CN113158415A - Vehicle track similarity evaluation method based on error analysis - Google Patents

Vehicle track similarity evaluation method based on error analysis Download PDF

Info

Publication number
CN113158415A
CN113158415A CN202110200652.XA CN202110200652A CN113158415A CN 113158415 A CN113158415 A CN 113158415A CN 202110200652 A CN202110200652 A CN 202110200652A CN 113158415 A CN113158415 A CN 113158415A
Authority
CN
China
Prior art keywords
error
jitter
scalar
vector
track
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.)
Granted
Application number
CN202110200652.XA
Other languages
Chinese (zh)
Other versions
CN113158415B (en
Inventor
韦云凯
张陈瑜
马立香
冷甦鹏
杨鲲
刘强
沈军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yangtze River Delta Research Institute of UESTC Huzhou
Original Assignee
Yangtze River Delta Research Institute of UESTC Huzhou
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Yangtze River Delta Research Institute of UESTC Huzhou filed Critical Yangtze River Delta Research Institute of UESTC Huzhou
Priority to CN202110200652.XA priority Critical patent/CN113158415B/en
Publication of CN113158415A publication Critical patent/CN113158415A/en
Application granted granted Critical
Publication of CN113158415B publication Critical patent/CN113158415B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06315—Needs-based resource requirements planning or analysis
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Abstract

The invention discloses a vehicle track similarity evaluation method based on error analysis, which comprises the following steps of: s1, forming a predicted track and a real track of the vehicle according to the track step length k; s2, calculating correlation errors between the real track and the predicted track, wherein the correlation errors comprise scalar errors, vector errors, scalar error jitter and vector error jitter; s3, determining an influence factor and calculating the size of a jitter window; and S4, calculating the similarity. According to the method, the calculation efficiency of the track similarity of the predicted track and the real track of the vehicle can be improved by calculating the scalar error and vector error values of the predicted and real tracks and dynamically adjusting the influence degree of the scalar error and the vector error on the similarity according to the scalar error jitter and the vector error jitter values, the updating of a vehicle track prediction model can be efficiently assisted, and the driving safety of the vehicle is enhanced.

Description

Vehicle track similarity evaluation method based on error analysis
Technical Field
The invention belongs to the field of intelligent transportation, and particularly relates to a vehicle track similarity evaluation method based on error analysis.
Background
In recent years, global positioning technology has been rapidly developed and widely used in intelligent transportation systems. Among them, predicting the driving trajectory of a vehicle based on an artificial intelligence technique is one of the key directions of current research. The method and the device realize the prediction of the future driving track by utilizing the history and real-time data of the vehicle.
The vehicle equipped with the GPS can locate its own position in real time while sensing surrounding vehicles through sensors mounted on the vehicle. According to the sensed collected information, the system can predict the running track of the surrounding vehicles in a future period of time in advance. The autonomous vehicle can dynamically plan its own driving route according to the future driving track of the surrounding vehicle. Thus, the ability of the autonomous vehicle to cope with changing complex traffic environments is improved.
In a real-world problem, the trajectory prediction model is directly put into use after being trained by a data set, but the trajectory prediction model trained at one time cannot adapt to various surrounding running vehicles due to the randomness of the driving behaviors of other traffic participants and the constraint of road geometry. Therefore, the lack of feedback and the updated prediction model can cause a certain deviation of the prediction result, and finally the aim of improving the safety of the automatic driving vehicle cannot be achieved. Therefore, a method for evaluating the similarity between the prediction and the real track is needed to evaluate the accuracy of the track prediction, and the prediction model can be updated by taking the index as the feedback of the model.
Secondly, the track is predicted by historical data to predict the position single point of the vehicle at the next moment, and if the similarity is measured by the Euclidean distance between the predicted track single point and the real track single point in the traditional mode, the driving tendency of the vehicle in a period of time is ignored. Therefore, the accuracy of the trajectory prediction in a period of time needs to be considered by fitting a plurality of trajectory single points into a trajectory.
Finally, in the process of predicting the track of the surrounding vehicles by the automatic driving vehicle, a certain error exists in the track prediction model, so that the similarity evaluation method needs to take certain measures to eliminate the randomness of each time point.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a vehicle track similarity evaluation method based on error analysis, which can improve the calculation efficiency of the track similarity of a predicted track and a real track of a vehicle by calculating the values of scalar errors and vector errors of the predicted track and the real track and dynamically adjusting the influence degree of the scalar errors and the vector errors on the similarity by the values of scalar error jitter and vector error jitter, can efficiently assist the update of a vehicle track prediction model and enhance the running safety of the vehicle.
The purpose of the invention is realized by the following technical scheme: a vehicle track similarity evaluation method based on error analysis comprises the following steps:
s1, forming a predicted track and a real track of the vehicle according to the track step length k;
s2, calculating correlation errors between the real track and the predicted track, wherein the correlation errors comprise scalar errors, vector errors, scalar error jitter and vector error jitter;
s3, determining an influence factor and calculating the size of a jitter window;
and S4, calculating the similarity.
Further, the scalar error refers to the area of a closed graph formed by enclosing two tracks on a coordinate axis;
the vector error refers to the sum of absolute values of the variation of the area enclosed by every two adjacent tracks between 0.1s in the step length of the k time;
scalar error jitter refers to the variance of the scalar error for each k time step over the time of the jitter window size;
vector error jitter refers to the variance of the vector error for each k time step in time, the size of the jitter window.
Further, the specific implementation method of step S3 is as follows: in the initial state, the default scalar error and the default vector error influence the track similarity to the same extent, namely the scalar error influence factor alpha is 0.5, and the vector error influence factor beta is 0.5; and the system defines the scalar error jitter threshold at the initial moment
Figure BDA0002948633970000022
Sum vector error jitter threshold
Figure BDA0002948633970000023
When the scalar error jitter and the vector error jitter are both smaller than or equal to a set threshold, alpha and beta in the track similarity are 0.5; when both the scalar error and the vector error jitter are greater than a set threshold, the track similarity is 0; when one of the scalar error jitter and the vector error jitter exceeds a set threshold, increasing an influence factor of an error corresponding to the jitter in the track similarity evaluation, and correspondingly reducing an influence factor of the other error in the track similarity evaluation, wherein the increasing and reducing methods can be customized according to application scenarios and requirements, for example, linear increase and decrease are performed, and α + β ═ 1 is satisfied.
Setting the jitter window at the initial moment to be 1, and calculating the variance of the initial k time step length only by error jitter, so that the result is 0; when the scalar error jitter and the vector error jitter are both smaller than or equal to the set threshold, the size of the jitter window is unchanged; when both the scalar error jitter and the vector error jitter are greater than the set threshold, adding 2 to the jitter window size; when one of the scalar error jitter and the vector error jitter exceeds a set threshold, the size of the jitter window is increased by 1.
Further, the specific implementation method of step S3 is as follows:
s41, using the scalar error, the vector error, the scalar error jitter and the vector error jitter as the track similarity measurement basis, and adjusting the influence factors of the scalar error and the vector error on the track similarity by using the values of the scalar error jitter and the vector error jitter; the specific calculation method comprises the following steps: respectively normalizing the scalar error, the vector error, the scalar error jitter and the vector error jitter by using a Gaussian kernel function to obtain:
Figure BDA0002948633970000021
wherein a, d, q, z are respectively scalar error, vector error, scalar error jitter and vector error jitter after normalization, and A, D, Q, Z is respectively scalar error, vector error, scalar error jitter and vector error jitter before normalization; the sigma is a width parameter of the Gaussian kernel function, the radial action range of the function is controlled, and the width parameter can be determined according to application scenes and requirements;
wherein
Figure BDA0002948633970000031
Represents the mean value of the scalar error over time, A1，A2，...，AnRepresents the scalar error in the 1 st, 2 nd, … th step time;
Figure BDA0002948633970000032
representing the mean value of the vector errors over time, D1，D2，...，DnRepresents the vector error in the 1 st, 2 nd, … th step time;
s42, calculating the track similarity theta:
θ＝αa+βd
α + β is 1, α ≧ 0 and β ≧ 0.
The invention has the beneficial effects that: according to the method, the calculation efficiency of the track similarity of the predicted track and the real track of the vehicle can be improved by calculating the scalar error and vector error values of the predicted and real tracks and dynamically adjusting the influence degree of the scalar error and the vector error on the similarity according to the scalar error jitter and the vector error jitter values, the updating of a vehicle track prediction model can be efficiently assisted, and the driving safety of the vehicle is enhanced.
Drawings
FIG. 1 is a flow chart of a vehicle trajectory similarity assessment method of the present invention;
FIG. 2 is a schematic diagram of the actual trajectory and predicted trajectory of the present invention;
FIG. 3 is a schematic diagram of the error between the real track and the predicted track according to the present invention;
FIG. 4 is a diagram of error dithering according to the present invention.
Detailed Description
The technical scheme of the invention is further explained by combining the attached drawings.
As shown in fig. 1, the method for estimating vehicle trajectory similarity based on error analysis of the present invention includes the following steps:
s1, forming a predicted track and a real track of the vehicle according to the track step length k; the trajectory-based prediction method is a method of predicting the position of the vehicle at a future time (usually 0.1s later) from the historical trajectory at the present time. When a time step k is selected, all the trajectories within the time k can be single-point fitted to form a predicted trajectory. And (4) acquiring the real track similarly, and acquiring the position single point of the vehicle every 0.1 s. And fitting all the track single points acquired in the k time to form a real track. The method for forming the trajectory by fitting the trajectory single points when the time step k is 0.5s is shown in fig. 2, and the predicted and collected trajectory single points are generated every 0.1s, so that the trajectory single points from 0 time to 0.1 time are connected, the trajectory single points from 0.1 time to 0.2 time are connected, and the trajectory from 0.4 time to 0.5 time is connected, thereby forming the trajectory of the X coordinate. After the predicted trajectory and the actual trajectory are obtained, a similarity evaluation process between the two trajectories is performed.
S2, calculating correlation errors between the real track and the predicted track, wherein the correlation errors comprise scalar errors, vector errors, scalar error jitter and vector error jitter;
the trajectory prediction mode is to separately predict the abscissa X and the ordinate Y, and therefore, when the trajectory similarity is considered, the trajectory similarity evaluation is performed on the transverse trajectory and the longitudinal trajectory, respectively. And measuring the track similarity of the automatic driving vehicle to the predicted peripheral vehicles from the transverse direction and the longitudinal direction to finally obtain two track similarity values, so that the accuracy of the track prediction model in the transverse direction and the longitudinal direction is analyzed in more detail. Since the similarity evaluation methods of the transverse trajectory and the longitudinal trajectory are the same, the trajectory similarity evaluation method based on the error analysis will be explained herein by taking the transverse trajectory as an example. According to the relationship between the coordinate axes of the two tracks, the two tracks can be divided into two cases, i.e. no overlap and overlap, which are respectively represented by a diagram a and a diagram b in fig. 2. The definition of these four parameters can be specifically analyzed in conjunction with fig. 3:
the scalar error A refers to the area of a closed graph formed by the two tracks on the coordinate axis in a surrounding mode; in the diagram a, the scalar error a is a1+ a2+ A3+ a4+ a5, where a1, a2, A3, a4, and a5 are the areas formed between two adjacent 0.1s tracks. In fig. B, scalar error a ═ B1+ B2[1] + B2[2] + B3+ B4[1] + B4[2] + B5, where B1, B2(B2 ═ B2[1] + B2[2]), B3, B4(B4 ═ B4[1] + B4[2]), and B5 are areas formed between two adjacent 0.1s tracks.
The vector error D refers to the sum of absolute values of the area variation enclosed by every two adjacent tracks between 0.1s in the step length of the k time; vector errors are a trend in measuring trajectory, and therefore, directionality needs to be added to numerical deviations. When the predicted value is higher than the true value, the directivity is positive; when the predicted value is lower than the true value, the directivity is negative. In fig. a, the vector error D | a2-a1| + | A3-a2| + | a4-A3| + | a5-a4|, where a1, a2, A3, a4, a5 are the areas formed between two adjacent 0.1s tracks. In fig. B, the vector error D | (B2[1] -B2[2]) -B1| + | B3- (B2[1] -B2[2]) | + | (B4[2] -B4[1]) -B3| + | B5- (B4[2] -B4[1]) |, where B1, B2(B2 ═ B2[1] + B2[2]), B3, B4(B4 ═ B4[1] + B4[2]), B5 are the areas formed between two adjacent 0.1s tracks.
Scalar error jitter Q refers to the variance of the scalar error for each k time step over the time of the jitter window size; scalar error dithering needs to be scaled according to the size of the dither windowIf the jitter window is 1 at the initial time, the scalar error jitter in the first k steps is 0. The scalar error dithering after that requires pushing forward the dithering window size by k time steps at the current time instant, calculating the variance of the scalar error in each k step during this time. As shown in fig. 4, when the jitter window size is 3, the scalar error jitter is
Figure BDA0002948633970000041
Wherein A isk1、Ak2、Ak3Respectively represents k1Scalar error, k, in time step2Scalar error sum k within a time step3Scalar error within a time step.
Figure BDA0002948633970000042
Is Ak1、Ak2、Ak3The average of these three scalar errors.
Vector error jitter Z refers to the variance of the vector error for each k time step in time of the size of the jitter window. The vector error jitter also needs to be calculated according to the size of the jitter window, and if the jitter window is 1 at the initial time, the vector error jitter at the first k step is 0. Scalar error dithering later requires advancing the dither window size by k time steps at the current k step size, calculating the variance of the vector error in each k step in this time. As shown in fig. 4, when the jitter window size is 3, the vector error jitter is reduced
Figure BDA0002948633970000051
Wherein Dk1、Dk2、Dk3Respectively represents k1Vector error, k, in time step2Vector error sum k in time step3Vector error in time steps.
Figure BDA0002948633970000052
Is Dk1、Dk2、Dk3The average of these three vector errors.
S3, determining an influence factor and calculating the size of a jitter window(ii) a The specific implementation method comprises the following steps: in the initial state, the default scalar error and the default vector error influence the track similarity to the same extent, namely the scalar error influence factor alpha is 0.5, and the vector error influence factor beta is 0.5; and the system defines the scalar error jitter threshold at the initial moment
Figure BDA0002948633970000053
Sum vector error jitter threshold
Figure BDA0002948633970000054
When the scalar error jitter and the vector error jitter are both smaller than or equal to a set threshold, alpha and beta in the track similarity are 0.5; when both the scalar error and the vector error jitter are greater than a set threshold, the track similarity is 0; when one of the scalar error jitter and the vector error jitter exceeds a set threshold, increasing an influence factor of an error corresponding to the jitter in the track similarity evaluation, and correspondingly reducing an influence factor of the other error in the track similarity evaluation, wherein the increasing and reducing methods can be customized according to application scenarios and requirements, for example, linear increase and decrease are performed, and α + β ═ 1 is satisfied.
Setting the jitter window at the initial moment to be 1, and calculating the variance of the initial k time step length only by error jitter, so that the result is 0; when the scalar error jitter and the vector error jitter are both smaller than or equal to the set threshold, the size of the jitter window is unchanged; when both the scalar error jitter and the vector error jitter are greater than the set threshold, adding 2 to the jitter window size; when one of the scalar error jitter and the vector error jitter exceeds a set threshold, the size of the jitter window is increased by 1.
S4, calculating the similarity; the specific implementation method comprises the following steps:
s41, using the scalar error, the vector error, the scalar error jitter and the vector error jitter as the track similarity measurement basis, and adjusting the influence factors of the scalar error and the vector error on the track similarity by using the values of the scalar error jitter and the vector error jitter; the specific calculation method comprises the following steps: since A, D, Q and Z are both numbers equal to or greater than 0, normalizing scalar error, vector error, scalar error jitter, and vector error jitter, respectively, with a Gaussian kernel function yields:
Figure BDA0002948633970000055
wherein a, d, q, z are respectively scalar error, vector error, scalar error jitter and vector error jitter after normalization, and A, D, Q, Z is respectively scalar error, vector error, scalar error jitter and vector error jitter before normalization; the sigma is a width parameter of the Gaussian kernel function, the radial action range of the function is controlled, and the width parameter can be determined according to application scenes and requirements;
wherein
Figure BDA0002948633970000056
Represents the mean value of the scalar error over time, A1，A2，...，AnRepresents the scalar error in the 1 st, 2 nd, … th step time;
Figure BDA0002948633970000061
representing the mean value of the vector errors over time, D1，D2，...，DnRepresents the vector error in the 1 st, 2 nd, … th step time;
s42, calculating the track similarity theta:
θ＝αa+βd
alpha + beta is 1, alpha is not less than 0 and beta is not less than 0
Since 1 ≧ a ≧ 0,1 ≧ d ≧ 0, and α + β ═ 1, θ is a value ranging between [0,1], it can be used as an evaluation of the trajectory similarity.
It will be appreciated by those of ordinary skill in the art that the embodiments described herein are intended to assist the reader in understanding the principles of the invention and are to be construed as being without limitation to such specifically recited embodiments and examples. Those skilled in the art can make various other specific changes and combinations based on the teachings of the present invention without departing from the spirit of the invention, and these changes and combinations are within the scope of the invention.

Claims (4)

1. A vehicle track similarity evaluation method based on error analysis is characterized by comprising the following steps:
s1, forming a predicted track and a real track of the vehicle according to the track step length k;
s2, calculating correlation errors between the real track and the predicted track, wherein the correlation errors comprise scalar errors, vector errors, scalar error jitter and vector error jitter;
s3, determining an influence factor and calculating the size of a jitter window;
and S4, calculating the similarity.
2. The trajectory similarity evaluation method based on error analysis according to claim 1, wherein the scalar error refers to an area of a closed graph formed by enclosing two trajectories on a coordinate axis;
the vector error refers to the sum of absolute values of the variation of the area enclosed by every two adjacent tracks between 0.1s in the step length of the k time;
scalar error jitter refers to the variance of the scalar error for each k time step over the time of the jitter window size;
vector error jitter refers to the variance of the vector error for each k time step in time, the size of the jitter window.
3. The method for estimating the similarity of the trajectory based on the error analysis as claimed in claim 1, wherein the step S3 is implemented by: in the initial state, the default scalar error and the default vector error influence the track similarity to the same extent, namely the scalar error influence factor alpha is 0.5, and the vector error influence factor beta is 0.5; and the system defines the scalar error jitter threshold at the initial moment
Figure FDA0002948633960000011
Vector of sumMagnitude error jitter threshold
Figure FDA0002948633960000012
When the scalar error jitter and the vector error jitter are both smaller than or equal to a set threshold, alpha and beta in the track similarity are 0.5; when both the scalar error and the vector error jitter are greater than a set threshold, the track similarity is 0; when one of the scalar error jitter and the vector error jitter exceeds a set threshold, increasing an influence factor of an error corresponding to the jitter in the track similarity evaluation, correspondingly reducing an influence factor of the other error in the track similarity evaluation, and meeting the requirement that alpha + beta is 1.
Setting the jitter window at the initial moment to be 1, and calculating the variance of the initial k time step length only by error jitter, so that the result is 0; when the scalar error jitter and the vector error jitter are both smaller than or equal to the set threshold, the size of the jitter window is unchanged; when both the scalar error jitter and the vector error jitter are greater than the set threshold, adding 2 to the jitter window size; when one of the scalar error jitter and the vector error jitter exceeds a set threshold, the size of the jitter window is increased by 1.
4. The method for estimating the similarity of the trajectory based on the error analysis as claimed in claim 3, wherein the step S4 is implemented by:
s41, using the scalar error, the vector error, the scalar error jitter and the vector error jitter as the track similarity measurement basis, and adjusting the influence factors of the scalar error and the vector error on the track similarity by using the values of the scalar error jitter and the vector error jitter; the specific calculation method comprises the following steps: respectively normalizing the scalar error, the vector error, the scalar error jitter and the vector error jitter by using a Gaussian kernel function to obtain:
Figure FDA0002948633960000013
1≥a≥0，1≥d≥0，1≥q≥0，1≥z≥0
wherein a, d, q, z are respectively scalar error, vector error, scalar error jitter and vector error jitter after normalization, and A, D, Q, Z is respectively scalar error, vector error, scalar error jitter and vector error jitter before normalization; wherein, sigma is a width parameter of the Gaussian kernel function, and controls the radial action range of the function;
wherein
Figure FDA0002948633960000021
Figure FDA0002948633960000022
Represents the mean value of the scalar error over time, A1，A2，…，AnRepresents the scalar error in the 1 st, 2 nd, … th step time;
Figure FDA0002948633960000023
Figure FDA0002948633960000024
representing the mean value of the vector errors over time, D1，D2，…，DnRepresents the vector error in the 1 st, 2 nd, … th step time;
s42, calculating the track similarity theta:
θ＝αa+βd
α + β is 1, α ≧ 0 and β ≧ 0.
CN202110200652.XA 2021-02-23 2021-02-23 Vehicle track similarity evaluation method based on error analysis Active CN113158415B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110200652.XA CN113158415B (en) 2021-02-23 2021-02-23 Vehicle track similarity evaluation method based on error analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110200652.XA CN113158415B (en) 2021-02-23 2021-02-23 Vehicle track similarity evaluation method based on error analysis

Publications (2)

Publication Number Publication Date
CN113158415A true CN113158415A (en) 2021-07-23
CN113158415B CN113158415B (en) 2023-09-08

Family

ID=76883342

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110200652.XA Active CN113158415B (en) 2021-02-23 2021-02-23 Vehicle track similarity evaluation method based on error analysis

Country Status (1)

Country Link
CN (1) CN113158415B (en)

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0696234A (en) * 1992-09-09 1994-04-08 Hitachi Ltd Processing system for time sequential data
US20110172874A1 (en) * 2010-01-13 2011-07-14 Gm Global Technology Operations, Inv. Fault prediction framework using temporal data mining
US20140316698A1 (en) * 2013-02-21 2014-10-23 Regents Of The University Of Minnesota Observability-constrained vision-aided inertial navigation
US20150097707A1 (en) * 2013-08-21 2015-04-09 Robert Leonard Nelson, Jr. Non-visual navigation feedback system and method
CN104657746A (en) * 2015-01-29 2015-05-27 电子科技大学 Anomaly detection method based on vehicle trajectory similarity
US20150363865A1 (en) * 2014-06-13 2015-12-17 Truecar, Inc. Systems and methods for vehicle purchase recommendations
CN105512157A (en) * 2014-10-28 2016-04-20 中国民用航空总局第二研究所 Method for integration processing of comprehensive track data
KR20160150212A (en) * 2015-06-19 2016-12-29 (주)연결해 Techniques for matching the movement path of the carpool driver and rider
CN107679558A (en) * 2017-09-19 2018-02-09 电子科技大学 A kind of user trajectory method for measuring similarity based on metric learning
US20190196472A1 (en) * 2016-08-30 2019-06-27 Continental Automotive Gmbh System and method for analyzing driving trajectories for a route section
CN110598311A (en) * 2019-09-06 2019-12-20 广东工业大学 Automatic driving vehicle track tracking method
CN111930791A (en) * 2020-05-28 2020-11-13 中南大学 Similarity calculation method and system for vehicle track and storage medium
CN112015956A (en) * 2020-09-04 2020-12-01 杭州海康威视数字技术股份有限公司 Similarity determination method, device, equipment and storage medium for mobile object
CN112116154A (en) * 2020-09-18 2020-12-22 北京嘀嘀无限科技发展有限公司 Data processing method, data processing apparatus, storage medium, and electronic device

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0696234A (en) * 1992-09-09 1994-04-08 Hitachi Ltd Processing system for time sequential data
US20110172874A1 (en) * 2010-01-13 2011-07-14 Gm Global Technology Operations, Inv. Fault prediction framework using temporal data mining
US20140316698A1 (en) * 2013-02-21 2014-10-23 Regents Of The University Of Minnesota Observability-constrained vision-aided inertial navigation
US20150097707A1 (en) * 2013-08-21 2015-04-09 Robert Leonard Nelson, Jr. Non-visual navigation feedback system and method
US20150363865A1 (en) * 2014-06-13 2015-12-17 Truecar, Inc. Systems and methods for vehicle purchase recommendations
CN105512157A (en) * 2014-10-28 2016-04-20 中国民用航空总局第二研究所 Method for integration processing of comprehensive track data
CN104657746A (en) * 2015-01-29 2015-05-27 电子科技大学 Anomaly detection method based on vehicle trajectory similarity
KR20160150212A (en) * 2015-06-19 2016-12-29 (주)연결해 Techniques for matching the movement path of the carpool driver and rider
US20190196472A1 (en) * 2016-08-30 2019-06-27 Continental Automotive Gmbh System and method for analyzing driving trajectories for a route section
CN107679558A (en) * 2017-09-19 2018-02-09 电子科技大学 A kind of user trajectory method for measuring similarity based on metric learning
CN110598311A (en) * 2019-09-06 2019-12-20 广东工业大学 Automatic driving vehicle track tracking method
CN111930791A (en) * 2020-05-28 2020-11-13 中南大学 Similarity calculation method and system for vehicle track and storage medium
CN112015956A (en) * 2020-09-04 2020-12-01 杭州海康威视数字技术股份有限公司 Similarity determination method, device, equipment and storage medium for mobile object
CN112116154A (en) * 2020-09-18 2020-12-22 北京嘀嘀无限科技发展有限公司 Data processing method, data processing apparatus, storage medium, and electronic device

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
张林: "动态车辆导航系统车道级路径引导方法研究", 中国博士学位论文全文数据库 工程科技II辑, pages 1 - 167 *

Also Published As

Publication number Publication date
CN113158415B (en) 2023-09-08

Similar Documents

Publication Publication Date Title
CN107958269B (en) Driving risk degree prediction method based on hidden Markov model
CN110610271B (en) Multi-vehicle track prediction method based on long and short memory network
Liu et al. Parking like a human: A direct trajectory planning solution
CN109885883B (en) Unmanned vehicle transverse motion control method based on GK clustering algorithm model prediction
Min et al. RNN-based path prediction of obstacle vehicles with deep ensemble
CN107610464A (en) A kind of trajectory predictions method based on Gaussian Mixture time series models
CN109186610B (en) Robust BSLAM method for AUV terrain matching navigation
CN112906858A (en) Real-time prediction method for ship motion trail
CN110539752A (en) Intelligent automobile multi-prediction-range model prediction trajectory tracking control method and system
CN113859266B (en) Method and system for predicting lane change track of unstructured road target vehicle
US11300663B2 (en) Method for predicting a motion of an object
CN111694913B (en) Ship AIS track clustering method and device based on convolution self-encoder
CN116215569B (en) Automatic driving automobile planning method and system based on driving risk assessment
CN108460481B (en) Unmanned aerial vehicle reconnaissance target evolution rule prediction method based on recurrent neural network
CN109878530B (en) Method and system for identifying lateral driving condition of vehicle
Liu et al. Early recognition of driving intention for lane change based on recurrent hidden semi-Markov model
CN115683145A (en) Automatic driving safety obstacle avoidance method based on track prediction
CN112052802A (en) Front vehicle behavior identification method based on machine vision
CN115158364A (en) Method for joint prediction of driving intention and track of surrounding vehicle by automatic driving vehicle
CN115547040A (en) Driving behavior prediction method based on inner neural network under safety potential field
CN113158415B (en) Vehicle track similarity evaluation method based on error analysis
CN112163521A (en) Vehicle driving behavior identification method, device and equipment
CN111160089A (en) Trajectory prediction system and method based on different vehicle types
US11782815B2 (en) Tool for offline perception component evaluation
Emamifar et al. Modeling and state estimation of autonomous vehicles in signalized intersections

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