied space comprising static target and dynamic target |
| CN112053589A (en) * | 2020-08-18 | 2020-12-08 | 北京航空航天大学 | Target vehicle lane changing behavior adaptive identification model construction method |
| US11151880B1 (en) * | 2020-08-21 | 2021-10-19 | Toyota Motor Engineering & Manufacturing North America, Inc. | Systems and methods for providing guidance to vehicle drivers regarding predicted lane-change behavior of other vehicle drivers |
| DE102020214203A1 (en) * | 2020-11-11 | 2022-05-12 | Volkswagen Aktiengesellschaft | Method for determining a lane change intention of another motor vehicle located in the immediate vicinity of a motor vehicle, and assistance system |
| CN112347567A (en) * | 2020-11-27 | 2021-02-09 | 青岛莱吉传动系统科技有限公司 | Vehicle intention and track prediction method |
| CN112819845A (en) * | 2021-02-26 | 2021-05-18 | 华南理工大学 | Flexible packaging substrate contour, line width and line distance defect detection method, medium and equipment |
| CN113096379A (en) * | 2021-03-03 | 2021-07-09 | 东南大学 | Driving style identification method based on traffic conflict |
| CN115056798A (en) * | 2022-05-30 | 2022-09-16 | 天津大学 | Automatic driving vehicle lane change behavior vehicle-road cooperative decision algorithm based on Bayesian game |
| CN115018016A (en) * | 2022-08-03 | 2022-09-06 | 苏州大学 | Method and system for identifying lane changing intention of manually-driven vehicle |
Non-Patent Citations (1)
| Title |
|---|
| 基于贝叶斯网络的车辆换道决策模型研究;赵树恩;柯涛;柳平;;重庆交通大学学报(自然科学版)(05);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115731708A (en) | 2023-03-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110758382B (en) | Surrounding vehicle motion state prediction system and method based on driving intention | |
| Tang et al. | A hierarchical prediction model for lane-changes based on combination of fuzzy C-means and adaptive neural network | |
| CN112249008B (en) | Unmanned automobile early warning method aiming at complex dynamic environment | |
| CN110077398B (en) | Risk handling method for intelligent driving | |
| Li et al. | Lane change maneuver recognition via vehicle state and driver operation signals—Results from naturalistic driving data | |
| CN112572443B (en) | Real-time collision-avoidance trajectory planning method and system for lane changing of vehicles on highway | |
| CN111216713A (en) | Automatic driving vehicle speed pre-aiming control method | |
| CN111159642B (en) | Online track prediction method based on particle filtering | |
| CN113720346B (en) | Vehicle path planning method and system based on potential energy field and hidden Markov model | |
| CN112258893B (en) | Intelligent vehicle lane change collision probability assessment method based on track prediction | |
| CN115523934A (en) | Vehicle track prediction method and system based on deep learning | |
| Amsalu et al. | Driver intention estimation via discrete hidden Markov model | |
| CN115731708B (en) | Real-time vehicle track lane change point monitoring method based on Bayesian theory | |
| Ouyang et al. | Lane change decision planning for autonomous vehicles | |
| Zhang et al. | A lane-changing prediction method based on temporal convolution network | |
| Lin et al. | Energy management for a dual-motor coupling propulsion electric bus based on model predictive control | |
| CN113635900B (en) | Channel switching decision control method based on energy management in predicted cruising process | |
| CN114872727A (en) | Peripheral vehicle track prediction method applied to automatic driving vehicle | |
| CN110936954B (en) | Intelligent vehicle prediction decision fusion method considering vehicle bidirectional interaction | |
| Yu et al. | Drivers' car-following correlative behavior with preceding vehicles in multilane driving | |
| Yuan et al. | Research on key technologies of autonomous driving platform | |
| Zeng et al. | Risk-aware deep reinforcement learning for decision-making and planning of autonomous vehicles | |
| CN112150816A (en) | Multi-vehicle interaction risk assessment system | |
| Guo et al. | Model Predictive Adaptive Cruise Control of Intelligent Electric Vehicles Based on Deep Reinforcement Learning Algorithm FWOR Driver Characteristics | |
| Fang et al. | Distributed Cooperative Control of Vehicle Platoon Based on a Composite Safety Distance |
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 |