CN114495489B - Intersection lane topology connection relation generation method - Google Patents
Intersection lane topology connection relation generation method Download PDFInfo
- Publication number
- CN114495489B CN114495489B CN202111662498.4A CN202111662498A CN114495489B CN 114495489 B CN114495489 B CN 114495489B CN 202111662498 A CN202111662498 A CN 202111662498A CN 114495489 B CN114495489 B CN 114495489B
- Authority
- CN
- China
- Prior art keywords
- lane
- road section
- intersection
- calculating
- list
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
- G01C21/32—Structuring or formatting of map data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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 road junction lane topological connection relation generation method, which relates to the technical field of road traffic, and is characterized in that all topological connections and occurrence probabilities thereof are automatically obtained by collecting vehicle track data and carrying out data statistical analysis, the topological connection with higher occurrence probability can be selected as a basis for generating lane connection lines on a map, the driving habit of a human driver is fully considered, the road junction topology generation method is more reasonable than the method of mechanically using a simple fixed rule, the intention and the route of the current vehicle can be easily predicted by other traffic participants, the safe driving is facilitated, the traffic accidents are reduced, and the road junction passing efficiency is improved.
Description
Technical Field
The invention relates to the technical field of road traffic, in particular to a method for generating a road junction lane topological connection relationship.
Background
The high-precision map is a necessary link of the current unmanned technology, lane data is core content of the high-precision map, and a vehicle usually needs to automatically run along a series of coordinate points given by lane central line data of the high-precision map as a preset track, so that the lane central line needs to be smooth in curvature and the topological relation needs to be reasonable. In addition, at the intersection, since no clear ground mark is used for determining the topological relation, manual judgment is usually needed, the lane topological relation is added and generated, the manual generation efficiency is very low due to the fact that the intersection topological relation is complex, the judgment rules are fuzzy, the judgment methods of different people are inconsistent, data quality is easy to be inconsistent, and if the fixed rules are uniformly set, the data quality can be ensured to be consistent, but a plurality of topological relations are unreasonable, and the vehicle is unfavorable for safely, stably and efficiently running when the vehicle runs actually. In order to make the vehicle run more stably and safely at the intersection, the center line of the lane should not only meet the requirements of traffic regulations and curvature continuity, but also meet the driving habit of human beings as much as possible, thus being convenient for other traffic participants to predict the intention and route of the current vehicle better, reducing unnecessary traffic accidents and improving the passing efficiency.
At present, the intersection topological relation is mainly marked by ground arrows, and then a plurality of simple topological connection rules are designed to automatically calculate or manually add the intersection topological relation one by one. The partial technology is used for clustering the vehicle track information, but is mainly used for generating common lanes, is not used for generating the topology relation inside the intersection, and is only used for generating the connection relation of lanes inside the intersection where the track is located. The road topology relationship is determined by the ground arrow mark, and the disadvantage is that many small road ports or special road ports have no ground arrow mark or lack part of ground arrow mark, so that the road topology cannot be determined. The road junction lane topology is generated by manually setting some fixed rules, some lane topologies are unreasonable, and the probability of occurrence in actual driving is relatively low, so that after lane connecting lines are generated, when vehicles run along the connecting lines, other traffic participants are difficult to predict the intention of the current vehicle, and traffic accidents are easy to cause.
Disclosure of Invention
Aiming at the technical problems and overcoming the defects of the prior art, the invention provides a method for generating the topological connection relation of the road junction lane, which comprises the following steps:
1. intersection lane shape parametrization
For each intersection, determining whether a lane enters or leaves the intersection according to the lane direction, dividing the lane into an outgoing lane and an incoming lane, forming a road section by lanes which are adjacent left and right and are arranged side by side in the same lane direction, and dividing the road section into an outgoing road section and an incoming road section;
when a lane topological relation is generated for each intersection, sequentially calculating the topological relation from each outgoing road section to all incoming road sections, determining whether topological connection should be generated between each lane, and determining all topological connections in the whole intersection after the calculation of all outgoing road sections is completed;
2. calculating the relationship between an individual outgoing road segment and an incoming road segment
For a certain outgoing road section, starting from the outgoing road section, sequentially finding all incoming road sections along the anticlockwise direction or the clockwise direction in the intersection to obtain a list, and setting the list as an incoming road section list;
normalizing parameters for the known outgoing road section and the incoming road section list;
sequentially calculating the lane topology connection between all the outgoing road sections in the intersection and the corresponding incoming road section list to obtain all the lane topology connection of the whole intersection;
3. collecting intersection vehicle track information, converting the intersection vehicle track information into lane topology connection information, counting the occurrence times of each lane topology connection, and calculating the probability of each lane topology connection
For a certain intersection, collecting vehicle track information, after obtaining the vehicle track information, calculating the point of each track entering the intersection and the point of each track leaving the intersection, and respectively calculating which lane the 2 points belong to according to coordinates, so as to obtain lane topological connection corresponding to the current track;
counting the occurrence times of each lane topological connection after a large number of track collection is carried out on the same intersection, calculating the occurrence times of all lane topological connections of the same driving-out lane as the total number, and calculating the occurrence probability of each lane topological connection, namely dividing the occurrence times of each lane topological connection by the corresponding total number;
4. the method comprises the following steps: performing parameter discretization on the data set, directly inquiring a required result in the data set, and performing result calculation on any unknown intersection after processing and data collection;
the second method is as follows: training a neural network model by using a data set, calculating a required result by using the trained neural network model, and calculating the result of any unknown intersection after processing and data collection.
The technical scheme of the invention is as follows:
the method for generating the road junction lane topological connection relation comprises the following steps of:
taking the end points of lane side lines of all lanes in the current driving-out road section, performing straight line fitting to obtain straight lines, wherein the angle of the straight lines is set to be the direction from left to right of the lanes, the direction of the straight lines is taken as the 0-degree direction, and the included angle between the straight lines and the positive direction of the x-axis is set to be v0 as the transverse angle of the driving-out road section;
calculating the intersection point between the straight line and the extension line of the leftmost lane boundary, and setting the intersection point as P0 (x 0, y 0) as a reference point of the outgoing road section;
calculating the direction angles of all lane side lines at the end point, namely calculating the angle formed between a point before the end point and the end point for each side line, and then averaging all the obtained direction angles to be used as the longitudinal angle h0 of the outgoing road section;
calculating a lane direction list, and setting a lane direction value: the method comprises the steps that 0 is used for indicating no direction, 1 is used for indicating straight running, 2 is used for indicating left turning, 4 is used for indicating right turning, 8 is used for indicating turning around, a composite value can be calculated for a plurality of directions, a lane direction value is set for each lane according to ground marking and road marking conditions, and then a lane direction list { t0, t1, t2, } of the whole current driving-out road section is obtained;
calculating a lane type list, and setting a lane type value: 0 is used for representing an unknown type, 1 is used for representing a motor vehicle lane, 2 is used for representing a non-motor vehicle lane, 4 is used for representing a bus lane, a composite value can be set, a lane type value is set for each lane according to actual conditions, and then a lane direction list { c0, c1, c2, } of the whole current driving-out road section is obtained;
a lane width list is calculated, a lane width value at the end point of each lane is calculated as w in meters, and then a lane width list { w0, w1, w2, & gt of the current whole outgoing road section is obtained.
The method for generating the road junction lane topological connection relation comprises the following steps of:
the method for calculating the transverse angle v1 of the driving-in road section is similar to the method for calculating v0 in the driving-out road section, except that the starting points of all lanes are taken for straight line fitting to obtain straight lines;
calculating a reference point P1 of the driving-in road section, wherein the method is the same as that of P0 in the driving-out road section;
calculating a longitudinal angle h1 of the entering road section, wherein the method is similar to the h1 calculation method in the entering road section, and the difference is that the angle at the starting point is calculated and then the average value is calculated;
calculating a lane direction list, wherein the lane directions of the entering road sections are uniformly set to 0, namely, no direction exists;
calculating a lane type list, which is the same as the driving-out road section;
the lane width list is calculated similarly to the above-described outgoing link, except that the lane width at the start point is calculated.
The intersection lane topological connection relation generation method comprises the following steps of: for the outgoing road section, P0 is translated to the origin of coordinates (0, 0), v0 is rotated to 0 degrees, the same rotation is performed for h0, then the same translation is performed for all reference points in the incoming road section list, the same rotation is performed for all transverse angles and longitudinal angles, and the range of all angles is set to 0 to 360 degrees, or-180 degrees to 180 degrees.
The method for generating the road junction lane topological connection relation comprises the following steps of: and (2) calculating the intersection point between the track and the transverse straight line obtained by fitting in the step (1), simultaneously calculating the intersection point between all lane side lines and the transverse straight line, and then calculating the relation between the intersection point of the track and the intersection point of the lane side lines, and calculating which lane the intersection point belongs to between which two lane side line intersection points.
The aforementioned intersection lane topological connection relation generation method includes two methods for collecting vehicle track information: (1) the vehicle is provided with a positioning device, and various sensors including a satellite positioning receiver, a gyroscope, an accelerometer, a wheel speed meter, a camera and a laser radar are used for helping to position the vehicle, so as to obtain the track information of the vehicle, the tracks of different vehicles are collected together, then the coordinate range of the current intersection is known, and the track of which section is in the current intersection is calculated, so as to obtain the track information of the vehicle corresponding to each intersection; (2) the method comprises the steps that movement measurement is carried out through a sensor arranged on a vehicle, or fixed measurement is carried out through a sensor arranged on a roadside unit, the sensor comprises a camera, a laser radar and a millimeter wave radar, track information of other vehicles on a road is calculated and collected together, and then vehicle track information corresponding to each intersection is calculated.
The method for generating the road junction lane topological connection relation comprises the following steps: performing parameter discretization on the data set, directly inquiring a required result in the data set, and performing result calculation on any unknown intersection after processing and data collection:
discretizing the intersection lane form parameterization result;
for an intersection data set formed by collecting data of a large number of different roads, constructing all (an outgoing road section and an incoming road section list) by using corresponding discretization parameters, then counting the total number of occurrence of all lane topology connections corresponding to the same (the outgoing road section and the incoming road section list), and calculating the total probability of occurrence of each lane topology connection;
setting a probability threshold T, deleting the lane topological connection when the probability value of the lane topological connection in the data set is smaller than T, and updating the data set to obtain a new correspondence table between discretized input parameters (a driving-out road section, a driving-in road section list) and output parameters;
calculating each unknown intersection (an outgoing road section and an incoming road section list) in the same way, discretizing the same parameters of the intersection, then removing the data set to match the output parameters corresponding to the completely same input parameters, directly obtaining a lane topological relation list, and directly automatically generating lane connecting lines in the intersection according to the obtained lane topological relation when a map is manufactured; when the input parameters are matched, if the input parameters which are not completely the same in the data set are not matched, the output parameters corresponding to the data with the smallest distance value of the current input parameters in the data set can be calculated as a result through the input parameter distance value calculation module;
the input parameter distance value calculation module calculates the distance d between two (an outgoing road section, an incoming road section list) and (an outgoing road section 1, an incoming road section list 1) and (an outgoing road section 2, an incoming road section list 2), sets a fixed rule, compares the difference between the outgoing road section 1 and the outgoing road section 2 with the difference between the incoming road section list 1 and the incoming road section list 2 respectively, quantifies the difference, and adds the two values together to obtain a distance value;
the second method is as follows: training a neural network model by using a data set, calculating a required result by using the trained neural network model, and calculating the result of any unknown intersection after processing and data collection:
according to the obtained (outgoing road section, incoming road section list) as input parameters, a corresponding lane topological relation list { lane topological connection 1, lane topological connection 2, lane topological connection 3, & gt.} and probability values { p1, p2, p3, & gt.} are used as output parameters, a training data set is constructed, a neural network model is used, the neural network model is trained by the data set, and a trained neural network model is obtained;
the same parameterization calculation is carried out on any unknown intersection to obtain input parameters (an outgoing road section and an incoming road section list), the input parameters are input into a neural network model, and output values can be obtained from the model, wherein the lane topological relation list { lane topological connection 1, lane topological connection 2, lane topological connection 3, & gt and probability values { p1, p2, p3, >
setting a probability threshold T, deleting the lane topological connection when the probability value of the lane topological connection in the output result is smaller than T, and then directly and automatically generating the lane connecting lines in the intersection according to the obtained lane topological relation when the map is manufactured, wherein the rest result is a final lane topological relation list.
The aforementioned intersection lane topological connection relation generation method comprises the following steps: for the parameters in each (outgoing road section, incoming road section list), all the lateral angle V, longitudinal angle H, reference point P (X, Y), lane width W in the parameters are discretized, the 4 parameters are set with unified discretization step steps step_v, step_h, step_xy, step_w respectively, and then 5 integer values are obtained respectively, namely, discretization lateral angle v=rounding (V/step_v), discretization longitudinal angle h=rounding (H/step_h), discretization reference point coordinate x=rounding (X/step_xy), y=rounding (Y/step_xy), discretization lane width w=rounding (W/step_w).
The fixed rule in the first method is to compare the number of the road segments in the entering road segment list 1 with the number of the road segments in the entering road segment list 2, and if the number is equal, the road segments are in one-to-one correspondence, then the comparison between the two road segments is performed pair by pair, the difference is calculated, and the quantization is performed.
According to the intersection lane topological connection relation generation method, when certain lane width values in an outgoing road section or an incoming road section are overlarge, a certain rule is set manually to divide lanes; or clustering is carried out through the collected current position history track information, whether the current lane is segmented or not is judged, and the segmentation proportion is determined.
In the aforementioned method for generating the road junction lane topological connection relation, for some small intersections or small intersections, no obvious marking or identification is used for determining the direction of the current road section, at this time, the current road section is judged by calling the vehicle history track information at the current position, if the current position has no vehicle history track information, the judgment cannot be performed, and the current road section can be considered to be bidirectional.
The beneficial effects of the invention are as follows:
(1) According to the invention, through collecting vehicle track data and carrying out data statistical analysis, all topological connections and the occurrence probability thereof are automatically obtained, the topological connection with higher occurrence probability can be selected as the basis for generating the lane connecting line on the map, the driving habit of a human driver is fully considered, the method is more reasonable than the method of mechanically using a simple fixed rule to generate the lane topology, other traffic participants can easily predict the intention and the route of the current vehicle, the safe driving is facilitated, the traffic accidents are reduced, and the traffic efficiency of the crossing is improved;
(2) According to the invention, through collecting vehicle track data and constructing an intersection data set after a series of processing, not only can the topological relation of the intersection where the track is located be generated, but also the topological relation of the unknown intersection can be generated, the intersection lane connection relation can be automatically constructed, the map lane connection line data manufacturing efficiency at the intersection is greatly improved, and the manufactured intersection lane is more reasonable;
(3) According to the method, all topological relations and occurrence probabilities of the unknown intersections can be obtained, when other vehicles appear near the intersections, the future tracks of the unknown intersections can be predicted by using the results obtained by the method, so that a plurality of possible tracks and probabilities of the unknown intersections are obtained, the intention of the own vehicle on the other vehicles can be automatically prejudged in advance, the smooth running of the own vehicle at the intersections is facilitated, and the running efficiency and the running safety of the own vehicle can be effectively improved.
Drawings
FIG. 1 is a graph of calculating the relationship between a single outgoing road segment and all incoming road segments;
FIG. 2 is a parameterization of the outgoing road segment;
FIG. 3 is a parameterization of an entry road segment;
fig. 4 shows two topology relation generation methods after parameterizing the road junction lane morphology.
Detailed Description
The method for generating the road junction lane topological connection relation provided by the embodiment comprises the following steps:
1. intersection lane shape parametrization
For each intersection, determining whether a lane enters or leaves the intersection according to the lane direction, dividing the lane into an outgoing lane and an incoming lane, forming a road section by lanes which are adjacent left and right and are arranged side by side in the same lane direction, and dividing the road section into an outgoing road section and an incoming road section;
when a lane topological relation is generated for each intersection, the topological relation between each outgoing road section and all incoming road sections is calculated in sequence, whether topological connection should be generated between each lane is determined, and after the calculation of all outgoing road sections is completed, all topological connections in the whole intersection are determined.
The method for parameterizing the driving-out road section comprises the following steps:
taking the end points of lane edges of all lanes in the current driving-out road section, and performing straight line fitting (a straight line fitting algorithm can use a least square method and other fitting algorithms), wherein the angle of the obtained straight line is set to be the left-to-right direction of the lane, the direction of the straight line is taken as the 0-degree direction, and the included angle between the straight line and the positive direction of the x-axis is set to be v0 as the transverse angle of the driving-out road section;
calculating the intersection point between the straight line and the extension line of the leftmost lane boundary, and setting the intersection point as P0 (x 0, y 0) as a reference point of the outgoing road section;
calculating the direction angles of all lane side lines at the end point, namely calculating the angle formed between a point before the end point and the end point for each side line, and then averaging all the obtained direction angles to be used as the longitudinal angle h0 of the outgoing road section;
calculating a lane direction list, and setting a lane direction value: a direction is not shown by 0, a straight running is shown by 1, a left turning is shown by 2, a right turning is shown by 4, a turning around is shown by 8, a composite value can be calculated for a plurality of directions, for example, 10 indicates that the lane can turn left and turn around, for example, 11 indicates that the lane can be straight, turn left and turn around, a lane direction value is set for each lane according to ground marking and road marking conditions, and then a lane direction list { t0, t1, t2, } of the current whole driving-out road section is obtained, taking fig. 2 as an example, and {10,1,4};
calculating a lane type list, and setting a lane type value: with 0 representing an unknown type, 1 representing a motor vehicle lane, 2 representing a non-motor vehicle lane, 4 representing a bus lane (any other type may be added later, with the n-th power of 2 as a value), a composite value may be set, for example, 3 representing a common lane of motor vehicles and non-motor vehicles. Setting a lane type value for each lane according to actual conditions, and then obtaining a lane direction list { c0, c1, c2, & gt} of the current whole driving-out road section, wherein {1, 1} is taken as an example in fig. 2;
a lane width list is calculated, a lane width value at the end point of each lane is calculated as w in meters, and then a lane width list { w0, w1, w2, & gt}, which is {3.30,3.40,3.30} of the current entire outgoing road section, is obtained, taking fig. 2 as an example.
The method for parameterizing the driving-in road section comprises the following steps:
the method for calculating the transverse angle v1 of the driving-in road section is similar to the method for calculating v0 in the driving-out road section, except that the starting points of all lanes are taken for straight line fitting to obtain straight lines;
calculating a reference point P1 of the driving-in road section, wherein the method is the same as that of P0 in the driving-out road section;
calculating a longitudinal angle h1 of the entering road section, wherein the method is similar to the h1 calculation method in the entering road section, and the difference is that the angle at the starting point is calculated and then the average value is calculated;
calculating a lane direction list, wherein the lane directions of the entering road sections are uniformly set to be 0, namely, no direction exists, and the directions are {0, 0}, taking fig. 3 as an example;
calculating a lane type list, which is the same as the driving-out road section;
the lane width list is calculated similarly to the above-described outgoing link, except that the lane width at the start point is calculated.
2. Calculating the relationship between an individual outgoing road segment and an incoming road segment
For a certain outgoing road section, starting from the outgoing road section, sequentially finding all incoming road sections along the anticlockwise direction or the clockwise direction in the intersection to obtain a list, and setting the list as an incoming road section list;
for the known outgoing road section and the incoming road section list, carrying out normalization processing on parameters, wherein the normalization processing method is that P0 is translated to an origin of coordinates (0, 0), v0 is rotated to 0 degrees, h0 is similarly rotated, then all reference points in the incoming road section list are similarly translated, all transverse angles and longitudinal angles are similarly rotated, and all angles are set to 0 to 360 degrees or-180 to 180 degrees;
sequentially calculating the lane topology connection between all the outgoing road sections in the intersection and the corresponding incoming road section list to obtain all the lane topology connection of the whole intersection; assuming that the lane topology connection calculation result of the single outgoing road section and the incoming road section list is a lane topology connection list { lane topology connection 0, lane topology connection 1, lane topology connection 2,...;
3. collecting intersection vehicle track information, converting the intersection vehicle track information into lane topology connection information, counting the occurrence times of each lane topology connection, and calculating the probability of each lane topology connection
For a certain intersection, two methods exist for collecting vehicle track information; (1) the vehicle is provided with a positioning device, and various sensors including a satellite positioning receiver, a gyroscope, an accelerometer, a wheel speed meter, a camera and a laser radar are used for helping to position the vehicle to obtain the track information of the vehicle, the tracks of different vehicles are collected together, then the coordinate range of the current intersection is known, and the track of which segments is in the current intersection is calculated to obtain the track information of the vehicle corresponding to each intersection; (2) the method comprises the steps that movement measurement is carried out through a sensor arranged on a vehicle or fixed measurement is carried out through a sensor arranged on a roadside unit, the sensor comprises a camera, a laser radar and a millimeter wave radar, track information of other vehicles on a road is calculated and collected together, and then vehicle track information corresponding to each intersection is calculated;
after the track information of the vehicle is obtained, calculating the point of entering the intersection and the point of leaving the intersection of each track, and respectively calculating which lane the 2 points belong to according to coordinates, so as to obtain the lane topology connection corresponding to the current track; the method for calculating the intersection point of the entering intersection point and the intersection point of the exiting intersection point comprises the steps of calculating an intersection point between a track and the transverse straight line obtained by fitting in the step 1, calculating intersection points between all lane side lines and the transverse straight line, calculating a relation between the intersection point of the track and the intersection point of the lane side lines, and calculating the intersection point of the two lane side lines, namely which lane the intersection point belongs to;
counting the occurrence times of each lane topological connection after a large number of track collection is carried out on the same intersection, calculating the occurrence times of all lane topological connections of the same driving-out lane as the total number, and calculating the occurrence probability of each lane topological connection, namely dividing the occurrence times of each lane topological connection by the corresponding total number;
4. the method comprises the following steps: performing parameter discretization on the data set, directly inquiring a required result in the data set, and performing result calculation on any unknown intersection after processing and data collection:
discretizing the intersection lane form parameterization result, wherein the discretization method comprises the following steps: for the parameters in each (outgoing road section, incoming road section list), all the lateral angles V, longitudinal angles H, reference points P (X, Y), lane widths W in the parameters are discretized, unified discretization step steps step_v, step_h, step_xy, step_w are respectively set for the 4 parameters, then 5 integer values are respectively obtained, namely, discretization lateral angles v=rounding (V/step_v), discretization longitudinal angles h=rounding (H/step_h), discretization reference point coordinates x=rounding (X/step_xy), y=rounding (Y/step_xy), and discretization lane widths w=rounding (W/step_w);
for an intersection data set formed by collecting data of a large number of different roads, constructing all (an outgoing road section and an incoming road section list) by using corresponding discretization parameters, then counting the total number of occurrence of all lane topology connections corresponding to the same (the outgoing road section and the incoming road section list), and calculating the total probability of occurrence of each lane topology connection;
setting a probability threshold T, for example, t=0.05, that is, 5%, deleting the lane topology connection in the dataset, wherein the probability value of the lane topology connection in the dataset is smaller than T, and then updating the dataset to obtain a corresponding relation table between new discretized input parameters (outgoing road section, incoming road section list) and output parameters (lane topology relation list);
calculating each unknown intersection (an outgoing road section and an incoming road section list) in the same way, discretizing the same parameters of the intersection, then removing the data set to match the output parameters corresponding to the completely same input parameters, directly obtaining a lane topological relation list, and directly automatically generating lane connecting lines in the intersection according to the obtained lane topological relation when a map is manufactured; when the input parameters are matched, if the input parameters which are not completely the same in the data set are not matched, the output parameters corresponding to the data with the smallest distance value of the current input parameters in the data set can be calculated as a result through the input parameter distance value calculation module;
the input parameter distance value calculation module calculates the distance d between two (an outgoing road section, an incoming road section list), and supposes (an outgoing road section 1, an incoming road section list 1) and (an outgoing road section 2, an incoming road section list 2), a fixed rule is set, for example, d=1000 if the number of incoming road sections in the outgoing road section list 1 and the incoming road section list 2 is not equal, if the number is equal, the distances between the incoming road section 1 and the incoming road section 2 in the two are compared in a one-to-one pairing manner in sequence, the minimum value is 0, the maximum value is 100 if the number of lanes is not equal, if the number of lanes is equal, the distances between the lanes 1 and the lanes 2 in the two are compared in a one-to-one pairing manner in sequence, the minimum value is 0, the maximum value is 10, the distance calculation is performed on the attribute values in the lanes, the minimum value and the maximum value are set for each attribute value, and then the calculation is performed respectively, so that the total distance d is finally obtained; the distance between the outgoing road section 1 and the outgoing road section 2 is calculated in the same way as the distance between two incoming road sections.
(2) The second method is as follows: training a neural network model by using a data set, calculating a required result by using the trained neural network model, and calculating the result of any unknown intersection after processing and data collection:
according to the obtained (outgoing road section, incoming road section list) as input parameters, a corresponding lane topological relation list { lane topological connection 1, lane topological connection 2, lane topological connection 3, & gt.} and probability values { p1, p2, p3, & gt.} are used as output parameters, a training data set is constructed, a neural network model is used, the neural network model is trained by the data set, and a trained neural network model is obtained;
the same parameterization calculation is carried out on any unknown intersection to obtain input parameters (an outgoing road section and an incoming road section list), the input parameters are input into a neural network model, and output values can be obtained from the model, wherein the lane topological relation list { lane topological connection 1, lane topological connection 2, lane topological connection 3, & gt and probability values { p1, p2, p3, >
setting a probability threshold T, for example, t=0.05, that is, 5%, deleting the lane topological connection when the probability value of the lane topological connection in the output result is smaller than T, and then directly and automatically generating the lane connecting lines in the intersection according to the obtained lane topological relation when the map is manufactured, wherein the rest result is a final lane topological relation list.
When the width value of some lanes in the driving-out road section or the driving-in road section is overlarge, manually setting a certain rule to divide the lanes, for example, if the width of the lanes exceeds 6 meters, automatically dividing the lanes into two lanes with the width of 3 meters on average; or clustering is carried out through the collected current position history track information, whether the current lane is segmented or not is judged, and the segmentation proportion is determined.
For some small intersections or small turnouts, such as a garage entrance or a district entrance of a mall, no obvious marking or identification is used for determining the direction of the current road section, at this time, the current road section is judged by calling the historical track information of the vehicle at the current position, if the current position has no historical track information of the vehicle, the current road section can not be judged, and the current road section can be considered to be bidirectional.
The method designs a set of road junction lane form parameterization method, converts a large number of real track information of vehicles at different road junctions into topological relation data, correlates the road junction lane form with the topological relation data, establishes a corresponding relation, and then designs two methods for automatically generating the topological relation for any road junction, wherein one method is to discretize the road junction lane form parameter, then establish a mapping relation table between the road junction form and the topological relation data, parameterize the road junction lane form for any road junction, then inquire the mapping relation table obtained before to obtain the topological relation data, and the other method is to use a neural network model, take the road junction form data as input data, take the corresponding topological relation data as output data, train the neural network model, calculate the road junction lane form parameter for any road junction, input the road junction lane form parameter to the neural network model, and then obtain the output topological relation data.
The method can automatically generate the road junction lane topological relation, has high generation speed and good effect, greatly improves the map lane data production efficiency at the road junction, simultaneously greatly improves the data quality, and the generated map is used for automatically driving the vehicle, has more reasonable route, is beneficial to more accurately prejudging the intention and the route of the self-vehicle and other vehicles when the self-vehicle and other vehicles pass through the road junction, and improves the road junction passing efficiency and stability.
In addition to the embodiments described above, other embodiments of the invention are possible. All technical schemes formed by equivalent substitution or equivalent transformation fall within the protection scope of the invention.
Claims (10)
1. A method for generating a road junction lane topological connection relation is characterized by comprising the following steps of: the method comprises the following steps:
1. intersection lane shape parametrization
For each intersection, determining whether a lane enters or leaves the intersection according to the lane direction, dividing the lane into an outgoing lane and an incoming lane, forming a road section by lanes which are adjacent left and right and are arranged side by side in the same lane direction, and dividing the road section into an outgoing road section and an incoming road section;
when a lane topological relation is generated for each intersection, sequentially calculating the topological relation from each outgoing road section to all incoming road sections, determining whether topological connection should be generated between each lane, and determining all topological connections in the whole intersection after the calculation of all outgoing road sections is completed;
2. calculating the relationship between an individual outgoing road segment and an incoming road segment
For a certain outgoing road section, starting from the outgoing road section, sequentially finding all incoming road sections along the anticlockwise direction or the clockwise direction in the intersection to obtain a list, and setting the list as an incoming road section list;
normalizing parameters for the known outgoing road section and the incoming road section list;
sequentially calculating the lane topology connection between all the outgoing road sections in the intersection and the corresponding incoming road section list to obtain all the lane topology connection of the whole intersection;
3. collecting intersection vehicle track information, converting the intersection vehicle track information into lane topology connection information, counting the occurrence times of each lane topology connection, and calculating the probability of each lane topology connection
For a certain intersection, collecting vehicle track information, after obtaining the vehicle track information, calculating the point of each track entering the intersection and the point of each track leaving the intersection, and respectively calculating which lane the 2 points belong to according to coordinates, so as to obtain lane topological connection corresponding to the current track;
counting the occurrence times of each lane topological connection after a large number of track collection is carried out on the same intersection, calculating the occurrence times of all lane topological connections of the same driving-out lane as the total number, and calculating the occurrence probability of each lane topological connection, namely dividing the occurrence times of each lane topological connection by the corresponding total number;
4. the method comprises the following steps: performing parameter discretization on the data set, directly inquiring a required result in the data set, and performing result calculation on any unknown intersection after processing and data collection;
the second method is as follows: training a neural network model by using a data set, calculating a required result by using the trained neural network model, and calculating the result of any unknown intersection after processing and data collection.
2. The intersection lane topology connection relation generation method according to claim 1, wherein: the method for parameterizing the driving-out road section comprises the following steps:
taking the end points of lane side lines of all lanes in the current driving-out road section, performing straight line fitting to obtain straight lines, wherein the angle of the straight lines is set to be the direction from left to right of the lanes, the direction of the straight lines is taken as the 0-degree direction, and the included angle between the straight lines and the positive direction of the x-axis is set to be v0 as the transverse angle of the driving-out road section;
calculating the intersection point between the straight line and the extension line of the leftmost lane boundary, and setting the intersection point as P0 (x 0, y 0) as a reference point of the outgoing road section;
calculating the direction angles of all lane side lines at the end point, namely calculating the angle formed between a point before the end point and the end point for each side line, and then averaging all the obtained direction angles to be used as the longitudinal angle h0 of the outgoing road section;
calculating a lane direction list, and setting a lane direction value: the method comprises the steps that 0 is used for indicating no direction, 1 is used for indicating straight running, 2 is used for indicating left turning, 4 is used for indicating right turning, 8 is used for indicating turning around, a composite value can be calculated for a plurality of directions, a lane direction value is set for each lane according to ground marking and road marking conditions, and then a lane direction list { t0, t1, t2, } of the whole current driving-out road section is obtained;
calculating a lane type list, and setting a lane type value: 0 is used for representing an unknown type, 1 is used for representing a motor vehicle lane, 2 is used for representing a non-motor vehicle lane, 4 is used for representing a bus lane, a composite value can be set, a lane type value is set for each lane according to actual conditions, and then a lane direction list { c0, c1, c2, } of the whole current driving-out road section is obtained;
a lane width list is calculated, a lane width value at the end point of each lane is calculated as w in meters, and then a lane width list { w0, w1, w2, & gt of the current whole outgoing road section is obtained.
3. The intersection lane topology connection relation generation method according to claim 2, wherein: the method for parameterizing the driving-in road section comprises the following steps:
the method for calculating the transverse angle v1 of the driving-in road section is similar to the method for calculating v0 in the driving-out road section, except that the starting points of all lanes are taken for straight line fitting to obtain straight lines;
calculating a reference point P1 of the driving-in road section, wherein the method is the same as that of P0 in the driving-out road section;
calculating a longitudinal angle h1 of the entering road section, wherein the method is similar to the h1 calculation method in the entering road section, and the difference is that the angle at the starting point is calculated and then the average value is calculated;
calculating a lane direction list, wherein the lane directions of the entering road sections are uniformly set to 0, namely, no direction exists;
calculating a lane type list, which is the same as the driving-out road section;
the lane width list is calculated similarly to the above-described outgoing link, except that the lane width at the start point is calculated.
4. The intersection lane topology connection relation generation method according to claim 1, wherein: the normalization method is as follows: for the outgoing road section, P0 is translated to the origin of coordinates (0, 0), v0 is rotated to 0 degrees, the same rotation is performed for h0, then the same translation is performed for all reference points in the incoming road section list, the same rotation is performed for all transverse angles and longitudinal angles, and the range of all angles is set to 0 to 360 degrees, or-180 degrees to 180 degrees.
5. The intersection lane topology connection relation generation method according to claim 1, wherein: the calculation method of the entering intersection point and the leaving intersection point comprises the following steps: and (2) calculating the intersection point between the track and the transverse straight line obtained by fitting in the step (1), simultaneously calculating the intersection point between all lane side lines and the transverse straight line, and then calculating the relation between the intersection point of the track and the intersection point of the lane side lines, and calculating which lane the intersection point belongs to between which two lane side line intersection points.
6. The intersection lane topology connection relation generation method according to claim 1, wherein: there are two methods of collecting vehicle track information: (1) the vehicle is provided with a positioning device, and various sensors including a satellite positioning receiver, a gyroscope, an accelerometer, a wheel speed meter, a camera and a laser radar are used for helping to position the vehicle, so as to obtain the track information of the vehicle, the tracks of different vehicles are collected together, then the coordinate range of the current intersection is known, and the track of which section is in the current intersection is calculated, so as to obtain the track information of the vehicle corresponding to each intersection; (2) the method comprises the steps that movement measurement is carried out through a sensor arranged on a vehicle, or fixed measurement is carried out through a sensor arranged on a roadside unit, the sensor comprises a camera, a laser radar and a millimeter wave radar, track information of other vehicles on a road is calculated and collected together, and then vehicle track information corresponding to each intersection is calculated.
7. The intersection lane topology connection relation generation method according to claim 1, wherein:
the method comprises the following steps: performing parameter discretization on the data set, directly inquiring a required result in the data set, and performing result calculation on any unknown intersection after processing and data collection:
discretizing the intersection lane form parameterization result;
for an intersection data set formed by collecting data of a large number of different roads, constructing all (an outgoing road section and an incoming road section list) by using corresponding discretization parameters, then counting the total number of occurrence of all lane topology connections corresponding to the same (the outgoing road section and the incoming road section list), and calculating the total probability of occurrence of each lane topology connection;
setting a probability threshold T, deleting the lane topological connection when the probability value of the lane topological connection in the data set is smaller than T, and updating the data set to obtain a new correspondence table between discretized input parameters (a driving-out road section, a driving-in road section list) and output parameters;
calculating each unknown intersection (an outgoing road section and an incoming road section list) in the same way, discretizing the same parameters of the intersection, then removing the data set to match the output parameters corresponding to the completely same input parameters, directly obtaining a lane topological relation list, and directly automatically generating lane connecting lines in the intersection according to the obtained lane topological relation when a map is manufactured; when the input parameters are matched, if the input parameters which are not completely the same in the data set are not matched, the output parameters corresponding to the data with the smallest distance value of the current input parameters in the data set can be calculated as a result through the input parameter distance value calculation module;
the input parameter distance value calculation module calculates the distance d between two (an outgoing road section, an incoming road section list) and (an outgoing road section 1, an incoming road section list 1) and (an outgoing road section 2, an incoming road section list 2), sets a fixed rule, compares the difference between the outgoing road section 1 and the outgoing road section 2 with the difference between the incoming road section list 1 and the incoming road section list 2 respectively, quantifies the difference, and adds the two values together to obtain a distance value;
the second method is as follows: training a neural network model by using a data set, calculating a required result by using the trained neural network model, and calculating the result of any unknown intersection after processing and data collection:
according to the obtained (outgoing road section, incoming road section list) as input parameters, a corresponding lane topological relation list { lane topological connection 1, lane topological connection 2, lane topological connection 3, & gt.} and probability values { p1, p2, p3, & gt.} are used as output parameters, a training data set is constructed, a neural network model is used, the neural network model is trained by the data set, and a trained neural network model is obtained;
the same parameterization calculation is carried out on any unknown intersection to obtain input parameters (an outgoing road section and an incoming road section list), the input parameters are input into a neural network model, and output values can be obtained from the model, wherein the lane topological relation list { lane topological connection 1, lane topological connection 2, lane topological connection 3, & gt and probability values { p1, p2, p3, >
setting a probability threshold T, deleting the lane topological connection when the probability value of the lane topological connection in the output result is smaller than T, and then directly and automatically generating the lane connecting lines in the intersection according to the obtained lane topological relation when the map is manufactured, wherein the rest result is a final lane topological relation list.
8. The intersection lane topology connection relation generation method of claim 7, wherein: the discretization method comprises the following steps: for the parameters in each (outgoing road section, incoming road section list), all the lateral angle V, longitudinal angle H, reference point P (X, Y), lane width W in the parameters are discretized, the 4 parameters are set with unified discretization step steps step_v, step_h, step_xy, step_w respectively, and then 5 integer values are obtained respectively, namely, discretization lateral angle v=rounding (V/step_v), discretization longitudinal angle h=rounding (H/step_h), discretization reference point coordinate x=rounding (X/step_xy), y=rounding (Y/step_xy), discretization lane width w=rounding (W/step_w).
9. The intersection lane topology connection relation generation method according to claim 1, wherein: manually setting a certain rule to divide lanes when certain lane width values in the driving-out road section or the driving-in road section are overlarge; or clustering is carried out through the collected current position history track information, whether the current lane is segmented or not is judged, and the segmentation proportion is determined.
10. The intersection lane topology connection relation generation method according to claim 1, wherein: for some small intersections or small intersections, no obvious marking or identification is used for determining the direction of the current road section, at this time, the current road section can be considered to be bidirectional by calling the historical track information of the vehicle at the current position to judge, and if the current position does not have the historical track information of the vehicle, the current road section can not be judged.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111662498.4A CN114495489B (en) | 2021-12-30 | 2021-12-30 | Intersection lane topology connection relation generation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111662498.4A CN114495489B (en) | 2021-12-30 | 2021-12-30 | Intersection lane topology connection relation generation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114495489A CN114495489A (en) | 2022-05-13 |
| CN114495489B true CN114495489B (en) | 2023-07-25 |
Family
ID=81497123
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111662498.4A Active CN114495489B (en) | 2021-12-30 | 2021-12-30 | Intersection lane topology connection relation generation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114495489B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115331425B (en) * | 2022-06-30 | 2023-12-19 | 银江技术股份有限公司 | Traffic early warning method, device and system |
| CN115061479B (en) * | 2022-08-03 | 2022-11-04 | 国汽智控(北京)科技有限公司 | Lane relation determination method and device, electronic equipment and storage medium |
| CN117576950B (en) * | 2024-01-16 | 2024-04-09 | 长沙行深智能科技有限公司 | Method and device for predicting vehicle to select crossing entrance and crossing exit |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105651295A (en) * | 2016-01-15 | 2016-06-08 | 武汉光庭信息技术股份有限公司 | Connection curve algorithm for constructing intersection entry and exit lane Links based on Bezier curve |
| DE102015211150A1 (en) * | 2015-06-17 | 2016-12-22 | Bayerische Motoren Werke Aktiengesellschaft | Method, driver assistance system and vehicle for learning a trajectory of a road section |
| CN109186617A (en) * | 2018-08-13 | 2019-01-11 | 武汉中海庭数据技术有限公司 | A kind of view-based access control model crowdsourcing data automatically generate method, system and the memory of lane grade topological relation |
| CN111065893A (en) * | 2017-06-01 | 2020-04-24 | 罗伯特·博世有限公司 | Method and device for creating a lane-accurate road map |
| CN111142525A (en) * | 2019-12-31 | 2020-05-12 | 武汉中海庭数据技术有限公司 | High-precision map lane topology construction method and system, server and medium |
| CN112580179A (en) * | 2020-12-29 | 2021-03-30 | 武汉中海庭数据技术有限公司 | High-precision map intersection lane shape updating method and system, server and medium |
| CN112699708A (en) * | 2019-10-22 | 2021-04-23 | 北京初速度科技有限公司 | Method and device for generating lane-level topology network |
| CN113074744A (en) * | 2021-03-18 | 2021-07-06 | 重庆数字城市科技有限公司 | Method for generating topological connection line of map for intelligent network vehicle connection |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10761535B2 (en) * | 2018-08-21 | 2020-09-01 | GM Global Technology Operations LLC | Intelligent vehicle navigation systems, methods, and control logic for multi-lane separation and trajectory extraction of roadway segments |
| US11738770B2 (en) * | 2019-07-02 | 2023-08-29 | Nvidia Corporation | Determination of lane connectivity at traffic intersections for high definition maps |
| US11754408B2 (en) * | 2019-10-09 | 2023-09-12 | Argo AI, LLC | Methods and systems for topological planning in autonomous driving |
-
2021
- 2021-12-30 CN CN202111662498.4A patent/CN114495489B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102015211150A1 (en) * | 2015-06-17 | 2016-12-22 | Bayerische Motoren Werke Aktiengesellschaft | Method, driver assistance system and vehicle for learning a trajectory of a road section |
| CN105651295A (en) * | 2016-01-15 | 2016-06-08 | 武汉光庭信息技术股份有限公司 | Connection curve algorithm for constructing intersection entry and exit lane Links based on Bezier curve |
| CN111065893A (en) * | 2017-06-01 | 2020-04-24 | 罗伯特·博世有限公司 | Method and device for creating a lane-accurate road map |
| CN109186617A (en) * | 2018-08-13 | 2019-01-11 | 武汉中海庭数据技术有限公司 | A kind of view-based access control model crowdsourcing data automatically generate method, system and the memory of lane grade topological relation |
| CN112699708A (en) * | 2019-10-22 | 2021-04-23 | 北京初速度科技有限公司 | Method and device for generating lane-level topology network |
| CN111142525A (en) * | 2019-12-31 | 2020-05-12 | 武汉中海庭数据技术有限公司 | High-precision map lane topology construction method and system, server and medium |
| CN112580179A (en) * | 2020-12-29 | 2021-03-30 | 武汉中海庭数据技术有限公司 | High-precision map intersection lane shape updating method and system, server and medium |
| CN113074744A (en) * | 2021-03-18 | 2021-07-06 | 重庆数字城市科技有限公司 | Method for generating topological connection line of map for intelligent network vehicle connection |
Non-Patent Citations (4)
| Title |
|---|
| 一种面向智能驾驶的电子地图模型;许广宏 等;《上海汽车》;第15-18页 * |
| 利用轨迹大数据进行城市道路交叉口识别及结构提取;唐炉亮 等;《测绘学报》;第46卷(第6期);第770-779页 * |
| 智能高精地图数据逻辑结构与关键技术;刘经南 等;《测绘学报》;第48卷(第8期);第939-953页 * |
| 通用化高精地图数据模型;张攀 等;《测绘学报》;第50卷(第11期);第1432-1446页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114495489A (en) | 2022-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114495489B (en) | Intersection lane topology connection relation generation method | |
| CN104819724B (en) | A kind of autonomous travel assist system of Unmanned Ground Vehicle based on GIS | |
| CN109448370B (en) | Traffic control subarea division method based on vehicle track data | |
| CN108267747B (en) | Road feature extraction method and device based on laser point cloud | |
| CN114005280B (en) | Vehicle track prediction method based on uncertainty estimation | |
| CN108955693A (en) | A kind of method and system of road network | |
| CN110008872B (en) | Road network extraction method combining vehicle track and remote sensing image | |
| CN104700617A (en) | High-precision lane information extracting method based on low-precision GPS track data | |
| CN103218240B (en) | A kind of unmade road recognition methods based on Floating Car track | |
| CN107328423B (en) | Curve identification method and system based on map data | |
| CN111210612A (en) | Method for extracting bus route track based on bus GPS data and station information | |
| CN103177585B (en) | Road turning average travel speed calculating method based on floating car data | |
| CN103092949A (en) | Recognition and construction method of compound intersections in probe vehicle track fusion | |
| CN111314857B (en) | Vehicle real-time travel track acquisition method based on vehicle passing video data | |
| CN103092948B (en) | A kind of super expressway shape restorative procedure being applied to Floating Car Trace Formation | |
| CN112530158B (en) | Road network supplementing method based on historical track | |
| CN105096590A (en) | Traffic information generation method and device | |
| CN115435798A (en) | Unmanned vehicle high-precision map road network generation system and method | |
| CN116678394A (en) | Real-time dynamic intelligent path planning method and system based on multi-sensor information fusion | |
| CN112249009A (en) | Vehicle speed control method, device and system and electronic equipment | |
| CN113511204A (en) | Vehicle lane changing behavior identification method and related equipment | |
| CN115112143A (en) | Method for planning running track of accident rescue vehicle | |
| Meng et al. | Trajectory prediction for automated vehicles on roads with lanes partially covered by ice or snow | |
| CN111551185B (en) | Method for adding traffic lane | |
| CN115610435B (en) | Method and device for predicting object driving intention, storage medium and electronic device |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230323 Address after: 1 / F, building 28, 6055 Jinhai highway, Fengxian District, Shanghai 201400 Applicant after: Zhongzhixing (Shanghai) Transportation Technology Co.,Ltd. Applicant after: Tianyi Transportation Technology Co.,Ltd. Address before: 1 / F, building 28, 6055 Jinhai highway, Fengxian District, Shanghai 201400 Applicant before: Zhongzhixing (Shanghai) Transportation Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |