WO2021043505A1 - Verfahren und vorrichtung zur ermittlung einer trajektorie eines fahrzeugs - Google Patents
Verfahren und vorrichtung zur ermittlung einer trajektorie eines fahrzeugs Download PDFInfo
- Publication number
- WO2021043505A1 WO2021043505A1 PCT/EP2020/071205 EP2020071205W WO2021043505A1 WO 2021043505 A1 WO2021043505 A1 WO 2021043505A1 EP 2020071205 W EP2020071205 W EP 2020071205W WO 2021043505 A1 WO2021043505 A1 WO 2021043505A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- sequence
- vehicle
- time
- values
- value
- Prior art date
Links
Classifications
-
- 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
- G01C21/005—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 with correlation of navigation data from several sources, e.g. map or contour matching
-
- 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
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
- G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
-
- 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
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/393—Trajectory determination or predictive tracking, e.g. Kalman filtering
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/40—Correcting position, velocity or attitude
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
- G01S19/45—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement
- G01S19/47—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement the supplementary measurement being an inertial measurement, e.g. tightly coupled inertial
Definitions
- the invention relates to a method and a corresponding device for
- Determination of the trajectory driven by a vehicle in particular to generate a high-precision digital (HD) map for a road network.
- a vehicle can use high-precision digital maps to expand and / or supplement the vehicle sensors.
- An HD map provides a-priori knowledge about the vehicle's surroundings, which enables improved localization of the vehicle and / or the detection of outliers in the vehicle sensor system.
- HD cards can serve as a fallback layer in the event of a sensor failure and the convenience of an automated one
- HD Maps contain information about the passability and connectivity of lanes as well as applicable traffic rules that improve automated driving.
- Dedicated mapping vehicles equipped with a number of high-precision sensors such as LID AR (light detection and ranging) and / or high-precision GPS receivers can be used to create an HD map.
- LID AR light detection and ranging
- GPS receivers can be used to create an HD map.
- the use of dedicated mapping vehicles is associated with a relatively high cost.
- the number of mapping vehicles is typically limited, so that only a relatively small portion of the road network can be traveled regularly and / or so that the frequency of travel for an individual road segment is relatively low.
- changes in the road network may not always be recognized promptly and taken into account in an HD map.
- the use of not sufficiently up-to-date HD maps can in turn impair the quality of an automated driving function of a vehicle.
- driving data from (conventional) vehicles can be recorded and evaluated.
- the driving data of a vehicle can include sensor data from different sensors of the vehicle. Based on the driving data of the individual vehicles, trajectories of the individual vehicles can then be determined, from which in turn the course of the roadways can be inferred. The driving data from vehicles can thus be used to adapt an HD map.
- the accuracy and / or the resolution of the sensor data of the one or more sensors of a vehicle is typically less than the accuracy and / or the resolution of the sensor data of the sensors of a mapping vehicle.
- a device for estimating an actual (driving) trajectory of a vehicle is described.
- the trajectory can be estimated on the basis of sensor data from one or more sensors of the vehicle.
- the device can be arranged at least partially (or completely) inside the vehicle and / or at least partially (or completely) outside the vehicle (for example in a backend server).
- the device can be set up to create and / or adapt a digital map in relation to a road network on the basis of the estimation of the actual trajectory of the vehicle.
- the digital map can then be used to provide an automated driving function (in particular for highly automated driving).
- the digital map can describe the course of roads and / or lanes and / or lanes of the road network relative to a reference coordinate system (for example relative to the world coordinate system).
- the device can be set up to determine a sequence of measured position values in relation to the respective position of the vehicle at a corresponding sequence of times on the basis of the sensor data of a position sensor (of the vehicle).
- a measured position value can include coordinates, in particular GPS coordinates, in relation to the position of the vehicle within the reference coordinate system (for example within the world coordinate system) for the road network.
- the sequence of measured position values can thus describe a measured trajectory of the vehicle within the reference coordinate system. Due to measurement errors and / or due to measurement inaccuracies, stochastic and / or systematic deviations of the individual measured position values from the respective actual position of the vehicle can occur.
- the device is also set up to determine a sequence of odometry values for at least part of the sequence of times on the basis of sensor data from one or more vehicle sensors (of the vehicle).
- An odometry value for a point in time can show how the pose (i.e. the position and / or the orientation of the vehicle) has changed compared to a (directly) previous point in time.
- Exemplary vehicle sensors indicate the driving speed, the steering angle, the acceleration and / or the yaw rate of the vehicle.
- a pose value can indicate the pose of the vehicle.
- a position value can include coordinates with respect to the position of the vehicle within a coordinate system of the vehicle.
- An odometry value can indicate the change in the position (and / or the orientation) of the vehicle between two points in time relative to the coordinate system of the vehicle.
- the coordinate system of the vehicle can be shifted in relation to the reference coordinate system.
- the odometry values can thus indicate how the position (and possibly the orientation) of the vehicle at the sequence of points in time (relative to the coordinate system of the vehicle) has changed between two points in time. Consequently, on the basis of the odometry values, a sequence of pose values can be determined which indicates a trajectory that is shifted (and possibly rotated) with respect to the actual trajectory of the vehicle.
- the odometry values can have errors (due to measurement inaccuracies of the one or more vehicle sensors), so that the pose values determined solely on the basis of the odometry values (in addition to a translation and / or rotation) typically differ from the actual pose values of the vehicle.
- the device can be set up to combine and / or superimpose the sequence of measured position values and the sequence of odometry values in order to determine an estimate of the actual trajectory.
- a (systematic) position offset can be taken into account in order to shift the measured position values in a uniform manner and thus to take into account and compensate for a systematic error in the measurement of the measured position values (in particular the measured GPS or satellite coordinates).
- the device can be set up to determine a sequence of estimated position values for the sequence of points in time as an estimate of the actual trajectory of the vehicle.
- An estimated position value for a specific point in time can display the pose of the vehicle at the specific point in time relative to the reference coordinate system.
- the (uniform) value of the position offset can be determined for the sequence of measured position values.
- the sequence of estimated position values and the value of the position offset can be determined in such a way that an optimization criterion is improved, in particular at least locally optimized.
- the optimization criterion can include a position value deviation term for each of the sequence of points in time.
- the position value deviation term for a point in time can depend on the (for example square) deviation of the estimated position value for the respective point in time from the measured position value shifted by the (uniform and / or systematic) position offset for the respective point in time.
- the sequence of estimated pose values (and thus the estimation of the trajectory) can thus be determined in a particularly precise manner.
- the optimization criterion can include an odometry deviation term for at least some of the points in time of the sequence of points in time (in particular for N-1 points in time, for the case that the sequence of points in time comprises N points in time).
- the odometry deviation term for a point in time can depend on the (possibly quadratic) deviation of the change in the vehicle's pose resulting from the sequence of estimated pose values at the point in time on the odometry value for the point in time.
- the optimization criterion can thus be designed to determine the sequence of estimated pose values in such a way that the (mean) deviation of the estimated pose values from the measured odometer values and from the measured position values (shifted by the position offset) is reduced, in particular minimized.
- the actual trajectory of the vehicle can thus be estimated in a particularly precise manner.
- the device can be set up to determine the estimation of the actual trajectory of the vehicle by means of a graph SLAM, ie Simultaneous Localization and Mapping, method.
- the position offset can be taken into account as a movable anchor node within the framework of the graph SLAM method. This enables a particularly efficient and precise estimation of the actual trajectory.
- the measured position values typically have a certain position measurement inaccuracy. As a result, there can be a probability distribution of possible values around the respective measured position value for each measured position value. The optimization criterion can depend on the position measurement inaccuracy (in particular on the probability distribution) of the measured position values.
- the dependency can be such that an increase in the position measurement inaccuracy (or a broadening of the probability distribution) leads to a reduction in the effect of the position value deviation terms on the optimization criterion. In this way, the accuracy of the estimation of the actual trajectory can be increased further.
- the odometry values also typically have an odometry measurement inaccuracy.
- the optimization criterion can depend on the odometry measurement inaccuracy (in particular on the probability distribution) of the odometry, in particular in such a way that an increase in the odometry measurement inaccuracy (or a broadening of the probability distribution) leads to a reduction in the effect of the odometry deviation terms on the optimization criterion. In this way, the accuracy of the estimation of the actual trajectory can be increased further.
- the device can be set up to determine the position offset for the sequence of measured position values in such a way that the value of the position offset is the same for all measured position values of the sequence of measured position values and / or for all times in the sequence of times.
- Position offset for all measured position values of the trajectory are taken into account.
- a systematic error that acts over the entire trajectory in the measurement of the measured Position values e.g. a systematic error due to the atmosphere
- the device can be set up to limit the value of the position offset to a maximum value.
- the device can be set up to determine the value of the position offset, taking into account a covariance and / or a probability distribution for the position offset.
- the optimization criterion can include a term by which an increase in the amount of the value of the position offset is penalized. A precise localization of the estimation of the actual trajectory within the reference coordinate system (in particular within the world coordinate system) can thus be effected in an efficient and reliable manner.
- the device can be set up to subdivide the sequence of times into a plurality of successive partial sequences.
- the measured position values of a partial sequence can then be shifted with a partial position offset for the partial sequence and with the position offset for the entire sequence in order to determine the estimate of the actual trajectory.
- the device can be set up to determine the sequence of estimated position values for the sequence of times, the position offset for the entire sequence of measured position values and the plurality of partial position offsets for the plurality of partial sequences in such a way that the optimization criterion improves, in particular at least locally optimized.
- the device can be set up to determine the estimate of the actual trajectory by means of a graph SLAM method.
- the device can be set up to create a graph, the graph comprising the individual estimated pose values of the sequence of estimated pose values as nodes (which are referred to in this document as pose variable nodes).
- the estimated pose values can be initialized on the basis of the measured position values and / or on the basis of the (measured) odometry values.
- the graph with the initialized, estimated pose values can then be used as a starting point for (iterative) optimization of the graph and thus for the estimation of the actual trajectory.
- the graph can comprise an odometry factor which is dependent on the sensor data of the one or more vehicle sensors and / or which indicates a movement of the vehicle between the two nodes.
- the odometry factor between the pose variable node for a specific point in time and the pose variable node for a previous point in time can depend on the measured odometry value for the specific point in time.
- the odometry factor can display a probability distribution in relation to the change in pose values between two pose variable nodes.
- the graph can also have a position variable node for each measured position value. Furthermore, for each of the position variable nodes, the graph can include an association via a position factor (ie via an edge) to a corresponding position variable node (or to a corresponding measured position value).
- the position factor can be used to display how the position variable node is arranged relative to the respective position variable node. The position factor can depend on the measured position value for the respective position variable node.
- the position variable node for a specific point in time be arranged at a position within the graph which corresponds to the measured position value for the specific point in time.
- the position factor (ie the edge) between a position variable node and a corresponding position variable account can be associated with a probability distribution that depends on the position measurement inaccuracy.
- position variable nodes On the basis of the measured position values, position variable nodes and on the basis of the measured odometry values (initialized) position variable nodes of a graph can thus be provided.
- the nodes can be connected to one another via edges, wherein the edges can each be associated with a probability distribution or a covariance that depends on the position measurement inaccuracy and / or on the odometry measurement inaccuracy. In this way, the available sensor data relating to the position of the vehicle can be represented in an efficient manner within a graph.
- the position variable nodes of the graph can be connected (in a rigid manner) to a position anchor (i.e. to an anchor node) in such a way that a displacement of the position anchor leads to a corresponding displacement of the position variable nodes of the graph.
- the position offset can thus be taken into account in an efficient manner within the graph.
- the device can be set up to determine the sequence of estimated position values (ie the estimated value of the actual trajectory) by optimizing the graph.
- the optimization of the graph can include moving the position anchor and / or changing one or more pose values of the sequence of pose values and / or moving the position variable nodes.
- the graph can be optimized in such a way that a specific optimization criterion is improved, in particular at least locally optimized.
- the optimization criterion can Position deviation terms and / or odometry deviation terms.
- the device can be set up, as part of the optimization of the graph, a pose of the position anchor as a function of a
- the probability distribution can be such that a translation of the position anchor is made possible and that a rotation of the position anchor is essentially prevented. In this way, a position offset and thus a systematic error in the measurement of the measured position values can be taken into account and compensated for in a particularly reliable manner.
- the sequence of times can comprise a plurality of successive partial sequences.
- the position variable nodes of the graph of a partial sequence can then each be connected to an intermediate anchor, so that a shift of the intermediate anchor leads to a corresponding shift of the position variable nodes of the partial sequence.
- the intermediate anchors of the plurality of partial sequences can be connected to the position anchor in such a way that a displacement of the position anchor leads to a corresponding displacement of the intermediate anchors of the plurality of partial sequences.
- the device can be set up to determine a measurement position of a landmark in an environment of the vehicle for a specific point in time of the sequence of points in time on the basis of sensor data from one or more environment sensors (for example cameras and / or lidar sensors) of the vehicle. It can then be a Landmark deviation term are taken into account in the optimization criterion, the landmark deviation term being able to depend on the deviation of the measurement position of the landmark from a reference position of the landmark. By taking one or more landmarks into account, the quality of the estimation of the actual trajectory can be further increased.
- the device can be set up to determine a sequence of measured position values at a corresponding sequence of times for a plurality of journeys on a segment of a road network (and possibly within a limited time interval). Furthermore, the device can be set up to determine a sequence of odometry values for at least part of the sequence of times for the plurality of journeys. In addition, the device can be set up to determine a sequence of estimated position values for the sequence of times and a position offset for the plurality of journeys.
- the sequences of estimated position values (i.e. the estimates of the actual trajectories for the different journeys) and the position offset can be determined in such a way that an optimization criterion is improved in each case, in particular at least locally optimized.
- the sequences of estimated pose values (ie the estimates of the actual trajectories for the different journeys) and the position offset can be determined in such a way that the position offset is the same for the majority of journeys (in particular if the majority of journeys within a relatively short Time interval). It can thus be taken into account in an efficient manner that a systematic error in the position measurement has the same effect on different journeys. As a result, the quality of the estimated estimates of the actual journeys can be further increased.
- a specific position offset can be determined at least partially for the different journeys (in particular if the different journeys are relatively far apart in time). So can Changes in the presence of systematic measurement errors are reliably detected and taken into account.
- the device can be set up to determine alternative data relating to the position of the vehicle and to determine a value of at least one further deviation term for the optimization criterion on the basis of the alternative data.
- the at least one further deviation term can be such that the further deviation term brings about an increase in the amount of the value of the position offset.
- the further deviation term can, for example (as set out above) depend on a landmark and / or depend on the measured position values that were recorded during a further journey.
- the alternative data can thus include, for example, the measurement position of a landmark and / or measured position values from a further trip.
- the device can be set up to receive the sensor data of the position sensor of the vehicle or data derived therefrom from the vehicle. Furthermore, the device can be set up to receive the sensor data of the one or more vehicle sensors of the vehicle or data derived therefrom from the vehicle.
- the data can be received via a (wireless) communication link, for example.
- the sequence of estimated Position widths for the sequence of points in time can then be determined by the (vehicle external device) on the basis of the received data.
- a (road) motor vehicle in particular a passenger car or a truck or a bus or a motorcycle
- a vehicle-external unit eg a server
- a (computer-implemented) method for estimating an actual trajectory of a vehicle comprises determining, on the basis of the sensor data of a position sensor, a sequence of measured position values in relation to a respective position of the vehicle at a corresponding sequence of points in time.
- the measured position values can indicate the position of the vehicle relative to a reference coordinate system.
- the method comprises determining, on the basis of sensor data from one or more vehicle sensors, a sequence of odometry values for at least part of the sequence of times.
- An odometry value for a point in time can show how the pose of the vehicle has changed compared to a (directly) preceding point in time.
- the method further comprises determining (as an estimate of the actual trajectory of the vehicle) a sequence of estimated position values for the sequence of points in time and determining a (systematic and / or uniform) position offset for the sequence of measured position values, so that an optimization criterion improves in particular at least locally optimized.
- the optimization criterion can include a position value deviation term for each of the sequence of times.
- the position value deviation term for a point in time can depend on the deviation of the estimated position value for the point in time from the measured position value for the point in time shifted by the position offset.
- the optimization criterion can include an odometry deviation term for at least some of the points in time of the sequence of points in time.
- the odometry deviation term for a point in time can depend on the deviation of a change in the vehicle's pose resulting from the sequence of estimated pose values at the point in time from the odometry value for the point in time.
- SW software program
- the software program can be set up to be executed on a processor (e.g. on a control unit of a vehicle and / or on a server) and thereby to execute the method described in this document.
- the storage medium can comprise a software program which is set up to be executed on a processor and thereby to execute the method described in this document.
- FIG. 1 exemplary components of a vehicle
- FIG. 2a shows exemplary sensor data along a vehicle trajectory
- FIG. 2b shows an exemplary, estimated on the basis of the sensor data of FIG.
- 3a shows an exemplary position anchor for position values
- 3b shows an exemplary, estimated by moving the position anchor
- FIG. 4a shows an exemplary tree of position anchors for different partial sequences of position values
- FIG. 5 shows a flow chart of an exemplary method for determining a trajectory of a vehicle.
- the present document deals with the precise determination of the trajectory of a vehicle on the basis of the (possibly faulty) sensor data from one or more sensors of the vehicle.
- a precise localization of the trajectory within a (global or world) reference coordinate system should be made possible.
- the vehicle 100 comprises one or more Elmfeld sensors 102, which are set up to acquire sensor data (also referred to as Elmfeld data in this document) in relation to the Elmfeld of the vehicle 100.
- Elmfeld sensors 102 are: an image camera, a radar sensor, a lidar sensor, an EU trasonic sensor, etc.
- a control unit 101 of the vehicle 100 can be set up, based on the Elmfeld data (in particular based on image data from a camera), one or more objects in the To detect Elmfeld of the vehicle 100.
- a landmark eg a building in the surroundings of the vehicle 100 can be detected for which the exact (reference) position (within the reference coordinate system) is known. Furthermore, a measurement position of the landmark can be determined on the basis of the surrounding data. The measurement position can then be compared with the reference position of the landmark to locate the vehicle 100 (within the reference coordinate system).
- the vehicle 100 further comprises a position sensor 103 which is set up to acquire sensor data (also referred to as position data in this document) with regard to the position of the vehicle 100.
- the position data can be acquired repeatedly at a sequence of points in time.
- the position data can include position values for different points in time, the position value for a specific point in time indicating the position of the vehicle 100 at the specific point in time (within the reference coordinate system).
- a (multidimensional) position value can include the GPS coordinates of the vehicle 100, for example.
- a position value is typically associated with a certain uncertainty (e.g. with a certain standard deviation).
- the vehicle 100 can include one or more vehicle sensors 104 that are set up to acquire sensor data (also referred to as vehicle data in this document) with regard to a state of the vehicle 100.
- the vehicle data can display, for example: the speed, the orientation, the yaw rate, the acceleration, etc.
- the control unit 101 can be set up, on the basis of the vehicle data, a pose of the vehicle 100, ie a position and orientation of the vehicle 100 (determined on the basis of odometry) Vehicle 100 to determine.
- (multi-dimensional) pose values in relation to the pose of the vehicle 100 can be determined for a sequence of points in time.
- the individual pose values typically show a certain uncertainty (e.g. a certain standard deviation).
- the vehicle 100 can include a communication unit 105 which is set up to exchange data with an external unit (for example with a backend server) via a (wireless) communication connection.
- the Vehicle 100 can be set up to send the sensor data (in particular the environment data, the position data and / or the vehicle data) captured when the vehicle 100 is driving to the external unit in order to enable the external unit to determine the trajectory driven by the vehicle 100 (within the reference coordinate system).
- the control unit 101 of the vehicle 100 can be set up to determine (at least partially) the trajectory driven by the vehicle 100 on the basis of the detected sensor data and to send it to the external unit via the communication unit 105.
- FIG. 2a illustrates exemplary sensor data that were acquired while a vehicle 100 was traveling.
- FIG. 2a shows a sequence of position values 201 at a sequence of successive points in time.
- the individual position values 201 have a certain uncertainty, which is illustrated by the circles 202 around the individual position values 201.
- the individual position values 201 can have been recorded using the position sensor 103 of the vehicle 101.
- the individual position values 201 can be viewed as position variable accounts of a graph 215.
- FIG. 2a shows position values 211 for the sequence of times.
- the position values 211 (possibly alone) can have been determined on the basis of the vehicle data of the one or more vehicle sensors 104.
- the pose values 211 can be pose variable nodes of the graph 215, the graph 215 describing a trajectory of the vehicle 100.
- the pose values 211 can be determined on the basis of odometry values, the odometry value describing the change in the pose of the vehicle 100 between two pose values 211.
- the odometry values can be determined on the basis of the vehicle data. In the case of an exact measurement and / or determination of the position values 211 and the position values 201, the position of the position value 211 and the position value 201 should each coincide for a specific point in time (assuming that the position of the individual position values 211 is specified relative to the reference coordinate system ).
- Errors and / or inaccuracies in the measurement and / or the determination of the position values 211 (in particular the odometry values) and the position values 201 have the effect that the position of the position value 211 and the position value 201 typically differ from one another for a specific point in time.
- the association 213 of the position value 211 and the position value 201 is illustrated for the same point in time (by a dashed straight line).
- the association 213 can be taken into account in the graph 215 by an edge.
- landmarks 220 can be detected at isolated points in time (based on the surroundings data).
- the (reference) position of a landmark 220 e.g. a traffic sign
- the measured value 221 of the position of the landmark 220 can be subject to a specific error and a specific inaccuracy 222.
- the error in the measured value 221 of the position of the landmark 220 can be caused by an error in relation to the estimated value of the position of the vehicle 100.
- FIG. 2a the association 223 between the measured value 221 of the position and the actual position of a landmark 220 is illustrated (by a dashed straight line). The association 223 can in turn be taken into account by an edge in the graph 215.
- the sensor data illustrated in FIG. 2a can be used to estimate the position and / or the course of the actual trajectory of the vehicle 100 within the reference coordinate system.
- the so-called graph SLAM (simultaneous localization and mapping) method can be used for this purpose.
- a graph 215 can be provided on the basis of the pose values 211 describing the pose of the vehicle 100 at a sequence of points in time.
- the individual pose variable nodes of the graph 215 correspond to the individual pose values 211.
- Directly adjacent pose variable nodes are connected to one another via edges, the edges having one or more boundary conditions or odometry factors 214 for the transition from a pose value 211 to the directly following pose value 211 include.
- the one or more boundary conditions or odometry factors 214 typically depend on technical properties of vehicle 100 (such as a maximum steering angle, etc.) and / or on measurement inaccuracies of the vehicle data.
- the odometry factors 214 can depend on the measurement inaccuracy of the odometry values between two position values 211.
- the graph SLAM method can be aimed at determining the graph 215, by means of which a certain error criterion (eg a mean square error) with regard to the deviation of the determined graph 215 from the available sensor data is reduced, in particular minimized.
- a certain error criterion eg a mean square error
- the estimated value of the position of the vehicle 100 at a specific point in time n can be referred to, for example, as x (n)
- the position value 201 at the point in time n can be referred to as p (n).
- a position value deviation term (x (n) ⁇ p (n)) 2 with respect to the deviation of the estimated value of the position from the position value 201 thus results at the point in time n.
- the change between two estimated positions of the vehicle 100 at a specific one Time n can be referred to as d (n) and the odometry value at the particular time n (which represents the measured change in position) can be referred to as o (n).
- An odometry deviation term (d (n) - o (n)) 2 then results in relation to the deviation of the estimated change in position (in particular the estimated change in pose) from the measured change in position (in particular the measured change in pose).
- the deviation terms can be weighted, whereby the weight for the respective term depends on the uncertainty of the respective measured value of the position or the change in position depends (and decreases with increasing uncertainty).
- JV of the considered section of the trajectory to be determined are taken into account, e.g. added.
- additional measured values of the position of vehicle 100 can be determined on the basis of a landmark 220.
- the estimated value of the position of the vehicle 100 can be adapted in such a way that the deviation between the measured value 221 of the position of the landmark 220 and the reference value of the position of the landmark 220 known (e.g. from the digital map) is reduced. Since the reference value of the position of the landmark 220 can typically be determined with relatively high accuracy, the deviation term with respect to a landmark 220 typically has a relatively high weight within the overall error or optimization criterion.
- a graph 215 with a sequence of estimated values of the position of the vehicle 100 or with a sequence of estimated position values 231 of the vehicle 100 at the sequence of times n 1,. Error or optimization criterion is reduced, in particular minimized.
- the optimized graph 215, in particular the sequence of estimated position values 231, represents an estimate of the actual trajectory of the vehicle 100.
- the consideration of isolated landmarks 220 can lead to the optimized graph 215 in the direct vicinity of a landmark 220 representing a relatively good estimate of the actual trajectory of the vehicle 100.
- Due to systematic errors in the position data however, in an area 230 between two landmarks 220 relatively strong deviations of the estimated trajectory (ie the sequence of estimated position values 231) from the actual trajectory of the vehicle 100 arise.
- the deviations are caused in particular by the fact that in an area 230 between two landmarks 220 no measured values 221 of the position of a landmark 220 are available and / or are taken into account, and the graph 215 (in particular the sequence of estimated position values 231) is therefore determined in such a way that that the deviation from the available position values 201 is reduced.
- the systematic error in the position data can be seen in FIG. 2 b from the relatively large deviation between the estimated value 231 of the position and the position value 201 in the immediate vicinity of the two landmarks 220.
- the relatively large deviation of the estimated trajectory ie the sequence of estimated pose values 231 from the actual trajectory of the vehicle 100 in the area 230 between two landmarks 220 leads, as shown in FIG. 2b, to a “sagging” of the sequence of estimated pose values 231.
- the systematic error in the measurement of the position values 201 can be taken into account by introducing an additional variable (i.e. an additional node) when determining the graph 215, by means of which all position values 201 to be taken into account can be shifted together.
- the individual position values 201 ie the position variable nodes
- the individual position values 201 can each be fastened via a fixed edge 312 to a common position armature 312, which can be shifted by a translational movement 323 in order to convert the individual measured position values 201 (ie the position variable values).
- Node is shifted in the same way.
- the position anchor 321 can, if necessary, be shifted according to a predefined covariance or probability distribution 322.
- the Position anchor 321 moved (in particular moved by translation 323).
- the shift can take place by a position offset 330.
- a systematic error in the measured position values 201 can be determined and compensated implicitly (by moving the position armature 321).
- the size of the systematic error is described by the position offset 330.
- deviations of the optimized graph 215 (in particular the sequence of estimated position values 231) from the actual trajectory of the vehicle 100, which can be attributed to a systematic error in the measured position values 201 can be avoided.
- 3b shows an optimized graph 215 (in particular an optimized sequence of estimated position values 231) and the displacement of the position anchor 321 brought about as part of the optimization.
- the systematic error in the acquisition of the measured position values 201 can depend on the direct surroundings of the vehicle 100. For example, a relatively tall building in the direct vicinity of the vehicle 100 (e.g. due to multipath effects) can lead to a change in the systematic error.
- a tree or a hierarchy of anchors 321, 421 can be used.
- an intermediate anchor 421 can be defined for each segment of the trajectory, to which the measured position values (or a position variable 301 corresponding to the position values) of the respective segment are permanently connected.
- the intermediate anchors 421 can then be shifted relative to an anchor point 424 according to a covariance or probability distribution 422 of the respective intermediate anchor 421 (represented by the connection 423).
- the anchor points 424 of the individual intermediate anchors can then be connected to the (main) position anchor 321 (possibly via one or more further levels of intermediate anchor 421).
- systematic errors of the position values 201 can thus be taken into account in the individual segments of the trajectory in order to determine an optimized graph 215, ie an estimate of the actual trajectory, in a particularly precise manner.
- a method is thus described with which a systematic error in the position measurement, in particular in the case of a GPS-based position measurement, can be taken into account and at least partially compensated for.
- the systematic error in the position measurement can be caused by atmospheric effects or by local effects such as the shielding by a house wall or a forest.
- the systematic error can lead to measurements being correlated with one another and not independent of one another. For the systematic error based on atmospheric effects, this applies to all measurements in a certain period of time, e.g. when vehicle 100 is driven through or driven in a certain way.
- local effects can occur in which, in a certain area, for example in front of a high house, shading and multipath effects can occur, which lead to a systematic error locally.
- a graph SLAM method is expanded to include a modeling of systematic errors in the position data.
- Each measured position value 201 (or a position variable node 301 corresponding to the measured position value 201) is connected to a position anchor 321 via a rigid edge 312.
- the position anchor 321 can be defined in such a way that the position anchor (accounts) 321 can be shifted (exclusively) by a translation 323 via a prior with defined covariances 322.
- a systematic shift of all measured position values 201 or position variable nodes 301 is implicitly integrated into the factor graph 215.
- the graph SLAM optimization therefore takes systematic errors in the position data into account when determining the driving trajectory and determines the most likely one systematic shifting of the measured position values 201 or the position variable nodes 301.
- Local systematic errors in the position measurement can also be modeled and determined through a hierarchical system with several intermediate anchors 421.
- a factor graph 215 is built up.
- the individual measured position values 201 are not used directly as priorities for the vehicle position at the respective points in time. Instead, a corresponding position variable is inserted into the factor graph 215 as position variable node 301 for each position measurement.
- These position variable nodes 301 can each be connected to the associated vehicle pose or pose variable node 211 via a position factor 313 (ie via corresponding edges). The uncertainty of the position measurements originally contained in the position prior can be modeled by the position factor 313.
- all position variable nodes 301 are connected to a virtual position anchor variable 321 via virtual ideally rigid edges 312.
- This position anchor variable 321 can represent a pose (position + orientation) and is typically in turn provided with a prior (ie with a probability distribution 322 in relation to the pose of the position anchor variable 321).
- this prior preferably has a translation covariance 322 which codes the corresponding assumptions with regard to systematic shifting.
- the orientation of the anchor pose can be fixed by an ideally small orientation covariance in order to avoid a rotation of the position anchor variables 321 (and thus to ensure reliable modeling of the systematic error of the position measurement). Due to the rigid factors 312 between the position variable nodes 301 and the anchor node 321, the internal geometry between the position variable nodes 301 is retained and “any” systematic translations can be modeled and optimized in the factor graph 215. This leads to an improved localization of the driving trajectory and to a systematic shift of the position measurements.
- a hierarchical system with several intermediate anchors 421 is described. This means that local systematic errors can also be modeled.
- the development of the neighborhood relationships can be carried out temporally and / or spatially. This allows various local systematic errors to be modeled and taken into account.
- the intermediate anchors 421 can be linked to one another due to spatial or temporal proximity to the spatial and / or temporal dependencies of the underlying errors in the position measurement to model different trajectories.
- An example of a spatial dependency is a systematic error caused by a house wall.
- a temporal dependency can be caused by ionospheric conditions at a certain point in time or by identical satellite constellations for different passages at the same point in time.
- the method 500 shows a flowchart of an exemplary method 500 for estimating an actual trajectory of a vehicle 100.
- the method 500 can be carried out, for example, by a control unit 101 of the vehicle 100 and / or by a unit external to the vehicle (e.g. a jaw server).
- the method 500 comprises determining 501, on the basis of the sensor data of a position sensor 103 (for example on the basis of the sensor data of a GPS receiver), a sequence of measured position values 201 (for example GPS coordinates) in Relation to the respective position of the vehicle 100 at a corresponding sequence of points in time.
- a measured position value 201 for a point in time can indicate the position of the vehicle 100 at the point in time relative to a reference coordinate system.
- the position sensor 103 can be part of the vehicle 100.
- the measured position values 201 can reproduce a trajectory of the vehicle 100 measured (using the sensor data of the position sensor 103).
- the method 500 comprises determining 502, on the basis of sensor data from one or more vehicle sensors 104, a sequence of odometry values for at least part of the sequence of points in time.
- the odometry value can indicate for a point in time how the pose of the vehicle 100 has changed compared to a previous point in time.
- the one or more vehicle sensors 104 can display, for example, the speed, the distance covered, the yaw rate, the yaw rate, and / or the acceleration of the vehicle 100 in order to determine the odometer values.
- the odometry values can be determined on the basis of one or more control variables with which, for example, the drive motor, a braking device and / or a steering device of the vehicle 100 is controlled.
- the individual odometry values can each indicate the change in position and / or the change in orientation of vehicle 100.
- a relative trajectory of the vehicle 100 can be reproduced, which can be converted into the estimation of the actual trajectory by translation and / or rotation.
- the method 500 further comprises determining 503 (as an estimate of the actual trajectory of vehicle 100) a sequence of estimated position values 231 for the sequence of points in time, as well as determining a (systematic) position offset 330 for the sequence of measured position values 201.
- the estimated position value 231 for a point in time may indicate the pose of the vehicle 100 at the point in time relative to the reference coordinate system.
- the sequence of estimated position values 231 and the position offset 330 can be determined in such a way that an optimization criterion is improved, in particular optimized at least locally.
- the optimization criterion can include a position value deviation term for each of the sequence of times.
- the position value deviation term for a point in time can depend on the deviation 313 of the estimated position value 231 for the point in time from the measured position value 201 shifted by the position offset 330 for the point in time.
- a sequence of estimated position values 231 can thus be determined, by means of which the (mean, possibly quadratic) deviation of the estimated position values 231 from the measured position values 201 shifted by the position offset is reduced, in particular minimized.
- the odometry deviation term for a point in time n can depend on the deviation of a change in the pose of the vehicle 100 resulting from the sequence of estimated pose values 231 at the point in time from the odometry value for the point in time.
- the optimization criterion can be, for example include a (possibly weighted) sum of the position value deviation terms and the odometry deviation terms.
- the quality of the location of a trajectory relative to an existing digital map and / or the quality of the synchronous location of several trajectories by means of common landmark sightings can be determined by the modeling systematic global and local errors in position measurement can be increased.
- the quality of the localization of the travel trajectories relative to a map or relative to one another can be improved through the implicit modeling of systematic errors.
- the methods described in this document can be used, for example, for change detection and learning from high-precision digital maps (e.g. for automated driving).
Abstract
Description
Claims
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2022513504A JP2022546483A (ja) | 2019-09-03 | 2020-07-28 | 車両の軌道を決定する方法および装置 |
KR1020227002048A KR20220024791A (ko) | 2019-09-03 | 2020-07-28 | 차량의 궤적을 결정하기 위한 방법 및 장치 |
US17/636,119 US20220290991A1 (en) | 2019-09-03 | 2020-07-28 | Method and Device for Determining a Trajectory of a Vehicle |
CN202080060302.1A CN114286924B (zh) | 2019-09-03 | 2020-07-28 | 用于确定车辆轨迹的方法和装置 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102019123538.3A DE102019123538A1 (de) | 2019-09-03 | 2019-09-03 | Verfahren und Vorrichtung zur Ermittlung einer Trajektorie eines Fahrzeugs |
DE102019123538.3 | 2019-09-03 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021043505A1 true WO2021043505A1 (de) | 2021-03-11 |
Family
ID=71899717
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/EP2020/071205 WO2021043505A1 (de) | 2019-09-03 | 2020-07-28 | Verfahren und vorrichtung zur ermittlung einer trajektorie eines fahrzeugs |
Country Status (6)
Country | Link |
---|---|
US (1) | US20220290991A1 (de) |
JP (1) | JP2022546483A (de) |
KR (1) | KR20220024791A (de) |
CN (1) | CN114286924B (de) |
DE (1) | DE102019123538A1 (de) |
WO (1) | WO2021043505A1 (de) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR3102879A1 (fr) * | 2019-10-30 | 2021-05-07 | Renault S.A.S | Système et procédé de gestion de la position d’un véhicule autonome. |
US20220164595A1 (en) * | 2020-11-25 | 2022-05-26 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method, electronic device and storage medium for vehicle localization |
DE102021211988A1 (de) | 2021-10-25 | 2023-04-27 | Robert Bosch Gesellschaft mit beschränkter Haftung | Verfahren zum Generieren einer Kartendarstellung für Fahrzeuge |
DE102022103856A1 (de) | 2022-02-18 | 2023-08-24 | Bayerische Motoren Werke Aktiengesellschaft | Verfahren und Vorrichtung zur Erkennung eines Problems bei der Ermittlung eines Fahrpfades |
DE102022207829A1 (de) | 2022-07-29 | 2024-02-01 | Robert Bosch Gesellschaft mit beschränkter Haftung | Verfahren zum Hinzufügen eines oder mehrerer Ankerpunkte zu einer Karte einer Umgebung |
DE102022209276A1 (de) | 2022-09-07 | 2024-03-07 | Robert Bosch Gesellschaft mit beschränkter Haftung | Verfahren zum Verringern einer Sendefrequenz von Nachrichten eines Fahrzeugs |
CN115200591B (zh) * | 2022-09-16 | 2022-12-09 | 毫末智行科技有限公司 | 一种位姿确定方法、装置、整车控制器及可读存储介质 |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102016205193A1 (de) * | 2016-03-30 | 2017-10-05 | Volkswagen Aktiengesellschaft | Marginalisieren eines Posen-Graphen |
WO2020016385A1 (de) * | 2018-07-20 | 2020-01-23 | Volkswagen Ag | Verfahren und system zum bestimmen einer position eines fahrzeugs |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4124249B2 (ja) * | 2006-07-25 | 2008-07-23 | トヨタ自動車株式会社 | 測位装置、ナビゲーションシステム |
JP5152677B2 (ja) * | 2009-02-26 | 2013-02-27 | アイシン・エィ・ダブリュ株式会社 | ナビゲーション装置及びナビゲーション用プログラム |
CN104374395A (zh) * | 2014-03-31 | 2015-02-25 | 南京邮电大学 | 基于图的视觉slam方法 |
US11536572B2 (en) * | 2016-11-09 | 2022-12-27 | The Texas A&M University System | Method and system for accurate long term simultaneous localization and mapping with absolute orientation sensing |
DE102016223999A1 (de) * | 2016-12-02 | 2018-06-07 | Volkswagen Aktiengesellschaft | Bestimmen einer Referenztrajektorie mit einem Posen-Graphen |
CN107272673A (zh) * | 2017-05-18 | 2017-10-20 | 中山大学 | 基于位姿链模型的slam后端轨迹优化方法 |
CN107229063A (zh) * | 2017-06-26 | 2017-10-03 | 奇瑞汽车股份有限公司 | 一种基于gnss和视觉里程计融合的无人驾驶汽车导航定位精度矫正方法 |
CN109029433B (zh) * | 2018-06-28 | 2020-12-11 | 东南大学 | 一种移动平台上基于视觉和惯导融合slam的标定外参和时序的方法 |
CN109887032B (zh) * | 2019-02-22 | 2021-04-13 | 广州小鹏汽车科技有限公司 | 一种基于单目视觉slam的车辆定位方法及系统 |
-
2019
- 2019-09-03 DE DE102019123538.3A patent/DE102019123538A1/de active Pending
-
2020
- 2020-07-28 US US17/636,119 patent/US20220290991A1/en active Pending
- 2020-07-28 CN CN202080060302.1A patent/CN114286924B/zh active Active
- 2020-07-28 JP JP2022513504A patent/JP2022546483A/ja active Pending
- 2020-07-28 KR KR1020227002048A patent/KR20220024791A/ko unknown
- 2020-07-28 WO PCT/EP2020/071205 patent/WO2021043505A1/de active Application Filing
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102016205193A1 (de) * | 2016-03-30 | 2017-10-05 | Volkswagen Aktiengesellschaft | Marginalisieren eines Posen-Graphen |
WO2020016385A1 (de) * | 2018-07-20 | 2020-01-23 | Volkswagen Ag | Verfahren und system zum bestimmen einer position eines fahrzeugs |
Also Published As
Publication number | Publication date |
---|---|
CN114286924A (zh) | 2022-04-05 |
US20220290991A1 (en) | 2022-09-15 |
KR20220024791A (ko) | 2022-03-03 |
JP2022546483A (ja) | 2022-11-04 |
CN114286924B (zh) | 2024-04-23 |
DE102019123538A1 (de) | 2021-03-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021043505A1 (de) | Verfahren und vorrichtung zur ermittlung einer trajektorie eines fahrzeugs | |
DE102010005293B4 (de) | System und Verfahren zur Spurpfadschätzung unter Verwendung einer Sensorvereinigung | |
WO2017016799A1 (de) | Bestimmung einer anordnungsinformation für ein fahrzeug | |
DE102017108774A1 (de) | Fahrzeugspurkartenschätzung | |
DE112018006665T5 (de) | Verfahren zum zugreifen auf ergänzende wahrnehmungsdaten von anderen fahrzeugen | |
DE102015111535A1 (de) | Algorithmus zur genauen Krümmungsschätzung für die Bahnplanung von autonom fahrenden Fahrzeugen | |
DE102018107935A1 (de) | Vorrichtung zur Bestimmung der Operational Design Domain (ODD) | |
EP3581886B1 (de) | Verfahren und vorrichtung zum bestimmen einer position eines kraftfahrzeugs | |
DE102016209232B4 (de) | Verfahren, Vorrichtung und computerlesbares Speichermedium mit Instruktionen zur Bestimmung der lateralen Position eines Fahrzeuges relativ zu den Fahrstreifen einer Fahrbahn | |
EP3491339A1 (de) | Verfahren, vorrichtung und computerlesbares speichermedium mit instruktionen zur bestimmung der lateralen position eines fahrzeuges relativ zu den fahrstreifen einer fahrbahn | |
DE102019100034A1 (de) | Autonome lenksteuerung | |
DE102016114402A1 (de) | Verfahren und gerät zur bewertung der funktion eines bordnavigationssystems für ein fahrzeug unter nutzung von lateralversatzdaten | |
DE102016213817B4 (de) | Verfahren, Vorrichtung und computerlesbares Speichermedium mit Instruktionen zur Bestimmung der lateralen Position eines Fahrzeuges relativ zu den Fahrstreifen einer Fahrbahn | |
DE102019214628A1 (de) | Validierung von Umfelderfassung mittels Satelitenbildern und SAR-Radardaten | |
DE102019126446A1 (de) | Fahrzeugsteuerungsvorrichtung | |
DE102020100022A1 (de) | Positionsbestimmungstechnik | |
DE102021105823A1 (de) | Dynamische lidar-anpassung | |
DE102022112395A1 (de) | Von kreuzungsknoten unterstützte hochauflösende kartierung | |
DE102018215753A1 (de) | Vorrichtung und Verfahren zum Ermitteln einer Trajektorie eines Fahrzeugs | |
DE102018203753A1 (de) | Verfahren und Vorrichtung zur robusten Lokalisierung eines Fahrzeugs | |
DE102017108107A1 (de) | Verfahren, vorrichtung und computerlesbares speichermedium mit instruktionen zur schätzung einer pose eines kraftfahrzeugs | |
DE112020004203T5 (de) | Fahrzeugpositionsbestimmungsvorrichtung und Fahrzeugpositionsbestimmungsverfahren | |
EP3410158A1 (de) | Verfahren, vorrichtungen und computerlesbares speichermedium mit instruktionen zur ortsbestimmung eines durch ein kraftfahrzeug erfassten datums | |
DE102020105619A1 (de) | System und verfahren zur bestimmung der fahrzeugposition | |
EP3739511A1 (de) | Verfahren zum einbetten von lokalen sensordaten in eine karte |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20750202 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 20227002048 Country of ref document: KR Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 2022513504 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20750202 Country of ref document: EP Kind code of ref document: A1 |