JPH0674778A - Navigation system for mobile - Google Patents

Abstract

PURPOSE:To obtain a navigation system for mobile in which map matching processing is carried out correctly. CONSTITUTION:The navigation system comprises a geomagnetism sensor 1, a distance sensor 2, a central processor 3A, an external memory 4, a display 8, and an infrared camera 11. A mobile travels while recognizing a white line on one end of road through the infrared camera 11 and when the white line interrupts for a predetermined interval, the central processor 3A recognizes presence of an intersection and performs map matching of current position with the nearest intersection designated by map data stored in the external memory 4. This constitution allows correct matching and thereby correct determination of current position.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a navigation device for a mobile body, which displays the current location of the mobile body on a map.

[0002]

2. Description of the Related Art FIG. 15 shows a configuration example of a conventional navigation device disclosed in, for example, Japanese Utility Model Laid-Open No. 3-88117. In FIG. 15, 1 is a geomagnetic sensor, 2 is a distance sensor, and 3 is a central processing unit. 4, external storage device, 5 media controller, 6 image memory, 7 display control device, 8 display device, 9 buffer memory, 10
Is a keyboard.

Next, the operation will be described with reference to the flowchart of FIG. After the current position of the vehicle is determined and the vehicle starts traveling, first in step S301, the traveling angle of the vehicle is calculated based on the signal from the geomagnetic sensor 1. Then step S
After it is determined in 302 whether the vehicle has traveled straight for a certain distance or more, it is determined in step S303 whether or not the vehicle has just left. If it is not immediately after departure, the process jumps to step S306, and if it is immediately after departure, the process proceeds to step S304.

In step S304, it is determined whether the vehicle is going straight. When the vehicle is not going straight, the process jumps to step S306, and when the vehicle is going straight, the process is step S305.
Move on to. In this step S305, the traveling angle of the vehicle obtained by the geomagnetic sensor 1 is initialized with the angle of the nearest road, and the coordinates of the current position are initialized.

In step S306, the estimated current position is matched on the road map. At this time, the allowable range of the error between the traveling angle obtained from the geomagnetic sensor 1 and the road angle based on the road map data is set, and the departure is started. Immediately after that, the error of the traveling angle detected by the geomagnetic sensor 1 is allowed to be large and the estimated current position is aligned with the road.

[0006]

In the conventional navigation device for a mobile body, the judgment material for map matching is only the signals of the geomagnetic sensor 1, the distance sensor 2 and the like.
Moreover, it depends on the map data stored in the map data storage means, and it cannot be used as a judgment material when grasping the road condition currently running and performing map matching.

The present invention has been made in order to solve the above-mentioned problems, and the map data stored in an external storage device is determined by grasping and judging the road condition on which the vehicle is traveling, extracting characteristic points. The object of the present invention is to obtain a navigation device for a mobile object that performs map matching to the feature points of the mobile object, and to obtain a navigation device for a mobile object that can prevent the feature points from being erroneously detected. Aiming to obtain a navigation device for a mobile body that can prevent the erroneous detection of undetected feature points of the above, and also to obtain a navigation device for a mobile body that can again detect a lost or lost target object while traveling. In addition, it is necessary to obtain a navigation device for a mobile body that can recognize feature points that actually exist but do not exist in map data. Target and to have, in addition, it can actually present to the recording feature points do not exist in the map data,
It is an object of the present invention to provide a navigation device for a mobile body, which can create map data by itself.

[0008]

A navigation device for a moving body according to the present invention comprises a current position estimating means for estimating a current position of a moving body, a road condition detecting means for detecting a road condition, and a road condition detecting means. The feature point detection means for detecting the change of the detection signal by detecting the feature point of the road, and the feature point of the map data to which the feature point detected by the feature point detection means is determined, and the current position estimation means Position correction means for correcting the current position of the moving body to the position coordinates of the feature point detected by the feature point detection means when the current position does not match the estimated current position coordinate.

Further, there is provided a road condition detecting means for starting detection of the road condition after the moving body exceeds a certain speed after the start of traveling.

Further, the road condition detecting means has a function of detecting a target object within a certain area of the road viewed from the moving body, and when the position of the target object during traveling changes, the target object is tracked and repeatedly detected. Is provided.

Further, it has a function of detecting a target object within a certain area of the road viewed from the moving body, and when the target object cannot be detected within this certain area after the start of traveling, or the target object is detected within the traveling area. Road detection means is provided to search for a target in this area when it cannot be detected.

When it cannot be determined which feature point on the map data of the map data storage means the detected feature point of the road corresponds to, a feature point detection for outputting a signal indicating the position of the detected road feature point is detected. Means are provided.

Furthermore, the map data stored in the map data storage means, the display means for displaying the current position of the moving body detected by the position detection means, and the map data in which the detected road feature points are stored in the map data storage means When it is not possible to determine which of the above feature points the feature points correspond to, a feature point detecting means for displaying the detected road feature points on the display means is provided.

In addition, when it cannot be determined which feature point on the map data stored in the map data storage means corresponds to the feature point of the road detected by the feature point detection means, the road of the road detected by the feature point detection means can be determined. A feature point recording means for recording feature points is provided.

[0015]

In the navigation device for a moving body constructed as described above, the current position estimating means estimates the current position of the moving body, and the road state detecting means detects the road state on which the moving body moves. When the feature point detection means detects a change in the value of the road as a road feature point, it is determined which feature point in the map data the detected feature point corresponds to, and the current position coordinate estimated by the current position estimation means does not match. The position correction means matches the current position of the moving body with the position coordinates of the characteristic point detected by the characteristic point detection means.

Further, the road condition detecting means starts detecting the road condition after the moving body exceeds a certain speed after starting the traveling, thereby preventing erroneous detection of the characteristic points.

Further, the road condition detecting means detects a target object within a certain area while the moving body is moving, and when the position of the target object changes, the target object is tracked and repeatedly detected,
Prevent undetected target.

Further, when the road condition detecting means cannot detect the target object within a certain area of the road on which the moving body is moving, or when the target object cannot be detected, the road condition detecting means within this area. When it becomes impossible to search for the target object, the road condition detecting means searches for the target object in this area, thereby detecting again the target object that is lost or interrupted during the movement of the moving body.

Further, when it is not possible to determine which feature point on the map data stored in the map data storage means corresponds to the feature point of the road detected by the feature point detection means,
A signal indicating the position of the characteristic point of the road detected by the characteristic point detecting means is output, and the characteristic point which actually exists but does not exist in the map data can be confirmed.

Further, the display means displays the map data stored in the map data storage means and the current position of the moving body detected by the position detection means, and the characteristic points of the road detected by the characteristic point detection means are map data. When it is not possible to confirm which feature point on the map data stored in the storage means corresponds, the detected road feature point is displayed on the display means so that it actually exists, but it does not exist in the map data. The occupant can recognize the feature points that do not exist.

In addition, when it cannot be confirmed which feature point on the map data stored in the map data storage means corresponds to the feature point of the road detected by the feature point detection means, the road of the road detected by the feature point detection means is detected. By recording the position of the characteristic point in the characteristic point recording means, it is possible to record the characteristic point which actually exists but does not exist in the map data, and it becomes possible to record the map data by oneself.

[0022]

【Example】

Example 1. An embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a block diagram showing a navigation device for a mobile body. In FIG. 1, reference numeral 1 is a geomagnetic sensor that detects the geomagnetism and the direction of the vehicle, and 2 is a distance sensor that detects the travel distance of the vehicle. Based on these two signals, the central processing unit 3A indicates The position is being calculated.

Reference numeral 4 denotes an external storage device composed of a CD-ROM storing map data, 5 a media controller, 6 an image memory, 7 a display control device, 8 a map, and a display device for displaying the current position of the vehicle. is there.

The central processing unit 3A converts the calculated map data around the current position of the vehicle into the media controller 5
It is read from the external storage device 4 via the and is sequentially transmitted to the memory 6. The display control device 7 converts the map data stored in the image memory 6 into an image and displays it on the display device 8 together with the current position of the vehicle calculated by the central processing unit 3A.

Reference numeral 10 is a keyboard operated by a vehicle occupant. Reference numeral 11 denotes an infrared camera, which is attached below the left side surface of the vehicle body. The state of the road surface at the left end of the road on which the vehicle is traveling is transmitted as a signal to the central processing unit 3A. The central processing unit 3A extracts the intersection of the traveling road from the received signal.

Reference numeral 12 is a feature point recording section. If the extracted intersection does not exist in the map data stored in the external storage device 4, the central processing unit 3A records the position information of the extracted intersection in the feature point recording unit 12.

The infrared camera 11, as shown in FIG.
It is attached to the lower left of the vehicle body A and photographs the road surface on the left side of the vehicle. The infrared camera 11, as shown in FIG. 3, theta ₁
The angle can be adjusted from (maximum value) to θ ₂ (minimum value).

FIG. 4 is a road surface image taken by the infrared camera 11. The asphalt part of the road surface is dark and the white line part is bright. As shown in FIG. 4, the upper width of the white line is a, the white line width is b, and the lower width of the white line is c.

The central processing unit 3A extracts a white line on the road from the image of the infrared camera 11. If the white line is interrupted, it is determined to be an intersection, and the current position is set to the node point (intersection) closest to the current position. Map matching. The white line described here is the white line at the right end of the road that separates the driving lane and the roadside belt, and the broken white line that separates the lanes when there are two or more driving lanes.

Next, the map matching operation of the central processing unit 3A will be described with reference to the flow charts shown in FIGS. 5 and 6 are flowcharts showing the map matching operation of the central processing unit 3A of this embodiment. 5 and 6, first, in step S10
In step 1, the current position of the vehicle is determined by operating the keyboard 10, and in step S102, the vehicle starts running. In step S103, when the vehicle exceeds a predetermined speed (here, set as Skm per hour), it is determined in step S104 whether the vehicle is traveling straight ahead. If it is traveling straight ahead, step S103
Proceeding to 105, the road white line search processing by the infrared camera 11 is started. In this case, the white line search is started after the speed exceeds the predetermined speed when the vehicle is running at low speed.
This is because there are many cases where the vehicle is traveling on a place other than the road such as a parking lot.

When the white line on the road is recognized in step S105 and the white line search process is completed, the process proceeds to step S106, and the white line tracking process for tracking the recognized white line is performed. The white line tracking process of step S106 is repeated until the vehicle runs at the intersection and the white line disappears from the image of the infrared camera 11.

In step S107, when the vehicle runs at the intersection and the white line disappears from the image of the infrared camera 11 (that is, the white line on the road disappears because the vehicle is running at the intersection), the process proceeds to step S108 and the white line is again displayed. Start the search process. When the white line is recognized and the white line search process ends,
In step S109 of the flowchart of FIG. 6, from the speed of the vehicle and the time when the white line is captured by the infrared camera 11,
The distance in the section with the white line is obtained (put as L ₁ ), and the distance in the section without the white line is obtained from the time when the white line disappears from the infrared camera 11 (put as L ₂ ).

In steps S110 to S111,
Based on the distance relationship between L ₁ and L ₂ , the white line recognized by the infrared camera 11 is the white line at the right end of the road that separates the driving lane and the roadside zone, or a broken line that separates the lanes when there are two or more driving lanes. Judge whether it is the white line. According to the provisions of the Six Roads Act, the broken lines that separate lanes have a white line length of 3 to 10
The distance between the white line and the white line is 6 to 20 m, which is 1 to 2 times that.

When L ₁ (section with white line) is 3 to 10 m, it is possible that the recognized white line was a broken line separating the lanes. In step S110, 3m ≦ L ₁ ≦ 10m
In this case, the process proceeds to step S111 to check the distance relationship between L ₁ and L ₂ . In step S111, L ₁ ≤L ₂ ≤2L ₁
When the white line-free section is 1 to 2 times the white line-containing section, the recognized white line is determined to be a broken line that divides the lane, and the process returns to step S106 in FIG. Step S1
When L ₁ > L ₂ or L ₂ > 2L ₁ in 11, it is determined that the recognized white line is the white line at the right end of the road that separates the driving lane from the roadside zone, and the process proceeds to step S112.

In step S112, if the section without white line is within a certain distance (for example, W _{1 to} W ₂ m), the section without white line is determined to be an intersection. If the section without white line is W ₁ m or less or W ₂ m or more, it is not judged as an intersection.If it is W ₁ m or less, it is judged that the white line is interrupted for some reason, not the intersection, This is because when it is W ₂ m or more, it is determined that the vehicle is traveling on a road without a white line.

The central processing unit 3A has a step S101.
After determining the current position of the vehicle, the current position of the vehicle is constantly calculated from the signals of the geomagnetic sensor 1 and the distance sensor 2. In step S113, if there is an intersection near by comparing with the map data around the current position, step S114
Then, map matching is performed at the intersection, and step S10 is performed.
Return to 3. If there is no intersection near the current position in step S113, position information of the intersection is detected in step S115, the position information of the detected intersection is recorded in the feature point recording unit 12 in step S116, and the process returns to step S103. .

FIG. 7 is a flowchart showing the white line search processing operation in step S105 of FIG. The white line search processing means that when the central processing unit 3A cannot recognize the white line on the road from the video signal of the infrared camera 11 immediately after the vehicle starts traveling or the vehicle is traveling at an intersection, the angle of the infrared camera 11 is determined. It is the process of changing and searching for a white line on the road. The angle of the infrared camera 11 is set to θ, and the maximum value of the angle is set to θ ₁ and the minimum value is set to θ ₂ as shown in FIG.

Referring to FIG. 7, first in step S151,
It is checked whether the angle of the infrared camera 11 is the minimum value, and if it is not the minimum value, it is checked in step S152 whether the angle of the infrared camera 11 is the maximum value. If it is not the maximum value, the process proceeds to step S153. In step S153, 1 ° is added to θ to correct the angle of the infrared camera 11 by 1 °, and then in step S153.
Proceed to 154. When the white line on the road is recognized in step S154, the white line search processing ends. The process of steps S152 to S154 is repeated until the white line on the road is recognized or the angle of the infrared camera 11 reaches the maximum value.

When the angle of the infrared camera 11 is the maximum value in step S152, the process proceeds to step S155. In step S155, the infrared camera 1
The angle of 1 is corrected by 1 ° and the process proceeds to step S156. When the white line on the road is recognized in step S156, the white line search processing ends.

If the white line on the road is not recognized, the process proceeds from step S156 to step S157 and the angle of the infrared camera 11 is set to the minimum value θ _2, and whether the white line on the road is recognized in step S156. , Step S1 until the angle of the infrared camera 11 reaches the minimum value
The processes of 55 to step S157 are repeated.

FIG. 8 is a flowchart showing the white line tracking processing operation of step S106 of the flowchart of FIG. The white line tracking process means that when the central processing unit 3A recognizes the white line on the road from the video signal of the infrared camera 11, the white line position is always in the center of the image of the infrared camera 11. 11 is a process for adjusting the angle. FIG. 4 is a road surface image taken by the infrared camera 11. The asphalt part of the road surface is dark and the white line part is bright. As shown in FIG. 4, as described above, the upper width of the white line is a, the white line width is b, and the lower width of the white line is c.
And put.

In FIG. 8, first, in step S171,
Check the magnitude relationship between a and c. When a ≠ c, step S
Proceed to 172. In step S172, when a> c, the process proceeds to step S173. 1 from θ in step S173
The angle of the infrared camera 11 is corrected by 1 °. When a <c in step S172, the process proceeds to step S174. In step S174, 1 ° is added to θ to correct the angle of the infrared camera 11 by 1 °. Step S10 in FIG.
In the process of No. 7, the white line tracking process of FIG. 8 is repeated until the vehicle runs at the intersection and the white line disappears from the image of the infrared camera 11.

FIG. 9 is a flow chart showing the operation of the map drawing process while the vehicle is traveling. When the intersection recorded by the feature point recording unit 12 exists around the position coordinates of the traveling vehicle (that is, the central processing unit 3A stores the map data in the external storage unit 4 in the map data of the external storage device 4 when the peripheral road was previously traveling). An intersection that does not exist is detected, and its position information is recorded in the characteristic point recording unit 12.), and the central processing unit 3A reads the position information from the characteristic point recording unit 12 and displays it on the display device 8.

In FIG. 8, first, in step S191,
The current position of the vehicle is detected from the signals of the geomagnetic sensor 1 and the distance sensor 2, and the detected position information is transmitted to the image memory 6. In step S192, the detected map information around the current position is read from the external storage device 4 via the media controller 5 and transmitted to the image memory 6. In step S193, if the intersection recorded in the feature point recording unit 12 has an intersection located on the link data of the map information read in step S192, in step S194, the position information of the corresponding intersection from the feature point recording unit 12 Is read out and transmitted to the image memory 6. In step S195, the display control device 7 is used to convert the current position information, the map information, and the intersection position information stored in the image memory 6 into an image and display it on the display device 8.

FIG. 10 is a map screen displayed on the display device 8. The current position mark 15 is displayed at the center, and the position of the intersection read from the feature point recording unit 12 is displayed as a short branch road as shown at the intersection position 16. The intersections recorded in the feature point recording unit 12 are displayed only on the detailed map and not on the wide area map.

Example 2. In the first embodiment, the white line on the road is detected by the infrared camera 11 to extract the intersection. However, a normal camera is used to detect the white line on the road due to the color difference between the asphalt and the white line. However, the intersection may be extracted.

Example 3. Further, in the first embodiment, the white line on the road is detected by the infrared camera 11 to extract the intersection, but infrared rays or visible light is emitted from the vehicle body to illuminate the white line, and the reflected light is detected. By doing so, a white line on the road may be sensed and an intersection may be extracted.

Example 4. Further, in the first embodiment, the white line on the road is detected by the infrared camera 11 to extract the intersection, but in the case of a road without a white line, the infrared camera or the like is used to detect the boundary between the road and the side of the road. However, the intersection may be extracted.

Example 5. Embodiment 5 of the present invention will be described below with reference to the drawings. FIG. 11 is a block diagram showing a navigation device for a mobile body according to the fifth embodiment. In this FIG. 11, 1 to 10 are the same as those in FIG.
It is omitted here.

Reference numeral 13 is an ultrasonic wave transmitter, and 14 is an ultrasonic wave receiver. These are attached to the left side of the vehicle body A as shown in FIG. The ultrasonic wave emitted from the ultrasonic wave transmitting unit 13 bounces off an object on the left side of the vehicle, and the ultrasonic wave receiving unit 1
4 receives the reflected ultrasonic waves. Utilizing this, the central processing unit 3A extracts the intersection of the road on which the vehicle is running.

The ultrasonic transmitter 13 and the ultrasonic receiver 14
Always repeats transmission and reception of ultrasonic waves. When ultrasonic waves are not received during a certain section during traveling, the point is regarded as an intersection and the current position is map-matched to the intersection closest to the current position.

Next, the map matching operation of the central processing unit 3A will be described with reference to the flowchart shown in FIG. 13 and 14 are flowcharts showing the map matching operation of the central processing unit 3A of the fifth embodiment. First, in FIG. 13, first in step S201.
Then, the current position of the vehicle is determined by operating the keyboard 10, and the vehicle starts traveling in step S202. Step S
In 203, when the speed exceeds a predetermined speed (for example, Skm / hour), the ultrasonic wave transmission unit 13 and the ultrasonic wave reception unit 14 start transmitting and receiving ultrasonic waves.

In step S204, the ultrasonic wave is transmitted from the ultrasonic wave transmitting section 13, and in step S205, it is determined whether or not the ultrasonic wave is received from the ultrasonic wave receiving section 14. While traveling on a normal road, there are obstacles such as guardrails and buildings on the left side of the vehicle. Therefore, the ultrasonic waves transmitted from the ultrasonic wave transmission unit 13 bounce off those obstacles and are received by the ultrasonic wave reception unit 14. , When the vehicle is passing the intersection, ultrasonic waves do not bounce because there are no obstacles.

If no ultrasonic wave is received in step S205, it is determined in step S206 whether the vehicle is traveling straight ahead. If the vehicle is traveling straight ahead, step S2
In 07 and step S208, the transmission of ultrasonic waves is repeated again.

When an ultrasonic wave is received in step S208, the distance in the obstacle-free section is determined (put L ₂ ) from the vehicle speed and the time when the ultrasonic wave was not received in step S209.

Then, in step S210 of the flowchart shown in FIG. 14, L ₂ is within a certain distance (for example, W ₁ to
In the case of W ₂ m), the section with no obstacle is judged as an intersection.
If the section without obstacles is W ₁ m or less, or W ₂ m or more, it is not judged as an intersection. If it is W ₁ m or less, it is judged that there is a gap in the obstacle instead of the intersection. However, when it is W ₂ m or more, it is because it is determined that the vehicle is running on a road without obstacles beside it.

In step S211, when compared with the map data stored in the external storage device 4, if there is an intersection near the current position, map matching is performed in the intersection in step S212, and the process returns to step S203.

[0058]

Since the present invention is constructed as described above, it has the following effects.

By extracting the characteristic points of the road on which the mobile body is traveling, the characteristic points on the map data corresponding to the extracted characteristic points are determined, and the current position is corrected to the position coordinates of the determined characteristic points. It is possible to obtain a more accurate current position than the current position calculated from the signals from the geomagnetic sensor and the distance sensor.

Further, by starting the extraction of the characteristic points after the moving body starts traveling and exceeds a certain speed, the characteristic points are erroneously extracted when the moving body is traveling on a place other than the road. It is possible to prevent the mistake of doing so and surely extract the feature points while traveling on a normal road.

Further, the target is repeatedly detected within a certain area of the road viewed from the moving body, and when the position of the target changes during traveling, the target is tracked and repeatedly detected to detect the road. There is an effect that the feature point detection system is not affected by the slight displacement of the target position or the displacement of the moving body itself.

In addition, when the target cannot be detected within a certain area of the road viewed from the moving body after the start of traveling, or when the target cannot be detected within the area while traveling, the inside of the area By searching for the target object with, the target object can be detected after the start of traveling, and the target object lost or interrupted during traveling can be detected again.

Further, when it is not possible to determine which feature point on the map data the road feature point detected by the road condition detecting means corresponds to, the map is output by outputting a signal indicating the detected road feature point. The navigation system can recognize feature points such as intersections that do not exist on the data but actually exist on the road.

When it is not possible to determine which feature point on the map data the feature point of the road detected by the road state detecting means corresponds to, the detected feature point of the road is displayed on the display means or the like, whereby the map data is displayed. There is an effect that the occupant of the moving body can recognize a feature point such as an intersection, which does not exist above the road but actually exists on the road.

In addition, when it cannot be determined which feature point on the map data the feature point of the road detected by the road condition detecting means corresponds to, the detected feature point of the road is recorded in the feature point recording means. Although the moving body itself does not exist in the map data, it is possible to create a map database in which characteristic points such as intersections existing on the actual road are recorded.

[Brief description of drawings]

FIG. 1 is a block diagram of a navigation device for a mobile body according to a first embodiment of the present invention.

FIG. 2 is an external perspective view of a vehicle equipped with the navigation device for a mobile body according to the first embodiment.

FIG. 3 is a schematic diagram of an infrared camera according to the first embodiment.

FIG. 4 is an image of a road surface imaged by the infrared camera according to the first embodiment.

FIG. 5 is a first half flowchart showing a map matching operation of the central processing unit according to the first embodiment.

FIG. 6 is a second half flowchart showing the map matching operation of the central processing unit of the above-mentioned first embodiment.

FIG. 7 is a flowchart showing a white line search processing operation of the flowchart of FIG.

8 is a flowchart showing a white line tracking operation process of the flowchart of FIG.

FIG. 9 is a flowchart showing the operation of map drawing processing while the vehicle of the central processing unit according to the first embodiment is running.

FIG. 10 is a screen displayed on the display device according to the first embodiment.

FIG. 11 is a block diagram of a mobile navigation device according to a fifth embodiment of the present invention.

FIG. 12 is an external perspective view of a vehicle equipped with the system according to the fifth embodiment.

FIG. 13 is a first half flowchart showing a map matching operation of the central processing unit of the fifth embodiment.

FIG. 14 is a second half flowchart showing the map matching operation of the central processing unit of the fifth embodiment.

FIG. 15 is a block diagram showing a conventional navigation device for a mobile body.

FIG. 16 is a flowchart showing an operation of a conventional navigation device for a mobile body.

[Explanation of symbols]

 1 Geomagnetic Sensor 2 Distance Sensor 3A Central Processing Unit 4 External Storage Device 5 Media Controller 6 Image Memory 7 Display Control Device 8 Display Device 10 Keyboard 11 Infrared Camera 12 Feature Point Recording Unit 13 Ultrasonic Transmitter 14 Ultrasonic Receiver A Body

Claims (7)

[Claims] 1. A map data storage means for storing map data, a current position estimating means for estimating current position coordinates of a moving body, a road condition detecting means for detecting a road condition, and a detection signal by the road condition detecting means. By detecting a change in the road, a feature point detection means for detecting a feature point of the road, and at the time of feature point detection, which feature point on the map data the detected feature point corresponds to is determined. If the current position coordinates estimated by the current position estimating means do not match, the position correction means for correcting the current position of the moving body to the position coordinates of the characteristic point detected by the characteristic point detecting means, and the moving body A navigation device for a mobile body, comprising: an output unit that outputs a current position. 2. The navigation device for a mobile body according to claim 1, wherein the road state detecting means starts detecting the road state after the mobile body exceeds a certain speed after the start of traveling. 3. The road condition detecting means has a function of detecting a target object within a certain area of the road viewed from the moving body, and when the position of the target object changes during traveling,
2. The navigation device for a mobile body according to claim 1, wherein the target object is tracked and repeatedly detected. 4. The road condition detecting means has a function of detecting a target in a certain area of the road viewed from the moving body, and when the target cannot be detected in the area after the start of traveling, or 2. The navigation device for a mobile body according to claim 1, wherein when the target object cannot be detected in the area while traveling, the target object is searched for in the area. 5. When it is not possible to determine which feature point on the map data of the map data storage means the feature point of the road detected by the feature point detecting means corresponds to, the position of the detected feature point of the road is determined. The navigation device for a mobile body according to claim 1, wherein a navigation signal is output. 6. A display means for displaying the map data by the map data storage means and the current position of the moving body detected by the position detection means, wherein the feature points of the road detected by the feature point detection means are stored in the map data storage. 2. The moving object according to claim 1, wherein when the characteristic point on the map data of the means cannot be determined, the characteristic point of the road detected by the characteristic point detecting means is displayed on the display means. Navigation device. 7. The road detected by the feature point detecting means when it cannot be determined to which feature point on the map data of the map data storage means the feature point of the road detected by the feature point detecting means corresponds. 2. The navigation device for a mobile body according to claim 1, further comprising a feature point recording means for recording the feature point.