CN111415531B - Expressway confluence area traffic conflict discrimination method based on travel track prediction - Google Patents
Expressway confluence area traffic conflict discrimination method based on travel track prediction Download PDFInfo
- Publication number
- CN111415531B CN111415531B CN202010150537.1A CN202010150537A CN111415531B CN 111415531 B CN111415531 B CN 111415531B CN 202010150537 A CN202010150537 A CN 202010150537A CN 111415531 B CN111415531 B CN 111415531B
- Authority
- CN
- China
- Prior art keywords
- track
- vehicles
- vehicle
- priority
- prediction
- 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.)
- Expired - Fee Related
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/167—Driving aids for lane monitoring, lane changing, e.g. blind spot detection
-
- 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
-
- 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
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method for judging traffic conflicts in a highway confluence area based on vehicle running track prediction, which comprises the following steps: (1) establishing a two-dimensional coordinate system in the confluence area; (2) dividing the priority of the processing sequence of the vehicle track data set according to time; (3) classifying the running track data sets of the vehicles in the confluence area at the initial moment of the same priority, (4) predicting the running track points of each vehicle on each lane by adopting a Kalman filtering method based on the running track data sets of the vehicles; (5) performing linear fitting on the coordinate points and then drawing a vehicle trajectory line based on a function expression; (6) carrying out conflict judgment on the track intersection points; the method is used for innovatively judging whether traffic conflicts exist in vehicles in the highway confluence area from the vehicle track angle, and establishing a mathematical model for function fitting by combining track point space-time information, so that the reliability and feasibility of the method are ensured.
Description
Technical Field
The invention relates to the field of traffic safety, in particular to a method for judging a traffic conflict area in the field of highway safety, and especially relates to a method for judging a traffic conflict in a highway confluence area based on vehicle running track prediction.
Background
With the continuous development of highway construction in China, the importance of safety management problems in highways is increasingly highlighted, and particularly, when vehicles enter a main road of the highway from an entrance of the highway through a confluence area, the problem of traffic conflict can be caused. Traffic conflicts refer to the fact that under observable conditions, 2 or more than 2 traffic participants are close to each other in space and time, so that if either party does not change their travel trajectory, there is a risk of collision. The confluence area is a common traffic conflict accident high-occurrence area of the expressway, and if the time and the place of the traffic conflict possibly occurring in the confluence area can be sensed and judged in advance through a certain technical means, the safety of the confluence area of the expressway can be greatly improved, and the probability of the traffic accident occurring in the confluence area can be reduced.
At present, in the prior art, the research on traffic conflicts under the control of signal lamps is mainly focused, the research on the traffic conflicts in a confluence area is relatively less, most of the research is focused on the construction aspect of a safety evaluation index system and an evaluation method, and the used model method is complex and is difficult to be directly used in practical application.
Therefore, the invention needs to fill up the gap, so the invention considers the convenience of practical application, converts the traffic conflict discrimination problem in the running process of the actual vehicles in the confluence area into the coincidence discrimination problem of the movement track of the objects in the confluence area, considers the factors of the size of the actual vehicles, the fluctuation of the actual traffic flow and the like, determines a circular area by taking the intersection point of the running track of the vehicles as the center of a circle and a standard length of a car as the radius, and further determines the existence of conflict.
Disclosure of Invention
The invention aims to solve the problem of filling the blank of the merging area vehicle conflict discrimination technology convenient for practical application and provides a highway merging area traffic conflict discrimination method based on vehicle running track prediction.
In order to solve the technical problems, the invention is realized by adopting the following technical scheme:
the method for judging the traffic conflict in the highway confluence area based on the vehicle running track prediction comprises the following steps:
step one, establishing a two-dimensional coordinate system in a confluence area;
and a two-dimensional coordinate system which takes the intersection point of the central line of the lane at the outermost side of the main road and the extension line of the road shoulder closest to the main road of the ramp as the origin, takes the lane line at the outermost side of the main road of the expressway as the horizontal axis and takes the line passing through the origin and vertical to the horizontal axis as the vertical axis is established in the range of the confluence area.
Dividing the priority of the processing sequence of the vehicle track data set according to time;
the priority for dividing the vehicle track data processing sequence according to the time refers to the sequence of dividing the vehicle track data set processing from the angle of time, the principle of dividing the priority is that the vehicle entering the confluence area firstly carries out track prediction, and the expression form of the vehicle track data is the coordinate representation of the driving track point of the central position of the vehicle based on the two-dimensional coordinate system;
step three, classifying the running track data sets of the vehicles in the confluence area at the initial time of the same priority;
the method comprises the following steps that two types of vehicle running track data sets are provided on a lane closest to a ramp on the outermost side of a main road of a confluence area and a vehicle running track data set on each lane of the ramp, and each type of track data set comprises a position value, a speed component and an acceleration component of a vehicle in the transverse direction, namely the X direction; and the position value, velocity component, acceleration component of the longitudinal direction, i.e. the Y direction;
fourthly, on the basis of the vehicle running track data set, conducting running track point prediction on each vehicle on each lane; the method for predicting the driving track points of each vehicle on each lane is a Kalman filtering method, and the Kalman filtering method for predicting the track mainly comprises the following steps: (a) determining motion model parameters according to a state equation and an observation equation, and initializing the parameters; (b) knowing an optimal state estimation value and an estimation error variance matrix at an initial moment, predicting a predicted value of a detected vehicle track at the next moment according to a state equation, and simultaneously obtaining a covariance matrix of estimation errors; (c) obtaining an optimal state estimation value and a covariance matrix of an optimal estimation error according to an observation value at the next moment, and finishing one-step filtering; sequentially iterating to obtain the optimal state estimation of the previous moment, and finishing the filtering process; (d) predicting the track point position of the next moment according to the previously obtained optimal state estimation of the previous moment and the observed value of the current moment, comparing the predicted point with the real track point, and calculating a predicted error; sequentially repeating the operation to complete the prediction of future track points, and calculating to obtain a prediction error mean value;
step five, performing linear fitting processing on the coordinate points to obtain a function expression between the ordinate and the abscissa of the track point, and then drawing a vehicle track line based on the function expression;
step six, performing conflict judgment on the track intersection points
In the method for judging the traffic conflict in the expressway confluence area based on the vehicle running track prediction, the specific substep of judging the existence of the conflict at the track intersection is as follows:
(a) judging whether the predicted running track lines of two vehicles which are not on the same lane have an intersection or not, and if the two vehicles do not have the intersection, determining that the two vehicles do not have traffic conflict; if the collision area exists, a circular area is defined by taking the intersection point as the circle center and taking a standard car length as the radius, and the circular area is recorded as the collision area;
(b) and judging whether the two vehicles reach the conflict area within a certain time threshold, if so, judging that the two vehicles in the confluence area have traffic conflict within the time range of the area, and otherwise, judging that the two vehicles do not have conflict.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention innovatively judges the traffic conflict of vehicles in the highway confluence area from the angle of the vehicle running track, in particular to a method for judging the traffic conflict of the highway confluence area based on the vehicle running track prediction, and carries out mathematical modeling by combining the time-space information of the vehicles, thereby ensuring the reliability and feasibility of the method for judging the conflict and filling the blank that the existing technology for judging the traffic conflict of the confluence area is inconvenient for practical application.
2. The Kalman filtering algorithm used in the method for judging the traffic conflict area of the highway confluence area is particularly suitable for track data with uncertain motion states and different motion modes, which are frequently changed, can carry out optimal estimation on the system state, can realize the estimation and prediction of real-time running state, and can carry out higher self-adaptive adjustment even considering the frequent change of the motion state in the running process of an actual vehicle.
Drawings
The invention is further described with reference to the accompanying drawings in which:
FIG. 1 is a schematic flow chart of a method for judging traffic conflicts in a confluence area of a highway based on vehicle running track prediction according to the present invention;
FIG. 2 is a schematic diagram of a coordinate system of a method for judging traffic conflicts at a confluence area of a highway based on vehicle running track prediction according to the present invention;
fig. 3 is a schematic diagram of vehicle prioritization based on the method for judging traffic conflicts at the confluence area of the expressway based on vehicle driving track prediction according to the invention.
Detailed Description
For the purpose of facilitating understanding, the following description is made with reference to the accompanying drawings.
The specific real-time mode relates to a method for judging traffic conflicts in a highway confluence area based on vehicle running track prediction, as shown in fig. 1, the method comprises the following steps:
step one, establishing a two-dimensional coordinate system in a confluence area
As shown in fig. 2, considering that the coordinate system where the data is unified for mathematical operation is needed when performing trajectory prediction in the subsequent steps, establishing a two-dimensional coordinate system in the merge area according to the present invention means establishing a two-dimensional coordinate system in the merge area, where an intersection of a center line of an outermost lane of the main road and an extension line of a shoulder of a ramp closest to the main road is an origin, a lane line of an outermost lane of the highway is a horizontal axis, and a line passing through the origin and perpendicular to the horizontal axis is a vertical axis.
Dividing the priority of the processing sequence of the vehicle track data set according to time;
the priority for dividing the processing sequence of the vehicle track data according to the time is the sequence of dividing the vehicle track data set from the angle of time according to a certain principle, the principle of dividing the priority is that the vehicle firstly enters the confluence area and the track prediction is carried out, the expression form of the vehicle track data is that the coordinate representation of the driving track point of the central position of the vehicle is carried out based on the two-dimensional coordinate system, and is expressed as (x)i,yi)。
The reason for performing the above processing is to consider that when the merge area vehicle trajectory data is processed in the subsequent trajectory prediction step, if the trajectory data processing is not divided temporally, the data processing efficiency may be affected due to the fact that the traffic flow is huge in a certain period of time, and to avoid the above situation, the vehicle trajectory data processing order is prioritized.
Step three, classifying the running track data sets of the vehicles in the confluence area at the initial time of the same priority
As shown in fig. 3, in specific implementation, the priority is divided from the perspective of time, and a time window corresponding to an initial T time is determined first, and it is noted that all vehicles in the time window are first-priority vehicles; then, setting a time window corresponding to the time T +1, and recording that all vehicles in the time window are second-priority vehicles; and then, recording that all vehicles in the time window corresponding to the time T +2 are the vehicles with the third priority, so that the vehicles with the Nth priority can be obtained in sequence. When the traffic conflict is identified, the vehicles with different priorities are processed in sequence by processing the vehicles with the first priority, then processing the vehicles with the second priority and then processing the vehicles with the third priority.
The classification of the travel track data sets of vehicles in the confluence area at the initial moment of the same priority level refers to the classification according to main roads and ramps of the confluence area, in particular to the classification into a vehicle travel track data set on a lane closest to a ramp on the outermost side of the main road of the confluence area and a vehicle travel track data set on each lane of the ramp, wherein each track data set comprises a position value, a speed component and an acceleration component of the vehicle in the transverse direction (namely the X direction) and a position value, a speed component and an acceleration component of the vehicle in the longitudinal direction (namely the Y direction).
Fourthly, based on the vehicle driving track data set, driving track points are carried out on each vehicle on each lane
Predicting;
the method for predicting the running track point of each vehicle on each lane is a Kalman filtering method, and the advantages of applying the Kalman filtering algorithm to the vehicle track prediction of the confluence area are mainly embodied in the following two aspects that (1) the motion of the vehicles in the confluence area is complex and changeable and has high uncertainty, and the Kalman filtering algorithm is particularly suitable for track data with frequent change of motion states, uncertainty and different motion modes, can optimally estimate the system state, can realize the estimation and prediction of the real-time running state, and is suitable for the linear and nonlinear space-time tracks with limited dimensions; (2) when the merge area vehicle track is predicted, the merge area vehicle track prediction method has very high requirements on the real-time performance and accuracy of a prediction result, prediction failure can be caused by overlarge prediction deviation or inaccuracy of a prediction position point, and the Kalman filtering algorithm has the advantage of high real-time performance when applied to track prediction, has high self-adaptability to a moving object with a frequently changed motion state, and is a universal machine learning method.
The Kalman filtering prediction trajectory mainly comprises the following steps: (a) determining motion model parameters according to a state equation and an observation equation, and initializing the parameters; (b) knowing an optimal state estimation value and an estimation error variance matrix at an initial moment, predicting a predicted value of a detected vehicle track at the next moment according to a state equation, and simultaneously obtaining a covariance matrix of estimation errors; (c) obtaining an optimal state estimation value and a covariance matrix of an optimal estimation error according to an observation value at the next moment, and finishing one-step filtering; sequentially iterating to obtain the optimal state estimation of the previous moment, and finishing the filtering process; (d) predicting the track point position of the next moment according to the previously obtained optimal state estimation of the previous moment and the observed value of the current moment, comparing the predicted point with the real track point, and calculating a predicted error; and sequentially repeating the operation to complete the prediction of the future track points, and calculating to obtain a prediction error mean value.
The specific operation process for predicting the vehicle track by using the kalman filter is described as follows:
the starting point position of the target vehicle needing to be subjected to track prediction is set, for convenience of description, the starting point of the target vehicle needing to be subjected to track prediction is set to be 200 meters away from the entrance of the confluence area, meanwhile, coordinate axes are considered separately when the track is predicted, and Kalman algorithm prediction is carried out on each coordinate axis independently, so that two-dimensional prediction can be converted into one-dimensional prediction, and prediction efficiency is improved.
The following is an example of kalman trajectory prediction in the X direction.
Let the state vector in the X direction of the vehicle for which trajectory prediction is required be expressed as:
in the formula (1), x1(n) is a position value of the target vehicle at the nth time in the X direction; x is the number of2(n) is the speed value of the target vehicle at the nth time in the X direction; x is the number of3(n) is an acceleration value of the target vehicle at the nth time in the X direction.
The system equation of the central motion state of the target vehicle is as follows:
X(n+1)=A*X(n)+ε(n) (2)
in formula (2):is the system noise;is a state transition equation; and tau is the time interval of data uploading.
The covariance matrix of the system noise is:
the measurement equation is as follows:
Z(n)=C*X(n)+η(n) (4)
in formula (4): c ═ 100]Is a measurement matrix; η (n) is the measurement noise, and the variance of the measurement noise isHere setting
As can be seen from the above, the initial value of the prediction covariance matrix at the previous time of the target vehicle must be obtained before the recurrence calculation is started, and in order to obtain the initial value, the center point positions x (t), x (t +1), and x (t +2) of three consecutive target vehicles need to be selected in a selected time period, and a vector estimation matrix needs to be obtained according to the selected values:
the true value of the state when n is t +2 can be found from the state equation and the measurement equation of the system as follows:
and then predicting the next moment, and still obtaining a predicted value according to the equation, wherein the predicted value comprises a position value, a velocity value and an acceleration value. And similarly, the Kalman prediction in the Y direction can obtain a predicted value in the Y direction, and the predicted value comprises a position value, a speed value and an acceleration value.
In order to further ensure the accuracy of the track prediction, the geometric space error of the predicted track point and the actual track point is calculated by adopting a root mean square error RMSE:
wherein (x)i,yi) -the position coordinates of the actual track points;
(x'i,y'i) -predicting the position coordinates of the trace points;
k is the number of predicted trace points.
When the track prediction is finished, determining whether the track prediction result is accurate according to the size relation between the root mean square error RMSE and a given threshold (the threshold is set to be 3m), and if the root mean square error RMSE is smaller than the threshold, determining that the prediction is accurate and hitting track points; otherwise, the prediction point is not hit, if the prediction point is not hit, the prediction point is discarded, and the relevant parameters are readjusted for prediction.
Step five, processing the track points obtained by prediction in time and space to obtain the predicted vehicle running track of each vehicle on each lane;
for each vehicleThe vehicle is subjected to the space-time processing, coordinates of predicted driving track points can be obtained, then linear fitting processing is carried out on the coordinate points by adopting unary linear regression, and a function expression between the ordinate and the abscissa of the track points can be obtained by the processing: y isi=f(xi)=a*xi+ b, then, the vehicle trajectory line is drawn based on the functional expression.
The method includes the steps of carrying out linear fitting processing on the obtained actual coordinate points and the obtained predicted coordinate points of the target vehicle, carrying out unary linear regression based on a least square method during fitting to better obtain a function expression between the ordinate and the abscissa of the track point of the target vehicle, carrying out linear fitting processing on the coordinate points to obtain a function expression between the ordinate and the abscissa of the track point, then drawing a vehicle track line based on the function expression, and if so, carrying out the space-time processing on each vehicle on each lane of the traffic area to better judge the existence of subsequent conflicts.
And step six, carrying out conflict judgment.
When a vehicle passes through a confluence area, there must be a place where the track lines of vehicles in different lanes intersect, that is, there are track intersections, which are potential conflict points, that is, there is a possibility of traffic conflict but not necessarily traffic conflict. Next, the presence of a collision between the vehicles at the merge area is determined. Then, collision judgment is carried out on the track intersection, and the specific sub-steps are as follows:
(a) judging whether the predicted running track lines of two vehicles which are not on the same lane have an intersection or not, and if the two vehicles do not have the intersection, determining that the two vehicles do not have traffic conflict; if the collision area exists, a circular area is defined by taking the intersection point as the circle center and taking a standard car length as the radius, and the circular area is recorded as the collision area;
(b) and judging whether the two vehicles reach the conflict area within a certain time threshold, if so, judging that the two vehicles in the confluence area have traffic conflict within the time range of the area, and otherwise, judging that the two vehicles do not have conflict.
The above is only a preferred embodiment of the present patent, and the object is to clarify the inventive essence of the present patent, and all modifications, such as replacement, change and deletion of some elements, made under the inventive concept of the present patent should be included in the protection scope of the present patent as it does not depart from the inventive concept of the present patent.
Claims (1)
1. A method for judging traffic conflicts at a highway confluence area based on vehicle driving track prediction is characterized by comprising the following steps:
step one, establishing a two-dimensional coordinate system in a confluence area;
establishing a two-dimensional coordinate system in the range of the confluence area, wherein the intersection point of the center line of the lane at the outermost side of the main road and the extension line of the road shoulder closest to the main road of the ramp is taken as an origin, the lane line at the outermost side of the main road of the expressway is taken as a transverse axis, and the line passing through the origin and perpendicular to the transverse axis is taken as a longitudinal axis; firstly, determining a time window corresponding to an initial T moment, and recording that vehicles in the time window are all first-priority vehicles; then, setting a time window corresponding to the time T +1, and recording that all vehicles in the time window are second-priority vehicles; secondly, recording the vehicles in the time window corresponding to the time T +2 as third-priority vehicles; sequentially obtaining vehicles with Nth priority; when the traffic conflict is identified, the vehicles with the first priority are processed, then the vehicles with the second priority are processed, then the vehicles with the third priority are processed, and the vehicles with different priorities are processed in sequence;
dividing the priority of the processing sequence of the vehicle track data set according to time;
the priority for dividing the vehicle track data processing sequence according to the time refers to the sequence of dividing the vehicle track data set processing from the angle of time, the principle of dividing the priority is that the vehicle entering the confluence area firstly carries out track prediction, and the expression form of the vehicle track data is the coordinate representation of the driving track point of the central position of the vehicle based on the two-dimensional coordinate system;
step three, classifying the running track data sets of the vehicles in the confluence area at the initial time of the same priority;
the method comprises the following steps that two types of vehicle running track data sets are provided on a lane closest to a ramp on the outermost side of a main road of a confluence area and a vehicle running track data set on each lane of the ramp, and each type of track data set comprises a position value, a speed component and an acceleration component of a vehicle in the transverse direction, namely the X direction; and the position value, velocity component, acceleration component of the longitudinal direction, i.e. the Y direction;
fourthly, on the basis of the vehicle running track data set, conducting running track point prediction on each vehicle on each lane;
the method for predicting the driving track points of each vehicle on each lane is a Kalman filtering method, and the Kalman filtering method for predicting the track mainly comprises the following steps: (a) determining motion model parameters according to a state equation and an observation equation, and initializing the parameters; (b) knowing an optimal state estimation value and an estimation error variance matrix at an initial moment, predicting a predicted value of a detected vehicle track at the next moment according to a state equation, and simultaneously obtaining a covariance matrix of estimation errors; (c) obtaining an optimal state estimation value and a covariance matrix of an optimal estimation error according to an observation value at the next moment, and finishing one-step filtering; sequentially iterating to obtain the optimal state estimation of the previous moment, and finishing the filtering process; (d) predicting the track point position of the next moment according to the previously obtained optimal state estimation of the previous moment and the observed value of the current moment, comparing the predicted point with the real track point, and calculating a predicted error; sequentially repeating the operation to complete the prediction of future track points, and calculating to obtain a prediction error mean value;
step five, performing linear fitting processing on the track points to obtain a function expression between the ordinate and the abscissa of the track points, and then drawing a vehicle track line based on the function expression;
step six, performing conflict judgment on the track intersection points
In the method for judging the traffic conflict in the expressway confluence area based on the vehicle running track prediction, the specific substep of judging the existence of the conflict at the track intersection is as follows:
(a) judging whether the predicted running track lines of two vehicles which are not on the same lane have an intersection or not, and if the two vehicles do not have the intersection, determining that the two vehicles do not have traffic conflict; if the collision area exists, a circular area is defined by taking the intersection point as the circle center and taking a standard car length as the radius, and the circular area is recorded as the collision area;
(b) and judging whether the two vehicles reach the conflict area within a preset time threshold, if so, judging that the two vehicles in the confluence area have traffic conflicts within the time range of the area, and otherwise, judging that the two vehicles do not have conflicts.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910522080.XA CN110310516A (en) | 2019-06-17 | 2019-06-17 | A kind of highway merging area traffic conflict method of discrimination based on vehicle driving trace prediction |
CN201910522080X | 2019-06-17 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111415531A CN111415531A (en) | 2020-07-14 |
CN111415531B true CN111415531B (en) | 2021-08-24 |
Family
ID=68077574
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910522080.XA Pending CN110310516A (en) | 2019-06-17 | 2019-06-17 | A kind of highway merging area traffic conflict method of discrimination based on vehicle driving trace prediction |
CN202010150537.1A Expired - Fee Related CN111415531B (en) | 2019-06-17 | 2020-03-06 | Expressway confluence area traffic conflict discrimination method based on travel track prediction |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910522080.XA Pending CN110310516A (en) | 2019-06-17 | 2019-06-17 | A kind of highway merging area traffic conflict method of discrimination based on vehicle driving trace prediction |
Country Status (1)
Country | Link |
---|---|
CN (2) | CN110310516A (en) |
Families Citing this family (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2021024423A (en) * | 2019-08-05 | 2021-02-22 | 本田技研工業株式会社 | Vehicle control device, vehicle control method, and program |
CN110781774A (en) * | 2019-10-10 | 2020-02-11 | 江苏理工学院 | Level crossing intelligent guiding system and method based on deep learning |
CN110855789B (en) * | 2019-11-18 | 2022-07-08 | 东软集团股份有限公司 | Position relation determining method and device, storage medium and equipment |
CN111145569A (en) * | 2019-11-22 | 2020-05-12 | 京东数字科技控股有限公司 | Road monitoring and vehicle running control method and device and vehicle-road cooperative system |
CN110825090A (en) * | 2019-11-29 | 2020-02-21 | 苏州智加科技有限公司 | Method, device and storage medium for dividing prediction priority of automatic driving vehicle |
JP7309594B2 (en) * | 2019-12-18 | 2023-07-18 | Kddi株式会社 | Merging Support Information Delivery Device, Merging Support System, Merging Support Information Delivery Method, and Computer Program |
CN112133089B (en) * | 2020-07-21 | 2021-11-19 | 西安交通大学 | Vehicle track prediction method, system and device based on surrounding environment and behavior intention |
CN112927512B (en) * | 2021-02-24 | 2022-03-29 | 山东科技大学 | Expressway ramp confluence control system and method |
CN113353080A (en) * | 2021-06-01 | 2021-09-07 | 上海网车科技有限公司 | Highway automatic lane changing method based on travelable area |
CN113706927B (en) * | 2021-08-16 | 2023-02-28 | 中汽创智科技有限公司 | Vehicle early warning method, device, electronic equipment, storage medium and program product |
CN113741443A (en) * | 2021-08-26 | 2021-12-03 | 北京京东乾石科技有限公司 | Method and device for controlling rail guided vehicle, storage medium and electronic equipment |
CN113963537A (en) * | 2021-10-19 | 2022-01-21 | 东软睿驰汽车技术(上海)有限公司 | Vehicle track prediction method for intersection and related device |
CN114120639B (en) * | 2021-11-09 | 2023-04-11 | 广州文远知行科技有限公司 | Vehicle traffic control method, device and storage medium |
CN114333419B (en) * | 2021-12-28 | 2023-04-07 | 杭州海康威视***技术有限公司 | Traffic conflict determination method, device, equipment and readable storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104882025A (en) * | 2015-05-13 | 2015-09-02 | 东华大学 | Crashing detecting and warning method based on vehicle network technology |
CN105894856A (en) * | 2016-05-10 | 2016-08-24 | 浙江树人大学 | Vehicle collision preventing method based on vehicle-vehicle communication |
CN109118786A (en) * | 2018-08-20 | 2019-01-01 | 浙江工业大学 | A kind of car speed prediction technique based on quantization adaptive Kalman filter |
CN109275121A (en) * | 2018-08-20 | 2019-01-25 | 浙江工业大学 | A kind of Vehicle tracing method based on adaptive extended kalman filtering |
CN109859500A (en) * | 2018-12-17 | 2019-06-07 | 中电海康集团有限公司 | A kind of high speed merging area safe early warning method based on bus or train route collaboration |
-
2019
- 2019-06-17 CN CN201910522080.XA patent/CN110310516A/en active Pending
-
2020
- 2020-03-06 CN CN202010150537.1A patent/CN111415531B/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104882025A (en) * | 2015-05-13 | 2015-09-02 | 东华大学 | Crashing detecting and warning method based on vehicle network technology |
CN105894856A (en) * | 2016-05-10 | 2016-08-24 | 浙江树人大学 | Vehicle collision preventing method based on vehicle-vehicle communication |
CN109118786A (en) * | 2018-08-20 | 2019-01-01 | 浙江工业大学 | A kind of car speed prediction technique based on quantization adaptive Kalman filter |
CN109275121A (en) * | 2018-08-20 | 2019-01-25 | 浙江工业大学 | A kind of Vehicle tracing method based on adaptive extended kalman filtering |
CN109859500A (en) * | 2018-12-17 | 2019-06-07 | 中电海康集团有限公司 | A kind of high speed merging area safe early warning method based on bus or train route collaboration |
Also Published As
Publication number | Publication date |
---|---|
CN110310516A (en) | 2019-10-08 |
CN111415531A (en) | 2020-07-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111415531B (en) | Expressway confluence area traffic conflict discrimination method based on travel track prediction | |
CN109885066B (en) | Motion trail prediction method and device | |
CN110675656B (en) | Intelligent vehicle lane change early warning method based on instantaneous risk identification | |
CN106428009B (en) | System and method for vehicle trajectory determination | |
CN112700470B (en) | Target detection and track extraction method based on traffic video stream | |
JP5620147B2 (en) | Movable object prediction apparatus and program | |
WO2018179539A1 (en) | Method for controlling host vehicle and control system of host vehicle | |
GB2608567A (en) | Operation of a vehicle using motion planning with machine learning | |
US10650256B2 (en) | Automatically perceiving travel signals | |
CN112577506B (en) | Automatic driving local path planning method and system | |
Kim et al. | Automated complex urban driving based on enhanced environment representation with GPS/map, radar, lidar and vision | |
CN111094095B (en) | Method and device for automatically sensing driving signal and vehicle | |
CN102616241A (en) | Lane departure alarm system based on lane line model detection method and on-line study method | |
CN102673560A (en) | Method for recognizing turn-off maneuver and driver assistance system | |
CN110047276A (en) | Method and device for determining congestion state of obstacle vehicle and related product | |
CN112389440A (en) | Vehicle driving risk prediction method in off-road environment based on vehicle-road action mechanism | |
CN115195790B (en) | Method and device for predicting vehicle track, electronic equipment and storage medium | |
CN109878530B (en) | Method and system for identifying lateral driving condition of vehicle | |
CN104395944A (en) | Carriageway recognition | |
CN114170274B (en) | Target tracking method and device, electronic equipment and storage medium | |
CN115147790B (en) | Future track prediction method of vehicle based on graph neural network | |
CN114446046A (en) | LSTM model-based weak traffic participant track prediction method | |
CN116187067A (en) | Human-vehicle conflict analysis method for pedestrian crossing crosswalk without signal control under mixed traffic flow | |
CN115451987A (en) | Path planning learning method for automatic driving automobile | |
CN112026774B (en) | Surrounding vehicle sideslip identification method based on own vehicle camera and radar sensing information |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210824 |
|
CF01 | Termination of patent right due to non-payment of annual fee |