Vehicle control device, vehicle control method, and vehicle control computer program

Abstract

To provide a vehicle control device that can suppress control which should not be executed originally from being automatically executed, even if a detected result of an own lane on which an own vehicle is travelling is not accurate.SOLUTION: A vehicle control device detects an own lane on which a vehicle 10 is travelling and determines whether there is a possibility that a position of the detected own lane with respect to one end of a road is different from an actual position of the lane or not. Further, the vehicle control device identifies first control of the vehicle 10 that is required on the own lane and second control of the vehicle that is required on an adjacent lane. Further, the vehicle control device transfers the control of the vehicle 10 to a driver, when there is the possibility that the position of the detected own lane is different from the actual position and when there is a possibility that safety of the vehicle 10 is impaired even when any of the first control and the second control is executed or predetermined action which is required to be attained before the vehicle reaches a destination away by a predetermined distance therefrom is not attained.SELECTED DRAWING: Figure 7

Description

[Technical field]

[0001] The present invention relates to a vehicle control device, a vehicle control method, and a computer program for vehicle control. [Background technology]

[0002] When controlling the autonomous driving of a vehicle, the vehicle control device executes a localization process to detect the lane in which the vehicle is traveling (hereinafter, sometimes referred to as the vehicle's own lane), and executes vehicle control such as lane changing as necessary based on the result of the localization process. Therefore, in order to appropriately control the autonomous driving of a vehicle, a technology for detecting the vehicle's own lane with high accuracy has been proposed (see Patent Document 1).

[0003] The vehicle control device disclosed in Patent Document 1 recognizes a dividing line that divides a road, and estimates a plurality of first parameters as a plurality of road parameters that specify the road based on the recognized dividing line. The vehicle control device also recognizes a preceding vehicle that exists in front of the vehicle, estimates a travel path of the preceding vehicle based on a history of the recognized position of the preceding vehicle, and estimates a plurality of second parameters as a plurality of road parameters based on the estimated travel path. The vehicle control device further calculates a first reliability of each estimated first parameter, and calculates a second reliability of each estimated second parameter. The vehicle control device further calculates an integrated parameter by integrating the first parameter and the second parameter for each road parameter according to the first reliability and the second reliability. The vehicle control device then estimates the road based on the calculated integrated parameter. The vehicle control device also performs driving assistance for the vehicle based on the integrated parameter. At that time, the vehicle control device changes the degree of driving assistance according to the integrated reliability. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2017-45356 A Summary of the Invention [Problem to be solved by the invention]

[0005] In some cases, even with the technology disclosed in the above Patent Document 1, it may be difficult for the vehicle control device to accurately detect the vehicle's own lane. For example, when lane markings are unclear, it is difficult to accurately detect the vehicle's own lane. In such a situation where it is difficult to detect the vehicle's own lane, there is a risk of an inconvenience such as the vehicle being automatically controlled when it should not be.

[0006] Therefore, an object of the present invention is to provide a vehicle control device that can prevent control that should not be executed from being automatically executed even if the detection result of the own lane is inaccurate. [Means for solving the problem]

[0007] According to one embodiment, a vehicle control device is provided, which includes a detection unit that detects a lane in which the vehicle is traveling among a plurality of lanes by comparing a sensor signal indicating the surroundings of the vehicle obtained by a sensor mounted on the vehicle with a map including information on a plurality of lanes provided on the road on which the vehicle is traveling, an erroneous detection determination unit that determines whether or not the position of the detected lane relative to one end of the road is likely to differ from the actual position, a determination unit that determines a first control of the vehicle that is required to be performed in the lane and a second control of the vehicle that is required to be performed in an adjacent lane adjacent to the lane on the basis of at least one of a predetermined action of the vehicle that is required to be achieved before the vehicle reaches a predetermined point a predetermined distance away from the current position of the vehicle, the sensor signal, and the map, and a control unit that transfers control of the vehicle to a driver when the detected position of the lane is likely to differ from the actual position and there is a possibility that the safety of the vehicle will be compromised or the predetermined action will not be achieved even if either the first control or the second control is performed.

[0008] In this vehicle control device, it is preferable that the control unit determines that there is a possibility that vehicle safety will be compromised or the specified action will not be achieved regardless of whether the first control or the second control is executed, if executing the first control would result in vehicle safety being compromised or the specified action not being performed if the vehicle was actually traveling in an adjacent lane, and executing the second control would result in vehicle safety being compromised or the specified action not being performed if the vehicle was actually traveling in the own lane.

[0009] In addition, in this vehicle control device, when construction information received from another device indicates that road construction will be carried out within a specified period including the current time in a section up to a specified distance from the vehicle's current position, it is preferable that the error detection determination unit determines that there is a possibility that the detected position of the vehicle's lane relative to one end of the road on which the vehicle is traveling differs from the actual position.

[0010] Alternatively, it is preferable that the erroneous detection determination unit determines that there is a possibility that the detected position of the vehicle's own lane relative to one end of the road on which the vehicle is traveling differs from the actual position if the map was last updated a predetermined period before the current time, or if the road structure differs between the map and the route search map used by the navigation device to search for the vehicle's traveling route in a section from the vehicle's current position to a predetermined distance ahead.

[0011] Alternatively, it is preferable that the erroneous detection determination unit determines that there is a possibility that the detected position of the vehicle's own lane relative to one end of the road on which the vehicle is traveling differs from the actual position when the driving trajectory of another vehicle in a section from the vehicle's current position to a specified distance ahead passes through an area on the map in which the vehicle cannot travel.

[0012] Alternatively, it is preferable that the erroneous detection determination unit determines that there is a possibility that the position of the detected vehicle's lane relative to one end of the road on which the vehicle is traveling may differ from the actual position before a certain amount of time has elapsed since detection of the vehicle's lane began, or until the vehicle has traveled a certain distance since detection of the vehicle's lane began.

[0013] Furthermore, it is preferable that the erroneous detection determination unit determines that there is a possibility that the position of the detected own lane relative to one end of the road on which the vehicle is traveling differs from the actual position when the number of lanes shown on the map or sensor signal at the vehicle's current position is a predetermined number or more and the detected own lane is located within a predetermined range from the center of the multiple lanes at the current position.

[0014] Furthermore, it is preferable that the erroneous detection determination unit determines that there is a possibility that the detected position of the vehicle's own lane relative to one end of the road on which the vehicle is traveling differs from the actual position if the number of lanes at the vehicle's current position has changed by more than a predetermined number compared to the number of lanes at the vehicle's position a predetermined time ago.

[0015] Furthermore, it is preferable that the erroneous detection determination unit determines that there is a possibility that the detected position of the own lane relative to one end of the road on which the vehicle is traveling differs from the actual position when the position of a specified feature detected from the sensor signal differs from the position of a corresponding feature on a map based on the detected position of the own lane.

[0016] Furthermore, it is preferable that the erroneous detection determination unit determines that there is a possibility that the detected position of the vehicle's own lane relative to one end of the road on which the vehicle is traveling differs from the actual position if the certainty of a specified feature detected from the sensor signal is equal to or lower than a specified certainty threshold.

[0017] Furthermore, if the erroneous detection determination unit cannot detect any other vehicles traveling within the range indicated by the sensor signal, which corresponds to the area on the map in which the vehicle can travel, based on the detected position of the own lane, for a certain period of time, it is preferable that the erroneous detection determination unit determines that there is a possibility that the detected position of the own lane relative to one end of the road on which the vehicle is traveling differs from the actual position.

[0018] Furthermore, it is preferable that the erroneous detection determination unit determines that there is a possibility that the detected position of the vehicle's own lane relative to one end of the road on which the vehicle is traveling differs from the actual position when the current position of the vehicle is within a predetermined range from a erroneous detection risk point designated in advance on the map.

[0019] According to another embodiment, a vehicle control method is provided, which includes: detecting a lane in which the vehicle is traveling among a plurality of lanes by comparing a sensor signal indicating the surroundings of the vehicle obtained by a sensor mounted on the vehicle with a map including information on a plurality of lanes provided on the road on which the vehicle is traveling, determining whether or not the position of the detected lane in relation to one end of the road may differ from the actual position, specifying a first control of the vehicle that is required to be performed in the lane and a second control of the vehicle that is required to be performed in an adjacent lane adjacent to the lane based on at least one of a predetermined action of the vehicle that is required to be achieved before the vehicle reaches a predetermined point a predetermined distance away from the current position of the vehicle, the sensor signal, and the map, and transferring control of the vehicle to a driver when the detected position of the lane in which the vehicle is traveling may differ from the actual position and the safety of the vehicle may be compromised or the predetermined action may not be achieved even if either the first control or the second control is performed.

[0020] According to yet another embodiment, a computer program for controlling a vehicle is provided, which includes instructions for causing a processor mounted on the vehicle to execute the following: by comparing a sensor signal indicating the surroundings of the vehicle obtained by a sensor mounted on the vehicle with a map including information on a plurality of lanes provided on a road on which the vehicle is traveling, to detect a lane in which the vehicle is traveling among the plurality of lanes, to determine whether or not the position of the detected lane relative to one end of the road may differ from the actual position, to identify a first control of the vehicle that is required to be performed in the lane and a second control of the vehicle that is required to be performed in an adjacent lane adjacent to the lane based on at least one of a predetermined action of the vehicle that is required to be achieved before the vehicle reaches a predetermined point a predetermined distance away from the current position of the vehicle, the sensor signal, and the map, and to transfer control of the vehicle to a driver when the detected position of the lane in which the vehicle is traveling may differ from the actual position and the safety of the vehicle may be compromised or the predetermined action may not be achieved even if either the first control or the second control is performed. Effect of the Invention

[0021] The vehicle control device according to the present invention has an effect of being able to suppress automatic execution of control that should not be executed even if the detection result of the own lane is inaccurate. [Brief description of the drawings]

[0022] [Figure 1] This figure shows an example in which the vehicle safety is compromised or a specified action is not achieved depending on the relationship between the detected position of the own lane and the actual position, depending on whether or not the control required for the detected own lane and adjacent lanes can be executed. [Diagram 2] FIG. 11 is a diagram showing another example in which the vehicle safety is compromised or a specified action is not achieved depending on the relationship between the detected position of the own lane and the actual position, depending on whether or not the control required for the detected own lane and adjacent lanes can be executed. [Diagram 3] This figure shows yet another example in which the vehicle safety is compromised or a specified action is not achieved depending on the relationship between the detected position of the own lane and the actual position, depending on whether or not the control required for the detected own lane and adjacent lanes can be executed. [Figure 4] This figure shows yet another example in which the vehicle safety is compromised or a specified action is not achieved depending on the relationship between the detected position of the own lane and the actual position, depending on whether or not the control required for the detected own lane and adjacent lanes can be executed. [Diagram 5] 1 is a schematic configuration diagram of a vehicle control system in which a vehicle control device is implemented. [Figure 6] 1 is a hardware configuration diagram of an electronic control device that is an embodiment of a vehicle control device. [Figure 7] FIG. 2 is a functional block diagram of a processor of an electronic control unit related to vehicle control processing. [Figure 8] 13(a) and 13(b) are diagrams showing examples in which the detected position of the own vehicle lane with respect to one edge of the road differs from the actual position. [Figure 9]4 is an operation flowchart of a vehicle control process. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0023] Hereinafter, a vehicle control device, a vehicle control method executed on the vehicle control device, and a computer program for vehicle control will be described with reference to the drawings. The vehicle control device detects the lane in which the vehicle is traveling among the multiple lanes by comparing a sensor signal indicating the surroundings of the vehicle obtained by a sensor mounted on the vehicle with a map including information on multiple lanes provided on the road on which the vehicle is traveling. The vehicle control device then determines whether or not the position of the detected lane relative to one end of the road on which the vehicle is traveling may differ from the actual position. The vehicle control device also specifies vehicle control that is required to be performed in the detected lane and adjacent lanes adjacent to the lane. If the detected lane position may differ from the actual position, the vehicle control device determines whether or not the specified control is performed, whether the safety of the vehicle is not compromised, and whether or not a predetermined action that should be performed before the vehicle reaches a predetermined distance away can be achieved. When the vehicle safety may be compromised or a predetermined action may not be achieved depending on whether the detected position of the vehicle's own lane is correct or different from the actual position, regardless of which lane the requested control is executed, the vehicle control device transfers control of the vehicle to the driver. This makes it possible for the vehicle control device to suppress automatic execution of control that should not be executed even if the detection result of the vehicle's own lane is not accurate.

[0024] Figures 1 to 4 each show an example in which vehicle safety is compromised or a specified action is not achieved depending on the relationship between the detected position of the own lane and the actual position, depending on whether or not the control required for the detected own lane and adjacent lanes can be executed.

[0025] In the example shown in FIG. 1, a road 100 on which the vehicle 10 is traveling branches into three roads 101 to 103 in the traveling direction of the vehicle 10. The vehicle 10 needs to head to the center road 102 among the three roads 101 to 103 in order to head to a destination. That is, the predetermined action required of the vehicle 10 is to head to the center road 102 before the roads 101 to 103 branch off. Here, it is assumed that the fourth lane 111 from the right is detected as the vehicle's own lane. In order for the vehicle 10 to head to the destination, the vehicle 10 only needs to travel along the lane 111, so that the control required of the vehicle 10 for the detected own lane is to maintain the lane. In contrast, the control required of the vehicle 10 for the lane 112 adjacent to the left of the detected own lane 111 is to change lanes to the right lane. Hereinafter, the control required of the vehicle 10 for the detected own lane is referred to as the first control, and the control required of the vehicle 10 for the lane adjacent to the detected own lane is referred to as the second control. Therefore, if the first control is executed to make the vehicle 10 maintain the lane in which it is traveling, when the actual position of the own lane is the lane 112, the vehicle 10 will proceed toward the road 101 heading in a direction different from the destination, and the predetermined action will not be achieved. Conversely, if the second control is executed to make the vehicle 10 change lanes to the right lane, the vehicle 10 will move to the lane 113 adjacent to the right of the lane 111 if the detected position of the own lane is correct. Since the lane 113 ends in front of the vehicle 10, changing lanes to the lane 113 may impair the safety of the vehicle 10. Thus, whether the first control or the second control is executed, the safety of the vehicle will be impaired or the predetermined action will not be achieved depending on the relationship between the detected position of the own lane and the actual position.

[0026] In the example shown in FIG. 2, the road 200 on which the vehicle 10 is traveling branches into three roads 201-203 in the traveling direction of the vehicle 10. The vehicle 10 needs to head to the center road 202 among the three roads 201-203 in order to head to the destination. That is, the predetermined action required of the vehicle 10 is to head to the center road 102 before the roads 201-203 branch off. Here, it is assumed that the fourth lane 211 from the right is detected as the vehicle's own lane. In order for the vehicle 10 to head to the destination, the vehicle 10 only needs to travel along the lane 211, so the control (first control) required of the vehicle 10 for the detected own lane is to maintain the lane. In contrast, the control (second control) required of the vehicle 10 for the lane 212 adjacent to the left of the detected own lane 211 is to change lanes to the right lane. Therefore, if the first control is executed to cause the vehicle 10 to maintain the lane in which it is traveling, when the actual position of the own lane is the lane 212, the vehicle 10 will proceed toward the road 201 heading in a direction different from the destination, and the predetermined action will not be achieved. Conversely, if the second control is executed to cause the vehicle 10 to change lanes to the right, when the actual position of the own lane is the lane 213 adjacent to the right side of the lane 211, the lane 214 to which the vehicle will change lanes will be connected to the road 203 heading in a direction different from the destination, and the predetermined action will not be achieved. In this way, whether the first control or the second control is executed, the predetermined action will not be achieved depending on the relationship between the detected position of the own lane and the actual position.

[0027] The same thing can happen if there is an intersection ahead on road 200, and only lanes 211 and 213 are permitted to go straight, while lane 212 is reserved for left turns and lane 214 is reserved for right turns.

[0028] In the example shown in FIG. 3, the road 300 on which the vehicle 10 is traveling branches into two roads, road 301 and road 302, in the traveling direction of the vehicle 10. The lanes 311 and 314 at both ends are connected to the road 301 heading to the right, and the central lanes 312 and 313 are connected to the road 302 going straight. It is assumed that the vehicle 10 needs to travel on the road 301 heading to the right in order to travel to the destination. That is, the predetermined action required of the vehicle 10 is to travel to the road 301 before the roads 301 and 302 branch off. Here, it is assumed that the second lane from the left, 312, is detected as the vehicle's own lane. In order for the vehicle 10 to travel to the destination, the vehicle 10 needs to change lanes to the lane 311 adjacent to the left of the lane 312. Therefore, the control (first control) required of the vehicle 10 for the detected own lane is to change lanes to the left. In contrast, the control (second control) required for the lane 313 adjacent to the right side of the detected own lane 312 is a lane change to the right lane. Therefore, if the first control is executed to change the vehicle 10 to the left lane, when the actual position of the own lane is the lane 313, the vehicle 10 advances toward the road 302 heading in a direction different from the destination, and the predetermined action is not achieved. Conversely, if the second control is executed to change the vehicle 10 to the right lane, when the detected position of the own lane is correct, the lane 313 to which the lane is to be changed is connected to the road 302 heading in a direction different from the destination, and the predetermined action is not achieved. In this way, whether the first control or the second control is executed, the predetermined action is not achieved depending on the relationship between the detected position of the own lane and the actual position.

[0029] In the example shown in FIG. 4, the road 400 on which the vehicle 10 is traveling includes four lanes 411 to 414, and the speed of other vehicles traveling in the lanes increases as the lane approaches the right side. In this example, the vehicle 10 is required to travel in a manner following other vehicles traveling in the lane and traveling in the second lane from the left 412, which is a predetermined behavior. Here, it is assumed that the lane 412 is detected as the vehicle's own lane. In this case, the control (first control) required of the vehicle 10 for the detected own lane is to maintain the lane and to control the speed of the vehicle 10 so as to match the speed of other vehicles traveling in the lane 412. In contrast, the control (second control) required of the vehicle 10 for the lane 413 adjacent to the right side of the detected own lane 412 is to change lanes to the left lane and to control the speed of the vehicle 10 so as to match the speed of other vehicles traveling in the lane adjacent to the left. Therefore, if the first control is executed to make the vehicle 10 maintain the lane in which it is traveling, the speed of the vehicle 10 will be different from the speed of other vehicles traveling in the same lane when the actual position of the own lane is lane 4111 or lane 413. This may result in failure to achieve the predetermined action and may compromise the safety of the vehicle 10. Conversely, if the second control is executed to make the vehicle 10 change lanes to the left, the vehicle 10 will move to the leftmost lane 411 if the detected position of the own lane is correct. Therefore, if the speed of the vehicle 10 is adjusted to match the speed of other vehicles traveling in lane 412, the speed of the vehicle 10 will be faster than the speed of other vehicles traveling ahead of the own vehicle, which may compromise the safety of the vehicle 10. On the other hand, if vehicle 10 is allowed to travel along the lane it is currently traveling in without changing lanes to the left lane, and if the lane in which vehicle 10 is actually traveling is lane 413, the speed of vehicle 10 will be slower than the speed of other vehicles traveling behind vehicle 10. This may result in the predetermined action not being achieved and may compromise the safety of vehicle 10. Note that a similar situation may occur when the speed limits for each lane are different in the example shown in FIG. 4.

[0030] In this embodiment, in any of the cases shown in Figures 1 to 4, control of the vehicle 10 is transferred to the driver, thereby preventing automatic execution of control that should not be executed even if the detection result of the vehicle's own lane is inaccurate.

[0031] FIG. 5 is a schematic diagram of a vehicle control system in which a vehicle control device is implemented. FIG. 6 is a hardware configuration diagram of an electronic control device, which is one embodiment of a vehicle control device. In this embodiment, a vehicle control system 1 is mounted on a vehicle 10 and controls the vehicle 10. To this end, the vehicle control system 1 has a camera 2, a GPS receiver 3, a navigation device 4, a wireless communication device 5, a user interface 6, a storage device 7, and an electronic control unit (ECU) 8, which is an example of a vehicle control device. The camera 2, the GPS receiver 3, the navigation device 4, the wireless communication device 5, the user interface 6, the storage device 7, and the ECU 8 are communicatively connected via an in-vehicle network conforming to a standard such as a controller area network. The vehicle control system 1 may further have a distance sensor (not shown) such as a LiDAR or a radar that measures the distance from the vehicle 10 to an object present around the vehicle 10.

[0032] Camera 2 is an example of a sensor that generates a sensor signal that represents the surroundings of vehicle 10, and has a two-dimensional detector configured with an array of photoelectric conversion elements sensitive to visible light, such as a CCD or C-MOS, and an imaging optical system that forms an image of the area to be photographed on the two-dimensional detector. Camera 2 is attached, for example, inside the passenger compartment of vehicle 10 so as to face the front of vehicle 10. Camera 2 photographs the area in front of vehicle 10 at a predetermined photographing period (for example, 1 / 30 to 1 / 10 seconds) and generates an image showing the area in front of vehicle 10. The image obtained by camera 2 is an example of a sensor signal. Note that vehicle 10 may be provided with multiple cameras with different photographing directions or focal lengths.

[0033] Every time the camera 2 generates an image, it outputs the generated image to the ECU 8 via the in-vehicle network.

[0034] 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 result of the own position of the vehicle 10 based on the GPS signals to the navigation device 4 and the ECU 8 via the in-vehicle network at predetermined intervals. Note that the vehicle 10 may have a receiver that receives positioning signals from satellites of other satellite positioning systems and determines the own position of the vehicle 10, instead of the GPS receiver.

[0035] The navigation device 4 executes navigation processing for the vehicle 10 according to a navigation program running on the device itself. For example, when the driver's operation instructs the navigation device 4 to start the navigation program and the destination of the vehicle 10 is input, the navigation device 4 searches for a travel route of the vehicle 10 from the current position of the vehicle 10 to the destination. At that time, the navigation device 4 may search for the travel route according to a predetermined route search method such as the Dijkstra algorithm, with reference to a route search map (hereinafter, sometimes referred to as a road map) that shows individual road sections and their connection relationships stored in the navigation device itself. The travel route includes information that shows, for example, roads to be passed through to the destination, the direction of travel at branch points located on the travel route, the positions of intersections at which to turn right or left, and the like. Note that the navigation device 4 can use, for example, the vehicle's own position based on the latest positioning result received from the GPS receiver 3 as the current position of the vehicle 10. When the navigation device 4 determines the driving route of the vehicle 10, the navigation device 4 outputs information representing the driving route to the ECU 8 via the in-vehicle network.

[0036] The wireless communication device 5 wirelessly communicates with a wireless base station in accordance with a predetermined mobile communication standard. The wireless communication device 5 receives traffic information indicating the traffic conditions on the road on which the vehicle 10 is traveling or around the road, or construction information indicating the status of construction (for example, information from a Vehicle Information and Communication System) from another device via the wireless base station. The wireless communication device 5 then outputs the received traffic information to the ECU 8 via an in-vehicle network. Note that the construction information includes, for example, information on the location and time period in which road construction is being carried out. The wireless communication device 5 may also receive a high-precision map used for automatic driving control for a predetermined area around the current position of the vehicle 10 from a map server via the wireless base station, and output the received high-precision map to the storage device 7.

[0037] The user interface 6 is an example of a notification unit, and has, for example, a display device such as a liquid crystal display or a touch panel display. The user interface 6 is installed in the vehicle interior of the vehicle 10, for example, near the instrument panel, facing the driver. The user interface 6 notifies the driver of various information received from the ECU 8 via the in-vehicle network by displaying the information as icons or as text information. The user interface 6 may have one or more light sources provided on the instrument panel, a speaker provided in the vehicle interior, or a vibration device provided on the steering wheel or the driver's seat. In this case, the user interface 6 notifies the driver of the information by outputting the various information received from the ECU 8 via the in-vehicle network as a sound signal. Alternatively, the user interface 6 may vibrate the vibration device in response to a signal received from the ECU 8 via the in-vehicle network, thereby notifying the driver of the predetermined information by the vibration. Alternatively, the user interface 6 may notify the driver of the predetermined information by turning on or blinking a light source in response to a signal received from the ECU 8 via the in-vehicle network.

[0038] The storage device 7 includes, for example, a hard disk device, a non-volatile semiconductor memory, or an optical recording medium and an access device therefor. The storage device 7 stores a high-precision map. The high-precision map is an example of a map including information on a plurality of lanes provided on a road. The high-precision map includes, for example, information on the number of lanes for each road included in a predetermined area shown on the high-precision map, information on road markings such as lane dividing lines or stop lines, and information on road signs. Furthermore, the high-precision map may include, for each road, information on control required for a vehicle traveling on each lane of the road. Furthermore, the high-precision map may include, for each road, information on control prohibited for a vehicle traveling on each lane of the road.

[0039] Furthermore, the storage device 7 may have a processor for executing an update process of the high-precision map, and a process related to a read request of the high-precision map from the ECU 8. The storage device 7 may transmit a request to acquire a high-precision map together with the current position of the vehicle 10 to the map server via the wireless communication device 5, for example, every time the vehicle 10 moves a predetermined distance. The storage device 7 may also receive a high-precision map of a predetermined area around the current position of the vehicle 10 from the map server via the wireless communication device 5. When the storage device 7 receives a read request of the high-precision map from the ECU 8, the storage device 7 extracts an area that includes the current position of the vehicle 10 and is relatively narrower than the above-mentioned predetermined area from the stored high-precision map, and outputs the area to the ECU 8 via the in-vehicle network.

[0040] The ECU 8 performs automatic driving control of the vehicle 10. In this embodiment, the ECU 8 compares the image obtained by the camera 2 with a high-precision map to detect the lane in which the vehicle 10 is traveling, and determines whether or not there is a possibility that the position of the detected lane in relation to one end of the road in which the vehicle 10 is traveling differs from the actual position. Then, the ECU 8 determines the control to be actually executed according to the control required for the detected lane and the control required for the lane adjacent to the lane in question, and executes the determined control.

[0041] 6, the ECU 8 has 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 configured integrally as a single integrated circuit.

[0042] The communication interface 21 has an interface circuit for connecting the ECU 8 to the in-vehicle network. The communication interface 21 passes the received image to the processor 23 every time it receives an image from the camera 2. The communication interface 21 passes the positioning information to the processor 23 every time it receives positioning information from the GPS receiver 3. When the communication interface 21 receives a travel route from the navigation device 4, it passes the travel route to the processor 23. When the communication interface 21 receives information such as traffic information that the wireless communication device 5 has received from another device, it passes the information to the processor 23. The communication interface 21 also passes a high-precision map read from the storage device 7 to the processor 23.

[0043] The memory 22 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 such as the focal length, shooting direction, and mounting position of the camera 2, and various parameters for identifying a classifier for object detection used to detect features. The memory 22 also stores a reference table that indicates the relationship between the type of road marking or road sign and the control corresponding to the type. The memory 22 also stores a travel route, positioning information of the vehicle 10, an image of the surroundings of the vehicle 10, and a high-precision map. The memory 22 also temporarily stores various data generated during the vehicle control process.

[0044] The processor 23 has one or more central processing units (CPUs) and their peripheral circuits. The processor 23 may further have other arithmetic circuits such as a logic arithmetic unit, a numerical arithmetic unit, or a graphic processing unit. The processor 23 executes vehicle control processing for the vehicle 10 at predetermined intervals.

[0045] 7 is a functional block diagram of the processor 23 related to the vehicle control process. The processor 23 has an own lane detection unit 31, an erroneous detection determination unit 32, a specification unit 33, and a control unit 34. 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.

[0046] The own lane detection unit 31 is an example of a detection unit, and detects the own lane in which the vehicle 10 is traveling by comparing an image (hereinafter, sometimes simply referred to as an image) showing the surroundings of the vehicle 10 generated by the camera 2 with a high-precision map. For example, the own lane detection unit 31 assumes the position and attitude of the vehicle 10 and projects features on or around the road detected from the image onto the high-precision map, or projects features on or around the road around the vehicle 10 shown on the high-precision map onto the image. The features on or around the road can be, for example, road markings such as lane markings or stop lines, or curbs. The own lane detection unit 31 estimates the position and attitude of the vehicle 10 when the features detected from the image and the features shown on the high-precision map most closely match as the own position of the vehicle 10.

[0047] The own lane detection unit 31 may determine the position where the feature is projected on the high-precision map or image by using the assumed initial values ​​of the position and attitude of the vehicle 10 and the parameters of the camera 2, such as the focal length, the installation height, and the shooting direction. As the initial values ​​of the position and attitude of the vehicle 10, the position of the vehicle 10 measured by the GPS receiver 3, or the position and attitude of the vehicle 10 estimated at the time of the previous own lane detection, corrected by using the odometry information, is used. Then, the own lane detection unit 31 calculates the degree of match between the feature on or around the road detected from the image and the corresponding feature shown on the high-precision map (for example, the inverse of the square sum of the distance between the corresponding features).

[0048] The own lane detection unit 31 repeats the above process while changing the assumed position and attitude of the vehicle 10. Then, the own lane detection unit 31 may estimate the assumed position and attitude when the degree of agreement is maximum as the actual own position of the vehicle 10. Then, the own lane detection unit 31 may refer to the high-precision map and identify the lane that includes the own position of the vehicle 10 as the own lane in which the vehicle 10 is traveling.

[0049] The vehicle lane detection unit 31 may detect the feature by inputting the image to a classifier that has been trained in advance to detect the feature from the image. The vehicle lane detection unit 31 may use a deep neural network (DNN) having a convolutional neural network (CNN) type architecture, such as Single Shot MultiBox Detector or Faster R-CNN, as such a classifier. Alternatively, the vehicle lane detection unit 31 may use a DNN having a self attention network (SAN) type architecture, such as Vision Transformer, as such a classifier. These classifiers may output a confidence level representing the likelihood of each detected feature. The classifier then detects an area on the image where the confidence level calculated for a specific feature is higher than a specific detection threshold as an object area representing the specific feature.

[0050] The own lane detection unit 31 notifies the erroneous detection determination unit 32, the identification unit 33, and the control unit 34 of information indicating the detected own lane.

[0051] The erroneous detection determination unit 32 determines whether or not there is a possibility that the position of the own lane detected by the own lane detection unit 31 with respect to one end of the road on which the vehicle 10 is traveling differs from the actual position.

[0052] 8(a) and 8(b) are diagrams showing examples in which the detected position of the own lane is different from the actual position. In the example shown in FIG. 8(a), the vehicle 10 is traveling in a lane 801, which is the second lane from the right in the traveling direction of the vehicle 10, among a plurality of lanes provided on a road 800. However, a lane 802 adjacent to the lane 801 is erroneously detected as the own lane. Therefore, the detected position of the own lane is different from the actual position of the own lane. Such erroneous detection of the own lane may occur, for example, when the number of lanes provided on the road on which the vehicle 10 is traveling is large, or when features such as lane markings provided on the road are blurred and therefore difficult to distinguish. In addition, erroneous detection of the own lane may also occur when a relatively short time has passed since the detection of the own lane was started, such as when the vehicle 10 has just entered an area covered by a high-precision map.

[0053] In the example shown in FIG. 8(b), the vehicle 10 is traveling in a rightmost lane 811 in the traveling direction of the vehicle 10 among a plurality of lanes provided on a road 810. In this example, the lane 811 itself is detected as the own lane. However, a lane 812 at the left end of the road 810 was added after the high-precision map used by the vehicle 10 to detect the own lane was generated, and therefore the lane 812 is not included in the road 810 on the high-precision map. As a result, the number of lanes existing between the own lane 811 and the left end of the road 810 recognized by the own lane detection unit 31 differs from the actual number of lanes existing between the own lane 811 and the actual left end of the road 810. For this reason, the position of the detected own lane with respect to the left end of the road 810 differs from the actual position. Such a discrepancy in the number of lanes to the left and right of the detected vehicle lane between the high-precision map and the actual environment can occur when the high-precision map does not reflect the latest road information or when construction work is taking place on the road.

[0054] Therefore, the erroneous detection determination unit 32 determines whether or not the position of the detected vehicle lane relative to one end of the road on which the vehicle 10 is traveling is likely to differ from the actual position based on the structure of the road on which the vehicle 10 is traveling, the traveling environment, the timing of generating or updating the high-precision map, and the like. Specifically, the erroneous detection determination unit 32 may determine whether or not the position of the detected vehicle lane relative to one end of the road on which the vehicle 10 is traveling is likely to differ from the actual position based on any of the determination processes described later. By executing the determination processes described later, the erroneous detection determination unit 32 can accurately determine whether or not the position of the detected vehicle lane relative to one end of the road on which the vehicle 10 is traveling is likely to differ from the actual position. Note that the erroneous detection determination unit 32 does not need to execute all of the determination processes described later, and may execute at least one of the determination processes. In addition, hereinafter, the fact that the position of the detected vehicle lane relative to one end of the road on which the vehicle 10 is traveling is different from the actual position may be expressed simply as the position of the detected vehicle lane being different from the actual position.

[0055] For example, the erroneous detection determination unit 32 refers to construction information received from another device via the wireless communication device 5. Then, when the construction information indicates that road construction will be carried out within a predetermined period including the current time in a section from the current position of the vehicle 10 to a predetermined distance away, the erroneous detection determination unit 32 determines that the detected position of the vehicle's own lane may differ from the actual position. This is because the number of passable lanes has changed due to road construction, and therefore the detected position of the vehicle's own lane may differ from the actual position.

[0056] Furthermore, the erroneous detection determination unit 32 determines that the detected position of the vehicle's own lane may differ from the actual position if the last update date and time of the high-precision map is a predetermined period or more before the current time. Alternatively, the erroneous detection determination unit 32 may determine that the detected position of the vehicle's own lane may differ from the actual position if the road structure in the section from the current position of the vehicle 10 to a predetermined distance ahead is different between the high-precision map and the road map. This is because the high-precision map does not accurately represent the road structure around the current position of the vehicle 10, so there is a possibility that the detected position of the vehicle's own lane is incorrect.

[0057] Furthermore, the erroneous detection determination unit 32 may determine that the detected position of the vehicle's own lane may differ from the actual position when the travel path of another vehicle traveling ahead of the vehicle 10 in a section from the current position of the vehicle 10 to a predetermined distance ahead passes through an area on the high-precision map where the vehicle cannot travel. This is because it is considered that there is a high possibility that the detected position of the vehicle's own lane is incorrect, since it is unlikely that another vehicle is actually traveling in an area where the vehicle cannot travel.

[0058] In this case, the erroneous detection determination unit 32 detects other vehicles traveling around the vehicle 10 from a series of time-series images obtained by the camera 2. In this case, the erroneous detection determination unit 32 inputs the series of images to a classifier that has been trained in advance to detect objects to be detected from images, and detects other vehicles present around the vehicle 10 from each of the series of images. The control unit 34 can use, as such a classifier, for example, a DNN having a CNN-type or SAN-type architecture, similar to the classifier used by the own lane detection unit 31.

[0059] The false detection determination unit 32 tracks the other vehicle detected from a series of images in time series to determine the running trajectory of the other vehicle. In this case, the false detection determination unit 32 applies a tracking process based on optical flow, such as the Lucas-Kanade method, to an object region in which the other vehicle of interest is represented in the latest image obtained by the camera 2 and an object region in the past image. In this way, the false detection determination unit 32 tracks the other vehicle represented in the object region. For this purpose, the false detection determination unit 32 applies a filter for extracting feature points, such as SIFT or Harris operator, to the object region of interest to extract multiple feature points from the object region. Then, the false detection determination unit 32 may calculate the optical flow by identifying the corresponding points in the object region in the past image for each of the multiple feature points according to the applied tracking method. Alternatively, the false detection determination unit 32 may track another vehicle depicted in the object area by applying another tracking method that is applied to tracking a moving object detected from an image to the object area of ​​interest in the latest image and the object area in the past image.

[0060] The erroneous detection determination unit 32 converts the coordinates in the image of the other vehicle into coordinates on the bird's-eye image (bird's-eye coordinates) by performing a viewpoint conversion process using information such as the mounting position of the camera 2 on the vehicle 10 for each other vehicle being tracked. At this time, the erroneous detection determination unit 32 can estimate the position of the detected other vehicle at the time of acquisition of each image based on the position and attitude of the vehicle 10 at the time of acquisition of each image, the estimated distance to the detected other vehicle, and the direction from the vehicle 10 to the other vehicle. Note that the erroneous detection determination unit 32 may acquire the position and attitude of the vehicle 10 from the own lane detection unit 31. Furthermore, the erroneous detection determination unit 32 can specify the direction from the vehicle 10 to the other vehicle based on the position of the object area including the detected other vehicle on the image and the optical axis direction of the camera 2. Furthermore, the estimated distance from the vehicle 10 to the detected other vehicle is calculated based on the ratio between the size of the area in which the other vehicle is represented on the image and the reference size of the other vehicle on the image when the distance to the other vehicle is the reference distance, and the size of the real space of the other vehicle. The reference distance, the reference size of the detected other vehicle on the image, and the size of the real space may be stored in advance in, for example, memory 22. The position of the bottom end of the object region is assumed to represent the position where the other vehicle depicted in the object region contacts the road surface. Therefore, erroneous detection determination unit 32 may estimate the distance to the other vehicle depicted in the object region based on the direction from camera 2 corresponding to the bottom end of the object region and the installation height of camera 2.

[0061] The erroneous detection determination unit 32 determines whether the travel path of the other vehicle obtained as described above passes through an area where the vehicle cannot travel by superimposing the travel path on the high-precision map. If at least a part of the travel path obtained for any other vehicle overlaps with an area where the vehicle cannot travel, the erroneous detection determination unit 32 determines that the detected position of the own vehicle lane may differ from the actual position.

[0062] Furthermore, the erroneous detection determination unit 32 may determine that the detected position of the own lane may differ from the actual position before a certain time has elapsed since the start of the detection of the own lane, or until the vehicle 10 has traveled a certain distance since the start of the detection of the own lane. This is because the detection accuracy of the own lane may not be sufficient immediately after the start of the detection process of the own lane.

[0063] Furthermore, the erroneous detection determination unit 32 determines whether or not the number of lanes shown on the high-precision map or the image generated by the camera 2 at the current position of the vehicle 10 is equal to or greater than a predetermined number. The predetermined number is set to any number equal to or greater than 3, for example, 3 to 5. If the number of lanes is equal to or greater than the predetermined number and the detected own lane is located within a predetermined range from the center of the lanes at the current position of the vehicle 10, the erroneous detection determination unit 32 determines that the detected position of the own lane may differ from the actual position. This is because the position of the detected own lane is likely to be shifted when the road has many lanes and the vehicle 10 is traveling near the center of the road.

[0064] Furthermore, the erroneous detection determination unit 32 determines that the detected position of the vehicle's own lane may differ from the actual position when the number of lanes at the vehicle's current position has changed by a predetermined number or more from the number of lanes at the vehicle's position a predetermined time ago. This is because the detected position of the vehicle's own lane is likely to be shifted at points where the number of lanes on the road on which the vehicle 10 is traveling changes suddenly.

[0065] Furthermore, when the position of a predetermined feature detected from an image generated by the camera 2 differs from the position of a corresponding feature on a high-precision map based on the detected position of the own vehicle lane, the erroneous detection determination unit 32 determines that the detected position of the own vehicle lane may differ from the actual position. The reason why the position of the feature on the image does not match the position of the corresponding feature on the high-precision map is that the estimated position of the vehicle 10 is inaccurate, and as a result, the estimated position of the own vehicle lane may be incorrect. The erroneous detection determination unit 32 may compare the position of the feature on the image with the position of the corresponding feature on the high-precision map by projecting the feature detected from the image onto the high-precision map using a method similar to the estimation of the own vehicle position described in the own vehicle lane detection unit 31.

[0066] Furthermore, if the certainty of a predetermined feature detected from an image generated by the camera 2 is equal to or lower than a predetermined certainty threshold, the erroneous detection determination unit 32 determines that the detected position of the own vehicle lane may differ from the actual position. In this case, the certainty may be the certainty output by the classifier used by the own vehicle lane detection unit 31. In addition, it is preferable that the predetermined certainty threshold is set to a value higher than the detection threshold used by the own vehicle lane detection unit 31 to detect features from an image. This is because the estimated position of the own vehicle lane may be erroneous due to insufficient detection accuracy of features around the vehicle 10.

[0067] Furthermore, the erroneous detection determination unit 32 detects other vehicles traveling within a range shown in the image generated by the camera 2, which corresponds to an area on the high-precision map in which the vehicle 10 can travel, based on the detected position of the own lane. If the erroneous detection determination unit 32 cannot detect such other vehicles for a certain period of time, it determines that the detected position of the own lane may differ from the actual position. It is usually assumed that other vehicles are traveling in the area on the high-precision map in which the vehicle 10 can travel. Therefore, if no other vehicles are detected within the range on the image corresponding to that area, the estimation of the position of the vehicle 10 may be incorrect, and as a result, the position of the own lane may be incorrect. The erroneous detection determination unit 32 may project the area on the high-precision map in which the vehicle 10 can travel onto the image using a method similar to the estimation of the vehicle position described in the own lane detection unit 31, thereby obtaining the range on the image corresponding to that area.

[0068] Furthermore, the high-precision map may contain information indicating points where detection of the vehicle's own lane is likely to fail (hereinafter, referred to as erroneous detection danger points). In this case, the erroneous detection determination unit 32 determines that the detected position of the vehicle's own lane may differ from the actual position when the current position of the vehicle 10 is included within a predetermined range from the erroneous detection danger points specified in advance on the high-precision map.

[0069] The erroneous detection determination unit 32 notifies the control unit 34 of the determination result as to whether or not there is a possibility that the detected position of the own lane differs from the actual position.

[0070] The identification unit 33 identifies a first control of the vehicle 10 that is required to be performed in the detected own lane. Furthermore, the identification unit 33 identifies a second control of the vehicle 10 that is required to be performed in an adjacent lane adjacent to the detected own lane. In this case, the identification unit 33 may identify the first control and the second control based on at least one of a predetermined action of the vehicle 10, an image, and a high-precision map that is required to be achieved before the vehicle 10 reaches a predetermined point a predetermined distance away from the current position of the vehicle 10. Note that the second control may be set separately for an adjacent lane adjacent to the left side of the own lane and an adjacent lane adjacent to the right side of the own lane. In addition, the first control and the second control include, for example, at least one of maintaining a vehicle speed according to a vehicle speed limit, suppressing lane changes to a no-entry lane, maintaining a lane while traveling, changing lanes to a specific lane, holding the steering wheel and a HandsOn notification for that purpose, and manual driving and a notification of a driving change request for that purpose. Further, the predetermined behaviors include driving in a lane toward the destination, driving at a speed specified by the driver or specified by regulations, and driving in accordance with regulations stipulated for the road or lane.

[0071] For example, the identification unit 33 determines that the vehicle 10 completes moving to a lane heading to the destination by the time the vehicle 10 reaches a point a predetermined distance away with reference to the travel route received from the navigation device 4 as the predetermined action. In this case, the identification unit 33 determines whether the lane heading to the destination and the detected own lane match with each other with reference to the high-precision map and the detected own lane. If the lane heading to the destination and the detected own lane are different, the identification unit 33 identifies lane change to the lane heading to the destination as the first control. Furthermore, if a lane adjacent to the detected own lane and the lane heading to the destination match, the identification unit 33 identifies the vehicle 10 traveling along the lane currently being traveled as the second control. Furthermore, if the lane heading to the destination and the detected own lane match, the identification unit 33 identifies the vehicle 10 traveling along the lane currently being traveled as the first control. Furthermore, when a lane adjacent to the detected own lane is different from a lane leading to the destination, the specification unit 33 specifies a lane change to a lane leading to the destination as the second control.

[0072] The identification unit 33 may also refer to information indicating a control set for the detected own lane, which is included in the high-precision map, and identify the control indicated by the information as the first control. Similarly, the identification unit 33 may refer to information indicating a control set for an adjacent lane, which is included in the high-precision map, and identify the control indicated by the information as the second control.

[0073] Alternatively, the identification unit 33 may identify the first control or the second control by detecting a road marking or road sign indicating the control of the detected own lane or adjacent lane from the image generated by the camera 2. In this case, the identification unit 33 detects the road marking or road sign by inputting the image to a classifier that has been trained in advance to detect the road marking or road sign. The identification unit 33 may use a classifier similar to that described with respect to the feature detection of the own lane detection unit 31 as such a classifier. Therefore, the classifier outputs identification information indicating the type of the detected road marking or road sign and information indicating the object area including the road marking or road sign. Alternatively, the feature detected by the classifier used by the own lane detection unit 31 may include the road marking or road sign. In this case, the identification unit 33 may receive, from the own lane detection unit 31, identification information of the detected road marking or road sign and information indicating the object area including the detected road marking or road sign on the image.

[0074] The identification unit 33 may determine whether the detected road marking or road sign represents the first control or the second control based on the position on the image of the object area including the detected road marking or road sign and the positional relationship with the lane dividing line on the image. To this end, the identification unit 33 may identify the range in which the own lane and the adjacent lane are represented on the image by projecting the own lane and the adjacent lane on the high-precision map onto the image using a method similar to the estimation of the own vehicle position described in the own lane detection unit 31. Then, when the object area including the detected road marking is included in the range representing the own lane or the degree of overlap with the range representing the own lane is equal to or greater than a predetermined threshold, the identification unit 33 may determine that the road marking is provided on the own lane. Then, the identification unit 33 may identify the control corresponding to the road marking provided on the own lane by referring to a reference table that indicates the relationship between the type of road marking and the control specified by the road marking, and may set the identified control as the first control. Similarly, the identification unit 33 determines that the road marking is provided on the adjacent lane when the object region including the detected road marking is included in the range representing the adjacent lane, or the degree of overlap with the range representing the adjacent lane is equal to or greater than a predetermined threshold. The identification unit 33 then identifies the control corresponding to the road marking provided on the adjacent lane by referring to a reference table that indicates the relationship between the type of road marking and the control specified by the road marking, and sets the identified control as the second control. Furthermore, the identification unit 33 may identify, as the marking for the own lane, a mark having the same positional relationship as the positional relationship of the detected own lane among the lanes on the road on which the vehicle 10 is traveling, among the marks for the individual lanes indicated on the detected road sign. For example, when the detected own lane is the second lane from the right, the identification unit 33 identifies, as the marking for the own lane, the second sign from the right among the marks indicated on the detected road sign. Similarly, the identification unit 33 may identify, among the signs for individual lanes indicated on the detected road signs, a sign that has the same positional relationship as that of an adjacent lane among the lanes on the road on which the vehicle 10 is traveling, as a sign for an adjacent lane.The identification unit 33 may identify the control corresponding to the road sign provided in the own lane or the adjacent lane by referring to a reference table that indicates the relationship between the type of the road sign and the control specified by the road sign, in the same manner as when identifying the first and second controls based on the road sign. Then, the identification unit 33 may set the identified control as the first control or the second control.

[0075] Furthermore, the identification unit 33 may identify a first control required for the own lane based on the surrounding conditions of the vehicle 10 shown in the images. For example, the identification unit 33 detects other vehicles traveling around the vehicle 10 from a series of images using a method similar to that described for the erroneous detection determination unit 32, and tracks the detected other vehicles. Then, when the other vehicle being tracked travels ahead of the vehicle 10 in the own lane, and the distance between the other vehicle and the vehicle 10 becomes shorter over time, and at a certain point in time, the distance becomes equal to or less than a predetermined distance threshold, the identification unit 33 may identify a lane change to an adjacent lane as the first control.

[0076] The identification unit 33 notifies the control unit 34 of the identified first control and second control. When either the first control or the second control is not detected at the current position of the vehicle 10, the identification unit 33 may notify the control unit 34 of the undetected control among those controls.

[0077] The control unit 34 executes the first control when there is no possibility that the detected own lane differs from the actual position. On the other hand, when there is a possibility that the detected own lane differs from the actual position, the control unit 34 judges whether or not there is a possibility that the safety of the vehicle 10 will be compromised or a predetermined action will not be achieved, regardless of whether the first control or the second control is executed. Then, when there is a possibility that the safety of the vehicle 10 will be compromised or a predetermined action will not be achieved, regardless of whether the first control or the second control is executed, the control unit 34 transfers the control of the vehicle 10 to the driver.

[0078] For this purpose, when the detected position of the own lane is different from the actual position, the control unit 34 determines whether or not there is a possibility that the safety of the vehicle 10 will be compromised or the predetermined action will not be achieved by executing the first control. In this case, the control unit 34 assumes that the vehicle 10 is traveling in a lane adjacent to the detected own lane, and estimates at least one of the behaviors of the vehicle 10, such as the lane in which the vehicle 10 will travel and the speed of the vehicle 10, when the first control is tentatively executed. Then, the control unit 34 refers to the travel route, high-precision map, image, etc., and determines whether or not any of the estimated lane and behavior satisfies a danger condition that compromises the safety of the vehicle 10 and a non-achievement condition that the predetermined action is not achieved. When the danger condition is satisfied, the control unit 34 determines that there is a possibility that the safety of the vehicle 10 will be compromised. Also, when the non-achievement condition is satisfied, the control unit 34 determines that there is a possibility that the predetermined action will not be achieved.

[0079] Similarly, when the detected position of the own lane is correct, the control unit 34 determines whether or not there is a possibility that the safety of the vehicle 10 will be compromised or the predetermined action will not be achieved by executing the second control. In this case, the control unit 34 assumes that the vehicle 10 is traveling in the detected own lane, and estimates at least one of the behaviors of the vehicle 10, such as the lane in which the vehicle 10 will travel and the speed of the vehicle 10, when the second control is tentatively executed. Then, the control unit 34 refers to the traveling route, high-precision map, images, etc., and determines whether or not any of the estimated lane and behaviors satisfy the danger condition and the non-achievement condition. When the danger condition is satisfied, the control unit 34 determines that there is a possibility that the safety of the vehicle 10 will be compromised. Also, when the non-achievement condition is satisfied, the control unit 34 determines that there is a possibility that the predetermined action will not be achieved.

[0080] When it is determined by the above process that the safety of the vehicle 10 may be compromised or a predetermined action may not be achieved regardless of whether the first control or the second control is executed, the control unit 34 determines to transfer the control of the vehicle 10 to the driver. In this case, the control unit 34 notifies the driver via the user interface 6 that the control of the vehicle 10 will be transferred. Then, when a predetermined time has elapsed since the notification, the control unit 34 transfers the control of the vehicle 10 to the driver. Then, after the control of the vehicle 10 is transferred to the driver, the control unit 34 may control the running of the vehicle 10 according to the driver's operation of the accelerator, brake, steering, and the like.

[0081] In addition, when the detected vehicle lane may differ from the actual position, if neither the danger condition nor the non-attainment condition is satisfied by executing the first control, the control unit 34 may execute the first control. Similarly, when the detected vehicle lane may differ from the actual position, if neither the danger condition nor the non-attainment condition is satisfied by executing the second control, the control unit 34 may execute the second control.

[0082] 9 is an operational flowchart of the vehicle control process executed by the processor 23. The processor 23 may execute the vehicle control process in accordance with the following operational flowchart at predetermined intervals.

[0083] The own lane detection unit 31 of the processor 23 detects the own lane on which the vehicle 10 is traveling (step S101). In addition, the erroneous detection determination unit 32 of the processor 23 determines whether or not there is a possibility that the position of the detected own lane with respect to one end of the road on which the vehicle 10 is traveling differs from the actual position (step S102).

[0084] Furthermore, the specifying unit 33 of the processor 23 specifies a first control that is requested to be executed in the own lane and a second control that is requested to be executed in the adjacent lane (step S103).

[0085] The control unit 34 of the processor 23 determines whether or not the determination result notified from the erroneous detection determination unit 32 indicates that the detected position of the vehicle's own lane may differ from the actual position (step S104). If the determination result indicates that the detected position of the vehicle's own lane may not differ from the actual position (step S104-No), the control unit 34 executes the specified first control (step S105). Then, the control unit 34 ends the vehicle control process.

[0086] On the other hand, if the determination result indicates that the detected position of the vehicle's own lane may differ from the actual position (step S104-Yes), the control unit 34 determines whether or not there is any inconvenience that may occur by executing either the first control or the second control. That is, the control unit 34 determines whether or not there is a possibility that the safety of the vehicle 10 may be impaired or the predetermined action may not be achieved by executing either the first control or the second control (step S106). If there is a possibility that the safety of the vehicle 10 may be impaired or the predetermined action may not be achieved even if any control is executed (step S106-Yes), the control unit 34 transfers control of the vehicle 10 to the driver (step S107). On the other hand, if the safety of the vehicle 10 is not impaired and the predetermined action is achieved even if any control is executed (step S106-No), the control unit 34 executes that control (step S108). After step S107 or step S108, the processor 23 ends the vehicle control process.

[0087] As described above, the vehicle control device determines whether or not the position of the detected own lane relative to one end of the road on which the vehicle is traveling may differ from the actual position. The vehicle control device also identifies a first control of the vehicle that is required to be executed in the detected own lane and a second control of the vehicle that is required to be executed in an adjacent lane adjacent to the detected own lane. The vehicle control device then determines whether or not there is an inconvenience that will occur to the vehicle 10 when the first control and the second control are executed in a case where the detected own lane may differ from the actual position. That is, when there is a possibility that the safety of the vehicle 10 will be impaired or a predetermined action will not be achieved even if either the first control or the second control is executed, the vehicle control device transfers the control of the vehicle 10 to the driver. This allows the vehicle control device to suppress automatic execution of a control that should not be executed even if the detected position of the own lane is not accurate.

[0088] A computer program for realizing the functions of the processor 23 of the ECU 8 according to the above embodiment or variant example 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.

[0089] 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]

[0090] 1 Vehicle Control System 10 Vehicles 2 Camera 3 GPS receiver 4. Navigation devices 5. Wireless communication devices 6 User Interface 7 Storage Devices 8 Electronic Control Unit (ECU) 21 Communication Interface 22 Memory 23 Processors 31 Lane detection unit 32 False positive judgment unit 33 Specific part 34 Control section

Claims

1. a detection unit that detects the lane in which the vehicle is traveling among a plurality of lanes by comparing a sensor signal indicating the surroundings of the vehicle obtained by a sensor mounted on the vehicle with a map including information on a plurality of lanes provided on a road on which the vehicle is traveling; an erroneous detection determination unit that determines whether or not there is a possibility that the detected position of the own lane with respect to the one end of the road is different from an actual position; an identification unit that identifies a first control of the vehicle that is required to be performed in the own lane and a second control of the vehicle that is required to be performed in an adjacent lane adjacent to the own lane, based on at least one of a predetermined action of the vehicle that is required to be achieved before the vehicle reaches a predetermined point that is a predetermined distance away from a current position of the vehicle, the sensor signal, and the map; a control unit that transfers control of the vehicle to a driver when there is a possibility that the detected position of the own lane is different from an actual position and when there is a possibility that the safety of the vehicle is compromised or the predetermined action is not achieved even if either the first control or the second control is executed; A vehicle control device having the above configuration.

2. 2. The vehicle control device according to claim 1, wherein the control unit determines that, when executing the first control, the safety of the vehicle would be compromised or the specified action would not be performed if the vehicle were actually traveling in the adjacent lane, and when executing the second control, the safety of the vehicle would be compromised or the specified action would not be performed if the vehicle were actually traveling in the own lane, and that regardless of whether the first control or the second control is executed, there is a possibility that the safety of the vehicle will be compromised or the specified action will not be achieved.

3. 3. The vehicle control device according to claim 1, wherein the erroneous detection determination unit determines that the position of the detected vehicle lane relative to one end of the road may differ from the actual position when construction information received from another device indicates that road construction will be carried out within a specified period including the current time in a section from the vehicle's current position to a specified distance away.

4. 3. The vehicle control device according to claim 1, wherein the erroneous detection determination unit determines that there is a possibility that the position of the detected vehicle lane relative to one end of the road may differ from the actual position if the last update date and time of the map is more than a predetermined period before the current time, or if the road structure differs between the map and a route search map used by a navigation device to search for a driving route for the vehicle in a section from the current position of the vehicle to a predetermined distance ahead.

5. 3. The vehicle control device according to claim 1, wherein the erroneous detection determination unit determines that there is a possibility that the position of the detected own lane relative to one end of the road is different from the actual position when the driving trajectory of another vehicle in a section from the current position of the vehicle to a predetermined distance ahead passes through an area on the map in which the vehicle cannot drive.

6. 3. The vehicle control device according to claim 1, wherein the erroneous detection determination unit determines that there is a possibility that the position of the detected vehicle lane relative to one end of the road is different from the actual position before a certain time has elapsed since the detection unit for the vehicle lane was started, or until the vehicle has traveled a certain distance since the detection of the vehicle lane was started.

7. 3. The vehicle control device according to claim 1, wherein the erroneous detection determination unit determines that there is a possibility that the position of the detected own lane relative to one end of the road differs from the actual position when the number of lanes indicated on the map or the sensor signal at the current position of the vehicle is equal to or greater than a predetermined number and the detected own lane is located within a predetermined range from the center of a plurality of lanes on the road at the current position of the vehicle.

8. 3. The vehicle control device according to claim 1, wherein the erroneous detection determination unit determines that the position of the detected vehicle lane relative to one end of the road may differ from the actual position when the number of lanes at the vehicle's current position has changed by a predetermined number or more from the number of lanes at the vehicle's position a predetermined time ago.

9. 3. The vehicle control device according to claim 1, wherein the erroneous detection determination unit determines that there is a possibility that the position of the detected vehicle lane relative to one end of the road is different from the actual position when the position of a specified feature detected from the sensor signal is different from the position of a corresponding feature on the map based on the detected position of the vehicle lane.

10. 3. The vehicle control device according to claim 1, wherein the erroneous detection determination unit determines that there is a possibility that the position of the detected vehicle lane relative to one end of the road is different from the actual position when the certainty of a predetermined feature detected from the sensor signal is equal to or lower than a predetermined certainty threshold.

11. 3. The vehicle control device according to claim 1, wherein the erroneous detection determination unit determines that the position of the detected vehicle lane relative to one end of the road may differ from the actual position when it is unable to detect another vehicle traveling within a range indicated by the sensor signal, which corresponds to an area on the map in which the vehicle can travel, based on the detected position of the vehicle lane, for a certain period of time.

12. 3. The vehicle control device according to claim 1, wherein the erroneous detection determination unit determines that the position of the detected vehicle lane relative to one end of the road may differ from the actual position when the current position of the vehicle is within a predetermined range from a erroneous detection danger point designated in advance on the map.

13. A sensor signal indicating the surroundings of the vehicle obtained by a sensor mounted on the vehicle is compared with a map including information on a plurality of lanes on a road on which the vehicle is traveling, thereby detecting a lane in which the vehicle is traveling among the plurality of lanes; determining whether the detected position of the vehicle lane relative to the one end of the road may differ from the actual position; Identifying a first control of the vehicle that is required to be performed in the own lane and a second control of the vehicle that is required to be performed in an adjacent lane adjacent to the own lane, based on at least one of a predetermined action of the vehicle that is required to be achieved before the vehicle reaches a predetermined point that is a predetermined distance away from a current position of the vehicle, the sensor signal, and the map; When there is a possibility that the detected position of the own lane is different from the actual position, and when there is a possibility that the safety of the vehicle is compromised or the predetermined action is not achieved even if either the first control or the second control is executed, the control of the vehicle is transferred to a driver. A vehicle control method comprising:

14. A sensor signal indicating the surroundings of the vehicle obtained by a sensor mounted on the vehicle is compared with a map including information on a plurality of lanes on a road on which the vehicle is traveling, thereby detecting a lane in which the vehicle is traveling among the plurality of lanes; determining whether the detected position of the vehicle lane relative to the one end of the road may differ from the actual position; Identifying a first control of the vehicle that is required to be performed in the own lane and a second control of the vehicle that is required to be performed in an adjacent lane adjacent to the own lane, based on at least one of a predetermined action of the vehicle that is required to be achieved before the vehicle reaches a predetermined point that is a predetermined distance away from a current position of the vehicle, the sensor signal, and the map; When there is a possibility that the detected position of the own lane is different from the actual position, and when there is a possibility that the safety of the vehicle is compromised or the predetermined action is not achieved even if either the first control or the second control is executed, the control of the vehicle is transferred to a driver. A computer program for vehicle control that causes a processor mounted on the vehicle to execute the above-mentioned steps.

Images