Vehicle control device

Abstract

To provide a vehicle control device that alerts without acquiring a map and position information even when a surrounding environment sensor cannot directly measure an alert target on a driving road.SOLUTION: A vehicle control device includes: an information acquisition device mounted on a vehicle for recognizing an environment outside the vehicle; a land mark detection unit for detecting a predetermined land mark from the information acquired by the information acquisition device; a warning target object management unit for detecting the position of a warning target object from the travel history of the vehicle; and a database in which the predetermined landmark, the warning target object, and the positional relationships are registered. The warning target object management unit controls, when the landmark detection unit detects the predetermined landmark, the vehicle with respect to the warning target object on the traveling road of the vehicle based on the positional relationship or notifies the occupants of the vehicle to that effect.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a vehicle control device that can provide information corresponding to the vehicle's position to a driver or a system even when a global navigation satellite system (GNSS) cannot be used. [Background technology]

[0002] A driving behavior data generating device in Patent Document 1 is known as a conventional technology for providing a system with information according to the vehicle's position. The abstract of the document states that the problem is to "generate a driving behavior database that takes into account local rules, knowledge suitable for the surrounding environment, and empirical know-how, in order to be used in a driving behavior support device that expresses two-dimensional spatial distribution on a road and to support automated driving based on driving behavior similar to that of a human being." As a solution, it states that "distribution information on local driving behaviors (course selection within an intersection, stopping positions at intersections without stop lines, multiple use of a single lane, etc.) that are customarily performed by drivers (human beings) is aggregated and managed and stored in association with road network information. By using this distribution information, the automated driving system realizes automated driving that is suitable for the environment and that is less uncomfortable for the occupants. The automated driving system plans human-like driving behavior that matches the environment and weather. Since the database is generated by automatic processing using the on-board sensor group 12, there is no manual processing by the operator and information is generated at low cost."

[0003] Furthermore, paragraph 0057 of the document states that "the positioning sensor 30 is primarily a GPS (Global Positioning System) and measures the absolute position, moving direction, and speed of the vehicle based on signals received from GPS satellites," suggesting that the absolute position, etc. of the vehicle based on GPS will be referred to when creating or using a local driving behavior database. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2019-109675 A Summary of the Invention [Problem to be solved by the invention]

[0005] In Patent Document 1, not only was a storage device (specifically, a GNSS vehicle-mounted device) that holds road network information (map information) essential as a prerequisite for managing and storing local information corresponding to the vehicle's position in association with road network information, but an expensive GNSS vehicle-mounted device that can cooperate with the vehicle control system was also essential as a prerequisite for providing information associated with the vehicle's absolute position to the vehicle control system.

[0006] However, vehicles that are used exclusively for local travel often do not have expensive GNSS onboard units that can be linked to vehicle control systems, and even if a vehicle is equipped with a GNSS onboard unit, it is unable to detect the absolute position of the vehicle in tunnels, underground parking lots, etc., and therefore the technology of Patent Document 1 is sometimes unable to output information corresponding to the vehicle's position.

[0007] Therefore, an object of the present invention is to provide a vehicle control device that can provide information corresponding to the vehicle's position to a passenger or a vehicle control system even when GNSS cannot be used. [Means for solving the problem]

[0008] In order to solve the above problems, the vehicle control device of the present invention comprises an information acquisition device mounted on a vehicle and recognizing the environment outside the vehicle, a landmark detection unit that detects specified landmarks from information obtained by the information acquisition device, an attention drawing object management unit that detects the position of an object to be warned about from the driving history of the vehicle, and a database in which the specified landmarks, the object to be warned about, and their positional relationships are registered, and when the landmark detection unit detects the specified landmark, the object to be warned about the object to be warned about the object to be warned about the vehicle's path of travel or notifies the occupants of the vehicle based on the positional relationship. Effect of the Invention

[0009] According to the vehicle control device of the present invention, even when the GNSS cannot be used, information corresponding to the vehicle's position can be provided to a passenger and a vehicle control system. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is an explanatory diagram of a vehicle according to a first embodiment and its driving environment; [Diagram 2] Diagram of the relative positions of obstacles and vehicles [Diagram 3] Functional block diagram of a vehicle control device according to a first embodiment [Figure 4] Processing flow chart of the vehicle control device according to the first embodiment [Diagram 5] Functional block diagram of a vehicle control device according to a second embodiment [Figure 6] Functional block diagram of a vehicle control device according to a third embodiment [Figure 7] Functional block diagram of a vehicle control device according to a fourth embodiment DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, an embodiment of a vehicle control device of the present invention will be described with reference to the drawings. EXAMPLES

[0012] First, a vehicle control device 100 according to a first embodiment of the present invention will be described with reference to FIGS.

[0013] 1 is an explanatory diagram of a vehicle V equipped with a vehicle control device 100 of this embodiment and an example of its driving environment. In the figure, 1 is a stereo camera, 2 is an ECU (Electronic Control Unit), 3 is a notification device such as a speaker or a display that notifies (notifies) the occupant of information, 4 is a steering device that steers the vehicle V, and 5 is a braking device that decelerates the vehicle V. In addition, a speed bump 200 that is a protrusion for encouraging the driver to decelerate is provided on the path of the vehicle V. Note that the speed bump 200 is an example of an obstacle that the vehicle control device 100 notifies the driver of, but the obstacle to be notified may be, for example, a fallen object on the road surface or unevenness caused by damage to the road surface.

[0014] The stereo camera 1 is an information acquisition device that has two cameras arranged on the left and right sides to capture images of the same object in front of the vehicle from left and right viewpoints, thereby outputting left and right image data, and is mounted, for example, on the upper part of the inner surface of the windshield of the vehicle V.

[0015] The ECU 2 is a control unit that controls each part of the vehicle V based on image data from the stereo camera 1, and is specifically a computer equipped with hardware such as a calculation device such as a CPU, a storage device such as a semiconductor memory, and a wired or wireless communication device. The calculation device executes a program loaded into the storage device to realize various functions described below. In the following, well-known techniques such as general operations of the calculation device and the storage device will be appropriately omitted. Note that, although FIG. 1 illustrates a configuration in which the stereo camera 1 and the ECU 2 are separated, they may be configured as an integrated unit.

[0016] One of the functions achieved by the cooperation between the stereo camera 1 and the ECU 2 is to calculate the distance to an object in the image data based on the difference in appearance (parallax) between the left and right image data captured by the stereo camera 1. A typical stereo camera 1 can calculate the distance to an object using the following formula 1.

[0017]

number

[0018] Here, Z [mm] is the distance to the object, f [mm] is the focal length of the camera, w [mm / px] is the pixel pitch, B [mm] is the distance between the left and right cameras (baseline length), and D [px] is the parallax.

[0019] When calculating the parallax, the left and right image data are aligned horizontally, and a position where the same point is captured in the right image data for a specific point in the left image data is searched for. In order to perform this search efficiently, a parallelization process is generally performed in advance. Here, parallelization means vertical alignment of image data. In other words, it is a process of calibrating image data so that the same point in the left and right image data is captured at the same height. In parallelized image data, when searching for corresponding points, only one horizontal row needs to be searched, and processing efficiency is high. Then, the parallelized left and right image data can be searched for matching positions on the left and right for each block to calculate the distance for each pixel. A plane is estimated from this distance data, and the point cloud on the plane is removed, and the remaining point cloud is grouped into points that are close in distance, making it possible to detect road signs, traffic lights, and obstacles.

[0020] Also, when it is desired to detect small obstacles such as fallen objects, one method is to detect any part of the road along the travel path that is a gentle flat surface as a fallen object, since the road can be assumed to be a gentle flat surface. However, in order to detect low and small steps such as fallen objects, it is necessary to increase the focal length of the stereo camera 1, i.e., to use a zoom lens or a high-resolution camera sensor. In order to cover a wide range of obstacles around the vehicle, a wide field of view is required, and to achieve both, it is necessary to attach a high-pixel sensor or multiple sensors with different focal lengths.

[0021] Informing the driver in advance of a step such as the speed bump 200 as an obstacle is effective in avoiding accidents that occur when the driver passes the step without decelerating. In order to notify the driver of a known step in advance, it is necessary to grasp the vehicle's position relative to the step. However, even if a vehicle without a GNSS onboard device or a vehicle equipped with a GNSS onboard device approaches a known step registered in an obstacle database in an environment where GNSS cannot be used, such as inside a tunnel, the vehicle's position cannot be detected, so that it is difficult to warn the driver of the presence of the step in advance even if the vehicle approaches the known step registered in the obstacle database. Therefore, in the vehicle control device 100 of this embodiment, when a new step (obstacle) is detected, the information of the landmark closest to the step (obstacle) is also registered in the obstacle database, so that the presence of the step (obstacle) can be warned early the next time the landmark is passed.

[0022] <Advance warning by the vehicle control device 100> 2 illustrates an example of the operation of the vehicle control device 100 when the vehicle V approaches a known speed bump 200 registered in the obstacle database of the ECU 2. If the combination of the illustrated road signs and traffic lights is registered in the obstacle database as the nearest landmark to the known speed bump 200, the distance L to the speed bump 200 that has not yet been detected by the stereo camera 1 at the time when the ECU 2 detects the landmark (the combination of the road signs and traffic lights) in FIG. 2(a) is calculated as 1 In this example, the vehicle V is a vehicle used exclusively for nearby travel, and there is no other combination of the indicated contents of the road signs, the shapes and positions of the road signs and traffic signals, the distances between the road signs and traffic signals, and the like, as shown in the figure, in the daily travel range of the vehicle V, and it is assumed that the vehicle position and travel direction of the vehicle V can be uniquely identified based on the combination of these landmark information.

[0023] After that, in FIG. 2(b), the distance to the speed bump 200 is a predetermined distance L 2When the speed bump 200 reaches the threshold, the ECU 2 issues an advance warning to the driver of the presence of the speed bump 200 via the notification device 3. This allows the driver to sufficiently decelerate the vehicle V before the vehicle V reaches the speed bump 200, and to safely pass the speed bump 200 at a low speed, as shown in Fig. 2(c). If the driver does not sufficiently decelerate the vehicle V after the warning, the ECU 2 may control the braking device 5 to assist in deceleration.

[0024] <Functional block diagram of the vehicle control device 100> 3 is a functional block diagram of the vehicle control device 100 of this embodiment. As shown in this figure, the ECU 2 includes an image input unit 21, a distance measurement unit 22, an object detection unit 23, a landmark detection unit 24, a vehicle behavior estimation unit 25, and an obstacle management unit 26. Each unit will be described in detail below. Note that when a LiDAR is used as the information acquisition device instead of the stereo camera 1, the image input unit 21 may be omitted.

[0025] The image input unit 21 is an interface for inputting image data captured by the stereo camera 1. When left and right image data captured at the same time are synchronously input, distances and objects can be determined more accurately in subsequent processing. The image data input to the image input unit 21 is stored in a storage device (not shown) of the ECU 2.

[0026] The distance measurement unit 22 performs the calculation of the above-mentioned formula 1 for each pixel of the left and right image data input from the stereo camera 1, and calculates three-dimensional data such as distance data for each pixel. The calculated three-dimensional data is stored in a storage device (not shown) of the ECU 2.

[0027] The object detection unit 23 detects an area where an object exists (object area) based on image data from the image input unit 21 or three-dimensional data from the distance measurement unit 22. Methods for detecting an object area include a method for detecting a pattern of a person or a car from image data, and a method for grouping areas with a short distance from distance data included in three-dimensional data. In addition, a method for detecting a road step such as a speed bump 200 includes a method for detecting a road portion that is a plane in the traveling direction and detecting unevenness of the road surface from its depth height information. In order to detect unevenness of the road surface, the maximum and minimum values ​​of the depth height information are detected, and points corresponding to the time series are tracked along the movement of the vehicle, and the points where tracking has been successful multiple times are set as the positions of the steps, so that the steps can be detected with high accuracy. In addition, instead of detecting the maximum and minimum values ​​of the road surface, there is also a method for learning which positions are steps by machine learning using depth height data as input as teacher data. According to this method, it becomes possible to detect steps with complex shapes and multiple consecutive steps, which is effective in improving detection accuracy.

[0028] The landmark detection unit 24 detects landmark information by using the image data from the image input unit 21 or the three-dimensional data from the distance measurement unit 22. The landmark information detected here is, for example, the indications on road signs, the shapes and positions of road signs and traffic signals, the distance between landmarks, etc.

[0029] The vehicle behavior estimation unit 25 calculates the vehicle behavior such as the moving path based on the vehicle speed, yaw rate, steering angle, etc. of the vehicle. In this embodiment, the vehicle speed, yaw rate, and steering angle of the vehicle are listed as inputs to the vehicle behavior estimation unit 25, but a method of estimating the amount of movement of the camera by tracking points in image data may also be used. In that case, it becomes unnecessary to use the sensor outputs such as the vehicle speed, yaw rate, and steering angle of the vehicle.

[0030] The obstacle management unit 26 manages an obstacle database stored in a storage device (not shown) of the ECU 2, and controls each part of the vehicle V while referring to the obstacle database. Specifically, when the object detection unit 23 detects an unknown obstacle, the obstacle management unit 26 registers a combination of the obstacle and the immediately preceding landmark information in the obstacle database. On the other hand, when the landmark detection unit 24 detects a landmark registered in the obstacle database, the obstacle management unit 26 notifies the driver of the approach to the obstacle in advance via the notification device 3 when the vehicle V approaches an obstacle corresponding to the landmark information, and outputs a command to the steering device 4 and the braking device 5 to safely pass the obstacle. For this reason, the obstacle management unit 26 stores the movement trajectory of the host vehicle obtained from the host vehicle behavior estimation unit 25 from the time the landmark detection unit 24 detects the landmark.

[0031] As described above, the storage device of the ECU 2 stores image data, three-dimensional data, an obstacle database, and the like. However, since the memory capacity of the storage device is limited, it is advisable to repeatedly use a certain amount. Also, when many landmarks are found, it is desirable to store the data output from the obstacle management unit 26 when the amount of movement is greater than a certain distance. By storing only particularly prominent landmarks within a certain interval, it is possible to store information for a wide area, and the memory capacity of the storage device can be reduced, improving the ease of installation in inexpensive systems.

[0032] <Processing flowchart of the vehicle control device according to the present embodiment> Next, specific processing contents of the vehicle control device 100 of this embodiment will be described with reference to the processing flowchart of FIG.

[0033] First, in step S1, the stereo camera 1 captures an image of the area in front of the vehicle and generates left and right image data. Then, the image input unit 21 of the ECU 2 stores the left and right image data acquired from the stereo camera 1 in a storage device.

[0034] Next, in step S2, the distance measurement unit 22 calculates the distance for each pixel based on the left and right image data stored in the storage device, and stores the calculated distance in the storage device as three-dimensional data.

[0035] In step S3, the object detection unit 23 detects an object based on the image data or three-dimensional data, and determines the type of the object.

[0036] In step S4, the landmark detection unit 24 determines whether the object detected in step S3 is a landmark registered in the obstacle database, and if it is a registered landmark, the process proceeds to step S5, and if not, the process proceeds to step S6.

[0037] In step S5, the obstacle management unit 26 reads the relative position of the obstacle corresponding to the landmark from the obstacle database, and based on the vehicle position estimated based on the output of the vehicle behavior estimation unit 25, warns the driver of the presence of the obstacle in front of the obstacle via the notification device 3 (see FIG. 2), and notifies the vehicle control system of the obstacle position via the communication device. Then, the process returns to step S1.

[0038] On the other hand, in step S6, it is determined whether the object detected in step S3 is an obstacle not yet registered in the obstacle database. If the object detected is an unknown obstacle, the process proceeds to step S7, and if not, the process returns to step S1.

[0039] In step S7, the landmark detection unit 24 detects landmark information closest to the unknown obstacle based on the left and right image data or three-dimensional data stored in the storage device.

[0040] In step S8, the obstacle management unit 26 associates the new obstacle with information about the landmark closest to the obstacle and registers the new obstacle in the obstacle database.

[0041] According to the vehicle control device of the present embodiment described above, when a landmark registered in the obstacle database is detected based on the output of the stereo camera, the presence of an obstacle corresponding to the landmark is warned to the driver or notified to the vehicle control system. Therefore, even when GNSS cannot be used, information corresponding to the vehicle's position can be provided to the occupants and the system. EXAMPLES

[0042] Next, a vehicle control device 100 according to a second embodiment of the present invention will be described with reference to Fig. 5. Note that a duplicated description of points common to the first embodiment will be omitted.

[0043] The vehicle control device 100 of this embodiment is provided with a signage management unit 27 instead of the obstacle management unit 26 of the first embodiment. When the vehicle V approaches a predetermined position, this signage management unit 27 notifies the driver and passengers of signage information registered in the signage database of the ECU 2 via the notification device 3. Note that the signage is information similar to an advertisement, such as an advertisement for a nearby restaurant.

[0044] For example, in an environment where image format information such as a QR code (registered trademark) is drawn on a wall surface or the like in front of the vehicle V, the object detection unit 23 can obtain signage information by decoding the image format information in the image data captured by the stereo camera 1. Then, by combining this signage information with the landmark information closest to the image format information and registering it in the signage database, it is possible to notify the occupant of the vehicle V of signage information corresponding to the image format information of a position that cannot yet be imaged at the time the landmark detection unit 24 detects the landmark information. Note that it is not necessary to use the stereo camera 1 to register the signage information, and for example, the signage information may be registered by wireless communication using a wireless communication device of the EUC 2.

[0045] In this way, if signage information can be registered from outside, any information can be notified to the driver, etc. at any location, so even if the vehicle V is not equipped with a GNSS onboard unit, it can display advertisements based on the vehicle's position or realize applications such as computer games that utilize virtual reality spaces. EXAMPLES

[0046] Next, a vehicle control device 100 according to a third embodiment of the present invention will be described with reference to Fig. 6. Note that a duplicated description of points common to the above-mentioned embodiments will be omitted.

[0047] The notification device 3 in Example 1 notifies an obstacle which is the output of the obstacle management unit 26, and the notification device 3 in Example 2 notifies a signage which is the output of the signage management unit 27. However, in the vehicle control device 100 in this example, an obstacle which is the output of the obstacle management unit 26 is notified by the notification device 3, and a signage which is the output of the signage management unit 27 is notified by the mobile terminal 6.

[0048] Because obstacle and signage notifications have different levels of importance to drivers, different notification sounds are often assigned to each type of information. However, because it requires a certain amount of learning to distinguish the information type from the notification sound, it is not only cumbersome for users, but also difficult for them to make quick decisions and understand the information content immediately.

[0049] Therefore, in this embodiment, the notification destinations of the obstacle information and the signage information are made different. That is, a mobile terminal 6 such as a smartphone is registered in advance in the vehicle control device 100, and the obstacle information is notified to the in-vehicle notification device 3, and the signage information is notified to the mobile terminal 6, so that the driver can easily distinguish the types of information. Note that the obstacle information may be notified to the driver's mobile terminal (not shown), and the signage information may be notified to the passenger's mobile terminal 6.

[0050] This makes it possible to notify low-priority signage information while ensuring the safety of the driver. In addition, it has the advantage of being able to reconcile warnings about obstacles with other priorities, so important information can be reliably notified. EXAMPLES

[0051] Next, a vehicle control device 100 according to a fourth embodiment of the present invention will be described with reference to Fig. 7. Note that a duplicated description of points common to the above-mentioned embodiments will be omitted.

[0052] In the above embodiment, the vehicle position is estimated based on the output of the vehicle behavior estimation unit 25, but if the vehicle V is equipped with GNSS7, the vehicle position can be estimated more accurately by using the output of the GNSS7. Therefore, in this embodiment, the vehicle position is estimated using the output of the GNSS7 in an environment where the GNSS7 can be used, and the vehicle position is estimated using the output of the vehicle behavior estimation unit 25 in an environment where the GNSS7 cannot be used (for example, inside a tunnel, an indoor parking lot, etc.).

[0053] 7, when the ECU 2 and the GNSS 7 are linked, the obstacle management unit 26 can receive the position information of the vehicle from the GNSS 7, and therefore in an environment where the GNSS 7 can be used, the obstacle can be notified to the driver in advance by comparing the position information from the GNSS 7 with the position information of the obstacle registered in the obstacle database. However, when the position information cannot be correctly received from the GNSS 7, the obstacle is notified in advance based on the relationship between the position where the landmark detection unit 24 detected the landmark and the vehicle position estimated from the output of the vehicle behavior estimation unit 25, as in each of the above-mentioned embodiments. EXAMPLES

[0054] Next, a vehicle control device 100 according to a fifth embodiment of the present invention will be described. Note that a duplicated description of points common to the above-mentioned embodiments will be omitted. In this embodiment, a method for improving the accuracy of landmark detection will be described.

[0055] In this embodiment, road surface gradient information is used as landmark information to be registered in the database. In FIG. 2, road signs and traffic signals are used as landmarks, but these may be removed or newly installed. In contrast, road surface gradient information obtained by detecting the planar parts of the three-dimensional information is more permanent than road signs and traffic signals, and is also robust to environmental changes such as road surface conditions and snowfall and rainfall. Therefore, by registering road surface gradient information in the database as landmark information, landmarks can be detected even if road signs, traffic signals, etc. are removed. Since road surface gradients are unlikely to change, there is a high possibility that they can be used as landmark information for a long period of time. EXAMPLES

[0056] Next, a vehicle control device 100 according to a sixth embodiment of the present invention will be described. Note that a duplicated description of points common to the above-mentioned embodiments will be omitted. In this embodiment, a high-speed search method for landmark information will be described.

[0057] Since landmark information is positional relationship information of objects around the vehicle V, if multiple points are registered, generating the landmark information requires a large calculation cost. Therefore, in this embodiment, the image input unit 21 monotonizes the image data (narrowing down the road type from lane width, road color, width information, and sign information) and divides the landmarks to be searched for, thereby reducing the number of searches and enabling landmark information to be searched for quickly. This makes it possible to store and search for a large amount of landmark information using few CPU resources. EXAMPLES

[0058] Next, a vehicle control device 100 according to a seventh embodiment of the present invention will be described. Note that overlapping explanations of points common to the above-mentioned embodiments will be omitted. In this embodiment, a method for registering landmark information and a method for using the landmark information in an environment where a moving object other than the vehicle itself exists will be described.

[0059] Although Fig. 2 shows an example of an environment where there are no vehicles other than the vehicle itself, there are usually many other vehicles besides the vehicle itself that are moving or stopped. As landmarks, structures that do not change easily must be selected, but in an environment where stopped vehicles exist, the following problems arise.

[0060] For example, if landmark information including a stopped vehicle is registered in the database, after the stopped vehicle moves, the landmark information detected by the landmark detection unit 24 will not match the landmark information registered in the database, and there is a possibility that an obstacle will not be notified even if the vehicle reaches a position where an obstacle should be notified. Therefore, in this embodiment, structures that may move, such as stopped vehicles, are excluded from the landmarks.

[0061] In addition, when there is another vehicle, even if a structure suitable as a landmark is present in the blind spot of the other vehicle, it may not be registered correctly. Therefore, in this embodiment, when the same feature is detected multiple times, that is, when the same road is passed multiple times and the same landmark is repeatedly extracted, the landmark is registered as landmark information, thereby making it possible to register landmark information that does not include moving objects.

[0062] Furthermore, in an environment where other vehicles, etc. are present, some landmarks may be hidden by the other vehicles, etc., and landmark information that should be detectable may not be detected. Therefore, in this embodiment, the position of the blind spot is estimated from the position of the other vehicle, and the position is excluded from candidates for landmark information, and it is determined whether the detected landmark is a landmark registered in the database, thereby preventing estimation failures when estimating the vehicle position. EXAMPLES

[0063] Next, a vehicle control device 100 according to an eighth embodiment of the present invention will be described. Note that the overlapping description of points common to the above-mentioned embodiments will be omitted. In this embodiment, a method for updating the database in the case where a related obstacle cannot be detected after landmark information registered in the database is detected will be described.

[0064] Since road conditions change from moment to moment, for example, an obstacle registered in the obstacle database may disappear from the road due to repairs. Therefore, in this embodiment, if the stereo camera 1 cannot detect an obstacle at a position a predetermined distance from the landmark, the landmark information registered in the database is deleted. However, since there is a possibility that the obstacle was not detected by chance, the obstacle is deleted from the database when the obstacle is not detected multiple times, so that the problem of erroneously deleting an actual obstacle can be prevented. In addition, when a stereo camera is used, the reliability is high when the effective parallax is large, so if an obstacle is not detected when the effective parallax is large, it is deleted immediately. This allows for quick deletion and keeps the information up to date.

[0065] Each of the above configurations may be partially or entirely configured as hardware, or may be configured to be realized by executing a program on a processor. Also, the control lines and information lines are shown as those considered necessary for the explanation, and not all of the control lines and information lines are shown in the product. In reality, it may be considered that almost all of the configurations are connected to each other. [Explanation of symbols]

[0066] V vehicle, 100 Vehicle control device, 1 stereo camera, 2 ECU, 21 Image input unit, 22 distance measuring unit, 23 object detection unit, 24 Landmark detection unit, 25 Vehicle behavior estimation unit, 26 Obstacle Management Division, 27 Signage Management Department, 3. Notification device, 4 Steering gear, 5 braking device, 6 mobile devices, 7 GNSS, 200 Speed ​​Bump

Claims

1. An information acquisition device mounted on a vehicle and configured to recognize an environment outside the vehicle; a landmark detection unit that detects a predetermined landmark from the information obtained by the information acquisition device; an attention-attracting object management unit that detects a position of an attention-attracting object from a driving history of the vehicle; a database in which the predetermined landmark, the attention-calling object, and a positional relationship therebetween are registered; the attention-attracting object management unit is a vehicle control device that, when the landmark detection unit detects the predetermined landmark, controls the vehicle or notifies an occupant of the vehicle regarding the attention-attracting object on a traveling path of the vehicle based on the positional relationship, The attention-attracting object is an obstacle and a signage, the database is an obstacle database in which a positional relationship between the predetermined landmark and the obstacle is registered, and a signage database in which a positional relationship between the predetermined landmark and the signage is registered, The vehicle control device is characterized in that the attention-attention object management unit notifies the driver of the obstacle and notifies passengers of the signage.

2. The vehicle control device according to claim 1, The vehicle control device is characterized in that the attention-attracting object management unit notifies an in-vehicle alarm device of the obstacle and notifies a mobile terminal of the signage.

3. The vehicle control device according to claim 1, The vehicle control device is characterized in that the attention-attention object management unit notifies the driver of the obstacle to a mobile device and notifies a passenger of the signage to a mobile device.

4. An information acquisition device mounted in a vehicle and recognizing an environment outside the vehicle; a landmark detection unit that detects a predetermined landmark from the information obtained by the information acquisition device; an attention-attracting object management unit that detects a position of an attention-attracting object from a driving history of the vehicle; a database in which the predetermined landmark, the attention-calling object, and a positional relationship therebetween are registered; the attention-attracting object management unit is a vehicle control device that, when the landmark detection unit detects the predetermined landmark, controls the vehicle or notifies an occupant of the vehicle regarding the attention-attracting object on a traveling path of the vehicle based on the positional relationship, In addition, the vehicle is equipped with a GNSS vehicle-mounted device that stores map information and acquires location information. The attention-attention object management unit is In an environment where the GNSS vehicle-mounted device can be used, the vehicle is controlled or a passenger of the vehicle is notified based on the position information acquired from the GNSS vehicle-mounted device; A vehicle control device characterized in that, in an environment where the GNSS vehicle-mounted device cannot be used, the vehicle is controlled or a passenger of the vehicle is notified based on position information estimated from the driving history of the vehicle.

5. An information acquisition device mounted in a vehicle and recognizing an environment outside the vehicle; a landmark detection unit that detects a predetermined landmark from the information obtained by the information acquisition device; an attention-attracting object management unit that detects a position of an attention-attracting object from a driving history of the vehicle; a database in which the predetermined landmark, the attention-calling object, and a positional relationship therebetween are registered; the attention-attracting object management unit is a vehicle control device that, when the landmark detection unit detects the predetermined landmark, controls the vehicle or notifies an occupant of the vehicle regarding the attention-attracting object on a traveling path of the vehicle based on the positional relationship, The vehicle control device is characterized in that the attention-attention object management unit estimates blind spots from the positions of other vehicles recognized by the information acquisition device, and excludes the blind spot areas from the landmark detection areas.

6. An information acquisition device mounted in a vehicle and recognizing an environment outside the vehicle; a landmark detection unit that detects a predetermined landmark from the information obtained by the information acquisition device; an attention-attracting object management unit that detects a position of an attention-attracting object from a driving history of the vehicle; a database in which the predetermined landmark, the attention-calling object, and a positional relationship therebetween are registered; the attention-attracting object management unit is a vehicle control device that, when the landmark detection unit detects the predetermined landmark, controls the vehicle or notifies an occupant of the vehicle regarding the attention-attracting object on a traveling path of the vehicle based on the positional relationship, A vehicle control device characterized in that if an attention-attention object registered in the database cannot be detected based on the output of the information acquisition device, the attention-attention object management unit deletes the attention-attention object registered in the database.

Images