JP3738719B2 - Obstacle map creation device for vehicles - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to an apparatus for detecting an obstacle existing around a vehicle and creating an obstacle map.
[0002]
[Prior art]
In the obstacle recognition apparatus described in Japanese Patent Laid-Open No. 10-112000, each point in the measurement range of the distance measurement sensor is “obstacle”, based on the distance information to the obstacle measured by the distance measurement sensor. It is determined whether the area is “no obstacle” or “unknown”. The relationship between this determination result and the presence or absence of an actual obstacle is stored in advance as a determination correct answer rate, and the probability of the determination result of “with obstacle” and “without obstacle” is calculated based on the determination correct answer rate. To create a map of obstacles.
[0003]
[Problems to be solved by the invention]
However, in the above-described conventional obstacle recognition apparatus, it is necessary to calculate in advance the correct answer rate for the presence or absence of an obstacle by the distance measurement sensor. Further, in this method, when the obstacle recognition device is mounted on the vehicle, there is a problem that it is difficult to accurately recognize the obstacle corresponding to changes in the speed and direction of the vehicle.
[0004]
An object of the present invention is to provide a vehicle obstacle map creation device that can accurately grasp the structure and arrangement of an obstacle based on the characteristics of a distance measuring device and vehicle behavior.
[0005]
[Means for Solving the Problems]
(1) The invention according to claim 1 is based on a distance measuring device that measures a distance to an object, a vehicle information detecting device that detects a vehicle behavior, and a vehicle behavior detected by the vehicle information detecting device. A position information conversion storage device for converting the distance information to the object measured by the method into the position information of the object and storing it; A classification device for classifying the position information of the plurality of objects stored in the position information conversion storage device for each object; , A noise removing device for removing noise information based on the position information classified by the classification device; Said Noise information has been removed by the noise removal device The object is achieved by including an obstacle map generation device that generates an obstacle map based on the position information.
(2) The invention according to claim 2 is the vehicle obstacle map creation device according to claim 1, further comprising a distance measurement characteristic storage device for storing the measurement characteristic of the distance measurement device, wherein the noise removal device is a vehicle information detection device. The noise information is removed based on the vehicle behavior detected by the above and the measurement characteristics stored in the distance measurement characteristic storage device.
(3) The invention according to claim 3 is the obstacle map creation device for vehicle according to claim 2, wherein the measurement characteristics stored in the distance measurement characteristic storage device are the maximum detection distance, detection width, detection angle, and distance of the distance measurement device. It is one of resolution, measurement cycle, or a combination thereof.
(4) According to a fourth aspect of the present invention, in the vehicle obstacle map creating device according to any one of the first to third aspects, the vehicle behavior detected by the vehicle information detecting device is a position, a direction, and a speed of the vehicle. Features.
(5) The invention of claim 5 is the vehicle obstacle map creation device according to any one of claims 1 to 4, Classification The device In order to classify the position information of the objects by object, The position information of the object included in the search area determined based on the position of the distance measuring device and the position of the maximum detection distance is detected. put out It is characterized by that.
(6) The invention according to claim 6 is the obstacle map creation device for vehicle according to claim 5, wherein the width of the position information search region in the vehicle traveling direction is determined based on the vehicle speed and the measurement period of the distance measuring device. It is characterized by changing.
(7) The invention of claim 7 is claimed Any one of 1-6 In the vehicle obstacle mapping system of Classification device Is Classified by object The position information of the object is further classified by detecting the position information of the object having a linear structure from the position information of the plurality of objects.
(8) The invention according to claim 8 is the obstacle map creation device for a vehicle according to any one of claims 1 to 7, wherein the obstacle map generation device may have an object based on the classified location information. A plurality of areas are set according to, and an obstacle map including control / alarm level information is generated for each set area.
[0006]
【The invention's effect】
As described above in detail, the present invention has the following effects.
(1) According to the inventions of claims 1 to 7, after the distance data to the object is converted into the position information of the object based on the vehicle behavior, the position information of the object Categorized by object, remove noise information based on the classified location information, Since the obstacle map is created, the distance data that becomes noise can be eliminated, and the structure and arrangement of the obstacle can be accurately grasped.
(2) According to the invention of claim 2, further comprising a distance measurement characteristic storage device for storing the measurement characteristic of the distance measurement device, Classification The device removes noise information based on the vehicle behavior detected by the vehicle information detection device and the measurement characteristics stored in the distance measurement characteristic storage device, so that the structure and arrangement of obstacles can be grasped more accurately. Can do.
(3) According to the invention of claim 3, the measurement characteristic is any one of the maximum detection distance, detection width, detection angle, distance resolution, measurement cycle of the distance measurement device, or a combination thereof. It is possible to classify the position information of the object by accurately removing noise information based on the measurement characteristics.
(4) According to the invention of claim 4, since the vehicle behavior information is the position, orientation, and speed of the vehicle, it is possible to accurately grasp the positional relationship between the vehicle and the object, and to accurately identify the object. Can be classified.
(5) According to the invention of claim 5, since the area for classifying the position information of the object is a search area determined based on the position of the distance measuring device and the position of the maximum detection distance, the distance measuring device Thus, it is not necessary to process information existing in an undetectable area, and the processing time can be shortened.
(6) According to the invention of claim 6, the width of the position information search region in the vehicle traveling direction is changed based on the speed of the vehicle and the measurement period of the distance measuring device. And is not affected by changes in the measurement cycle.
(7) According to the invention of claim 7, the position / structure of the obstacle can be grasped more accurately by detecting the position information of the object having the linear structure and further classifying the position information.
(8) According to the invention of claim 8, since the obstacle map includes the control / alarm level corresponding to the area where the object may exist, the vehicle and the obstacle can be easily and accurately identified. The possibility of contact can be detected.
[0007]
DETAILED DESCRIPTION OF THE INVENTION
FIG. 1 is a diagram showing a configuration of an embodiment of a vehicle obstacle map creating apparatus according to the present invention. The obstacle map creation device for a vehicle includes a distance measurement device 101, a vehicle information detection device 201, a position information conversion storage device 301, a distance measurement characteristic storage device 401, a noise removal device 501, and an obstacle map generation device 601. With. The distance measuring device 101 is a device that measures the distance to an obstacle (object) existing around the vehicle, and an ultrasonic sensor, a microwave radar, a laser radar, or the like can be used. The distance measuring devices 101 are mounted on the left and right positions one by one in a direction transverse to the traveling direction of the vehicle. In the present embodiment, as shown in FIG. 2, the vehicle 1 is mounted on the right and left sides of the rear wheel of the vehicle 1 facing outward. The measurable range by the distance measuring apparatus 101 is within the range of the ellipse 102 shown in FIG.
[0008]
As shown in FIG. 3, the vehicle information detection device 201 includes a vehicle speed sensor 201a and a steering angle sensor 201b, and detects information related to vehicle behavior such as the position, direction, and speed of the vehicle 1. The detected vehicle behavior information is sent to the position information conversion storage device 301. The position information conversion storage device 301 converts the distance data to the obstacle measured by the distance measurement device 101 based on the vehicle behavior information sent from the vehicle information detection device 201 into the position information of the obstacle and stores it.
[0009]
The position information of the obstacle is expressed on coordinates in the storage area of the position information conversion storage device 301. 4A is a diagram showing a positional relationship between the vehicle 1 and the obstacle 206 in the coordinate system of the real space, and FIG. 4B is a coordinate system in the storage area of the position information conversion storage device 301. FIG. 4 is a diagram showing the position of an obstacle 206 relative to the vehicle 1. The position of the obstacle 206 in the coordinate system of the real space is indicated by a point 311 on the coordinates in the storage area of the position information conversion storage device 301 that indicates the position relative to the vehicle 1. Further, the position of the distance measuring device 101 indicated by reference numeral 204 in FIG.
[0010]
A method for converting the position of the obstacle in the coordinate system of the real space into a point in the coordinate system of the storage area will be described with reference to FIGS. A reference X axis and Y axis are defined in advance in the real space coordinate system, and a position 202 of the vehicle 1 and an angle 203 formed by the X axis and the traveling direction of the vehicle are detected. The vehicle information 202 is detected by the vehicle information detection device 301. Specifically, an axis connecting the left and right rear wheels of the vehicle 1 and an axis passing through the center of the vehicle orthogonal to this axis are defined as the fixed coordinate system of the vehicle 1, and the fixed coordinate system of the vehicle 1 at a certain time t0 is defined as real space coordinates. Set to system XY. The position 202 of the vehicle 1 and the angle 203 indicating the traveling direction for each time change Δt are detected using the vehicle speed sensor 201a and the steering angle sensor 201b. Based on the detected position 202 of the vehicle and the angle 203 indicating the traveling direction, a position 204 of the distance measuring device 101 and a direction of an axis 205 (hereinafter referred to as a measuring axis) 205 connecting the two distance measuring devices 101 are calculated. To do. In the coordinate system of the storage area shown in FIG. 4B, a point 311 that is position information of the obstacle 206 is determined on the calculated measurement axis 205 at a position corresponding to the distance data detected by the distance measuring device 101.
[0011]
Therefore, until the obstacle 206 is detected, the data in the storage area of the position information conversion storage device 301 is 0. When the obstacle 206 is detected, corresponding data is added on the coordinates in the storage area. Thereafter, the relative position of the obstacle 206 detected as the vehicle moves is added as data on the coordinates of the storage area. White circles 312, 313, 314, and 315 on the coordinates in the storage area shown in FIG. 4B are data indicating the positions of obstacles detected before 311.
[0012]
The noise removing device 501 stores the position information conversion memory based on the detection range characteristics of the distance measuring device 101 stored in the distance measuring property storage device 401 and the vehicle information such as the vehicle speed detected by the vehicle information detecting device 201. The obstacle position information stored in the device 301 is classified to create a first obstacle map. The obstacle location information classification method will be described with reference to FIG.
[0013]
In the coordinate system in the storage area of the position information conversion storage device 301, a search area for classifying obstacle position information and removing noise information is determined. This search area is an ellipse area 317 that has two points of focus, the position 310 of the distance measuring device 101 and the maximum detection distance position 316 on the measurement axis. By changing the search area 317 according to the distance measurement characteristic and the vehicle speed, the obstacle position information can be classified without depending on the vehicle speed.
[0014]
If the traveling direction of the vehicle 1 is taken on the x axis, the coordinates X of the ellipse focus position in the search area 317 are X0 and X1, the vehicle speed is Vc, and the measurement sampling period of the distance measuring device 101 is Ts, the search area 317 The coordinates X of the included points must satisfy the following formula (1).
| X−X0 | + | X−X1 | <Vc · Ts + α (1)
However, α is a correction term, and the elliptical focal point coordinates X 0 and X 1 correspond to the coordinate X of the maximum detection distance position 207 on the distance measuring device 101 and the measurement axis, respectively. FIG. 6A is a diagram showing the search region 317 when the vehicle speed Vc is low, and FIG. 6B is a diagram showing the search region 317 when the vehicle speed Vc is high. As can be seen from FIGS. 6A and 6B, the width of the search region in the x-axis direction is small when the vehicle speed Vc is low, and the width of the search region 317 in the x-axis direction is large when the vehicle speed is high.
[0015]
Referring to FIG. 5, the noise removing device 501 detects obstacle positions 311, 312, 313 included in the search region 317, and draws a straight line 318 constituted by the detected plurality of obstacle positions 311, 312, 313. , Using the least square method or the like. As shown in Expression (1), by changing the size of the search area 317 based on the vehicle speed Vc and the sampling period Ts, it is possible to secure a sufficient number of samples to specify the arrangement and structure of the obstacle. it can. Thereby, since the precision of the approximate straight line 318 can be improved, the precision which classifies the obstacle position information mentioned later can be improved.
[0016]
Subsequently, a variance value for the distance (deviation) from each obstacle position information 311, 312, 313 included in the search area 317 to the straight line 318 is obtained. The variance value depends on the resolution of the distance measuring device 101 and the like. Accordingly, the threshold value of the dispersion value is determined by the resolution of the distance measuring device 101, the measurement error, and the resolution of the position information conversion storage device 301. When the obtained variance value is less than or equal to a predetermined threshold value, it is determined that the obstacle positions 311, 312, and 313 belong to the same cluster (group). On the other hand, when the obtained variance value is larger than the predetermined threshold value, it is determined that the end point of the same cluster has been detected. That is, it is determined that a point whose variance value is equal to or smaller than a predetermined threshold belongs to the same cluster, and a point exceeding the predetermined threshold is noise information or position information belonging to another cluster. .
[0017]
Also, when the number of pieces of obstacle position information included in the search area 317 is smaller than a predetermined number, it is determined that the end point of the cluster has been detected. This will be described with reference to FIG. If the number of obstacle position information included in the search area 317 is smaller than a predetermined number when the clusters are sequentially classified, the obstacle position information 330 to 333 is as shown in FIG. Although the information belongs to the same cluster, the obstacle position information 334 belongs to another cluster. That is, since there is no continuity between the obstacle position information 330 and the obstacle position information 334, it is determined that both belong to different clusters.
[0018]
A method of obtaining the first obstacle map by removing noise information based on the result of classifying the obstacle position information will be described with reference to FIG. Examples of obstacles existing around the vehicle include a parked vehicle, a pillar, a wall, and a guardrail in a parking lot. When the vehicle moves, obstacles such as parked vehicles and guardrails are detected using the distance measuring device 101, and the obstacle position is stored on the coordinates of the storage area. You can see that it is composed. However, the obstacle position classification results described above include variations in the position information of the obstacles and measurement errors caused by the distance measuring device 101 itself. Therefore, in order to accurately detect an obstacle having a linear structure, it is necessary to perform a process for improving the linearity accuracy of the measurement result.
[0019]
In each cluster into which the obstacle position information described above is classified, re-search areas 320 and 321 for detecting obstacles having a linear structure are determined. The re-search areas 320 and 321 are defined based on the minimum area including the obstacle position information constituting the cluster. When the re-search areas 320 and 321 are defined, the y-axis direction shown in FIG. 8, that is, the area in the measurement axis direction, is the distance resolution of the distance measurement device 101, the distance resolution of the storage region of the position information conversion storage device 301, Expand in consideration of variations in measurement results of obstacle location information. Further, in the x-axis direction shown in FIG. 8, that is, the region in the traveling direction of the vehicle 1, in addition to the enlargement in the y-axis direction in consideration of variations in the measurement result of the obstacle position information, the vehicle speed Vc and the distance measuring device 101 Is increased in consideration of the sampling period Ts.
[0020]
As described above, by expanding the re-search areas 320 and 321, it is possible to reduce the influence of the quantization error when the obstacle position information is stored, that is, when analog data is converted into digital data and stored. . Also, since the obstacle position information that could not be classified as noise information can be used to define the obstacle structure, the accuracy of the obstacle map is improved.
[0021]
When the re-search areas 320 and 321 are determined, a point cloud of obstacle position information that satisfies a re-search condition described later is extracted from the obstacle position information included in the re-search areas 320 and 321. That is, the ellipse area 322 in which the number of points of the obstacle position information included in the ellipse area focusing on two arbitrary points of the obstacle position information included in the re-search area 320 is obtained (see FIG. 8). The obstacle position information included in this elliptical area is extracted.
[0022]
Specifically, the coordinates Y of the points included in the ellipse area 322 where the number of points of the obstacle position information is maximum must satisfy the following formula (2).
| Y−Y0 | + | Y−Y1 | <β (2)
However, Y0 and Y1 are two arbitrary coordinates Y of the obstacle position information included in the re-search area 320, and correspond to the focal coordinates of the ellipse. β is a predetermined constant. As β increases, the area of the ellipse 322 in the y-axis direction increases, and the linearity of the point group in the ellipse 322 decreases. Conversely, when β is small, the area of the ellipse 322 in the y-axis direction is small, and the linearity of the point group in the ellipse 322 in the x-axis direction is high. That is, the deviation between the straight line constituted by the point group included in the ellipse 322 and the point indicating each obstacle position information becomes small.
[0023]
In the re-search area 320 illustrated in FIG. 8, the obstacle position information 323 is not included in the ellipse 322. Therefore, the obstacle position information 323 is determined to be obstacle information different from the obstacle having a linear structure such as a side surface of the parked vehicle. Obstacle position information that satisfies the above condition (2) is used as the first obstacle map.
[0024]
The obstacle map generation device 601 generates a continuous obstacle map based on the first obstacle map. Vehicle control systems and warning systems for parking assistance control the brakes and steering wheel based on the information on the position of the vehicle and the predicted trajectory and the position of the obstacle, and determine the possibility of contact with the obstacle. Some alarms. In order to determine the possibility of contact between a vehicle and an obstacle, a map of obstacles around the vehicle can be used, but in order to calculate the possibility of contact with an obstacle as needed, a large amount of data Must use a high-speed processing device capable of handling For this reason, in the obstacle map creation device for a vehicle according to the present embodiment, the obstacle map itself includes data corresponding to the control target value or the alarm level.
[0025]
FIG. 9 is an obstacle map to which three levels of control / alarm levels are assigned based on the point cloud constituting each cluster of the first obstacle map shown in FIG. That is, a control / alarm level is assigned by defining a confidence interval with a confidence coefficient of 95%, 90%, 85%, etc. based on the obstacle position information. The reliability coefficient is a probability that a point indicating obstacle position information is included in the section, and the reliability coefficient of the central region including the point group included in the ellipse 322 is the lowest, and the region from the central region to the outer region The reliability coefficient increases.
[0026]
In FIG. 9, the central area including the point cloud is the control / alarm level 3, the control / alarm level in the middle area surrounding the control / alarm level 3 is 2, and the control / alarm level in the outermost area is 1. Yes. In this case, since the region where the control / warning level is 3 is most likely to have an obstacle, the possibility of contact between the vehicle and the obstacle when the vehicle enters this region is the highest. In the region of level 2 compared to level 3 and level 1 compared to level 2, the possibility of contact between the vehicle and the obstacle is low. By including the control / warning level together with the position information of the obstacle in the obstacle map, the possibility of contact between the vehicle and the obstacle can be easily checked. That is, when a vehicle enters an area where an obstacle exists, the current control level or alarm level of the vehicle can be grasped by examining the control / alarm level of the area where the vehicle has entered. Thereby, according to the control / alarm level of the area where the vehicle has entered, it is possible to issue an alarm using a speaker (not shown) or perform vehicle control using a brake (not shown).
[0027]
The obstacle map creation procedure described above will be briefly described with reference to the flowchart of FIG. In addition, in the processing content of each step, the description is abbreviate | omitted about the part detailed in the description mentioned above. In step S1, the distance measuring device 101 measures the distance to the obstacle 206. When the distance is measured, the process proceeds to step S2. In step S <b> 2, the vehicle information detection apparatus 201 detects the behavior of the vehicle. As described above, the behavior of the vehicle includes the position, traveling direction, speed, and the like of the vehicle. When the behavior of the vehicle is detected, the process proceeds to step S3. In step S3, the distance information to the obstacle detected in step S1 is converted into obstacle position information based on the behavior of the vehicle detected in step S2. The conversion to the position information is performed by the position information conversion storage device 301. Since the conversion method has been described above, the description thereof is omitted here. In step S4, the position information converted in step S3 is stored in the position information conversion storage device 301.
[0028]
Hereinafter, the processing performed in steps S5 to S8 is performed by the noise removing device 501. In step S5, a search area for classifying the position information of the obstacle stored in step S4 for each cluster is set. Since the search area setting method has also been described above, a description thereof will be omitted. In the next step S6, the position information of the obstacles included in the search area set in step S5 is classified for each cluster. That is, as described above, a straight line constituted by position information of a plurality of obstacles included in the search area is calculated, and a variance value for the distance between the calculated straight line and each obstacle position information is obtained. When the variance value is less than or equal to a predetermined threshold value, it is determined that they belong to the same cluster. When the variance value is larger than the threshold value, it is determined that the end point of the cluster has been detected, and it is determined that the obstacle position information having the variance value larger than the threshold value belongs to another cluster or is noise information.
[0029]
In step S7, a re-search area for detecting an obstacle having a linear structure is set from position information of a plurality of obstacles included in the cluster classified in step S6. Detailed description of the re-search area setting method is also omitted. In step S8, a point group satisfying the re-search condition is detected from the position information of the obstacle in the re-search area set in step S7. The point group that satisfies the re-search condition is a set of obstacle position information that satisfies the condition of Expression (2) as described above, and indicates an obstacle having a linear structure. When a point group satisfying the re-search condition is detected, the process proceeds to step S9. In step S9, an obstacle map is generated by the obstacle map generation device based on the point cloud detected in step S8, that is, the obstacle position information. The obstacle map includes the control / alarm level as well as the arrangement and structure of the obstacle as described above. Since the method for creating the obstacle map is also described above, the description thereof is omitted.
[0030]
As described above, according to the obstacle map creation device for a vehicle according to the present invention, the distance data to the obstacle is converted into the position information of the obstacle based on the vehicle behavior. can do. In addition, the obstacle position information is classified based on the vehicle behavior and the measurement characteristics of the distance measuring device, and further, the obstacle data having a linear structure is detected and the obstacle map is created to obtain the distance data that becomes noise. It can be eliminated, and the structure and arrangement of obstacles can be accurately grasped. In addition, by including control / alarm level information in the obstacle map, when the vehicle enters the area where the obstacle exists, the current control of the vehicle is checked by checking the control / alarm level of the area where the vehicle has entered. The level or alarm level can be grasped.
[0031]
The present invention is not limited to the embodiment described above. For example, the vehicle information detection device 201 detects the position and direction of the vehicle based on the vehicle speed sensor 201a and the steering angle sensor 201b, but may detect using a gyro or the like. Further, the control / alarm level is not limited to three stages, and can be divided into favorite stages. In the description of the embodiment described above, the control / alarm level region is set to the confidence intervals of 95%, 90%, and 85%, but the reliability coefficient is not limited to these values.
[Brief description of the drawings]
FIG. 1 is a diagram showing the configuration of an embodiment of a vehicle obstacle map creation device according to the present invention;
FIG. 2 is a diagram showing an in-vehicle position and a measurement range of the distance measuring device.
FIG. 3 is a diagram showing a configuration of a vehicle information detection device.
4A is a diagram showing a positional relationship between a vehicle and an obstacle in a real space coordinate system, and FIG. 4B is a diagram showing a positional relationship between the vehicle and an obstacle in a coordinate system of a storage area.
FIG. 5 is a diagram showing search areas for classifying obstacle position information.
6A is a diagram showing a search area when the vehicle is traveling at a low speed, and FIG. 6B is a diagram showing a search area when the vehicle is traveling at a high speed.
FIG. 7 is a diagram for explaining a classification method of obstacle position information;
FIG. 8 is a diagram showing a re-search area and a group of obstacle position information satisfying the re-search condition.
FIG. 9 is a diagram showing an obstacle map including control / alarm level information.
FIG. 10 is a flowchart showing a procedure for creating an embodiment of an obstacle map.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 1 ... Vehicle, 101 ... Distance measuring device, 102 ... Measuring range, 201 ... Vehicle information detecting device, 201a ... Vehicle speed sensor, 201b ... Steering angle sensor, 202 ... Position of vehicle, 203 ... Y axis and the advancing direction of a vehicle Angle formed by 204, position of distance measuring device, 205, measuring axis, 206, obstacle, 301, position information conversion storage device, 310, position of distance measuring device, 311, 312, 313, 314, 315, 323, 330 331, 332, 333, 334 ... obstacle position information, 316 ... maximum detection distance position, 317 ... search region, 318 ... approximate line, 320, 321 ... re-search region, 322 ... region satisfying the re-search condition, 401 ... Distance measurement characteristic storage device, 501 ... Noise removal device, 601 ... Obstacle map generation device

Claims (8)

A distance measuring device for measuring the distance to the object;
A vehicle information detection device for detecting vehicle behavior;
Based on the vehicle behavior detected by the vehicle information detection device, a position information conversion storage device that converts and stores the distance information to the object measured by the distance measurement device into the position information of the object;
A classification device for classifying the position information of the plurality of objects stored in the position information conversion storage device for each object;
A noise removing device for removing noise information based on the position information classified by the classification device;
An obstacle map generation device for a vehicle, comprising: an obstacle map generation device that generates an obstacle map based on position information from which noise information has been removed by the noise removal device. In the vehicle obstacle map creation device according to claim 1,
A distance measurement characteristic storage device for storing measurement characteristics of the distance measurement device;
The noise removing device removes the noise information based on a vehicle behavior detected by the vehicle information detecting device and a measurement characteristic stored in the distance measurement characteristic storage device. Map making device. The obstacle map creation device for a vehicle according to claim 2,
The measurement characteristic stored in the distance measurement characteristic storage device is any one of a maximum detection distance, a detection width, a detection angle, a distance resolution, a measurement cycle of the distance measurement device, or a combination thereof. Obstacle map creation device for vehicles. In the obstacle map creation device for vehicles according to any one of claims 1 to 3,
The vehicle behavior map detected by the vehicle information detection device is a position, a direction, and a speed of the vehicle, and the obstacle map creation device for vehicles. In the obstacle map creation device for vehicles according to any one of claims 1 to 4,
The classifier, to classify the location information of the object for each object, detects the position information of the object contained in the search region determined based on the positions of the maximum detection distance of the distance measuring device vehicle obstacle mapping apparatus according to claim Rukoto issue. In the obstacle map creation device for vehicles according to claim 5,
An obstacle map creation device for a vehicle, wherein a width in a vehicle traveling direction of a search area of the position information is changed based on a speed of the vehicle and a measurement cycle of the distance measurement device. In the obstacle map creation device for a vehicle according to any one of claims 1 to 6 ,
The classification device further classifies the position information of the object by detecting position information of the object having a linear structure from the position information of the plurality of objects classified for each object. Vehicle obstacle map creation device. In the obstacle map creation device for vehicles according to any one of claims 1 to 7,
The obstacle map generation device sets a plurality of areas according to the possibility that an object exists based on the classified position information, and includes obstacle / control level information for each set area. A vehicle obstacle map creating device characterized by generating a map.

Images