Vehicle control device

Abstract

To provide a vehicle control device capable of preventing inappropriate vehicle control caused by erroneous recognition of a structure on a road as a predetermined feature.SOLUTION: A vehicle control device comprises: a storage section 22 which stores structure information representing a location and a type of a structure visually recognizable from a vehicle traveling in a predetermined road section and similarity relation information representing either information on vehicle travel or a similarity relation between a predetermined feature affecting the vehicle travel and the structure; a detection section 31 which detects the predetermined based on an image, showing a surrounding situation of the vehicle 10, generated by a camera 2 mounted on the vehicle 10; a determination section 32 which determines whether the predetermined feature detected while the vehicle 10 is traveling in the predetermined road section is erroneously recognized as the structure based on the similarity relation information and the structure information; and a vehicle control section 33 which controls travel of the vehicle 10 depending on whether the detected feature is erroneously recognized as the structure.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to a vehicle control device. [Background technology]

[0002] In order to identify the vehicle's own position, a technique has been proposed in which predetermined features existing around the vehicle are recognized using images generated by an on-board camera (see Patent Document 1).

[0003] The self-localization system disclosed in Patent Document 1, when successful in image recognition of a target feature, determines whether there is a possibility of erroneous recognition, that is, the possibility that an object different from the target feature, the existence of which is known in advance, may have been image-recognized as the target feature. If this self-localization system determines that there is a possibility of erroneous recognition, it does not need to correct estimated self-location information based on the image recognition result of the target feature and target feature information. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2012-215442 Summary of the Invention [Problem to be solved by the invention]

[0005] Roads may be equipped with structures that resemble certain features that represent information about vehicle travel (for example, snow melting pipes that resemble lane markings). When an autonomous vehicle is traveling on a road section equipped with such structures, the vehicle control system may mistakenly recognize the structures in images obtained by the onboard camera as similar features, which may result in inappropriate vehicle control.

[0006] Therefore, an object of the present invention is to provide a vehicle control device that can prevent inappropriate vehicle control from being performed due to the false recognition of a structure on a road as a predetermined feature. [Means for solving the problem]

[0007] A vehicle control device provided in one embodiment has a memory unit that stores structure information indicating the position and type of structures visible from a vehicle traveling on a specified road section, feature information indicating the position and number of specified features that are located on the specified road section and that represent information related to the vehicle's travel or that affect the vehicle's travel, and similarity relationship information that indicates the similarity relationship between the specified features and the structures, a detection unit that detects the specified features based on an image that represents the situation around the vehicle and is generated by a camera located on the vehicle, a determination unit that determines whether the specified features detected while the vehicle is traveling on the specified road section are a misidentified structure based on the structure information, feature information, and similarity relationship information, and a vehicle control unit that controls the vehicle's travel depending on whether the detected specified features are a misidentified structure.

[0008] In one embodiment, the determination unit determines that at least one of the detected specified features is a misidentified structure if the number of specified features detected in a specified road section is greater than the number of specified features represented in the feature information, or if the position of the detected specified feature is closer to the position represented in the structure information for a structure similar to the detected specified feature, as represented in the similarity relationship information, than the position of the corresponding feature represented in the feature information.

[0009] In one embodiment, the structure is a snow melting pipe and the specified feature is a lane marking, the memory unit further stores map information representing the positional relationship between the snow melting pipe and the lane marking, and when the vehicle control unit determines that the specified feature detected in a specified road section has been mistakenly recognized as a snow melting pipe, it controls the vehicle's driving to maintain the specified positional relationship with respect to the lane marking based on the positional relationship between the snow melting pipe and the lane marking represented in the map information and the relative position of the snow melting pipe that has been mistakenly recognized as a lane marking with respect to the vehicle.

[0010] In one embodiment, the structure is a vehicle guide line and the specified feature is a lane marking, and when the vehicle control unit determines that the specified feature detected in a specified road section has been mistakenly recognized as a vehicle guide line, it controls the vehicle's travel so that the vehicle travels across the vehicle guide line that has been mistakenly recognized as a lane marking.

[0011] In one embodiment, the structure is a pattern that resembles a three-dimensional structure installed on the road surface, and the specified feature is a three-dimensional structure, and when the vehicle control unit determines that the specified feature detected in a specified road section is a mistakenly recognized three-dimensional structure, it controls the vehicle's driving so that it does not stop near the pattern that has been mistakenly recognized as a three-dimensional structure. [Effects of the Invention]

[0012] The vehicle control device according to the present disclosure has the effect of preventing inappropriate vehicle control from being performed due to the false recognition of a structure on a road as a predetermined feature. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a schematic configuration diagram of a vehicle control system in which a vehicle control device is implemented. [Figure 2] FIG. 2 is a functional block diagram of a processor of an electronic control device that is an embodiment of a vehicle control device. [Figure 3] FIG. 10 is a diagram showing an example of a detected feature and a structure similar to the feature. [Figure 4] FIG. 10 is a diagram showing another example of a detected feature and a structure similar to the feature. [Figure 5] FIG. 10 is a diagram showing another example of a detected feature and a structure similar to the feature. [Figure 6] 4 is an operational flowchart of a vehicle control process. DETAILED DESCRIPTION OF THE INVENTION

[0014] A vehicle control device, a vehicle control method, and a computer program for vehicle control executed on the vehicle control device will be described below with reference to the drawings. The vehicle control device uses information about a predetermined feature detected from an image showing the vehicle's surroundings generated by an onboard camera for automatic vehicle driving control or driving assistance for the vehicle driver. In this case, the vehicle control device references feature information about the predetermined feature, similarity relationship information showing a similarity relationship between the predetermined feature and a structure visible from the vehicle traveling on a predetermined road section, and structure information showing the location and type of the structure to determine whether a predetermined feature detected while the vehicle is traveling on the road section is a false recognition of the structure. The vehicle control device then controls the vehicle's driving depending on whether the detected predetermined feature is a false recognition of a structure, thereby preventing inappropriate vehicle control due to false recognition.

[0015] FIG. 1 is a schematic configuration diagram of a vehicle control system in which a vehicle control device is implemented. In this embodiment, the vehicle control system 1 is mounted on a vehicle 10 and controls the vehicle 10. The vehicle control system 1 includes a camera 2, a GPS receiver 3, a storage device 4, and an electronic control unit (ECU) 5, which is an example of a vehicle control device. The camera 2, the GPS receiver 3, the storage device 4, and the ECU 5 are communicably connected via an in-vehicle network. The vehicle control system 1 may further include a distance measurement sensor (not shown), such as a LiDAR or radar, that measures the distance to an object present around the vehicle 10. The vehicle control system 1 may also include a wireless communication terminal (not shown) for wireless communication with devices external to the vehicle 10.

[0016] Camera 2 is an example of a sensor that generates a sensor signal that represents the situation around vehicle 10, and is attached to vehicle 10 facing a predetermined area (for example, the area in front of vehicle 10) including the road surface around vehicle 10 so that the predetermined area is included in the shooting range of camera 2. Camera 2 then captures an image of the predetermined area at a predetermined shooting interval (for example, 1 / 30 to 1 / 10 seconds) and generates an image showing the predetermined area. Note that vehicle 10 may be provided with multiple cameras with different shooting directions or focal lengths.

[0017] Every time the camera 2 generates an image, it outputs the generated image to the ECU 5 via the in-vehicle network.

[0018] The GPS receiver 3 receives GPS signals from GPS satellites at predetermined intervals and determines the own position of the vehicle 10 based on the received GPS signals. Then, the GPS receiver 3 outputs positioning information indicating the positioning results of the own position of the vehicle 10 based on the GPS signals to the ECU 5 via the in-vehicle network at predetermined intervals. The vehicle 10 may have, instead of a GPS receiver, a receiver that receives positioning signals from satellites of another satellite positioning system to determine the own position of the vehicle 10.

[0019] The storage device 4 is an example of a storage unit, and includes, for example, a hard disk drive, a nonvolatile semiconductor memory, or an optical recording medium and its access device. The storage device 4 stores map information. The map information includes feature information for each road section included in a specific area represented by the map information, which indicates the location, number, and type of specific features installed in that road section. The specific features represent information related to the vehicle 10's travel or affect the vehicle's travel. The specific features include road markings such as lane markings or stop lines, road signs indicating stop signs, traffic lights, and three-dimensional structures installed on the road, such as blocks or cones that restrict vehicle entry or slow down vehicles. The map information further includes, for each road section, structure information for the location and type of structures visible from the vehicle 10 traveling on that road section, and similarity relationship information for indicating the similarity relationship between the structures and the specific features. The structures include snow-melting pipes, vehicle guide lines, patterns resembling three-dimensional structures, and signs. Furthermore, structures may include structures that resemble specific features only during a certain period of time, such as the moon. For such structures, the structure information may include information indicating their orientation or position as viewed from a specific road section at each date and time. Furthermore, the similarity relationship information associates, for each type of structure, the type of feature that has a similar appearance to the structure on the image. For example, the similarity relationship information may be expressed in a list format. As a specific example, the similarity relationship information indicates that a snow-melting pipe, which is an example of a structure, is similar to a lane marking, which is an example of a feature. Furthermore, the similarity relationship information indicates that a vehicle guide line, which is another example of a structure, is similar to a lane marking. Furthermore, the similarity relationship information indicates that a certain type of sign, which is yet another example of a structure, is similar to a specific road sign, which is yet another example of a feature. Furthermore, the similarity relationship information indicates that a pattern simulating a three-dimensional structure drawn on a road surface, which is yet another example of a structure, is similar to that three-dimensional structure, which is yet another example of a feature. Furthermore, the similarity relationship information indicates that the moon, which is yet another example of a structure, is similar to a traffic light, which is yet another example of a feature.The map information may also include information on the presence or absence of lane markings in each road section, the number of lanes, the width of each lane, and facilities installed on the road, such as toll booths. Furthermore, the map information may include information that indicates the positional relationship between a specific feature indicated in the feature information and a structure similar to the specific feature indicated in the structure information (for example, the position of the specific feature and the position of the structure, or the direction and relative distance from the specific feature to the structure). Furthermore, the map information may also include information that indicates the position and range of the section where the snow-melting pipes are installed.

[0020] Furthermore, the storage device 4 may have a processor for executing processing related to updating the map information and processing related to a request to read out the map information. The storage device 4 may transmit a request to obtain map information together with the current position of the vehicle 10 to a map server (not shown) via a wireless communication terminal every time the vehicle 10 moves a predetermined distance. The storage device 4 may then receive map information for a predetermined area around the current position of the vehicle 10 from the map server via the wireless communication terminal. Furthermore, when the storage device 4 receives a request to read out the map information from the ECU 5, the storage device 4 extracts from the stored map information an area that includes the current position of the vehicle 10 and is relatively smaller than the predetermined area, and outputs the map information for that area to the ECU 5 via the in-vehicle network.

[0021] The ECU 5 executes vehicle control processing for the vehicle 10 .

[0022] The ECU 5 includes a communication interface 21, a memory 22, and a processor 23. The communication interface 21, the memory 22, and the processor 23 may be configured as separate circuits, or may be integrated into a single integrated circuit.

[0023] The communication interface 21 has an interface circuit for connecting the ECU 5 to an in-vehicle network. The communication interface 21 passes the images received from the camera 2, the positioning information received from the GPS receiver 3, and the map information read from the storage device 4 to the processor 23.

[0024] The memory 22 is another example of a storage unit and includes, for example, a volatile semiconductor memory and a non-volatile semiconductor memory. The memory 22 stores various data used in the vehicle control process executed by the processor 23. For example, the memory 22 stores parameters of the camera 2, such as the focal length, shooting direction, and installation position, as well as various parameters for identifying an object detection classifier used to detect features, etc. The memory 22 also stores positioning information of the vehicle 10, images of the surroundings of the vehicle 10, and map information. The memory 22 also temporarily stores various data generated during the vehicle control process.

[0025] The processor 23 includes one or more central processing units (CPUs) and their peripheral circuits. The processor 23 may further include other arithmetic circuits such as a logic operation unit, a numerical operation unit, or a graphics processing unit. The processor 23 executes vehicle control processing for the vehicle 10 at predetermined intervals.

[0026] 2 is a functional block diagram of the processor 23 related to vehicle control processing. The processor 23 has a detection unit 31, a determination unit 32, and a vehicle control unit 33. Each of these units in the processor 23 is, for example, a functional module realized by a computer program running on the processor 23. Alternatively, each of these units in the processor 23 may be a dedicated arithmetic circuit provided in the processor 23.

[0027] The detection unit 31 detects predetermined features based on images representing the situation around the vehicle 10, generated by the camera 2. To this end, the detection unit 31 detects the predetermined features depicted in the images by inputting the images into a classifier that has been trained in advance to detect the predetermined features. The classifier may be configured, for example, as a convolutional neural network (CNN) for object detection, such as a Single Shot MultiBox Detector or Faster R-CNN, or as a CNN for semantic segmentation, such as U-Net. Alternatively, the classifier may be configured as a deep neural network (DNN) with an attention mechanism, such as a Vision Transformer. Alternatively, the classifier may be a classifier based on a machine learning method other than a DNN, such as a support vector machine. The classifier is trained in advance according to a predetermined learning method, such as backpropagation, using a large number of training images, including images depicting any type of feature to be detected.

[0028] The detection unit 31 determines that a feature of any type is represented in an area where the reliability calculated by the classifier, which indicates the likelihood that the feature of that type is represented, is equal to or greater than a predetermined detection threshold. The area in which the detected feature is represented is hereinafter referred to as an object area. When the detection unit 31 detects a feature from an image, it notifies the determination unit 32 and the vehicle control unit 33 of the type of the detected feature and the object area in which the feature is represented. Furthermore, the detection unit 31 notifies the determination unit 32 of the position of the vehicle 10 indicated in the positioning information generated at the time closest to the generation time of the image in which the feature was detected, as the position of the vehicle 10 at the time the feature was detected.

[0029] The determination unit 32 determines whether or not the detected feature is a falsely recognized structure based on the feature information, structure information, and similarity relationship information contained in the map information.

[0030] The determination unit 32 refers to the position of the vehicle 10 when the feature was detected and map information to identify the road section on which the vehicle 10 was traveling when the feature was detected. The determination unit 32 then refers to both the structure information and the similarity relationship information to determine whether or not the identified road section contains a structure similar to the detected feature. If the identified road section does not contain a structure similar to the detected feature, the determination unit 32 determines that the feature was correctly detected. On the other hand, if the identified road section contains a structure similar to the detected feature, the determination unit 32 determines whether or not the detected feature is a misidentified structure, depending on the type of the detected feature.

[0031] If the detected feature is a lane marking and a snow melting pipe, which is an example of a structure similar to a lane marking, is installed in the road section on which the vehicle 10 is traveling, the determination unit 32 refers to the feature information included in the map information and determines whether or not a lane marking is installed in that road section. For example, if the feature information for the road section on which the vehicle 10 is traveling indicates that the section does not have a lane marking, the determination unit 32 determines that the detected lane marking is a misidentified snow melting pipe.

[0032] Furthermore, if the number of detected lane markings is greater than the number of lane markings indicated in the feature information for the road section on which the vehicle 10 is traveling, the determination unit 32 determines that one of the detected lane markings is a mistaken recognition of a snow-melting pipe.

[0033] In this case, the determination unit 32 may compare the image with map information to estimate the exact position of the vehicle 10, and then estimate the position of each detected lane marking based on the estimation result.The determination unit 32 may then determine that a detected lane marking that is closer to a snow-melting pipe than any lane marking represented in the feature information included in the map information has been mistakenly recognized as a snow-melting pipe.

[0034] The determination unit 32 projects each of one or more features detected from the image onto map information using parameters of the camera 2, such as the installation position, shooting direction, and focal length, assuming the position and traveling direction of the vehicle 10. Preferably, these features are features other than lane markings. The determination unit 32 then calculates the total amount of positional deviation between each of the detected features and each of the corresponding features represented in the feature information. The determination unit 32 repeats the above process while varying the assumed position and traveling direction of the vehicle 10, and estimates the position and traveling direction of the vehicle 10 when the total amount of positional deviation is minimum as the actual position and traveling direction of the vehicle 10.

[0035] Furthermore, even if the number of detected lane markings is equal to or less than the number of lane markings indicated in the feature information, the determination unit 32 may estimate the position of each lane marking in the same manner as described above. If the estimated position of any lane marking is closer to a snow melting pipe than any lane marking indicated in the feature information, the determination unit 32 may determine that the detected lane marking is a misidentified snow melting pipe. Note that, if the estimated positions of all detected lane markings are closer to any lane marking than the snow melting pipe indicated in the structure information, the determination unit 32 determines that the detection results for all lane markings are correct.

[0036] Since the snow melting pipe is installed on the road surface and parameters such as the installation position of camera 2 are known, if any of the detected lane markings is a mistaken recognition of a snow melting pipe, the determination unit 32 can estimate the position of the snow melting pipe relative to camera 2 based on the position of the mistakenly recognized lane marking on the image, i.e., the position of the snow melting pipe.

[0037] By performing similar processing when the detected feature is a lane marking and a vehicle guide line, which is another example of a structure similar to a lane marking, is provided in the road section on which the vehicle 10 is traveling, the determination unit 32 can determine whether the detected lane marking is a false recognition of the vehicle guide line. Furthermore, the determination unit 32 can estimate the position of the vehicle guide line relative to the camera 2 based on the position of the vehicle guide line on the image.

[0038] Furthermore, even if the detected feature is a specific road sign and a signboard, which is an example of a structure similar to the road sign, is installed in a position visible from the vehicle 10 in the road section on which the vehicle 10 is traveling, the determination unit 32 performs the above-mentioned process of matching the image with the map information to estimate the position of the detected road sign. If the estimated position of the detected road sign is closer to the signboard than the corresponding road sign represented in the feature information, the determination unit 32 determines that the detected road sign is a misrecognized signboard. Furthermore, even if the detected road sign is not represented in the feature information in the road section on which the vehicle 10 is traveling, the determination unit 32 may determine that the detected road sign is a misrecognized signboard. On the other hand, if the estimated position of the detected road sign is closer to the corresponding road sign than the signboard represented in the structure information, the determination unit 32 determines that the detection result for the road sign is correct.

[0039] Furthermore, even if the detected feature is a three-dimensional structure on the road surface and a pattern on the road surface, which is an example of a structure similar to the three-dimensional structure, is present in the road section on which the vehicle 10 is traveling, the determination unit 32 performs the above-mentioned process of comparing the image with the map information to estimate the position of the detected three-dimensional structure. If the estimated position of the three-dimensional structure is closer to the pattern than to the corresponding three-dimensional structure, the determination unit 32 determines that the detected three-dimensional structure is a misrecognized pattern. The determination unit 32 can estimate the position of the pattern based on the camera 2 based on the position of the pattern on the image. Furthermore, even if the feature information does not indicate a three-dimensional structure in the road section on which the vehicle 10 is traveling, the determination unit 32 may determine that the detected three-dimensional structure is a misrecognized pattern. On the other hand, if the estimated position of the detected three-dimensional structure is closer to the corresponding three-dimensional structure than to the pattern represented in the structure information, the determination unit 32 determines that the detection result for the three-dimensional structure is correct.

[0040] Furthermore, if the detected feature is a traffic light and the moon, an example of a structure similar to a traffic light, is visible from the road section on which the vehicle 10 is traveling at the date and time the traffic light is detected, the determination unit 32 determines the direction of the detected traffic light from the vehicle 10 based on the position of the object area in which the traffic light is represented on the image. Furthermore, the determination unit 32 determines the direction of the actually installed traffic light from the vehicle 10 based on the position and direction of travel of the vehicle 10 and the position of the traffic light installed in that road section represented in the feature information. If the difference between the direction of the detected traffic light and the direction of the moon at the time of detection, indicated in the feature information, is smaller than the difference between the direction of the detected traffic light and the direction of the actually installed traffic light, the determination unit 32 determines that the detected traffic light is a false recognition of the moon. Furthermore, even if the feature information does not indicate a traffic light in the road section on which the vehicle 10 is traveling, the determination unit 32 may determine that the detected traffic light is a false recognition of the moon. Conversely, if the difference between the direction of the detected traffic light and the direction of the traffic light actually installed is smaller than the difference between the direction of the detected traffic light and the direction of the moon at the time of detection as shown in the structure information, the judgment unit 32 judges that the detection result for that traffic light is correct.

[0041] FIG. 3 is a diagram showing an example of a detected feature and a structure similar to that feature. In the example shown in FIG. 3, a snow melting pipe 301 is shown in image 300 generated by camera 2. Because snow melting pipe 301 resembles a lane marking, it may be erroneously detected as a lane marking. Because the position of snow melting pipe 301 differs from the actual position of lane marking 302, if the driving of vehicle 10 is controlled while snow melting pipe 301 is erroneously recognized as a lane marking, vehicle 10 may be positioned in an inappropriate position within the lane.

[0042] FIG. 4 is a diagram showing another example of detected features and structures similar to the features. In the example shown in FIG. 4, a vehicle guide line 401 is shown in image 400 generated by camera 2. Because vehicle guide line 401 resembles a lane marking, it may be erroneously detected as a lane marking. Like vehicle 402 shown in image 400, vehicle guide line 401 is not provided at the boundary between lanes, but at a position where vehicles traveling within the lane cross over. Therefore, if the travel of vehicle 10 is controlled while vehicle guide line 401 is erroneously recognized as a lane marking, there is a risk that vehicle 10 will be positioned in an inappropriate position within the lane.

[0043] FIG. 5 is a diagram showing yet another example of detected features and structures similar to the features. In the example shown in FIG. 5, image 500 generated by camera 2 shows pattern 501 on the road surface that resembles a three-dimensional structure. Because pattern 501 resembles the three-dimensional structure that is the target of imitation, it may be erroneously detected as a three-dimensional structure. In this example, pattern 501 is provided in an area of ​​the road surface through which vehicles pass. Therefore, if the traveling of vehicle 10 is controlled while pattern 501 is erroneously recognized as a three-dimensional structure, vehicle 10 may be forced to stop even though it does not need to do so.

[0044] The determination unit 32 notifies the vehicle control unit 33 of the determination result as to whether or not the detected feature has been erroneously recognized. Furthermore, the determination unit 32 notifies the vehicle control unit 33 of the estimated position of the vehicle 10 and the position of any structure that has been erroneously recognized as a feature, relative to the camera 2.

[0045] The vehicle control unit 33 controls the traveling of the vehicle 10 in accordance with the detected predetermined feature and the determination result as to whether or not the feature is a falsely recognized structure.

[0046] For example, if the detected lane marking is a false recognition of a snow melting pipe, the vehicle control unit 33 can estimate the distance from the actual lane marking to the vehicle 10 based on the positional relationship between the snow melting pipe and the actual lane marking, as shown in the map information, and the relative position of the snow melting pipe with respect to the vehicle 10, based on the installation position of the camera 2. The vehicle control unit 33 then controls the driving of the vehicle 10 so that the vehicle 10 maintains a predetermined positional relationship with the actual lane marking, based on the estimated distance from the actual lane marking to the vehicle 10. For example, the vehicle control unit 33 controls the steering of the vehicle 10 so that the vehicle 10 travels in the center of the lane. Alternatively, if the estimated distance from the actual lane marking to the vehicle 10 becomes less than a predetermined offset distance, the vehicle control unit 33 executes deviation prevention control. That is, the vehicle control unit 33 controls the steering so that the estimated distance is equal to or greater than the offset distance, or may notify the driver of a lane deviation warning via a notification device (not shown) provided in the cabin of the vehicle 10.

[0047] Furthermore, if the detected lane marking is a false recognition of a vehicle guide line, the vehicle control unit 33 controls each unit of the vehicle 10 so that the vehicle 10 travels while straddling the vehicle guide line, based on the estimated position of the vehicle guide line relative to the camera 2 and the installation position of the camera 2 on the vehicle 10. Furthermore, even if the distance from the vehicle 10 to the vehicle guide line that was falsely recognized as a lane marking is less than a predetermined offset distance, the vehicle control unit 33 does not execute deviation prevention control. Furthermore, when the vehicle control unit 33 refers to the map information and the position of the vehicle 10 indicated in the positioning information and detects that the vehicle 10 has entered a road section where a vehicle guide line is provided, the vehicle control unit 33 may guide the driver via a notification device to set the route of the vehicle 10 so that the vehicle 10 straddles the vehicle guide line.

[0048] Furthermore, if the detected three-dimensional structure is a false recognition of a road surface pattern, the vehicle control unit 33 controls the powertrain and brakes of the vehicle 10 to maintain the current speed of the vehicle 10. However, the road surface pattern itself may be provided to prompt deceleration. Therefore, the vehicle control unit 33 may control the powertrain and brakes of the vehicle 10 to decelerate to a predetermined speed (e.g., 20 km / h to 30 km / h) without stopping the vehicle 10 near the pattern. Alternatively, the vehicle control unit 33 may refer to the map information and the position of the vehicle 10 indicated in the positioning information, and when it detects that the vehicle 10 has entered a road section where a road surface pattern is provided, notify the driver via a notification device to decelerate the vehicle 10 to a predetermined speed.

[0049] Furthermore, if the detected road sign is a misidentified signboard, the vehicle control unit 33 ignores the instruction of the detected road sign and controls each unit of the vehicle 10 to maintain the current driving state of the vehicle 10. For example, if a signboard is misidentified as a stop sign, the vehicle control unit 33 controls the powertrain and brakes of the vehicle 10 to maintain the current speed without stopping the vehicle 10. Similarly, if the detected traffic light is a misidentified moon, the vehicle control unit 33 ignores the detected traffic light and controls each unit of the vehicle 10 to maintain the current driving state of the vehicle 10.

[0050] If a predetermined feature is correctly detected, the vehicle control unit 33 controls the traveling of the vehicle 10 in accordance with the detected feature. For example, if a lane marking is correctly detected, the vehicle control unit 33 may control each part of the vehicle 10 based on the detected lane marking so that the vehicle 10 travels in the center of the lane, or may execute deviation prevention control. If a road sign is correctly detected, the vehicle control unit 33 may control each part of the vehicle 10 so that the vehicle 10 follows the instructions of the detected road sign.

[0051] 6 is an operational flowchart of the vehicle control process. The processor 23 executes the vehicle control process in accordance with the following operational flowchart.

[0052] The detection unit 31 detects a predetermined feature from an image generated by the camera 2 (step S101). The determination unit 32 determines whether or not there is a structure similar to the detected feature in the section in which the vehicle 10 is traveling (step S102). If the section in which the vehicle 10 is traveling does not have a structure similar to the detected feature (step S102-No), the vehicle control unit 33 controls the traveling of the vehicle 10 in accordance with the detected feature (step S103).

[0053] On the other hand, if the section in which the vehicle 10 is traveling is a section in which there is a structure similar to the detected feature (step S102-Yes), the determination unit 32 determines whether the detected feature is a similar structure (step S104). If the detected feature is not a similar structure, that is, if the feature detection result is correct (step S104-No), the vehicle control unit 33 controls the traveling of the vehicle 10 in accordance with the detected feature (step S103).

[0054] On the other hand, if the detected feature is a misidentified similar structure (step S104-Yes), vehicle control unit 33 controls the traveling of vehicle 10 according to the misidentified structure (step S105). After step S103 or S105, processor 23 ends the vehicle control process.

[0055] As described above, this vehicle control device determines whether a predetermined feature detected while the vehicle is traveling on a road section on which a structure similar to the predetermined feature is provided is a mistakenly recognized structure. Then, this vehicle control device controls the traveling of the vehicle depending on whether the detected predetermined feature is a mistakenly recognized structure, thereby preventing inappropriate vehicle control due to mistaken recognition of the feature.

[0056] In snow-melting pipe sections, the road surface is wet, making it easy for vehicles to slip. Also, even if the snow on the road surface in the snow-melting pipe sections has cleared, snow may remain on the road surface outside the snow-melting pipe sections, or the road surface may become icy.

[0057] Therefore, according to this modification, the vehicle control unit 33 refers to map information and the position of the vehicle 10 indicated in a series of positioning information obtained over the most recent predetermined period to determine whether the vehicle 10 is traveling through a road section where snow melting pipes are installed (hereinafter referred to as a snow melting pipe section) and whether the distance until the vehicle 10 exits the snow melting pipe section is less than a predetermined distance. Then, while the vehicle 10 is traveling through the snow melting pipe section or when it exits the snow melting pipe section, the vehicle control unit 33 executes safe driving control on the vehicle 10 that provides a higher degree of safety than the driving control executed before the vehicle entered the snow melting pipe section.

[0058] Specifically, when vehicle 10 is traveling in a snow melting pipe section, vehicle control unit 33 controls each part of vehicle 10 so that vehicle 10 travels at a position at least a predetermined offset distance away from the snow melting pipes. Vehicle control unit 33 may also control each part of vehicle 10 so that the distance from a bicycle or another vehicle to vehicle 10 in a lateral direction perpendicular to the traveling direction of vehicle 10 (hereinafter referred to as the lateral distance) when vehicle 10 is traveling in a snow melting pipe section is greater than the lateral distance when vehicle 10 is traveling in a section other than the snow melting pipe section. Furthermore, vehicle control unit 33 may set the target speed when vehicle 10 is traveling in a snow melting pipe section or when the distance until exiting the snow melting pipe section becomes less than a predetermined distance to a speed that is a predetermined speed lower than the speed limit of the snow melting pipe section, and control each part of vehicle 10 so that the speed of vehicle 10 becomes the target speed. Furthermore, when the distance until the vehicle 10 enters or exits the snow melting pipe section becomes less than a predetermined distance, the vehicle control unit 33 may switch the applicable driving mode from automatic driving mode to manual driving mode, or may alert the driver to slippage via a notification device in the vehicle cabin.

[0059] A computer program that realizes the functions of the processor 23 of the ECU 5 according to the above embodiment or variant may be provided in a form recorded on a computer-readable portable recording medium such as a semiconductor memory, a magnetic recording medium or an optical recording medium.

[0060] As described above, those skilled in the art can make various modifications to the embodiments within the scope of the present invention. [Explanation of symbols]

[0061] 1 Vehicle control system, 10 Vehicle, 2 Camera, 3 GPS receiver, 4 Storage device, 5 Electronic control unit (ECU), 21 Communication interface, 22 Memory, 23 Processor, 31 Detection unit, 32 Determination unit, 33 Vehicle control unit

Claims

1. a storage unit that stores structure information that indicates the positions and types of structures that are visible from a vehicle traveling on a specified road section, feature information that indicates the positions and number of specified features that are provided on the specified road section and that indicate information related to the traveling of the vehicle or that affect the traveling of the vehicle, and similarity relationship information that indicates the similarity relationship between the specified features and the structures; a detection unit that detects the predetermined feature based on an image representing the situation around the vehicle, the image being generated by a camera provided on the vehicle; a determination unit that determines whether the predetermined feature detected while the vehicle is traveling on the predetermined road section is a false recognition of the structure, based on the structure information, the feature information, and the similarity relationship information; a vehicle control unit that controls the traveling of the vehicle depending on whether the detected predetermined feature is a false recognition of the structure; A vehicle control device having the above.

2. 2. The vehicle control device according to claim 1, wherein the determination unit determines that at least one of the detected predetermined features is a misrecognition of the structure when the number of the detected predetermined features in the specified road section is greater than the number of the detected predetermined features represented in the feature information, or when the position of the detected predetermined feature is closer to the position represented in the structure information for the structure similar to the detected predetermined feature, as represented in the similarity relationship information, than the position of the corresponding feature represented in the feature information.

3. the structure is a snow melting pipe, and the predetermined feature is a lane marking; The storage unit further stores map information indicating a positional relationship between the snow melting pipe and the lane markings, 3. The vehicle control device according to claim 1, wherein, when it is determined that the specified feature detected in the specified road section is a mistakenly recognized snow melting pipe, the vehicle control unit controls the driving of the vehicle so as to maintain a specified positional relationship with respect to the lane marking, based on the positional relationship between the snow melting pipe and the lane marking shown in the map information and the relative position of the snow melting pipe that was mistakenly recognized as the lane marking with respect to the vehicle.

4. the structure is a vehicle guide line, and the predetermined feature is a lane marking; 3. The vehicle control device according to claim 1, wherein, when it is determined that the specified feature detected in the specified road section is a vehicle guide line that has been mistakenly recognized, the vehicle control unit controls the vehicle's travel so that the vehicle travels across the vehicle guide line that has been mistakenly recognized as the lane dividing line.

5. the structure is a pattern that resembles a three-dimensional structure provided on a road surface, and the predetermined feature is the three-dimensional structure; 3. The vehicle control device according to claim 1, wherein, when it is determined that the specified feature detected in the specified road section is a mistakenly recognized three-dimensional structure, the vehicle control unit controls the driving of the vehicle so as not to stop near the pattern that has been mistakenly recognized as the three-dimensional structure.

Images