EP4540626A1 - Verfahren zur lokalisierung eines fahrzeugs, sensoreinrichtung, fahrzeug und computerprogrammprodukt - Google Patents
Verfahren zur lokalisierung eines fahrzeugs, sensoreinrichtung, fahrzeug und computerprogrammproduktInfo
- Publication number
- EP4540626A1 EP4540626A1 EP23733206.9A EP23733206A EP4540626A1 EP 4540626 A1 EP4540626 A1 EP 4540626A1 EP 23733206 A EP23733206 A EP 23733206A EP 4540626 A1 EP4540626 A1 EP 4540626A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- gaussian distributions
- vehicle
- gaussian
- distance
- sensor data
- 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.)
- Pending
Links
Classifications
-
- 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
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/52—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S15/00
- G01S7/523—Details of pulse systems
- G01S7/526—Receivers
- G01S7/53—Means for transforming coordinates or for evaluating data, e.g. using computers
-
- 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
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/02—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems using reflection of acoustic waves
- G01S15/06—Systems determining the position data of a target
- G01S15/08—Systems for measuring distance only
- G01S15/10—Systems for measuring distance only using transmission of interrupted, pulse-modulated waves
-
- 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
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/02—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems using reflection of acoustic waves
- G01S15/06—Systems determining the position data of a target
- G01S15/42—Simultaneous measurement of distance and other co-ordinates
-
- 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
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/86—Combinations of sonar systems with lidar systems; Combinations of sonar systems with systems not using wave reflection
-
- 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
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/88—Sonar systems specially adapted for specific applications
- G01S15/93—Sonar systems specially adapted for specific applications for anti-collision purposes
- G01S15/931—Sonar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- 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
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/88—Sonar systems specially adapted for specific applications
- G01S15/93—Sonar systems specially adapted for specific applications for anti-collision purposes
- G01S15/931—Sonar systems specially adapted for specific applications for anti-collision purposes of land vehicles
- G01S2015/932—Sonar systems specially adapted for specific applications for anti-collision purposes of land vehicles for parking operations
Definitions
- the invention relates to a method for localizing a vehicle from sensor data sets describing an environment of the vehicle and recorded with the aid of at least one sensor of a sensor device of the vehicle, the sensor data sets each comprising a plurality of Gaussian distributions, the Gaussian distributions each consisting of at least one measuring point of the sensor device are formed and each describe at least part of an object in the environment of the vehicle in relation to a coordinate system.
- the invention further relates to a sensor device, a vehicle and a computer program product.
- vehicles can have sensors that can, for example, detect objects in the vehicle's surroundings. Knowledge of the presence of the objects can make driving the vehicle easier.
- the information obtained via the sensors can be displayed to a driver and enable autonomous or semi-autonomous driving processes.
- Distance sensors can be used as sensors, for example, which can determine the distance between the sensor or the vehicle and an object in the area surrounding the vehicle.
- Distance sensors usually include a transmitting device that sends out signals and a receiving device that receives signals reflected from objects in the environment as echoes.
- the distance, or in other words, the distance, to the object can be determined based on a transit time difference between the time of sending the signal and the time of receiving the echo, taking into account the speed of propagation of the signal.
- Such distance sensors can usually be used in motor vehicles to detect the surroundings.
- Ultrasonic sensors for example, are particularly important, especially in semi-automatic or automatic driving maneuvers, especially in connection with parking applications, such as parking distance measurement, finding parking spaces or when parking.
- the motor vehicle is usually moved relative to the objects, with a measurement cycle being carried out at predetermined times during the movement. During each measurement cycle, at least one signal is sent out using a distance sensor.
- the position and/or orientation of the detected objects changes in relation to a coordinate system fixed to the vehicle. If information about the vehicle movement is to be derived from a comparison between the relative object arrangements from different measurement cycles, then it is necessary to carry out an assignment, also known as registration, of the objects determined in each case. This allows the relative change in position of the objects in relation to the vehicle to be determined. From the relative change in position of stationary objects, a movement of the vehicle can then be traced.
- the assignment or registration of the objects represents a challenge.
- the applicable methods can depend in particular on the type of object description in the environmental data, which is generated from the measured values of the sensors.
- the environmental data can be generated, for example, as point clouds from the measurement points or as object maps in which the detected objects are described as geometric figures, for example as polygons.
- a method for assigning different points in two data sets is described, for example, in the article by Besl, Paul J.; ND McKay 'A Method for Registration of 3-D Shapes", IEEE Transactions on Pattern Analysis and Machine Intelligence, 14 (2), pp. 239-256, 1992.
- a transformation or mapping rule is used, which creates a first point data set on a second point data set, determined by step by step looking for the closest point in the second data set for the points of the first data set. Then one of the data sets is transformed in a transformation step in order to minimize the distances. These steps are repeated as often carried out until a minimum of the distances has been reached.
- the mapping rule for the data sets then results from the sum of the transformation steps carried out.
- the method comprises the following steps:
- the second sensor data set comprising a plurality of second Gaussian distributions in a second coordinate system
- the assignment being carried out by evaluating at least one distance criterion describing a distance between two Gaussian distributions, - determining at least one transformation rule comprising a shift and/or a rotation between the first coordinate system and the second coordinate system while minimizing the distances described by the distance criterion between the nearest Gaussian distributions,
- a first sensor data set is therefore initially recorded at a first vehicle position.
- the first vehicle position can, for example, be the destination of a previously carried out vehicle movement.
- the vehicle can have moved into the first position at least partially independently, i.e. autonomously or semi-autonomously. Alternatively, the vehicle can also have been moved into the first position by a driver.
- the first vehicle position can be selected in particular depending on a driving maneuver to be carried out with the support of the method according to the invention.
- the driving maneuver can in particular be carried out autonomously or semi-autonomously.
- the driving maneuver can be, for example, a parking procedure, i.e. parking or pulling out of a parking space.
- the first vehicle position can be in the vicinity of a parking space, for example, and when leaving a parking space, the first vehicle position can be within the parking space.
- the first sensor data set is recorded, which consequently describes the objects in the area surrounding the vehicle.
- several measuring points are recorded using the at least one sensor, which is designed, for example, as an ultrasonic sensor.
- the sensor data set in particular, one or more measuring points, which describe, for example, signals (echoes) of the sensor reflected from a similar distance and/or from a similar direction, are combined into an ellipse described by a Gaussian distribution.
- the shape of the Gaussian distribution or the ellipse can in particular correspond to or correspond to the spatial distribution of the reflection locations of the echoes described by the respective measuring points at least be approximated.
- An ellipse or a Gaussian distribution describing the ellipse can each describe an object or a part or a section of an object in the area surrounding the vehicle.
- large objects and/or objects with a more complex geometry can be described by several Gaussian distributions or several ellipses.
- the spatial distribution of the measuring points and/or the spatial extent of the Gaussian distributions determined from the measuring points is specified in the first sensor data set in relation to the first coordinate system.
- the first coordinate system can, for example, describe the arrangement of the Gaussian distributions in relation to the sensor or in relation to the vehicle. Since the vehicle is in the first vehicle position when the first sensor data set is recorded, the first coordinate system indicates the spatial distribution of the Gaussian distributions in relation to the first vehicle position.
- the reference system to which the spatial distribution of the Gaussian distributions is specified when measuring the second sensor data set by the at least one sensor changes.
- the Gaussian distributions described in the second sensor data set are specified in a second coordinate system, which can also relate to the vehicle. Due to the vehicle movement into the second vehicle position, the Gaussian distributions now refer to the second vehicle position.
- the first sensor data set and the second sensor data set are then merged, for example by converting the Gaussian distributions of one sensor data set into the second without taking into account the offset between the coordinate systems Sensor data set can be adopted.
- the closest Gaussian distribution in the second sensor data set can then be determined for the first Gaussian distributions of the first sensor data set.
- the closest distribution is used determined by evaluating the distance criterion describing a distance between two Gaussian distributions. It is also possible at this point for the closest first Gaussian distribution to be determined for the second Gaussian distributions.
- a transformation rule comprising a shift and/or a rotation is determined between the first coordinate system and the second coordinate system.
- the transformation rule is determined by minimizing the distances between the closest Gaussian distributions described by the distance criterion.
- the first coordinate system and the second coordinate system are aligned relative to one another, whereby the different reference positions can be at least partially compensated.
- the second vehicle position is determined, for example calculated or at least approximated, using the transformation rule from the first position.
- a new, further assignment of the Gaussian distributions takes place and then a further transformation rule is determined by again minimizing the distances described by the distance criterion between the now assigned pairs of Gaussian distributions.
- the steps of assigning the Gaussian distributions and determining a transformation rule can be repeated until a minimum for the distances has been reached. The assignment and the subsequent determination of a transformation rule can therefore be repeated iteratively.
- the second vehicle position can then be determined in particular depending on all of the transformation regulations determined. For example, an overall transformation rule representing all displacements and/or all rotations can be determined, which is applied to the first vehicle position can be used to determine the second vehicle position.
- the closest Gaussian distribution i.e. the one at the shortest distance described by the distance criterion. This does not necessarily have to correspond to a Gaussian distribution assigned to the same object.
- the closest Gaussian distributions can also change for different assignment steps. Iteratively, a displacement and/or a rotation between the first coordinate system and the second coordinate system can advantageously be determined, so that localization of the vehicle is possible based on the first sensor data set and the second sensor data set.
- the vehicle can be localized in particular as part of a (partially) automated driving process of the vehicle.
- the first sensor data set and the second sensor data set can each also be referred to as maps or map information.
- the Gaussian distributions can each be a multidimensional probability density distribution. In the sensor data sets, the Gaussian distributions can be described, for example, as covariance matrices.
- the method according to the invention advantageously enables simple mapping of environmental information.
- the sensor data sets determined are memory efficient and require little computing power to create them.
- the localization of the vehicle can also be advantageously determined within a predetermined period of time with comparatively low computing power. This advantageously results in the method being suitable for sensor devices, which, in addition to the at least sensor, includes a computing device with a comparatively low computing capacity.
- the method according to the invention makes it possible to localize the vehicle in an acceptable time based on a first and a second sensor data set, even with such a sensor device.
- the localization of the vehicle from the sensor data sets has the advantage that precise position determination is possible, in particular during a driving maneuver involving several movements of the vehicle.
- the method according to the invention does not have any accumulating errors. Furthermore, the method can be used to precisely determine the position even when moving in a confined space and/or during driving maneuvers of the vehicle that involve a large proportion of rotational and/or transverse movement of the vehicle, such as a parking maneuver. The method can in particular also be used to determine a vehicle position multiple times during a driving maneuver.
- the Gaussian distributions in the first sensor data set and the second sensor data set each describe an ellipse combining one or more measuring points.
- Combining, in particular, several measurement points as an ellipse represents an efficient way to describe the objects in the sensor data sets.
- an ellipse has the advantage that its mathematical description is comparatively simple compared to a polygon or a point cloud and therefore requires only a small amount of data .
- an ellipse can take on different shapes, for example depending on the ratio of its semi-axes, and thus describe the geometry of different objects.
- Such an ellipse can advantageously be described by a Gaussian distribution.
- the ellipse can, for example, be assigned to a probability and a particularly two-dimensional Gaussian distribution can be determined in such a way that it maps the corresponding ellipse for this probability based on its covariance.
- a particularly two-dimensional Gaussian distribution can be determined in such a way that it maps the corresponding ellipse for this probability based on its covariance.
- describing the ellipses using Gaussian distributions represents an efficient type of mathematical description.
- the Gaussian distributions are each at least two-dimensional, with a distance criterion being used, which indicates at least one distance in relation to the at least two dimensions.
- the two dimensions can correspond to a plane of a road surface on which the vehicle is standing.
- the Gaussian distributions can each describe an ellipse lying in this plane. It is possible for three-dimensional Gaussian distributions to be used, in particular if the at least one sensor and/or a sensor device comprising the sensor is also designed to determine an object height assigned to the respective measuring points.
- a Mahalanobis distance, a Bhattacharyya distance, a Kullback-Leibler distance and/or a probability-based distance between two Gaussian distributions can be used as a distance criterion, the probability-based distance indicating the probability that the mean value of one of the Gaussian distributions can be used. Distributions in the other Gaussian distribution is assigned.
- the expected value of the Gaussian distribution can be used as the mean value of a Gaussian distribution.
- the probability-based distance can indicate the probability that the mean or expected value of a first Gaussian distribution lies in a second Gaussian distribution, with the second Gaussian distribution being selected as the closest Gaussian distribution in which the probability is greatest. Accordingly, this also applies if a first Gaussian distribution is reversed as the closest distribution to a second Gaussian distribution.
- mathematical distances can also be used as a distance criterion, which indicate a distance between two distributions, such as the Bhattacharyya distance or the Kullback-Leibler distance.
- a mathematical distance such as a Mahalanobis distance, which indicates the distance of a point, for example a center of one of the distributions, to a distribution, can also be used as a distance criterion, additionally or alternatively.
- the assignment of the closest Gaussian distributions depends on at least one Assignment criterion takes place, the assignment criterion being a ratio between the amplitudes of the measured values described by the Gaussian distributions, a ratio between directions which are assigned to the measured values described by the Gaussian distributions, and / or a ratio between the curvatures of the measured values described by the Gaussian distributions.
- Distribution objects described can be used.
- the assignment criteria can each be used in addition to the distance criterion, or one or more higher-dimensional distance criteria can be used, which, in addition to a spatial distance, for example in the x-direction and y-direction, also include at least one further dimension corresponding to an assignment criterion.
- the quality of the assignments can be improved.
- the number of iteration steps required can be reduced by using one or more assignment criteria, so that the assignment rule can be determined quickly.
- mapping criteria makes it more likely that a first Gaussian distribution will be mapped to a second Gaussian distribution (or vice versa) that includes measurements reflected from the same object. Since the properties of the object influence the echoes reflected from the object, properties of the echoes can be considered in order to determine appropriate Gaussian distributions or to avoid obvious or at least very likely misattributions.
- a different Gaussian distribution for example the second-smallest distance, is chosen as the closest Gaussian distribution if it is in the smallest Distance Gaussian distribution only has a poor degree of agreement for one or more considered assignment criteria.
- the relationship between the amplitudes of the measured values described by the Gaussian distributions can be used as the assignment criterion.
- a Gaussian distribution can be assigned as the closest Gaussian distribution if the amplitudes are as similar as possible or if the amplitude ratio lies within a predetermined interval.
- the relationship between directions that are assigned to the measured values described by the Gaussian distributions can also be considered as an assignment criterion, with an assignment taking place in particular when the same or at least a similar direction is assigned to the measured values.
- the direction can optionally be corrected based on movement information describing the movement of the vehicle in order to take into account a relative change in direction due to the vehicle movement.
- the azimuth angle at which the echoes forming the measured values are received by the sensor can be used as the direction, with a similar direction being possible if the ratio of the directions or the respective azimuth angles are in a predetermined interval .
- the curvature refers to the shape of the object or to the shape of a side surface of the object facing the sensor.
- Gaussian distributions can be considered as possible closest Gaussian distributions, which describe objects with the same or a similar curvature, that is, within a predetermined curvature interval.
- assignment criteria can be determined, for example, using machine learning.
- the first Gaussian distributions and at least a part of the second Gaussian distributions are each assigned a label, with only those Gaussian distributions which have a matching label being used to determine the closest Gaussian distribution exhibit.
- the label may, for example, indicate an object type and/or an object class of an object described by the Gaussian distribution. It is possible for a physical object to be described by multiple Gaussian distributions, where the Gaussian distributions each describe a part or a section of the object. Each of the Gaussian distributions can be assigned a label that describes the object type and/or the object class of the entire object.
- the closest Gaussian distribution it can be provided according to the invention that only Gaussian distributions are taken into account whose mean value is within a multiple of the variance of the Gaussian distribution for which the closest Gaussian distribution is determined. In this way, the computational effort in determining the respective distances resulting from the one or more distance criteria can be reduced. Of those Gaussian distributions that lie within the multiple of the variance, the Gaussian distribution lying at the shortest distance can then be chosen as the closest Gaussian distribution. When using one or more assignment criteria, the Gaussian distribution can also be selected in which the at least one assignment criterion matches and which of several Gaussian distributions with matching assignment criteria has the smallest distance.
- the transformation rule is determined in relation to mean values of the respective Gaussian distributions and/or in relation to covariance matrices of the respective Gaussian distributions.
- the transformation rule is determined in relation to mean values of the respective Gaussian distributions and/or in relation to covariance matrices of the respective Gaussian distributions.
- the entire information that can be derived from the respective Gaussian distributions can advantageously be taken into account, so that a more precise and/or faster determination of the transformation rule is made possible.
- Taking the covariance matrices into account also allows the particularly elliptical shape of the Gaussian distributions to be taken into account when determining the transformation rule describing a shift and/or a rotation.
- Taking the covariance matrices into account can be implemented as a weighted determination of the transformation regulations.
- the inverses of the covariance matrices for example, can be used as weighting factors.
- a transformation rule comprising scaling is determined, in particular by means of singular value decomposition.
- the transformation rule can include scaling to compensate for a different scale between the first coordinate system and the second coordinate system.
- the transformation rule can include, for example, an enlargement or reduction factor as a scaling in relation to one of the coordinate systems.
- singular value decomposition SMD is that the computational effort required to determine the transformation rule is comparatively low
- a transformation rule comprising an error covariance matrix is determined, in particular by means of a Gauss-Helmert model.
- the error covariance matrix can be used to provide information about the accuracy of the transformation rule.
- a Gauss-Helmert model to determine the transformation rule, in addition to a transformation rule describing, for example, a shift, a rotation and a scaling, an associated error covariance matrix can also be efficiently determined.
- efficient transferability and efficient application of the method can also be made possible with sensor data sets comprising more than two dimensions.
- an initial transformation can be applied to at least one of the coordinate systems, the initial transformation being determined as a function of movement information describing the movement.
- the initial transformation can be carried out in particular before a first assignment of the Gaussian distributions in order to at least partially compensate for an offset between the first coordinate system and the second coordinate system at the beginning.
- the initial transformation can be carried out in particular if the offset between the first coordinate system and the second coordinate system can be estimated at least approximately based on movement information which describes the movement of the vehicle from the first vehicle position to the second vehicle position.
- the movement information is determined using odometry and/or using a navigation method, in particular using satellite navigation.
- the movement information can be determined, for example, by a control device designed to carry out the method.
- the control device can be part of the vehicle and/or a sensor device that also includes the at least one sensor.
- the control device can be connected to determine the movement information, for example by means of an odometry device that provides odometry data and/or a navigation device that provides navigation data, for example a satellite navigation device, or can comprise an odometry device and/or a navigation device.
- a sensor device for a sensor device according to the invention it is provided that it comprises at least one sensor and at least one control device, the control device being designed to carry out a method according to the invention.
- the control device can form a structural unit with the at least one sensor or can be designed separately from the sensor and with it be communicatively connected.
- the control device can be a part of the vehicle or a control device external to the vehicle that is communicatively connected to the at least one sensor.
- a vehicle according to the invention it is intended for a vehicle according to the invention to comprise a sensor device according to the invention.
- the control device of the sensor device can be arranged in the vehicle.
- the control device can also be arranged external to the vehicle and communicate with the at least one sensor via a particularly wireless communication connection.
- a computer program product according to the invention is intended to include instructions that cause a control device to carry out a method according to the invention.
- the computer program product according to the invention can be stored on a non-transient data carrier, for example a CD, a floppy disk or a USB stick. It is also possible for the computer program product to be stored on a computing device, from which it can be accessed via a communication connection, for example the Internet, and/or stored on a control device.
- FIG. 1 shows an exemplary embodiment of a vehicle according to the invention with an exemplary embodiment of a sensor device according to the invention
- FIG. 2 shows a flowchart of an exemplary embodiment of a method according to the invention
- 3 shows a diagram comprising first Gaussian distributions and second Gaussian distributions to explain the exemplary embodiment of a method according to the invention
- FIG. 4 shows a further diagram comprising the measuring points of the sensor device used to form the Gaussian distributions.
- FIG. 1 An exemplary embodiment of a vehicle 1 is shown in FIG. In the vicinity of the vehicle 1, which is designed as a passenger car, there are two further vehicles 2, 3, between which there is a parking space 4.
- the vehicle 1 includes an exemplary embodiment of a sensor device 5, which includes a control device 6 and one or more sensors 7. For the sake of clarity, only a single sensor 7 is shown.
- the sensor 7 is designed as an ultrasonic sensor and is used to detect part of the surroundings of the vehicle 1.
- the control device 6 is set up to carry out a method for localizing the vehicle 1 in a sensor data set describing the surroundings of the vehicle 1.
- the sensor data set can be recorded using the sensor 7 or the sensor device 5.
- the control device 6 can form a structural unit with the at least one sensor 7 or can be designed separately from the sensor and connected to it in a communicative manner.
- the control device can be part of the vehicle 1 or a control device external to the vehicle that is connected to the at least one sensor 7, in particular in a wirelessly communicating manner.
- the sensor 7 has a detection area 8 in which signals emitted by the sensor 7 are reflected on objects in the surroundings of the vehicle 1, for example the vehicles 2, 3, and received again as echoes. From these echoes, the sensor device 5 can determine the distance to the objects or vehicles 2, 3, for example from a transit time measurement.
- the relative arrangement between the vehicle 1 and the external vehicle 2, 3 changes. For example, when this movement is carried out in the course of an assisted or At least partially automated driving maneuvers, it may be necessary to determine the second vehicle position 10 with a high level of accuracy. This requires localization of the vehicle 1, which can be carried out by the control device 6 on the basis of sensor data sets determined by the sensor 7.
- FIG. 2 shows a flowchart of an exemplary embodiment of a method for localizing a vehicle in a sensor data set describing an environment of the vehicle and recorded with the aid of at least one sensor of the vehicle.
- the method can be carried out by the control device 5.
- the vehicle moves into a second vehicle position in a step S2.
- a second sensor data set is then recorded in a step S3 via the sensor device 5 or the sensor 7.
- the sensor data set recorded in the second vehicle position 10 also includes several second Gaussian distributions, which are specified in relation to a second coordinate system. Both the first coordinate system and the second coordinate system can be specified in relation to the vehicle 1, but the coordinate systems have an offset from one another, which corresponds to the movement of the vehicle 1, i.e. the movement between the first vehicle position 9 and the second vehicle position 10 .
- control device 6 determines a transformation rule which determines the offset between the first coordinate system of the first Sensor data set and the second coordinate system of the second sensor data set. From the first vehicle position 9 and the transformation rule, the second vehicle position 10 and thus the current vehicle orientation at this point in time relative to the environment or the external vehicles 2, 3 can then be determined.
- a step S4 the first sensor data set and the second sensor data set are combined. This can be done, for example, by transferring the measuring points from the second sensor data set to the first sensor data set.
- the positions assigned to the respective measuring points differ due to the offset between the first coordinate system and the second coordinate system.
- FIG. 3 shows a diagram which includes first Gaussian distributions 11 and second Gaussian distributions 12.
- the diagram represents, for example, the first coordinate system, with an x coordinate plotted on the abscissa and a y coordinate plotted on the ordinate.
- the first Gaussian distributions 11 are each formed from the measuring points of the first sensor data set and are shown with closed points.
- the second Gaussian distributions 12 are each formed from the measuring points of the second sensor data set.
- the second Gaussian distributions 12 are represented by X-shaped points.
- the first Gaussian distributions 11 in the first sensor data set and the second Gaussian distributions 12 each describe an ellipse summarizing one or more measurement points in the second sensor data set.
- the measuring points used to form the Gaussian distributions 11, 12 are shown in FIG. 4, with symbols corresponding to the representation of the Gaussian distributions being used for the measuring points.
- the measuring points shown in Fig. 4 are for illustrative purposes only.
- the measuring points are preferably not part of the sensor data sets, which in particular only contain the Gaussian distributions instead of the measuring points in order to enable simpler data processing and data storage.
- the Gaussian distributions 11, 12 each extend in the x-direction and in the y-direction and are therefore each two-dimensional. It can be seen that there is a spatial offset between the second Gaussian distributions 12 and the first Gaussian distributions 11.
- each of the first Gaussian distributions 11 from the first sensor data set recorded in the first vehicle position 9 is assigned the closest second Gaussian distribution 12 from the second sensor data set.
- the assignment is carried out by evaluating at least one distance criterion describing a distance between two Gaussian distributions.
- the second Gaussian distribution 12 is selected as the closest Gaussian distribution which has the shortest distance to the first Gaussian distribution 11.
- the second Gaussian distributions 12_1, ..., 12_K are assigned to the first Gaussian distributions 11_1, ..., 11_N.
- each first Gaussian distribution 11_1, ..., 11_N is assigned a second Gaussian distribution 12.
- the number K of the second Gaussian distributions 12 can differ from the number N of the first Gaussian distributions.
- the second Gaussian distribution 12 with the smallest distance is assigned to the first Gaussian distributions 11.
- a Mahalanobis distance, a Bhattacharyya distance, a Kullback-Leibler distance and/or a probability-based distance between two Gaussian distributions can be used as a distance criterion, the probability-based distance indicating the probability that the mean of one of the Gaussians -Distributions in the other Gaussian distribution is assigned.
- the aforementioned distances each enable the calculation of a spatial distance between a first Gaussian distribution 11 and a second Gaussian distribution 12 in relation to the x coordinate and the y coordinate.
- the closest Gaussian distribution In order to reduce the computational effort in determining the closest Gaussian distribution, for example, only those second Gaussian distributions 12 can be taken into account whose mean value is within a multiple of the variance of the first Gaussian distribution 11 to which the closest Gaussian distribution is should be determined. Of the second Gaussian distributions 12, which lie within the multiple of the variance, the second Gaussian distribution 12 located at the shortest distance can then be selected as the closest Gaussian distribution.
- a transformation rule is then determined which describes a shift and/or a rotation of the second Gaussian distributions 12 in relation to the first Gaussian distributions 11.
- the second Gaussian distributions 13 transformed according to the transformation rule are shown in FIG. 3 by means of O-shaped points. Points corresponding to the transformed Gaussian distributions 13 are also shown in FIG. These measuring points also serve for illustrative purposes only. Preferably, the measuring points corresponding to the transformed measuring points are also not part of the sensor data sets, which in particular contain the Gaussian distributions instead of the measuring points.
- the transformed second Gaussian distributions 13 have a smaller spatial offset from the first Gaussian distributions 11.
- the transformation rule is determined in particular by minimizing the distances described by the distance criterion between the first Gaussian distributions 11 and their respective assigned ones. closest second Gaussian distributions 12. In particular, a sum of the distances can be minimized.
- the transformation rule can also describe a scaling in order to compensate for a different scale between the first coordinate system and the second coordinate system.
- the transformation rule can be determined, for example, using singular value decomposition. It is possible for a transformation rule comprising an error covariance matrix to be determined, the transformation rule being able to be determined, for example, using a Gauss-Helmert model.
- the transformation rule can be determined, for example, in relation to the mean values of the respective first and second Gaussian distributions 11, 12 and/or in relation to covariance matrices of the respective first and second Gaussian distributions 11, 12. Taking the covariance matrices into account can be implemented as a weighted determination of the transformation regulations, with the inverses of the covariance matrices being used as weighting factors, for example.
- steps S5 and S6 are then carried out again at least once in order to further reduce the spatial offset between the first Gaussian distributions 11 and the transformed second Gaussian distributions 13.
- the first Gaussian distributions 11 it is possible for the first Gaussian distributions 11 to be assigned at least partially different second Gaussian distributions than in the first iteration of this step.
- a second Gaussian distribution 12, 13 it is also possible for a second Gaussian distribution 12, 13 to be assigned to more than one first Gaussian distribution 11 as the closest Gaussian distribution.
- a step S7 the second vehicle position 10 is determined based on the first vehicle position 9 and the one or more transformation rules determined in step S6 determined.
- an initial transformation can be applied to at least one of the coordinate systems in an optional step Si to improve the convergence of the method.
- the initial transformation can be determined depending on movement information describing the movement of the vehicle 1 from the first vehicle position 9 to the second vehicle position 10.
- the initial transformation can be applied in particular before the first implementation of step S5 and allows at least partial compensation of the offset between the first coordinate system and the second coordinate system.
- the movement information can be determined, for example, using odometry and/or using a navigation method, in particular using satellite navigation.
- the movement information can be determined by the control device 6, for example.
- the control device 6 can be connected to determine the movement information, for example by means of an odometry device (not shown) of the vehicle 1 that provides odometry data and/or a navigation device (not shown) of the vehicle 1 that provides navigation data.
- the control device 6 can comprise an odometry device and/or a navigation device.
- the closest Gaussian distributions can additionally or alternatively be assigned depending on at least one assignment criterion.
- the assignment criterion can be, for example, a ratio between the amplitudes of the measured values described by the Gaussian distributions, a ratio between directions that are assigned to the measured values described by the Gaussian distributions, and / or a ratio between the curvatures of the measured values described by the Gaussian distribution objects described can be used.
- the assignment criteria can be used in addition to the distance criterion, or one or more higher-dimensional distance criteria can be used, which, in addition to a spatial distance in relation to the x-coordinate and to the y-coordinate, also at least one further, include a dimension corresponding to an assignment criterion. It is possible for several assignment criteria to be used, which are weighted among each other using weighting factors.
- a first Gaussian distribution 11 is assigned a second Gaussian distribution 12, which reflected from the same object, for example one of the external vehicles 2, 3, or from the same part or section of an object Measured values included. Since the properties of the object influence the echoes reflected from the object, properties of the echoes can be considered in order to determine appropriate Gaussian distributions or to avoid obvious or at least very likely misattributions.
- assignable second Gaussian distributions 12 it is possible, for example, for several assignable second Gaussian distributions 12 to lie within a predetermined distance range around a first Gaussian distribution 11, with the closest Gaussian distribution from this group of second Gaussian distributions 12 depending on the at least one assignment criterion, in particular is selected depending on the degree of agreement between the properties of the Gaussian distributions and/or their measured values, which are considered as assignment criteria.
- assignment rules can also be used in relation to the assignment criteria and the distances between the Gaussian distributions described in each case by the distance criterion.
- the relationship between directions that are assigned to the measured values described by the Gaussian distributions 11, 12 can also be considered as an assignment criterion, with an assignment taking place in particular when the same or at least a similar direction is assigned to the measured values is.
- the direction can optionally be corrected based on the or further movement information describing the movement of the vehicle 1 in order to take into account a relative change in direction due to the vehicle movement.
- the azimuth angle of the sensor detection area 8 in the xy plane, at which the echoes forming the measured values are received by the sensor 7, can be used as the direction.
- the directions of individual measured values or the averaged directions of all measured values forming the respective Gaussian distribution can be considered.
- a similar direction can be assumed, for example, if the ratio of the directions or the respective azimuth angles lie in a predetermined interval.
- second Gaussian distributions 12 can be considered as possible closest Gaussian distributions, which describe objects or object sections with the same or a similar curvature, that is, within a predetermined curvature interval. It is possible for at least some of the first Gaussian distributions 11 and at least some of the second Gaussian distributions 12 to be assigned a label, with only those being used to determine the closest second Gaussian distribution 12 to a first Gaussian distribution 11 second Gaussian distributions 12 are used, which have a matching label.
- the label can, for example, describe an object type and/or an object class of an object described by the Gaussian distribution. For example, the label can indicate that the object is a third-party vehicle 2, 3 or a boundary of the parking space 4.
- the closest first Gaussian distribution 11 can also be assigned to the second Gaussian distributions 12, in particular to each of the second Gaussian distributions 12.
- the above statements apply analogously to such an assignment.
- more than two dimensions for example three-dimensional or comprising more than three dimensions
- sensor data sets and corresponding coordinate systems can also be used.
- the Gaussian distributions 11, 12 can also be three-dimensional or correspondingly multi-dimensional.
- the transformation rule can advantageously be determined as a covariance matrix, or comprising a covariance matrix.
- the method for localizing the vehicle 1 can take place in particular as part of an assisted, semi-autonomous or autonomous driving maneuver.
- the control device 6 or a further control device of the vehicle or an external computing device communicating with the control device 6 can be used to determine a travel trajectory for a semi-autonomous or autonomous vehicle movement based on the determined second position information.
- at least one actuator of the vehicle 1 can be controlled in order to carry out a longitudinal and/or transverse movement of the vehicle 1.
- one designed to display information to a driver of the vehicle 1 can also be used Display device can be controlled depending on the second vehicle position 10, in particular for displaying information determined depending on the second vehicle position 10.
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Traffic Control Systems (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102022206144.6A DE102022206144A1 (de) | 2022-06-20 | 2022-06-20 | Verfahren zur Lokalisierung eines Fahrzeugs, Sensoreinrichtung, Fahrzeug und Computerprogrammprodukt |
| PCT/DE2023/200108 WO2023246989A1 (de) | 2022-06-20 | 2023-05-31 | Verfahren zur lokalisierung eines fahrzeugs, sensoreinrichtung, fahrzeug und computerprogrammprodukt |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP4540626A1 true EP4540626A1 (de) | 2025-04-23 |
Family
ID=86903908
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP23733206.9A Pending EP4540626A1 (de) | 2022-06-20 | 2023-05-31 | Verfahren zur lokalisierung eines fahrzeugs, sensoreinrichtung, fahrzeug und computerprogrammprodukt |
Country Status (3)
| Country | Link |
|---|---|
| EP (1) | EP4540626A1 (de) |
| DE (1) | DE102022206144A1 (de) |
| WO (1) | WO2023246989A1 (de) |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014132711A (ja) | 2013-01-04 | 2014-07-17 | Kddi Corp | 複数の測位方式に基づく移動端末の位置情報から対象エリアを特定するエリア管理サーバ、プログラム及び方法 |
| DE102015214338A1 (de) | 2015-07-29 | 2017-02-02 | Volkswagen Aktiengesellschaft | Bestimmung einer Anordnungsinformation für ein Fahrzeug |
| EP3517996B1 (de) | 2018-01-25 | 2022-09-07 | Aptiv Technologies Limited | Verfahren zur bestimmung der position eines fahrzeugs |
| CN108332758B (zh) | 2018-01-26 | 2021-07-09 | 上海思岚科技有限公司 | 一种移动机器人的走廊识别方法及装置 |
| DE102018215753A1 (de) | 2018-09-17 | 2020-03-19 | Zf Friedrichshafen Ag | Vorrichtung und Verfahren zum Ermitteln einer Trajektorie eines Fahrzeugs |
| DE102019216607A1 (de) | 2019-10-29 | 2021-04-29 | Robert Bosch Gmbh | Verfahren und Vorrichtung zum Bereitstellen von Radardaten |
| DE102022000849A1 (de) | 2022-03-11 | 2022-07-14 | Mercedes-Benz Group AG | Verfahren zur Erzeugung einer Umgebungsrepräsentation für ein Fahrzeug |
-
2022
- 2022-06-20 DE DE102022206144.6A patent/DE102022206144A1/de active Pending
-
2023
- 2023-05-31 EP EP23733206.9A patent/EP4540626A1/de active Pending
- 2023-05-31 WO PCT/DE2023/200108 patent/WO2023246989A1/de not_active Ceased
Also Published As
| Publication number | Publication date |
|---|---|
| DE102022206144A1 (de) | 2023-12-21 |
| WO2023246989A1 (de) | 2023-12-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2561419B1 (de) | Verfahren zur bestimmung des fahrbahnverlaufes für ein kraftfahrzeug | |
| DE102017116088A1 (de) | Vorrichtung und Verfahren zum Abschätzen einer Position eines Fahrzeugs | |
| DE102018124108A1 (de) | VERFAHREN UND VORRICHTUNG ZUM ERFASSEN EINER STRAßENBEGRENZUNG | |
| DE102019114603A1 (de) | Geschwindigkeitsvektorschätzung von objekten durch mehrere radare mit unterschiedlichen beobachtungswinkeln | |
| DE102014111125A1 (de) | Verfahren zum Erkennen eines Objekts in einem Umgebungsbereich eines Kraftfahrzeugs mittels eines Ultraschallsensors, Fahrerassistenzsystem sowie Kraftfahrzeug | |
| DE102021125773A1 (de) | Verfahren zum gleichzeitigen schätzen von bewegung und form eines zielfahrzeugs mittels eines vorverteilungsmodells eines tracklets | |
| DE102016003261A1 (de) | Verfahren zur Selbstlokalisierung eines Fahrzeugs in einer Fahrzeugumgebung | |
| DE102005035746A1 (de) | Verfahren zur Bestimmung einer Relativposition einer mobilen Einheit durch Vergleich von Scans einer Umgebung und mobile Einheit | |
| WO2020244881A1 (de) | Verfahren zum erstellen einer universell einsetzbaren merkmalskarte | |
| DE102019132150A1 (de) | Verfahren zum automatischen Kalibrieren eines Umfeldsensors, insbesondere eines Lidar-Sensors, eines Fahrzeugs auf Grundlage von Belegungskarten sowie Recheneinrichtung | |
| DE102020202679A1 (de) | Verfahren und Vorrichtung zum Kalibrieren eines Sensorsystems eines beweglichen Objekts | |
| WO2020001690A1 (de) | Verfahren und system zur erkennung von hindernissen | |
| WO2023246989A1 (de) | Verfahren zur lokalisierung eines fahrzeugs, sensoreinrichtung, fahrzeug und computerprogrammprodukt | |
| WO2022018007A1 (de) | Verfahren zum schätzen einer eigenbewegung eines fahrzeugs anhand von messungen eines lidar-sensors sowie recheneinrichtung | |
| DE102019126276A1 (de) | Verfahren zum Erfassen zumindest eines Objekts in einem Umgebungsbereich eines Fahrzeugs durch Zuordnung von Objektpunkten, Recheneinrichtung sowie Ultraschallsensorvorrichtung | |
| DE102022208937A1 (de) | Verfahren zur Nickwinkelfehler- und zur Gierwinkelfehlerkompensation bei einer Geländehöhenmessung mit einem LiDAR-Sensorsystem | |
| WO2024027884A1 (de) | Verfahren zum ermitteln einer parklücke mithilfe eines faltenden neuronalen netzes | |
| WO2019141607A1 (de) | Zuordnung von objekten in vektor-basierter darstellung in eine gitter-basierte repräsentation | |
| WO2022194576A1 (de) | Verfahren zur bestimmung eines bewegungszustands eines starren körpers | |
| DE102022207370A1 (de) | Verfahren zum Erkennen einer fehlerhaften Karte einer Umgebung | |
| WO2022058331A1 (de) | Verfahren, computerprogramm, speichermedium, vorrichtung zum tracking eines objekts | |
| DE102020116027A1 (de) | Verfahren und Vorrichtung zur Ermittlung von Belegungsinformation für einen Umfeldpunkt auf Basis von Radardetektionen | |
| DE102021101172A1 (de) | Nur-peilungs-slam mit kameras als orientierungspunkte | |
| WO2025124941A1 (de) | Lagebestimmen eines linienartigen objekts | |
| DE102023204604A1 (de) | Verfahren zur Auswertung von ortsaufgelösten Ist-Sensordaten |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20250120 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC ME MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| RAP3 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: AUMOVIO AUTONOMOUS MOBILITY GERMANY GMBH |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) |