EP3646237A1 - Verfahren und vorrichtung zum bestimmen einer beschaffenheit einer oberfläche in der umgebung eines fahrzeugs - Google Patents
Verfahren und vorrichtung zum bestimmen einer beschaffenheit einer oberfläche in der umgebung eines fahrzeugsInfo
- Publication number
- EP3646237A1 EP3646237A1 EP18740122.9A EP18740122A EP3646237A1 EP 3646237 A1 EP3646237 A1 EP 3646237A1 EP 18740122 A EP18740122 A EP 18740122A EP 3646237 A1 EP3646237 A1 EP 3646237A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- curvature
- dimensional surface
- coordinates
- surface coordinates
- approximation
- 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
- 238000000034 method Methods 0.000 title claims abstract description 63
- 239000006185 dispersion Substances 0.000 claims description 2
- 238000005259 measurement Methods 0.000 description 11
- 238000011161 development Methods 0.000 description 7
- 230000018109 developmental process Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003746 surface roughness Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/06—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness for measuring thickness ; e.g. of sheet material
- G01B11/0608—Height gauges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
- G06T7/564—Depth or shape recovery from multiple images from contours
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/06—Road conditions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/06—Road conditions
- B60W40/064—Degree of grip
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/06—Road conditions
- B60W40/068—Road friction coefficient
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/36—Input/output arrangements for on-board computers
- G01C21/3602—Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
- G05D1/0251—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting 3D information from a plurality of images taken from different locations, e.g. stereo vision
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
- G06T7/593—Depth or shape recovery from multiple images from stereo images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
- B60W2050/143—Alarm means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
- B60W2050/146—Display means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
- B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
- B60W2420/403—Image sensing, e.g. optical camera
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2552/00—Input parameters relating to infrastructure
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
- G06T2207/30261—Obstacle
Definitions
- the present invention relates to a method for determining a condition of a surface in the vicinity of a vehicle.
- the method are by means of a
- the invention relates to a device for determining the nature of a surface in the vicinity of a vehicle.
- the device comprises a sensor arrangement, by means of which three-dimensional surface coordinates of the surface can be generated.
- the method and the device of the present invention are in particular for
- the present invention is therefore based on the object, a method and a
- Specify device of the type mentioned with which the nature of the surface in the environment of a vehicle, especially in the direction of travel of a vehicle, can be determined more accurately.
- this object is achieved by a method having the features of claim 1 and a device having the features of claim 14.
- the inventive method is characterized in that based on the three-dimensional surface coordinates an approximation of the curvature of the Surface is obtained in at least one direction and based on the curvature and / or vertical distances of the approximation of the curvature of the
- the surface coordinates include two
- Horizontal coordinates Further, they include a vertical coordinate or altitude coordinate which indicates, for a point defined by the horizontal coordinates, the height at which the surface is located.
- terms such as “up” and “down” refer to a vertical direction, i. H. on the direction of the effect of gravitational force on the earth.
- the characterization of the surface of the surface then becomes the curvature profile obtained in this way and / or vertical distances of the approximation of the
- Curvature of the three-dimensional surface coordinates determined. Since the curve or surface of the approximation need not pass through the three-dimensional surface coordinate on the basis of which the approximation was obtained, such a vertical distance may result.
- the vertical distance is thus the difference of the height coordinates of the three-dimensional surface coordinates and the curve or surface of the approximation for the same horizontal coordinates.
- the vertical distance also includes a sign, d. H. the information as to whether the curve or surface of the approximation lies above or below the three-dimensional surface coordinates.
- Curvature of the approximating curve or surface the nature of the surface can characterize that the surface can be classified with regard to a possible passability by the vehicle suitable.
- the inventive method even with a strong measurement noise in the detection of the surface in the vicinity of the vehicle to obtain a reliable determination of the surface profile. In this way, the condition of the surface in the vicinity of the vehicle can be reliably determined.
- the approximation of the curvature profile is carried out on the basis of an approximating spline curve.
- the support points are in this case of the generated by means of the sensor array three-dimensional
- the approximating spline curve describes a smooth curve, which is determined by the support points, without the curve necessarily having to pass through the support points.
- the approximating spline curve may be a so-called base spline curve, also referred to as a B-spline curve.
- a base spline curve a base function is used, for example, to determine a point at a particular point on the curve, the individual interpolation points are weighted using the base function values at that point. The weighting is chosen in particular such that the influence of a support point decreases with increasing distance from the point.
- a NURBS non-uniformly rational B-spline
- Bezier splines or so-called P-splines can be used, where an additional cost function is applied to the base spline curve.
- the curvature profile of the surface can advantageously be determined very accurately and reliably at least in a certain direction.
- the classification can then be carried out as a function of the curvature of the approximating spline curve.
- an approximation of the curvature profile in the transverse direction is obtained based on the three-dimensional surface coordinates, which extend in the transverse direction to a direction of travel of the vehicle.
- the classification is then carried out as a function of the curvature in the transverse direction.
- Transverse direction is particularly important for determining a lateral boundary of a roadway.
- An unpaved road can be, for example, ditches, slopes or other
- the classification is carried out as a function of the longitudinal curvature.
- Direction of travel of the vehicle safely and reliably identified by the classification. This is particularly important in the automatic driving of the vehicle, so that the vehicle does not collide with an obstacle in the direction of travel of the vehicle.
- an approximation of the curvature profile of the entire surface is obtained based on the surface coordinates.
- a continuous curved surface is thus calculated, which represents the real surface in the surroundings of the vehicle.
- a level map which of the
- the curvature can be determined in all directions and used to classify the
- Curvature course determined a passable area.
- passable area becomes a carriageway and an adjacent area one
- Road environment assigned. In an automatic driving of the vehicle can be based on This drivable area the vehicle are controlled so that only driving maneuvers are performed, which ensure that the vehicle is always on the passable area, ie the road.
- a roadway Under a roadway is understood in this document a surface which is suitable for driving through the vehicle.
- the roadway is in particular an unpaved roadway or a so-called offroad roadway.
- Under the lane environment is understood to be adjacent to the lane area, in particular the area laterally adjacent to the lane with respect to the direction of travel of the vehicle.
- a group of three-dimensional surface coordinates is assigned to a first class of the classification, which on average are arranged so far below the approximated curvature profile that a first limit value is exceeded.
- Such surface coordinates relate in particular to a surface, as formed by a pothole.
- the limit value is therefore set so that the measured surface coordinates are very far below the limit value
- the group of surface coordinates can be assigned to the first class only if they are in the drivable area of the surface, i. H. on the roadway. Only in this case, for example, a pothole for driving the vehicle relevant.
- a second class of the classification is assigned a region of the surface in which an increasingly sloping curve is determined in a defined first interval in the transverse direction.
- the second class is thus characterized by a more pronounced curvature, for example in the spline curve.
- the second class can therefore be used to determine areas that actually correspond to a slope or a ditch.
- Such slopes or trenches are relevant in particular laterally next to the roadway.
- the first interval is therefore defined in particular in the transverse direction to the direction of travel. In this way, a slope or a ditch next to the roadway, d. H. in the roadway environment. Especially such slopes or trenches are difficult to detect, if only the three-dimensional surface coordinates are taken into account, which have been generated by the sensor array.
- a third class of the classification is assigned a region of the surface in which an increasingly ascending curvature course and an increasingly sloping curvature course in a defined second interval of a surface direction is determined.
- the second interval is defined in particular in a surface direction on the road.
- a fourth class of classification is assigned a region of the surface in which an abrupt increase in the height coordinate of a plurality of adjacent surface coordinates is determined. Such an abrupt increase in altitude coordinate occurs at larger obstacles, such as parked
- Vehicles or trees Vehicles or trees.
- the detection of the area of the surface of the fourth class can serve on the one hand to delineate the road environment from the roadway. On the other hand, obstacles in the direction of travel of the vehicle can be detected in this way.
- the vertical deviation of the approximation of the curvature profile can be determined for each surface coordinate.
- Curvature course of the three-dimensional surface coordinates is then identified an obstacle and the movement of the obstacle is determined based on the time course of the obstacle associated three-dimensional surface coordinates.
- Moving Obstacles can be tracked in this way by means of several series of measurements in which the obstacle is detected.
- the positions of the bearing surfaces of the wheels of the vehicle on the surface are determined.
- the probable trajectories of the positions of the bearing surfaces of the wheels of the vehicle are then determined, and for the expected trajectories the navigability of the surface is checked on the basis of the classification of the surface coordinates belonging to the trajectories.
- the positions of the bearing surfaces of the wheels of the vehicle can be determined geometrically, since the position of the sensor arrangement is known to the bearing surfaces of the wheels of the vehicle. From the direction of movement and, if appropriate, the speed of the vehicle, the probable trajectories of the bearing surfaces of the wheels can then be determined. It can now, as explained above, be determined whether there are potholes or larger obstacles on these probable trajectories, which limit the trafficability of the surface or which cause the surface is no longer passable. This information can then be used during automatic driving of the
- the three-dimensional surface coordinates are generated by means of a stereo image. This has the advantage that the three-dimensional surface coordinates by means of a very cost-effective
- the three-dimensional surface coordinates obtained by means of a stereo image have the disadvantage that the measurement inaccuracies are too large for the obtained three-dimensional surface coordinates to be sufficient as the basis for the automatic driving control.
- slopes and other lateral boundaries of a roadway can only be recognized insufficiently.
- potholes and trenches are no longer reliably detected if the measuring noise is too great.
- the generated three-dimensional surface coordinates are processed further. An approximation of the curvature profile of the surface is carried out.
- the data of the stereo image can be prepared so that dangerous areas, such.
- the three-dimensional surface coordinates can be determined by means of a
- Laserscanners are obtained, which scans the surface in the direction of travel in the transverse direction.
- the approximation of the curvature profile ensures that such surface textures can be reliably detected.
- the use of the laser scanner also has the advantage that abrupt height changes in the surface can be detected very reliably.
- the inventive device for determining the condition of a surface in the vicinity of a vehicle is characterized by a computing unit which is designed to obtain an approximation of the curvature profile of the surface in at least one direction based on the three-dimensional surface coordinates, and a classification unit, by means of which Curvature and / or vertical distances of the approximation of the curvature of the three-dimensional
- a classification of the three-dimensional surface coordinates can be performed to identify the nature of the surface.
- the device according to the invention is designed as described above
- the sensor arrangement of the device according to the invention comprises in particular a
- Stereo camera Furthermore, a scanning laser measuring system or a laser-cut-based measuring system can also be used as the sensor arrangement.
- Measuring system has the advantage that it can detect the ground level very accurately. However, it has only a very limited range. In addition, the space requirement of such
- the method and the device according to the invention are used in particular in a vehicle, in particular a truck, which has a system for automatic driving.
- the vehicle can drive in this way without drivers automatically on a dirt road.
- the system for automatic driving is supported by the method according to the invention or the device according to the invention. It will provide information about the nature of the surface in the direction of travel of the
- Vehicle delivered It is determined which area of this surface is passable and thus suitable as a roadway. Furthermore, the nature of the roadway environment is determined, so that it can be taken into account in the control of the vehicle which surface in the surroundings of the vehicle is suitable for driving maneuvers during automatic driving.
- the device according to the invention can be integrated in the vehicle which has the system for automatic driving.
- the sensor arrangement detects the
- FIG. 1 shows a situation in which the method according to the invention can be used
- FIG 2 shows another situation in which the inventive method
- FIG. 3 shows schematically the structure of an embodiment of the
- FIG. 4 shows an example of a reconstructed height map, as in a
- FIG. 5 shows another example of a reconstructed height map, as obtained in the exemplary embodiment of the method according to the invention
- FIG. 6 illustrates the approximation of the curvature profile of FIG
- FIG. 7 illustrates the approximation of the curvature profile of FIG.
- Figure 8 illustrates the approximation of the curvature of the
- Procedure is carried out when driving on a highway with side trenches.
- a vehicle 1 is driving on a dirt surface.
- the vehicle 1 may drive automatically without the assistance of a driver.
- the unpaved surface comprises a roadway 2 and laterally adjacent thereto a roadway environment 3.
- This roadway environment 3 limits the roadway 2.
- the roadway environment 3 comprises trenches 4 laterally adjacent to the roadway 2.
- the roadway 2 is bounded laterally by a mound 5 and by trees 16 or pylons.
- Detected device which area of the surface in the direction of travel of the vehicle 1 is passable and therefore the roadway can be assigned. Furthermore, the nature of the surface of the roadway 2 and the nature of the roadway environment 3 can be determined.
- the device 6 comprises a stereo camera 7 and a connected thereto
- the stereo camera 7 and the image processing unit 8 form a sensor arrangement, by means of which three-dimensional surface coordinates of the surface in the environment of the vehicle 1, in particular in the direction of travel of the vehicle 1, can be generated.
- the sensor arrangement can thus be a three-dimensional height map of
- the image processing unit 8 is connected to a computing unit 9, to which it transmits the three-dimensional surface coordinates.
- the arithmetic unit 9 is designed based on the three-dimensional surface coordinates an approximation of
- the arithmetic unit 9 is connected to a classification unit 10, by means of which, on the basis of the curvature profile and the vertical distances of the approximation of the
- Curvature course of the three-dimensional surface coordinates a classification of the surface coordinates for delineation of the lane 2 of the lane environment 3 and for characterizing the nature of the surface is carried out, as will also be explained later with reference to the embodiment of the inventive method.
- the sensor assembly may also be a scanning
- Laser measuring system use a laser-cut-based measuring system or other measuring system, with which three-dimensional surface coordinates can be obtained.
- the device 6 may finally be coupled to a controller 13 for automatically driving the vehicle 1.
- a controller 13 for automatically driving the vehicle 1.
- To this controller 13 all data on the nature of the surface, in particular the lane 2 and the lane environment 3, transmitted.
- the stereo camera 7 of the sensor arrangement receives chronologically consecutive stereo images from the vehicle 1 in the direction of travel. Such images in different driving situations are shown in FIGS. 4, 5, 7 and 8.
- the image processing unit 8 processes the Stereo image in a known per se and obtains three-dimensional surface coordinates. In this case, the height coordinate for a horizontal grid is determined for each point of the grid. Between the points of the horizontal grid there is a distance, which is determined by the resolution of the stereo camera and the subsequent image processing.
- the reconstructed height maps formed from the three-dimensional surface coordinates obtained from the images of the stereo camera 7 are shown as mesh 17 in the images shown in FIGS. 4, 5, 7 and 8.
- the three-dimensional surface coordinates include coordinates in the transverse direction to the direction of travel. These three-dimensional surface coordinates in the transverse direction are also called row of the three-dimensional height map, that of the three-dimensional
- the three-dimensional surface coordinates include longitudinal coordinates to the direction of travel. These are also called the column of the three-dimensional height map.
- FIG. 6 schematically shows such spline curves 14 for a plurality of lines of a three-dimensional height map.
- the approximating spline curve 14 is characterized by the fact that, although it is separated from its support points, i. H.
- the three-dimensional surface coordinates of a line but not necessarily determined by these three-dimensional
- the course of the spline curves 14 now allows a division of the measured three-dimensional surface coordinates, ie the three-dimensional height map, based on various criteria. On the one hand, the vertical distance of a three-dimensional surface coordinate to the spline curve 14 can be taken into account. On the other hand, the curvature of the spline curves 14 can be taken into account.
- Classification unit 10 is performed:
- a vehicle accessible to the vehicle 1 range is first determined.
- a contiguous passable area is defined as carriageway 2.
- the non-drivable environment of this passable area is called
- this three-dimensional surface coordinate is classified as an outlier and is subsequently disregarded.
- the obtained three-dimensional surface coordinates can also be temporally filtered to correct misclassifications of individual three-dimensional surface coordinates.
- a group of three-dimensional surface coordinates, which on average are arranged so far below the approximated curvature profile, ie below the spline curves 14, that a first limit value is exceeded, is assigned to a first class.
- surface coordinates fall, which form a pothole, which should not be run over by the vehicle 1.
- the first limit value can be obtained by making measurements in advance on potholes having a certain depth.
- three-dimensional surface coordinates are considered, which run in the longitudinal direction to the direction of travel.
- a region of the surface is determined in which an increasingly sloping curvature profile was determined in a defined first interval in the transverse direction.
- This area is assigned to a second class of the classification.
- the second class is intended to cover in particular lateral slopes and ditches.
- the first interval therefore runs in the transverse direction.
- the curvature is determined using a spline curve 14, which consists of a line of the three-dimensional height map of the three-dimensional
- a region of the surface is determined in which an increasingly increasing curvature profile and an increasingly decreasing curvature profile are determined in a defined second interval of a surface direction.
- This area is assigned to a third class of the classification.
- This third class features bumps, smaller potholes or fouling.
- the second interval is chosen so that it runs in any surface direction and is arranged on the roadway 2.
- the third class may alternatively include only areas of the surface, which is characterized by a more increasing curvature in the spline curve 14.
- an area of the surface is determined in which an abrupt increase in the
- the fourth class includes larger obstacles such as parked vehicles, trees or the like. Such larger obstacles can be determined both on the roadway 2 and in the roadway environment 3.
- the road condition is determined based on the value of the dispersion of the vertical spacing of the spline curves 14 from the respective surface coordinates. In this way, a value for the road surface roughness and a value for the average road surface unevenness can be obtained.
- the three-dimensional surface coordinates are generated by the sensor arrangement in temporal succession. As the vehicle 1 travels, stereo images are sequentially taken and the three-dimensional surface coordinates are obtained therefrom. For each stereo image, ie for each set of three-dimensional height coordinates, the Curvature profile approximated by spline curves 14. Based on this curvature and the vertical distance of the spline curve 14 from the respective three-dimensional
- Surface coordinate can be identified as explained above, an obstacle.
- the movement of the obstacle can then be determined from the time profile of the three-dimensional surface coordinates assigned to the obstacle. Obstacles can be tracked in this way.
- the classification unit 10 thus generates a classification of the three-dimensional
- FIG. 4 shows an example in which the image taken by the stereo camera 7 is shown in the left part. Superimposed on this image is a reconstructed elevation map, d. H. the network 17 formed from the three-dimensional surface coordinates, superimposed. Furthermore, a lateral height profile 18 is shown in the picture. Right of the picture is the
- FIG. 5 shows the same for a driving situation on an unpaved road with lateral trenches.
- the picture at the bottom right in FIG. 5 shows the classification of
- the image recorded by the stereo camera 7 is shown at the bottom in a driving situation of an off-road track with a side gradient to the right of the roadway 2. Also in this case, the three-dimensional height map is superimposed on the basis of a network 17 in the image.
- the spline curves 14 for representing the roadway 2 and the roadway environment 3 are shown.
- the right part of these spline curves 14 can be determined by the curvature of the spline curves 14 and based on the vertical distances of three-dimensional surface coordinates of the spline curves 14 are closed on the strong lateral slope. This area is classified as not passable.
- FIG. 8 shows the image of the stereo camera 7 for a driving situation on a country road with lateral trenches on the right and left of the roadway 2.
- the three-dimensional height map is shown by means of a network 17.
- the associated spline curves 14 for representing the environment are shown.
- the lateral trenches are detected and the corresponding three-dimensional surface coordinates are classified accordingly.
- the bearing surfaces 1 1 of the wheels of the vehicle 1 are determined on the surface. It is a spatial reference between the three-dimensional surface coordinates and the bearing surfaces 1 1 of the wheels of the
- Vehicle 1 from the spatial arrangement of the bearing surfaces 1 1 of the wheels relative to the stereo camera 7 and the viewing angle of the stereo camera 7 determined.
- Control unit 13 are the probable trajectories of
- Support surfaces 1 1 of the wheels of the vehicle 1 determined. For this area, d. H. for the expected trajectories, the trafficability of the surface is then checked by the classification unit 10. It becomes the classification of the three-dimensional
- Classification unit 10 transmitted data ensure that the vehicle 1 automatically on a passable area, ie on the lane 2, is moved.
- the road environment 3 can be taken into account during driving maneuvers.
- a tree which laterally delimits the roadway 2 may be taken into account so that the automatically moving vehicle 1 does not collide laterally or upwardly with this obstacle, even if the bearing surfaces 11 of the wheels of the vehicle 1 are completely on the roadway 2 .
- the inventive method and the device 6 according to the invention are used in particular in an off-road use of trucks. For example, they can be used in trucks used in mining. The
- Trucks may in this case be equipped with an automatic driving system which uses the device 6 according to the invention and the method according to the invention to control the truck. Furthermore, that can
- Method according to the invention and the device 6 according to the invention can be used in an off-road use of a passenger car and when driving on unpaved ground. It can be provided in this way an assistance system that reliably detects obstacles and potholes and outputs the driver information about the road surface.
- inventive method and apparatus 6 can be used in an off-road use of motorcycles and motorbikes on unpaved ground. Also in this case, an assistance system can be provided which reliably detects obstacles and potholes. When used in motorcycles, the assistance system can point in particular to dangerous, particularly deep potholes and uneven ground.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Mathematical Physics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Electromagnetism (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102017114571.0A DE102017114571A1 (de) | 2017-06-29 | 2017-06-29 | Verfahren und Vorrichtung zum Bestimmen einer Beschaffenheit einer Oberfläche in der Umgebung eines Fahrzeugs |
PCT/EP2018/067445 WO2019002482A1 (de) | 2017-06-29 | 2018-06-28 | Verfahren und vorrichtung zum bestimmen einer beschaffenheit einer oberfläche in der umgebung eines fahrzeugs |
Publications (1)
Publication Number | Publication Date |
---|---|
EP3646237A1 true EP3646237A1 (de) | 2020-05-06 |
Family
ID=62904416
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP18740122.9A Pending EP3646237A1 (de) | 2017-06-29 | 2018-06-28 | Verfahren und vorrichtung zum bestimmen einer beschaffenheit einer oberfläche in der umgebung eines fahrzeugs |
Country Status (5)
Country | Link |
---|---|
US (1) | US11386568B2 (de) |
EP (1) | EP3646237A1 (de) |
CN (1) | CN110770744B (de) |
DE (1) | DE102017114571A1 (de) |
WO (1) | WO2019002482A1 (de) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102021201589B4 (de) | 2021-02-18 | 2023-06-22 | Volkswagen Aktiengesellschaft | Steuerung eines Fahrzeugs abhängig von einem topographischen Merkmal einer Fahrbahnoberfläche |
DE102022109423A1 (de) | 2022-04-19 | 2023-10-19 | Valeo Schalter Und Sensoren Gmbh | Verfahren zur lateralen Lokalisierung eines Fahrzeugs auf einer Straße, Computerprogramm und Fahrerassistenzsystem |
CN118447018B (zh) * | 2024-07-05 | 2024-10-11 | 季华实验室 | 模具表面曲线识别方法、装置、电子设备及存储介质 |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8050863B2 (en) | 2006-03-16 | 2011-11-01 | Gray & Company, Inc. | Navigation and control system for autonomous vehicles |
JP5441549B2 (ja) * | 2009-07-29 | 2014-03-12 | 日立オートモティブシステムズ株式会社 | 道路形状認識装置 |
EP2574958B1 (de) * | 2011-09-28 | 2017-02-22 | Honda Research Institute Europe GmbH | Straßenterrain-Erkennungsverfahren und System für Fahrerhilfssysteme |
DE102012112164A1 (de) * | 2012-12-12 | 2014-06-12 | Continental Teves Ag & Co. Ohg | Videobasierte erkennung von hindernissen auf einer fahrbahn |
DE102012024874B4 (de) * | 2012-12-19 | 2014-07-10 | Audi Ag | Verfahren und Vorrichtung zum prädikativen Ermitteln eines Parameterwertes einer von einem Fahrzeug befahrbaren Oberfläche |
DE102013101639A1 (de) * | 2013-02-19 | 2014-09-04 | Continental Teves Ag & Co. Ohg | Verfahren und Vorrichtung zur Bestimmung eines Fahrbahnzustands |
DE102013220303A1 (de) * | 2013-10-08 | 2015-04-09 | Ford Global Technologies, Llc | Verfahren zum Ermitteln einer relativen Fahrbahnsteigung |
EP3295422B1 (de) * | 2015-05-10 | 2020-01-01 | Mobileye Vision Technologies Ltd. | Strassenprofile entlang eines prognostizierten weges |
TW201727417A (zh) * | 2016-01-26 | 2017-08-01 | 鴻海精密工業股份有限公司 | 分析路面曲度並結合資料記錄的自動行走建議系統及方法 |
-
2017
- 2017-06-29 DE DE102017114571.0A patent/DE102017114571A1/de not_active Withdrawn
-
2018
- 2018-06-28 US US16/627,036 patent/US11386568B2/en active Active
- 2018-06-28 CN CN201880043557.XA patent/CN110770744B/zh active Active
- 2018-06-28 EP EP18740122.9A patent/EP3646237A1/de active Pending
- 2018-06-28 WO PCT/EP2018/067445 patent/WO2019002482A1/de unknown
Also Published As
Publication number | Publication date |
---|---|
DE102017114571A1 (de) | 2019-01-03 |
US11386568B2 (en) | 2022-07-12 |
WO2019002482A1 (de) | 2019-01-03 |
CN110770744B (zh) | 2024-02-02 |
US20200126247A1 (en) | 2020-04-23 |
CN110770744A (zh) | 2020-02-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP2561419B1 (de) | Verfahren zur bestimmung des fahrbahnverlaufes für ein kraftfahrzeug | |
EP1928687B1 (de) | Verfahren und fahrerassistenzsystem zur sensorbasierten anfahrtsteuerung eines kraftfahrzeugs | |
EP1240533B1 (de) | Verfahren zur optischen überwachung der umgebung eines sich bewegenden fahrzeugs | |
DE112018001378T5 (de) | Verbesserungen bei der fahrzeugsteuerung | |
WO2013117186A1 (de) | Bestimmung einer beschaffenheit einer fahrbahnoberfläche mittels einer 3d-kamera | |
DE10326190A1 (de) | Vorrichtung und Verfahren zur Ermittlung einer räumlichen Ausrichtung eines Auflegers oder Anhängers | |
DE102011056671A1 (de) | Bestimmung eines Höhenprofils einer Fahrzeugumgebung mittels einer 3D-Kamera | |
EP3142913B1 (de) | Umfeldkarte für fahrflächen mit beliebigem höhenverlauf | |
DE102012107885A1 (de) | Verfahren zur Bestimmung eines Fahrspurverlaufs für ein Fahrzeug | |
WO2005081200A2 (de) | Erfassungsvorrichtung für ein kraftfahrzeug | |
DE102005052510A1 (de) | Fahrzeug-Steuer-/Regelobjekt-Bestimmungssystem | |
EP3646237A1 (de) | Verfahren und vorrichtung zum bestimmen einer beschaffenheit einer oberfläche in der umgebung eines fahrzeugs | |
DE112019001080T5 (de) | Verfahren und vorrichtung zur erfassung und verfolgung, objektklassifizierung und gelände-inferenz | |
DE102015116542A1 (de) | Verfahren zum Bestimmen einer Parkfläche zum Parken eines Kraftfahrzeugs, Fahrerassistenzsystem sowie Kraftfahrzeug | |
DE102014221034A1 (de) | Verfahren zum Erkennen einer bevorstehenden Kollision eines Fahrzeugs mit einem Objekt | |
DE102018212779A1 (de) | Verfahren und System zum Bestimmen und Anzeigen einer Watsituation | |
WO2012163631A1 (de) | Verfahren zum bestimmen einer nickbewegung einer in einem fahrzeug verbauten kamera und verfahren zur steuerung einer lichtaussendung zumindest eines frontscheinwerfers eines fahrzeugs | |
DE102019116892A1 (de) | Fahrspurereignisantizipation durch LiDAR-Straßenbegrenzungserfassung | |
DE112020000735T5 (de) | Fahrzeugsteuerungssystem und -verfahren | |
DE102019218479A1 (de) | Verfahren und Vorrichtung zur Klassifikation von Objekten auf einer Fahrbahn in einem Umfeld eines Fahrzeugs | |
DE102006007550A1 (de) | Vorrichtung und Verfahren zur Erkennung einer Fahrbahnmarkierung für ein Kraftfahrzeug | |
EP1944212A1 (de) | Verfahren und Vorrichtung zum Ermitteln potentiell gefährdender Objekte für ein Fahrzeug | |
EP3830519A1 (de) | Verfahren und system zum bestimmen und anzeigen einer watsituation | |
DE102019208507A1 (de) | Verfahren zur Bestimmung eines Überlappungsgrades eines Objektes mit einem Fahrstreifen | |
DE102019205484A1 (de) | Verfahren und Vorrichtung zum Erstellen eines Höhenprofils für einen von einem Fahrzeug zu befahrenden Bereich |
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: 20200129 |
|
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 MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
AX | Request for extension of the european patent |
Extension state: BA ME |
|
DAV | Request for validation of the european patent (deleted) | ||
DAX | Request for extension of the european patent (deleted) | ||
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
17Q | First examination report despatched |
Effective date: 20210615 |