DE102020208981A1 - Method for estimating the geometry of a movement path - Google Patents

Abstract

Method for estimating the geometry of a movement path of an ego vehicle (101), in which sensor data including detection points are recorded by means of a sensor and the geometry of the movement path is estimated using the sensor data, with targets along the movement path being determined using the sensor data, location points for the respective position of the targets and the sensor are determined, based on the location points, several polygons are determined, in particular continuously, so that a polygon network is created, which is used to estimate the geometry of the movement path, the method comprising the following method steps:Step 1: the An ego point (S) is assigned to detected detection points, which indicates the sensor position,Step 2: the polygon network is created using the detection points,Step 3: the polygons are marked,Step 4: the edges of the polygons are determined, in particular depending on at least one edge parameters, weight et,Step 6: the edges are removed according to their weighting, so that in particular the edges are removed where the path of movement is not possible or only possible to a limited extent,Step 7: Recording possible orbits (UR) by recognizing cycles within the polygon network , andStep 8: Defining the movement path through the polygon mesh based on the recognized cycles.

Description

The present invention relates to a method for estimating the geometry of a movement path of a means of locomotion, in particular an ego vehicle, and a system for carrying out the method according to the invention.

Technological background

Modern means of transportation such as B. motor vehicles or motorcycles are increasingly equipped with driver assistance systems, which use sensor systems to detect the environment, recognize the traffic situation and support the driver, z. B. by a braking or steering intervention or by the output of a visual or acoustic warning. Radar sensors, lidar sensors, camera sensors or the like are regularly used as sensor systems for detecting the surroundings. From the sensor data determined by the sensors, conclusions can then be drawn about the environment, e.g. B. an object and / or environment classification can be made. Furthermore, the detection of the surroundings is almost indispensable in the field of (partially) autonomous driving. By processing the sensor and environment data, assistance functions can then be carried out, e.g. B. Accidents with other road users can be avoided or complicated driving maneuvers can be made easier by supporting or even completely taking over the driving task or vehicle guidance (partly / fully automated).

The detection and assessment of road edges or road boundaries is an elementary function in modern driver assistance systems and z. B. used in an automatic distance control (ADR) or adaptive cruise control (ACC) or an emergency brake assistant (EBA) to estimate the trajectory or the movement path of the respective means of transport or vehicle. The road boundary is usually expressed in the form of a clothoid. As a clothoid is used in modern road construction z. B. denotes the transition curve between a straight line and a curve. The respective course of the clothoids can, for. B. can be estimated based on static targets or objects that are located in the area of the road boundary and were detected by radar measurements. For example, such an estimation of the road boundary is based on a Kalman filter, which z. B. serves to reduce errors in real measured values and to provide estimates for non-measurable system variables.

Environment detection using radar sensors is often used in modern means of transportation. This is based on the emission of bundled electromagnetic waves (radar waves or radar signals) and their reflection, e.g. B. by other road users, obstacles on the road or the edge of the road. The differentiation of obstacles or objects such. B. other road users, traffic signs, road markings, peripheral buildings, crash barriers and the like is of great importance to determine when z. B. a braking or steering intervention is to be initiated.

Printed state of the art

From the U.S. 6,751,547 B2 a method for accurately estimating the geometry of a vehicle's forward path is known, which is based on a two-clothoid road model. Here road data provided by a camera or a radar system is collected. A measurement transfer function of the two-clothoid road model is then calculated using the road data. The near and far range clothoid coefficients are estimated simultaneously and the forward path of the vehicle is estimated from the data provided by the two clothoid model.

the U.S. 6,718,259 B1 discloses a method for estimating the geometry of a vehicle's forward path using an adaptive Kalman filter bank and a two-clothoid road model. A number of Kalman filters are used here, with weighting factors being provided for each filter which indicate the probability that the upcoming road geometry will match the road model assumed in the filter. After each filter has been assigned a weighted value, the weighted value road models are fused using a fusion element so that a weighted road model can be output.

Furthermore, the DE 10 2016 107 705 A1 a method in which a path for an autonomously driving vehicle is planned using Delaunay triangulation, collecting all detections including static and moving objects. Then the triangulation method and looking for triangle edges (triangle segments) that lie on the road surface and meet a set of criteria, one of the criteria being that each edge is not a road boundary edge. After finding the possible edges or the possible paths, the vertices of these edges are then extracted, at which the path is planned. A function of the various path costs is then estimated, choosing the path with the lowest cost.

Other methods, which are used to estimate the geometry of a movement path of a means of locomotion, are from DE 10 2015 013 084 A1 and the DE 10 2013 201 796 A1 known.

Furthermore, the DE 10 2018 215 448 B3 a method for estimating the geometry of a movement path of a means of locomotion according to the preamble of claim 1.

A problem with the known methods is that such algorithms often fail in urban scenarios in which there are multiple road corridors. The vehicle can usually choose different road corridors or routes, e.g. B. in an intersection, and each of these paths must be evaluated. However, the algorithms known from the prior art do not contain any additional information as to whether the roads or roads ahead are practical (i.e. can be driven on with little effort), maneuverable (i.e. the number of maneuvers required to complete the path) and passable (i.e. the driving corridor is like this wide for the vehicle to drive through). Due to the fact that there is not only one way in urban scenarios and each of the ways has to be evaluated, there is a particular interest in providing a method that overcomes these disadvantages.

Object of the present invention

Based on the prior art, the object of the present invention is now to provide a method in which the estimation of the geometry of the movement path, in particular in urban scenarios, is improved in a simple and cost-effective manner and which eliminates the disadvantages of the prior art technology can be overcome.

solution of the task

The above object is achieved by the entire teaching of claim 1 and the independent claim. Expedient developments of the invention are claimed in the dependent claims.

In the method according to the invention for estimating the geometry of the movement path of a means of transportation, in particular a vehicle, sensor data are collected by means of a sensor, the geometry of the movement path being estimated using the sensor data. This is done in that, in particular, static targets or objects along the movement path are determined using the sensor data and location points are defined for the respective position of the targets and the sensor. Furthermore, a polygon is determined based on the location points, z. B. by using a definable number of location points as corner points of the polygon. In particular, the polygon can include location points on each side of the street. Then the polygon is used to estimate the geometry of the movement path, i. H. the inner road boundary points can e.g. B. be determined for both road boundaries. This determination can e.g. B. be implemented in the form of an algorithm, i. H. With the aid of the invention, the inner road boundary of the road can be determined or calculated based on the sensor measurements. Because a number of polygons are also determined, in particular continuously, so that an entire polygon network is determined, the polygon network can be used to estimate the geometry of the movement path. The method according to the invention has the following method steps: Step 1, in which an ego point, which indicates the sensor position, is assigned to the detected detection points; Step 2, in which the polygon mesh is created using the detection points; Step 3 where the polygons are marked e.g. B. counted and numbered or the like; Step 4, in which the edges of the polygons are weighted, in particular as a function of at least one edge parameter; Step 6, in which the edges are removed according to their weighting, the edges in particular being removed at which the movement path is not possible or only possible to a limited extent, for example this can be done by falling below or exceeding a certain weighting value or weighting factor; Step 7, in which possible circumnavigations are detected by recognizing cycles within the polygon network, and step 8, in which finally the movement path through the polygon network is determined on the basis of the recognized cycles. The method and the algorithm according to the invention offer the advantage that the search for street corridors, circular arcs and cross streets in the static environment is made particularly easier. In addition, the quality of each road corridor is also estimated, and impassable corridors can be eliminated, so that the quality of selection is improved. Such features were not present in known methods or algorithms for identifying road corridors. In addition, the algorithm has a low computational complexity and is easy to implement or retrofit. Furthermore, the method is not dependent on the side classification or on the calculation of previous radar cycles. The method according to the invention can thus also be used for classifying or estimating the trajectory or movement path geometry in dynamic scenarios, such as e.g. B. in the case of road border expansion or narrowing, road construction work, missing crash barriers or the like.

According to a preferred embodiment, a radar sensor is provided as a sensor, which generates radar detections due to the emission of bundled electromagnetic waves (radar waves or radar signals) and their reflection, z. B. to other road users, obstacles on the road or the edge of the road. However, other sensors known from the prior art can also be provided, such as e.g. B. camera, ultrasonic or lidar sensors, whose detection points are fed to the algorithm.

It has proven to be particularly advantageous if the polygon is a triangle, since this can be calculated extremely easily with little computing effort. In the same advantageous manner, an entire polygon network can be created using triangular formations. This can be done in a simple way using a Delaunay triangulation or Delaunay triangle formation, as already described in DE 10 2018 215 448 B3 described.

The method may further include step 5, where the edges are mapped and labeled as terminals. As a result, the method can be made even safer and simplified.

The edge length, the edge angle, the angle of the road surface and/or the centroid angle can preferably be provided as edge parameters.

Conveniently, the path of movement can be determined by selecting the shortest path through the polygon mesh. As a result, the selection can be simplified accordingly.

According to a special embodiment of the method, the detection points can be grouped and displayed as polylines, so that a restricted polygon network is created using the polylines, with the polylines enclosing the grouped detection points. The method can be simplified to a particular degree by using a restricted polygon mesh or a restricted Delauney triangulation, as a result of which the calculation security can be improved and computing capacities can be saved.

Furthermore, the present invention includes a system for estimating the geometry of the movement path of a means of transportation. For this purpose, the system has a sensor for generating sensor data, in particular a radar sensor for generating radar detection points, and a control device. The geometry of the movement path is then estimated on the basis of the sensor data or the detection points, in that the control device is set up to receive the sensor data of the sensor and process them further in accordance with the method sequence according to the invention. The control device can expediently be set up in such a way that it can access actuators of the ego vehicle in order to carry out corresponding driving and assistance functions in a supportive and/or (partly) autonomous manner.

The method according to the invention can expediently be a purely computer-implemented method, with the term “computer-implemented method” in the sense of the invention describing a flow plan or procedure that is implemented or carried out using a computer. The calculator, such as B. a computer, a computer network, a control unit (z. B. ECU or Electronic Control Unit or ADCU or Assisted & Automated Driving Control Unit) or a computing device therein or any other programmable device known from the prior art, can process the corresponding data using programmable calculation rules. With regard to the method according to the invention and the system according to the invention, the essential properties z. B. be caused by a new program, new programs, an algorithm or the like, which is executed on the control unit.

character list

• 1 eine vereinfachte schematische Darstellung eines Fahrzeuges, bei dem eine Schätzung der Geometrie eines Bewegungsweges anhand des erfindungsgemäßen Verfahrens erfolgt;
• 2 eine vereinfachte schematische Darstellung von statischen Radardetektionen in einer Punktwolke;
• 3 eine vereinfachte schematische Darstellung der Punktwolke aus 2 mit gekennzeichnetem Ego-Punkt S (Schritt 1);
• 4 eine vereinfachte schematische Darstellung der Punktwolke aus 3 mit erfolgter Delaunay-Triangulation über allen statischen Punkten (Schritt 2);
• 5 eine vereinfachte schematische Darstellung der Punktwolke aus 4 mit nummerierten Dreiecken (Schritt 3);
• 6 eine vereinfachte schematische Darstellung der Punktwolke aus 4 mit nummerierten Dreiecken und gewichteten Kanten als Buchstaben markiert (Schritt 4);
• 7 eine vereinfachte schematische Darstellung der Punktwolke aus 5 als indirekter und gewichteter Graph, bei dem die Endkanten der Triangulation als Terminals t1-t6 gekennzeichnet sind (Schritt 5);
• 8 eine vereinfachte schematische Darstellung der Punktwolke aus 6 und des Diagramms aus 7, wobei undurchführbare Kanten der Triangulation im Graph entfernt werden (Schritt 6);
• 9 eine vereinfachte schematische Darstellung der Erkennung von Kreisen durch die Identifizierung von Zyklen in der Grafik (Schritt 7);
• 10 eine vereinfachte schematische Darstellung der finalen Ausgestaltung des kürzesten Weges vom Ego-Punkt S nach t3 aus 19 (Schritt 8);
• 11 eine vereinfachte schematische Darstellung einer Ausgestaltung einer eingeschränkten Delaunay-Triangulation;
• 12 eine vereinfachte schematische Darstellung einer Ausgestaltung der eingeschränkten Delaunay-Triangulation aus 11 als indirekter Graph (Gewichtungen werden der Übersichtlichkeit halber nicht gezeigt);
• 13 eine vereinfachte schematische Darstellung der eingeschränkten Delaunay-Triangulation aus 12, wobei der kürzeste Weg durch die Triangulierung durch Entfernen von Pfaden dargestellt ist, sowie
• 14 eine vereinfachte schematische Darstellung einer Ausgestaltung einer Kreuzungserkennung.

In the following, the invention is explained in more detail by means of expedient exemplary embodiments. Show it:

• 1 a simplified schematic representation of a vehicle in which the geometry of a movement path is estimated using the method according to the invention;
• 2 a simplified schematic representation of static radar detections in a point cloud;
• 3 a simplified schematic representation of the point cloud 2 with marked ego point S (step 1);
• 4 a simplified schematic representation of the point cloud 3 with completed Delaunay triangulation over all static points (step 2);
• 5 a simplified schematic representation of the point cloud 4 with numbered triangles (step 3);
• 6 a simplified schematic representation of the point cloud 4 with numbered th triangles and weighted edges marked as letters (step 4);
• 7 a simplified schematic representation of the point cloud 5 as an indirect and weighted graph with the end edges of the triangulation labeled as terminals t1-t6 (step 5);
• 8th a simplified schematic representation of the point cloud 6 and the diagram 7 , removing impracticable edges of the triangulation in the graph (step 6);
• 9 a simplified schematic representation of the detection of circles by identifying cycles in the graph (step 7);
• 10 a simplified schematic representation of the final embodiment of the shortest path from ego point S to t3 19 (step 8);
• 11 a simplified schematic representation of an embodiment of a constrained Delaunay triangulation;
• 12 Figure 12 shows a simplified schematic representation of an embodiment of the constrained Delaunay triangulation 11 as an indirect graph (weights are not shown for clarity);
• 13 presents a simplified schematic representation of the constrained Delaunay triangulation 12 , where the shortest path is represented by the triangulation by removing paths, and
• 14 a simplified schematic representation of an embodiment of an intersection detection.

Reference number 101 in 1 refers to an ego vehicle with a control device 102 (ECU, Electronic Control Unit or ADCU, Assisted and Automated Driving Control Unit), through which sensor control, sensor data fusion, environment and/or object recognition, trajectory planning and/or vehicle control, in particular (partial) can be done autonomously. To control the vehicle, the control device 102 can access various actuators (steering 103, motor 104, brake 105). The ego vehicle 1 also has various sensors (lidar 106, camera 107, radar 108 and ultrasonic sensors 109a-109d) for detecting the surroundings. Advantageously, the sensor data can be used for environment and object detection, so that various assistance functions such. B. emergency brake assistant (EBA, Emergency Brake Assist), distance following control (ACC, Automatic Cruise Control), lane departure control or a lane departure warning system (LKA, Lane Keep Assist) or the like can be realized. Furthermore, the assistance functions can also be executed via the control device 102 or another control unit provided for this purpose. The trajectory is planned based on an estimate of the geometry of the movement path according to the method according to the invention.

In the method according to the invention, the geometry of the movement path is estimated by determining or calculating the inner road boundary on the basis of sensor measurements. Exemplary embodiments are described below in which a radar sensor is used as the sensor. However, other sensors known from the prior art, such as e.g. B. lidar or camera sensors. In each scan cycle, the radar sensor provides a list of objects or targets with the corresponding relative position of the respective targets and their speed in relation to the ego vehicle, which includes the radar sensor and corresponds to the location 0 (x=0; y=0). . Based on the relative speed to the ego vehicle, the objects are then classified as static or mobile targets. In the present case, however, only the static targets to which a location point can be assigned are used for estimating the road boundary. The estimation then takes place by calculating or inserting a polygon network or a Delaunay triangulation (Delaunay triangle formation or Delaunay triangulation) on the basis of the position of the static targets or their location points and that of the ego vehicle. The creation of the polygon mesh or the Delaunay triangulation is carried out in particular by a method or a method configuration according to FIG DE 10 2018 215 448 B3 , to which direct reference is made.

In the following, the process flow according to the invention is based on the 2-10 shown. In 2 a point cloud from radar detections is shown first. In doing so, all drivable paths are to be determined, with an assessment of the feasibility of each path and, if possible, a scene image being determined. The first step is to first add an ego point (denoted here as S) representing the sensor position ( 3 ). In the second step 2, the polygon mesh is created or Delaunay triangulation ( 4 ), which in particular is placed over all static points. Then the polygons or triangles are marked (step 3), e.g. B. numbered or counted, as in 5 shown. In the next step (step 4), the borders/edges of the triangles can then be weighted, e.g. B. edge parameters of the polygons such. B. edge length, road edge angle, road surface angle, centroid angle and the like can be considered. exemplary is in 6 an example of Delaunay triangle triangulation is shown with numbered triangles and weighted edges. Thereafter, the edges of the triangulation can be mapped and labeled as terminals t1-t6, according to step 5. Such meshing of the triangles is presented as an indirect and weighted graph in 7 shown.

In a practical way, the edges can then be removed at which the movement path is not possible or only disadvantageously or conditionally possible (at high cost, borderline weighting factor or the like) (step 6), e.g. B. if the edge is too narrow or it is not possible to carry out certain driving maneuvers (e.g. turning or cornering maneuvers that are too steep with regard to the ego speed). In 8th the removal of impracticable edges in the triangulation (left) and in the graphic (right) is shown as an example. According to 8th become e.g. For example, the edges b and e (marked by an oval) are removed (and thus also the path through triangle 3), as these would require driving maneuvers that are too steep.

In step 7, the cycles can then be specified in the graph, in which each cycle represents a possible circumnavigation in the static environment, as in 9 shown (circumnavigation UR by detecting cycles in the graph). Furthermore, according to step 8, various heuristics can be used to carry out the search within the graphic or the tree structure, e.g. B. Breadth First Search, Greedy Method (Greedy Search) and the like. Here, statistics can be collected while driving through the tree (manuvreability or practicability). Each path in the tree is a possible movement path or road corridor (candidate), with the depth of a sub-tree reflecting the number of supported data points of an intersection. In 10 an assignment of the shortest path from S to t3 for triangulation is shown. The cycles can then be used to calculate the shortest path through the polygon mesh or the triangulation, so that this information can be used for trajectory planning. The algorithm particularly facilitates the search for suitable street corridors, circular arcs and cross streets in the static environment and also gives an estimate of the quality of the respective movement path or street corridor, whereby corridors that cannot be driven can be eliminated. The final configuration of the shortest path from S to t3 is in 10 shown.

Furthermore, the present algorithm can be expanded in particular for urban street scenarios. The detected objects or detection points are grouped (cluster) and displayed as polylines. A constrained Delaunay triangulation can then be applied, where the cluster polylines are considered to be bounded edges in the triangulation process. Constrained Delaunay triangulation is a generalization of Delaunay triangulation that forces certain required segments into the triangulation, with the polylines enclosing the grouped or clustered objects. Such a cluster process can be, for example, the 11 output the constrained Delaunay triangulation shown, where certain areas have been constrained (constraint ES). The polylines of the object clusters are considered as delimited edges in the triangle process.

Then the method steps 1-5 described can be applied to the restricted Delaunay triangulation. The result of the application to the restricted Delaunay triangulation is given as an indirect graph in 12 shown (for the sake of clarity without weighting). By subsequently removing the constrained edges associated with the objects of the graph (step 6), the weighted shortest path search algorithms from ego point S to terminals t1,...,t7 can be applied, as in 13 shown with the edges to be removed marked using scissors. The path can then be evaluated when running through the graph, e.g. B. by accumulating weights (e.g. centroid lengths). For example, as in 14 , the paths from S to t5 and t2 are analyzed, with triangle 22 being a crossing point KP, since two different paths pass through the two edges of triangle 22 here (see transition from 21 to 23 and from 21 to 20).

Reference List

101

ego vehicle

102

control device

103

steering

104

engine

105

brake

106

lidar sensor

107

camera

108

radar sensor

109a-109d

ultrasonic sensor

S

ego point

t1-t7

terminal

CP

crossing point

IT

restriction

QUOTES INCLUDED IN DESCRIPTION

This list of documents cited by the applicant was generated automatically and is included solely for the better information of the reader. The list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions.

Patent Literature Cited

• US 6751547 B2 [0005]
• US 6718259 B1 [0006]
• DE 102016107705 A1 [0007]
• DE 102015013084 A1 [0008]
• DE 102013201796 A1 [0008]
• DE 102018215448 B3 [0009, 0015, 0024]

Claims (10)

Method for estimating the geometry of a movement path of an ego vehicle (101), in which sensor data including detection points are recorded by means of a sensor and the geometry of the movement path is estimated using the sensor data, with targets along the movement path being determined using the sensor data, location points for the respective position of the targets and the sensor are determined, using the location points, several polygons are determined, in particular continuously, so that a polygon network is created, which is used to estimate the geometry of the movement path , characterized in that the method comprises the following method steps: step 1: an ego point (S) is assigned to the detected detection points, which indicates the sensor position, step 2: the polygon mesh is created using the detection points, step 3: the polygons are marked, step 4: the edges of the polygons are marked, especially in dependency at least one es edge parameters, weighted, step 6: the edges are removed according to their weighting, so that in particular the edges are removed where the path of movement is not possible or only possible to a limited extent, step 7: recording possible orbits (UR) by recognizing cycles within the polygon mesh, and step 8: Defining the movement path through the polygon mesh based on the recognized cycles. procedure after claim 1 , characterized in that at least one lidar sensor (106), a camera (107), a radar sensor (108) and/or an ultrasonic sensor (109a-109d) is provided as the sensor. procedure after claim 1 or 2 , characterized in that the polygon is a triangle or the polygons are triangles. procedure after claim 3 , characterized in that the polygon mesh is determined using a Delaunay triangulation. Method according to at least one of the preceding claims, characterized in that the method further comprises step 5, after which the edges are marked as terminals t1-t6. Method according to at least one of the preceding claims, characterized in that the edge length, the edge angle, the angle of the road surface and/or the centroid angle are provided as edge parameters. Method according to at least one of the preceding claims, characterized in that the movement path is defined by selecting the shortest path through the polygon network. Method according to at least one of the preceding claims, characterized in that detection points are grouped and displayed as polylines, so that a restricted polygon network is created using the polylines, the polylines enclosing the grouped detection points. Method according to at least one of the preceding claims, characterized in that System for estimating the geometry of a movement path of an ego vehicle (101), with at least one sensor for generating sensor data comprising detection points, and a controller (102), wherein the geometry of the movement path is estimated by the control device (102) using the sensor data of the sensor, in that the control device (102) carries out the estimation of the geometry of the movement path using a method according to one of the preceding claims.

Images