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

Abstract

The present invention relates to a vehicle control device, a vehicle control method, and a computer program for vehicle control. The vehicle control device detects the lane in which a vehicle (10) is traveling and determines whether there is a possibility that the position of the detected lane relative to one end of the road is different from the actual position. In addition, the vehicle control device determines a first control of the vehicle (10) required in the lane and a second control of the vehicle required in the adjacent lane. Then, when there is a possibility that the position of the detected lane is different from the actual position and that executing either the first control or the second control may damage the safety of the vehicle (10) or fail to achieve a predetermined action required to be achieved before reaching a predetermined distance ahead, the vehicle control device transfers control of the vehicle (10) to the driver.

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 Art

[0002] When a vehicle is autonomously controlled, the vehicle's control device performs positioning processing to detect the lane in which the vehicle is traveling (hereinafter sometimes referred to as the host lane). Based on the results of the positioning processing, the vehicle controls the vehicle, such as changing lanes, as needed. Therefore, in order to appropriately control the vehicle autonomously, a technology for accurately detecting the host lane has been proposed (see Japanese Patent Application Laid-Open No. 2017-45356).

[0003] The vehicle control device disclosed in Japanese Patent Application Laid-Open No. 2017-45356 identifies a dividing line that demarcates a driving road and, based on the identified dividing line, estimates a plurality of first parameters as a plurality of driving road parameters for determining the driving road. Furthermore, the vehicle control device identifies a preceding vehicle in front of the vehicle and, based on a historical record of the identified preceding vehicle's position, estimates the preceding vehicle's trajectory. Based on the estimated trajectory, the vehicle control device estimates a plurality of second parameters as the plurality of driving road parameters. Furthermore, the vehicle control device calculates a first confidence level for each of the estimated first parameters and a second confidence level for each of the estimated second parameters. Furthermore, for each driving road parameter, the vehicle control device integrates the first and second parameters based on the first and second confidence levels to calculate an integrated parameter. The vehicle control device then estimates the driving road based on the calculated integrated parameter. Furthermore, the vehicle control device provides driving assistance for the vehicle based on the integrated parameter. In this case, the vehicle control device varies the degree of driving assistance according to the integrated confidence level. Summary of the Invention

[0004] Even with the technology disclosed in Japanese Patent Application Laid-Open No. 2017-45356, the vehicle control device may have difficulty accurately detecting the vehicle's own lane. For example, if lane demarcation lines are unclear, accurate lane detection is difficult. This difficulty in detecting the vehicle's own lane can lead to undesirable situations, such as the automatic execution of vehicle control that should not have been performed.

[0005] Therefore, an object of the present invention is to provide a vehicle control device that can suppress the automatic execution of control that should not be executed even if the detection result of the own lane is inaccurate.

[0006] According to one embodiment, a vehicle control device is provided. The device includes: a detection unit for detecting a lane in which a vehicle is traveling among a plurality of lanes by comparing sensor signals indicating the vehicle's surroundings obtained by sensors mounted on the vehicle with a map containing information regarding a plurality of lanes on a road in which the vehicle is traveling; a false detection determination unit for determining whether the detected position of the lane in which the vehicle is traveling relative to one end of the road is likely to differ from the actual position; a determination unit for determining, based on at least one of a predetermined behavior of the vehicle, the sensor signals, and the map, a first vehicle control required to be executed in the lane in which the vehicle is traveling and a second vehicle control required to be executed in an adjacent lane adjacent to the lane in which the vehicle is traveling, the predetermined behavior being a behavior required to be executed by the vehicle before the vehicle reaches a predetermined location a predetermined distance ahead of the vehicle's current position; and a control unit for transferring control of the vehicle to the driver if there is a possibility that the detected position of the lane in which the vehicle is traveling is different from the actual position and if executing either the first control or the second control would compromise vehicle safety or prevent the predetermined behavior from being achieved.

[0007] In the vehicle control device, it is preferred that the control unit determines that regardless of which of the first control and the second control is executed, the safety of the vehicle may be compromised or the predetermined action cannot be achieved in the following situation, namely: by executing the first control, the safety of the vehicle will be compromised or the predetermined action cannot be performed when the vehicle is actually traveling in an adjacent lane, and by executing the second control, the safety of the vehicle will be compromised or the predetermined action cannot be performed when the vehicle is actually traveling in its own lane.

[0008] In addition, in the vehicle control device, it is preferred that: when the construction information received from other equipment indicates that road construction is being carried out within a predetermined period including the current moment in the interval from the current position of the vehicle to a predetermined distance ahead, the false detection judgment unit determines that the detected position of the own lane relative to one end of the road on which the vehicle is traveling may be different from the actual position.

[0009] Alternatively, preferably, when the last update date of the map is earlier than the current time by more than a predetermined period, or when the structure of the road in the section from the current position of the vehicle to a predetermined distance ahead in the map and the path search map used by the navigation device in searching the vehicle's driving route is different, the false detection determination unit determines that the detected position of the own lane relative to one end of the road on which the vehicle is traveling may be different from the actual position.

[0010] Alternatively, it is preferred that: when the driving trajectory of other vehicles in the interval from the current position of the vehicle to a predetermined distance ahead passes through an area in the map where the vehicle cannot drive, the false detection judgment unit determines that the detected position of the own lane relative to one end of the road on which the vehicle is traveling may be different from the actual position.

[0011] Alternatively, it is preferred that: before a certain time has passed since the start of detection of the own lane, or during the period from the start of detection of the own lane until the vehicle has traveled a certain distance, the false detection determination unit determines that the detected position of the own lane relative to one end of the road on which the vehicle is traveling may be different from the actual position.

[0012] Furthermore, it is preferred that: when the number of lanes indicated by the map or sensor signal at the current position of the vehicle is greater than a predetermined number, and the detected own lane is located within a predetermined range from the center of the multiple lanes at the current position, the false detection determination unit determines that the position of the detected own lane relative to one end of the road on which the vehicle is traveling may be different from the actual position.

[0013] In addition, it is preferred that: when the number of lanes at the current position changes by more than a predetermined number relative to the number of lanes at the position of the vehicle a predetermined time ago, the false detection determination unit determines that the detected position of the lane relative to one end of the road on which the vehicle is traveling is likely to be different from the actual position.

[0014] In addition, it is preferred that: when the position of a predetermined ground feature detected based on the sensor signal is different from the position of the corresponding ground feature on the map based on the detected position of the own lane, the false detection judgment unit determines that the detected position of the own lane relative to one end of the road on which the vehicle is traveling may be different from the actual position.

[0015] In addition, it is preferred that: when the accuracy of the predetermined ground feature detected based on the sensor signal is below a predetermined confidence threshold, the false detection judgment unit determines that the detected position of the lane relative to one end of the road on which the vehicle is traveling may be different from the actual position.

[0016] In addition, it is preferred that: when other vehicles traveling within the range indicated by the sensor signal on the map, which is equivalent to the area in which the vehicle can travel and is based on the detected position of the own lane, cannot be detected within a certain period of time, the false detection judgment unit determines that the detected position of the own lane relative to one end of the road on which the vehicle is traveling may be different from the actual position.

[0017] In addition, it is preferred that: when the current position of the vehicle is included in a predetermined range from a misdetected dangerous point pre-specified in the map, the misdetection judgment unit determines that the detected position of the own lane relative to one end of the road on which the vehicle is traveling may be different from the actual position.

[0018] According to another embodiment, a vehicle control method is provided. The method includes detecting a lane in which the vehicle is traveling among a plurality of lanes by comparing sensor signals indicating the vehicle's surroundings obtained by sensors mounted on the vehicle with a map containing information regarding a plurality of lanes on a road on which the vehicle is traveling, determining whether the detected position of the lane relative to one end of the road is likely to differ from the actual position, and determining a first control of the vehicle to be executed in the lane and a second control of the vehicle to be executed in an adjacent lane adjacent to the lane based on at least one of a predetermined behavior of the vehicle, the sensor signals, and the map. The predetermined behavior of the vehicle is a behavior that the vehicle is required to perform before reaching a predetermined location a predetermined distance ahead of the vehicle's current position. If the detected position of the lane is likely to differ from the actual position and execution of either the first or second control is likely to compromise vehicle safety or prevent the predetermined behavior from being achieved, control of the vehicle is transferred to the driver.

[0019] According to another embodiment, a vehicle control computer program is provided. The computer program includes instructions for causing a processor mounted on the vehicle to execute the following operations: detecting a lane in which the vehicle is traveling among multiple lanes by comparing sensor signals representing the vehicle's surroundings obtained by sensors mounted on the vehicle with a map containing information related to multiple lanes on a road on which the vehicle is traveling; determining whether the detected position of the lane relative to one end of the road is likely to differ from the actual position; determining a first vehicle control to be executed in the lane and a second vehicle control to be executed in an adjacent lane adjacent to the lane based on at least one of a predetermined vehicle behavior, the sensor signals, and the map; and transferring control of the vehicle to the driver if the detected position of the lane is likely to differ from the actual position and if executing either the first or second control would likely compromise vehicle safety or prevent the predetermined behavior from being achieved.

[0020] The vehicle control device of the present invention has the effect of being able to suppress the 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

[0021] Figure 1 This figure shows an example in which vehicle safety is impaired or a planned behavior cannot be achieved depending on the relationship between the detected position of the own lane and the actual position, depending on whether the control of the detected own lane and the adjacent lane request can be executed.

[0022] Figure 2 This figure shows another example in which vehicle safety is impaired or a planned behavior cannot be achieved depending on the relationship between the detected position of the own lane and the actual position, depending on whether the control of the detected own lane and the adjacent lane request can be executed.

[0023] Figure 3 This diagram shows another example in which vehicle safety is impaired or a planned behavior cannot be achieved depending on the relationship between the detected position of the own lane and the actual position, depending on whether the control of the detected own lane and the adjacent lane request can be executed.

[0024] Figure 4 This diagram shows another example in which vehicle safety is impaired or a planned behavior cannot be achieved depending on the relationship between the detected position of the own lane and the actual position, depending on whether the control of the detected own lane and the adjacent lane request can be executed.

[0025] Figure 5 This is a schematic diagram of the vehicle control system in which the vehicle control device is installed.

[0026] Figure 6 This is a hardware configuration diagram of an electronic control device as one embodiment of a vehicle control device.

[0027] Figure 7 This is a functional block diagram of a processor in an electronic control device related to vehicle control processing.

[0028] Figure 8A This is a diagram showing an example in which the detected position of the own lane relative to one end of the road is different from the actual position.

[0029] Figure 8B This is a diagram showing an example in which the detected position of the own lane relative to one end of the road is different from the actual position.

[0030] Figure 9 This is a flowchart of the vehicle control process. DETAILED DESCRIPTION

[0031] A vehicle control device, a vehicle control method executed by the vehicle control device, and a vehicle control computer program will be described below with reference to the accompanying drawings. The vehicle control device detects the vehicle's current lane among multiple lanes by comparing sensor signals representing the vehicle's surroundings obtained by sensors mounted on the vehicle with a map containing information regarding multiple lanes on the road the vehicle is traveling. The vehicle control device then determines whether the detected position of the current lane relative to one end of the road the vehicle is traveling may differ from its actual position. Furthermore, the vehicle control device determines the vehicle control required for the detected current lane and adjacent lanes. Furthermore, if the detected position of the current lane may differ from its actual position, the vehicle control device determines whether the vehicle's safety is compromised or whether a predetermined action can be achieved before reaching a predetermined distance ahead, based on whether the determined control is executed. If executing the requested control for any lane could compromise vehicle safety or prevent the vehicle from achieving the predetermined action, depending on whether the detected position of the current lane is correct or differs from its actual position, the vehicle control device transfers control of the vehicle to the driver. Thus, even if the detection result of the own lane is inaccurate, the vehicle control device can suppress the automatic execution of control that should not be executed.

[0032] Figures 1 to 4 Each diagram shows an example in which vehicle safety is impaired or a planned action cannot be achieved depending on the relationship between the detected position of the own lane and the actual position, depending on whether the control request for the detected own lane and the adjacent lane can be executed.

[0033] exist Figure 1In the example shown, road 100, on which vehicle 10 is traveling, branches into three roads 101 to 103 in the direction of vehicle 10's travel. To reach its destination, vehicle 10 must proceed to road 102 in the center of these three roads 101 to 103. That is, the action taken to proceed to center road 102 before roads 101 to 103 branch is the predetermined action required of vehicle 10. Here, it is assumed that lane 111, the fourth lane from the right, is detected as the vehicle's own lane. To reach its destination, vehicle 10 only needs to travel along lane 111. Therefore, the control required of vehicle 10 with respect to the detected own lane is lane maintenance. In contrast, the control required of lane 112, adjacent to the left of detected own lane 111, is a lane change to the right lane. Hereinafter, the control required of vehicle 10 with respect to the detected own lane is referred to as first control, and the control required of vehicle 10 with respect to the lane adjacent to the detected own lane is referred to as second control. Therefore, if the first control is executed to maintain vehicle 10 in its lane, and if the actual host lane position is lane 112, vehicle 10 will move toward road 101 in a direction different from the destination, preventing the intended action. Conversely, if the second control is executed to change lanes to the right, then if the detected host lane position is correct, vehicle 10 will move to lane 113, adjacent to the right side of lane 111. Lane 113 is interrupted in front of vehicle 10, and a lane change to lane 113 could compromise the safety of vehicle 10. Thus, regardless of whether the first or second control is executed, the relationship between the detected host lane position and the actual position could compromise vehicle safety or prevent the intended action.

[0034] exist Figure 2In the example shown, road 200, on which vehicle 10 is traveling, also branches into three roads 201-203 in the direction of vehicle 10's travel. To reach its destination, vehicle 10 must proceed to road 202, the center of the three roads 201-203. That is, the action of proceeding to the center road 102 before roads 201-203 branch off is the predetermined action required of vehicle 10. Here, it is assumed that lane 211, the fourth lane from the right, is detected as the vehicle's own lane. To reach its destination, vehicle 10 only needs to travel along lane 211. Therefore, the control required of vehicle 10 with respect to the detected own lane (first control) is lane maintenance. In contrast, the control required of lane 212, adjacent to the left of detected own lane 211 (second control), is a lane change to the right lane. Therefore, if the first control is executed to maintain vehicle 10's lane, if the actual own lane is lane 212, vehicle 10 will proceed in the direction of road 201, which is different from the destination, and the predetermined action will not be achieved. On the other hand, if the second control is executed to change lanes to the right lane, if the actual host lane position is lane 213 adjacent to the right of lane 211, the change destination lane 214 will connect to road 203 facing a different direction from the destination, thus preventing the intended action from being achieved. Thus, regardless of whether the first or second control is executed, the intended action cannot be achieved based on the relationship between the detected host lane position and the actual position.

[0035] It should be noted that the same situation may also occur when there is an intersection ahead of the road 200, only lanes 211 and 213 are allowed to go straight, lane 212 is dedicated to left turns, and lane 214 is dedicated to right turns.

[0036] exist Figure 3In the example shown, road 300, on which vehicle 10 is traveling, branches into two directions: road 301 and road 302. Lanes 311 and 314 at either end connect to road 301, which faces right, while lanes 312 and 313 in the center connect to road 302, which faces straight ahead. To reach its destination, vehicle 10 must travel on road 301, which faces right. In other words, the action required of vehicle 10 to proceed to road 301 before it branches off from road 301 is a predetermined action. Here, it is assumed that lane 312, the second lane from the left, is detected as the vehicle's lane. To reach its destination, vehicle 10 must change lanes to lane 311, adjacent to the left of lane 312. Therefore, the control required of vehicle 10 regarding the detected vehicle's lane (first control) is a lane change to the left. In contrast, the control required of lane 313, adjacent to the right of the detected vehicle's lane 312 (second control), is a lane change to the right. Therefore, if the first control is executed to change lanes to the left, if the actual position of the vehicle 10 is lane 313, the vehicle 10 will move toward road 302 facing a different direction from the destination, and the intended behavior will not be achieved. Conversely, if the second control is executed to change lanes to the right, if the detected position of the vehicle's lane is correct, lane 313 at the lane change destination will connect to road 302 facing a different direction from the destination, and the intended behavior will not be achieved. Thus, regardless of whether the first or second control is executed, the intended behavior cannot be achieved due to the relationship between the detected position of the vehicle's lane and the actual position.

[0037] exist Figure 4In the example shown, the road 400 on which the vehicle 10 is traveling includes four lanes 411 to 414, and the speeds of other vehicles traveling in the lanes to the right are faster. In this example, the vehicle 10 is following other vehicles traveling in its own lane, and traveling in the second lane from the left 412 is a predetermined action required of the vehicle 10. Here, it is assumed that lane 412 is detected as the own lane. In this case, the control required of the vehicle 10 with respect to the detected own lane (first control) is to maintain the lane and control the speed of the vehicle 10 in a manner consistent with the speeds of other vehicles traveling in lane 412. In contrast, the control required of the lane 413 adjacent to the right of the detected own lane 412 (second control) is to change lanes to the left lane and control the speed of the vehicle 10 in a manner consistent with the speeds of other vehicles traveling in the lane adjacent to the left. Therefore, if the first control is executed to maintain the lane in which the vehicle 10 is traveling, then when the actual position of the own lane is lane 411 or lane 413, the speed of the vehicle 10 is different from the speed of other vehicles traveling in the same lane. Therefore, there is a possibility that the intended action cannot be achieved, and the safety of the vehicle 10 may be compromised. On the contrary, if the second control is executed to change lanes to the left lane, then when the detected position of the own lane is correct, the vehicle 10 will move to the leftmost lane 411. Therefore, if the speed of the vehicle 10 is made consistent with the speed of other vehicles traveling in lane 412, the speed of the vehicle 10 is faster than the speed of other vehicles traveling in front of the vehicle, and the safety of the vehicle 10 may be compromised. On the other hand, if the lane change to the left lane is not implemented, and the vehicle 10 is caused to travel along the lane in which it is traveling, then when the lane in which the vehicle 10 is actually traveling is lane 413, the speed of the vehicle 10 is slower than the speed of other vehicles traveling behind the vehicle. Therefore, there is a possibility that the intended action cannot be achieved, and the safety of the vehicle 10 may be compromised. It should be noted that in Figure 4 In the example shown, the same situation may occur even when the speed limit for each lane is different.

[0038] In this embodiment, Figures 1 to 4 In any of the cases shown, by handing over the control of the vehicle 10 to the driver, even if the detection result of the own lane is inaccurate, it is possible to suppress the automatic execution of a control that should not be executed.

[0039] Figure 5 This is a schematic diagram of a vehicle control system equipped with a vehicle control device. Figure 6This is a hardware structure diagram of an electronic control device as an 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 communicator 5, a user interface 6, a storage device 7, and an electronic control unit (ECU) 8 as an example of a vehicle control device. The camera 2, the GPS receiver 3, the navigation device 4, the wireless communicator 5, the user interface 6, and the storage device 7 are connected to the ECU 8 via an in-vehicle network that complies with a standard such as a controller area network so as to be able to communicate. It should be noted that the vehicle control system 1 may also have a distance sensor (not shown) such as a LiDAR or a radar that measures the distance from the vehicle 10 to objects existing around the vehicle 10.

[0040] The camera 2 is an example of a sensor that generates a sensor signal representing the surroundings of the vehicle 10, and has a two-dimensional detector composed of an array of photoelectric conversion elements such as CCD or C-MOS that are sensitive to visible light, and an imaging optical system that forms an image of the area to be photographed on the two-dimensional detector. Furthermore, the camera 2 is installed, for example, in the cabin of the vehicle 10 in a manner facing the front of the vehicle 10. The camera 2 captures the area in front of the vehicle 10 at a predetermined shooting period (for example, 1 / 30 second to 1 / 10 second) and generates an image showing the area in front. The image obtained by the camera 2 is an example of a sensor signal. It should be noted that a plurality of cameras with different shooting directions or focal lengths may also be provided in the vehicle 10.

[0041] Every time the camera 2 generates an image, it outputs the generated image to the ECU 8 via the in-vehicle network.

[0042] The GPS receiver 3 receives GPS signals from GPS satellites at a predetermined interval and determines the position of the vehicle 10 based on the received GPS signals. Furthermore, the GPS receiver 3 outputs positioning information indicating the position of the vehicle 10 based on the GPS signals to the navigation device 4 and the ECU 8 at a predetermined interval via the in-vehicle network. It should be noted that the vehicle 10 may also include a receiver that receives positioning signals from satellites of other satellite positioning systems to determine the position of the vehicle 10, rather than a GPS receiver.

[0043] The navigation device 4 performs navigation processing for the vehicle 10 according to the navigation program running on the device. For example, when the driver instructs the driver to start the navigation program and inputs the destination of the vehicle 10, the navigation device 4 searches for the driving route of the vehicle 10 from the current position of the vehicle 10 to the destination. In this case, the navigation device 4 refers to a route search map (hereinafter sometimes referred to as a road map) stored in the device, which shows each road section and its connection relationship, and searches for the driving route according to a predetermined route search method such as the Dijkstra method. The driving route includes, for example, information indicating the roads to the destination, the direction of travel at branch points on the driving route, and the location of intersections for right or left turns. It should be noted that the navigation device 4 can use the vehicle 10's own position obtained based on the latest positioning results received from the GPS receiver 3 as the vehicle 10's current position.

[0044] When the navigation device 4 obtains the travel route of the vehicle 10 , it outputs information indicating the travel route to the ECU 8 via the in-vehicle network.

[0045] The wireless communicator 5 follows a predetermined mobile communication standard and performs wireless communication with a wireless base station. The wireless communicator 5 receives traffic information indicating the traffic conditions of the road on which the vehicle 10 is traveling or its surroundings, or construction information indicating the implementation status of construction (for example, information based on the Vehicle Information and Communication System) from other devices via the wireless base station. Furthermore, the wireless communicator 5 outputs the received traffic information to the ECU 8 via the in-vehicle network. It should be noted that the construction information includes, for example, information related to the location and time period for implementing road construction. In addition, the wireless communicator 5 can also receive a high-precision map of a predetermined area around the current position of the vehicle 10 from a map server via the wireless base station, which is used in automatic driving control, and output the received high-precision map to the storage device 7.

[0046] The user interface 6 is an example of a notification unit, and may include, for example, a display device such as a liquid crystal display or a touch panel display. The user interface 6 is provided in the vehicle cabin of the vehicle 10, for example, near the dashboard, facing the driver. Furthermore, the user interface 6 displays various information received from the ECU 8 via the in-vehicle network through icons or text messages, thereby notifying the driver of the information. The user interface 6 may also include one or more light sources provided on the dashboard, a speaker provided in the vehicle cabin, or a vibration device provided on the steering wheel or the driver's seat. In this case, the user interface 6 outputs various information received from the ECU 8 via the in-vehicle network as a sound signal, thereby notifying the driver of the information. Alternatively, the user interface 6 may vibrate the vibration device using a signal received from the ECU 8 via the in-vehicle network, thereby notifying the driver of predetermined information through the vibration. Alternatively, the user interface 6 may also notify the driver of predetermined information by lighting or flashing a light source using a signal received from the ECU 8 via the in-vehicle network.

[0047] 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 thereto. Furthermore, the storage device 7 stores a high-precision map. It should be noted that a high-precision map is an example of a map that includes information related to a plurality of lanes provided on a road. The high-precision map includes, for example, information indicating the number of lanes of each road included in a predetermined area represented by the high-precision map, road markings such as lane dividing lines or stop lines, and information indicating road signs. Furthermore, the high-precision map may also include, for each road, information indicating the control required for each lane of the road for vehicles traveling in the lane. Furthermore, the high-precision map may also include, for each road, information indicating the control prohibited for each lane of the road for vehicles traveling in the lane.

[0048] Furthermore, the storage device 7 may also have a processor for executing high-precision map update processing and processing related to the readout request of the high-precision map from the ECU 8. In addition, the storage device 7 may also send the current position of the vehicle 10 and a request to obtain the high-precision map to the map server via the wireless communicator 5 each time the vehicle 10 moves a predetermined distance. In addition, 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 communicator 5. In addition, if the storage device 7 receives a readout request for a high-precision map from the ECU 8, it cuts out a range 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 it to the ECU 8 via the in-vehicle network.

[0049] ECU 8 performs automated driving control of vehicle 10. In this embodiment, ECU 8 compares the image captured by camera 2 with a high-precision map to detect the lane in which vehicle 10 is traveling. It then determines whether the position of the detected lane relative to one end of the road on which vehicle 10 is traveling may differ from the actual position. ECU 8 then determines the actual control to be performed based on the control requested for the detected lane and the control requested for adjacent lanes, and executes the determined control.

[0050] like Figure 6 As shown, the ECU 8 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 integrally configured as a single integrated circuit.

[0051] The communication interface 21 includes an interface circuit for connecting the ECU 8 to the in-vehicle network. Furthermore, each time the communication interface 21 receives an image from the camera 2, it transmits the received image to the processor 23. Furthermore, each time the communication interface 21 receives positioning information from the GPS receiver 3, it transmits the positioning information to the processor 23. Furthermore, upon receiving a driving route from the navigation device 4, the communication interface 21 transmits the driving route to the processor 23. Furthermore, upon receiving information such as traffic information received by the wireless communicator 5 from other devices, the communication interface 21 transmits the information to the processor 23. Furthermore, the communication interface 21 transmits a high-precision map read from the storage device 7 to the processor 23.

[0052] The memory 22 includes, for example, a volatile semiconductor memory and a non-volatile semiconductor memory. Furthermore, the memory 22 stores various data used in the vehicle control processing executed by the processor 23. For example, the memory 22 stores parameters such as the focal length, shooting direction, and installation position of the camera 2, as well as various parameters of an identifier for object detection used to determine the detection of objects on the ground. In addition, the memory 22 stores a reference table indicating the relationship between the category of road signs or road markings and the control corresponding to the category. Furthermore, the memory 22 stores the driving path, the positioning information of the vehicle 10, an image of the surroundings of the vehicle 10, and a high-precision map. In addition, the memory 22 temporarily stores various data generated in the middle of the vehicle control processing.

[0053] The processor 23 includes one or more CPUs (Central Processing Units) and their peripheral circuits. The processor 23 may also include other arithmetic circuits such as a logic operation unit, a numerical operation unit, or a graphics processing unit. Furthermore, the processor 23 executes vehicle control processing for the vehicle 10 at a predetermined cycle.

[0054] Figure 7 This is a functional block diagram of the processor 23 related to vehicle control processing. The processor 23 includes a lane detection unit 31, a false detection determination unit 32, a determination unit 33, and a control unit 34. These components of the processor 23 are, for example, functional modules implemented by a computer program running on the processor 23. Alternatively, these components of the processor 23 may be dedicated computing circuits provided in the processor 23.

[0055] 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 the image (hereinafter sometimes referred to as the image) generated by the camera 2 and representing the surroundings of the vehicle 10 with the high-precision map. For example, the own lane detection unit 31 assumes the position and posture of the vehicle 10, and projects the ground objects on or around the road detected from the image onto the high-precision map, or projects the ground objects on or around the road around the vehicle 10 represented by the high-precision map onto the image. It should be noted that the ground objects on or around the road can be, for example, road markings such as lane dividing lines or stop lines, or curbs. Furthermore, the own lane detection unit 31 infers the position and posture of the vehicle 10 when the ground objects detected from the image are most consistent with the ground objects represented on the high-precision map as the own position of the vehicle 10.

[0056] The own lane detection unit 31 uses the parameters of the camera 2 such as the initial values ​​of the assumed position and posture of the vehicle 10, the focal length, the installation height, and the shooting direction to determine the position of the ground feature projected on the high-precision map or the image. It should be noted that as the initial values ​​of the position and posture of the vehicle 10, the position of the vehicle 10 located by the GPS receiver 3 or the position and posture of the vehicle 10 estimated during the last own lane detection are corrected using the odometer information. Then, the own lane detection unit 31 calculates the degree of consistency between the ground features on or around the road detected from the image and the corresponding ground features shown on the high-precision map (for example, the inverse of the sum of the squares of the distances between the corresponding ground features).

[0057] The host lane detection unit 31 repeats the above-described process while changing the assumed position and posture of the vehicle 10. Furthermore, the host lane detection unit 31 may estimate the assumed position and posture when the degree of consistency is the highest as the actual host position of the vehicle 10. Furthermore, the host lane detection unit 31 may refer to the high-precision map and identify the lane containing the host position of the vehicle 10 as the host lane in which the vehicle 10 is currently traveling.

[0058] It should be noted that the lane detection unit 31 can detect ground objects by, for example, inputting an image into a recognizer that has been pre-learned to detect ground objects from an image. As such a recognizer, the lane detection unit 31 can use a deep neural network (DNN) with a convolutional neural network (CNN)-type architecture, such as the Single Shot MultiBox Detector or Faster R-CNN. Alternatively, the lane detection unit 31 can use a DNN with a self-attention network (SAN)-type architecture, such as the Vision Transformer. These recognizers can also output a confidence level indicating the accuracy of each detected ground object. The recognizer then detects areas in the image where the confidence level calculated for a predetermined ground object exceeds a predetermined detection threshold as object regions representing the predetermined ground object.

[0059] The own lane detection unit 31 notifies the false detection determination unit 32 , the determination unit 33 , and the control unit 34 of information indicating the detected own lane.

[0060] The false detection determination unit 32 determines whether the position of the own lane detected by the own lane detection unit 31 relative to one end of the road on which the vehicle 10 is traveling may be different from the actual position.

[0061] Figure 8A and Figure 8B Each of them is a diagram showing an example where the detected position of the own lane is different from the actual position. Figure 8A In the example shown, the vehicle 10 is traveling in the second lane 801 from the right relative to the direction of travel of the vehicle 10, among a plurality of lanes provided on the road 800. However, the lane 802 adjacent to the lane 801 is mistakenly detected as the own lane. Therefore, the position of the detected own lane is different from the actual position of the own lane. Such a false detection of the own lane may occur, for example, when there are many lanes provided on the road on which the vehicle 10 is traveling, or when it is difficult to distinguish a ground feature such as a lane dividing line provided on the road due to blurriness. In addition, when the time elapsed from the start of the detection of the own lane is relatively short, such as when the vehicle 10 has just entered an area covered by a high-precision map, a false detection of the own lane may also occur.

[0062] exist Figure 8BIn the example shown, vehicle 10 is traveling in lane 811, the rightmost lane relative to the vehicle 10's direction of travel, among multiple lanes on road 810. Furthermore, in this example, lane 811 itself is detected as the vehicle's lane. However, lane 812 on the left side of road 810 was added after the high-precision map was generated, which vehicle 10 uses to detect its lane. Therefore, lane 812 is not included in road 810 on the high-precision map. As a result, the number of lanes identified by the vehicle's lane detection unit 31 between lane 811 and the left end of road 810 differs from the actual number of lanes between lane 811 and the actual left end of road 810. Consequently, the detected position of the vehicle's lane relative to the left end of road 810 differs from its actual position. This discrepancy between the number of lanes detected on the high-precision map and in the actual environment may occur when the high-precision map does not reflect the latest road information or when road construction is underway.

[0063] Therefore, the false detection determination unit 32 determines whether the detected position of the own lane relative to one end of the road on which the vehicle 10 is traveling is likely to be different from the actual position based on the structure of the road on which the vehicle 10 is traveling, the driving environment, the timing of the generation or update of the high-precision map, etc. Specifically, the false detection determination unit 32 can determine whether the detected position of the own lane is likely to be different from the actual position based on any of the determination processes described later. By executing the determination processes described later, the false detection determination unit 32 can accurately determine whether the detected position of the own lane relative to one end of the road on which the vehicle 10 is traveling is likely to be different from the actual position. It should be noted that the false detection determination unit 32 does not need to execute all of the determination processes described later, and it is sufficient to execute at least one of these determination processes. In addition, in the following, the situation where the detected position of the own lane relative to one end of the road on which the vehicle 10 is traveling is different from the actual position is sometimes expressed simply as the detected position of the own lane being different from the actual position.

[0064] For example, the false detection determination unit 32 refers to construction information received from another device via the wireless communicator 5. If this construction information indicates that road construction is occurring within a predetermined period, including the current time, between the current position of the vehicle 10 and a predetermined distance ahead, the false detection determination unit 32 determines that the detected position of the own lane may differ from the actual position. This is because the number of traversable lanes changes due to road construction, and therefore the detected position of the own lane may differ from the actual position.

[0065] Furthermore, if the high-precision map's last update date and time is more than a predetermined period prior to the current time, the false detection determination unit 32 may determine that the detected position of the own lane may differ from the actual position. Alternatively, if the road structures in the section from the vehicle 10's current position to a predetermined distance ahead differ between the high-precision map and the road map, the false detection determination unit 32 may also determine that the detected position of the own lane may differ from the actual position. This is because the high-precision map does not accurately represent the road structure surrounding the vehicle 10's current position, and therefore the detected position of the own lane may be incorrect.

[0066] Furthermore, if the trajectory of another vehicle traveling ahead of the vehicle 10 in the section from the current position of the vehicle 10 to a predetermined distance ahead passes through an area where the vehicle is prohibited from traveling on the high-precision map, the false detection determination unit 32 may determine that the detected position of the own lane may differ from the actual position. This is because it is generally not believed that another vehicle is actually traveling in an area where the vehicle is prohibited from traveling, and therefore the detected position of the own lane is likely to be incorrect.

[0067] In this case, the false detection determination unit 32 detects other vehicles traveling around the vehicle 10 based on a series of time-series images obtained by the camera 2. In this case, the false detection determination unit 32 can detect other vehicles existing around the vehicle 10 from each of the series of images by inputting the series of images to a recognizer that has been pre-learned to detect objects to be detected from images. As such a recognizer, for example, the control unit 34 can use a DNN having a CNN-type or SAN-type architecture, similar to the recognizer used by the own lane detection unit 31.

[0068] The false detection determination unit 32 determines the trajectory of other vehicles detected from a series of time-series images. To do this, the false detection determination unit 32 applies an optical flow-based tracking process, such as the Lucas-Kanade method, to the object region representing the other vehicle of interest in the latest image captured by the camera 2, as well as to the object regions in past images. Thus, the false detection determination unit 32 tracks the other vehicle represented by the object region. To this end, the false detection determination unit 32 applies a feature point extraction filter, such as the SIFT or Harris operator, to the object region of interest, extracting multiple feature points from the object region. The false detection determination unit 32 then calculates the optical flow for each of the multiple feature points by identifying the corresponding point in the object region in the past images according to the applied tracking method. Alternatively, the false detection determination unit 32 may track the other vehicle represented in the object region by applying another tracking method used for tracking moving objects detected from images to the object region of interest in the latest image and the object regions in past images.

[0069] The false detection determination unit 32 uses information such as the camera 2 installation position assigned to the vehicle 10 to perform a viewpoint conversion process on each of the other vehicles being tracked, thereby converting the other vehicle's in-image coordinates into coordinates on the bird's-eye view image (bird's-eye coordinates). The false detection determination unit 32 can estimate the position of the other vehicle detected at the time of each image acquisition based on the vehicle 10's position and posture at the time of each image acquisition, the estimated distance to the other vehicle detected, and the direction from the vehicle 10 toward the other vehicle. It should be noted that the false detection determination unit 32 can simply obtain the vehicle 10's position and posture from the lane detection unit 31. Furthermore, the false detection determination unit 32 can determine the direction from the vehicle 10 toward the other vehicle based on the position of the object area containing the detected other vehicle in the image and the direction of the optical axis of the camera 2. Furthermore, the estimated distance from the vehicle 10 to the other vehicle detected is calculated based on the ratio of the size of the area representing the other vehicle in the image to the reference size of the other vehicle in the image, using the distance to the other vehicle as the reference distance, and the actual size of the other vehicle in space. It should be noted that the reference distance, the reference size of the detected other vehicle in the image, and the size of the real space may be pre-stored in the memory 22, for example. Furthermore, it is assumed that the position of the lower end of the object region represents the position where the other vehicle represented by the object region contacts the road surface. Therefore, the false detection determination unit 32 may estimate the distance to the other vehicle represented by the object region based on the orientation relative to the camera 2 and the installation height of the camera 2 corresponding to the lower end of the object region.

[0070] The false detection determination unit 32 overlays the driving trajectory of another vehicle, calculated as described above, with the high-precision map to determine whether the trajectory passes through an area where the vehicle cannot travel. Furthermore, if at least a portion of the driving trajectory calculated for any other vehicle overlaps with the area where the vehicle cannot travel, the false detection determination unit 32 determines that the detected position of the own lane may differ from the actual position.

[0071] Furthermore, the false 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 passed since the start of the own lane detection process, or after the vehicle 10 has traveled a certain distance since the start of the own lane detection process. This is because the detection accuracy of the own lane may be insufficient immediately after the start of the own lane detection process.

[0072] Furthermore, the false detection determination unit 32 determines whether 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 greater than a predetermined number. It should be noted that the predetermined number is set to any number greater than 3, for example, 3 to 5. If the number of lanes is greater than the predetermined number and the detected own lane is within a predetermined range from the center of the multiple lanes at the current position of the vehicle 10, the false detection determination unit 32 determines that the detected position of the own lane is likely to be different from the actual position. This is because on a road with many lanes and when the vehicle 10 is traveling near the center of the road, the detected position of the own lane is likely to be offset.

[0073] Furthermore, if the number of lanes at the current position of vehicle 10 has changed by a predetermined number or more compared to the number of lanes at the position of vehicle 10 a predetermined time ago, false detection determination unit 32 determines that the detected position of the own lane is likely to differ from the actual position. This is because the detected position of the own lane is likely to deviate at locations where the number of lanes on the road on which vehicle 10 is traveling changes dramatically.

[0074] Furthermore, if the position of a predetermined feature detected in the image generated by the camera 2 differs from the position of the corresponding feature on the high-precision map based on the detected position of the own lane, the false detection determination unit 32 determines that the detected position of the own lane may differ from the actual position. As a result of this discrepancy between the position of the feature on the image and the position of the corresponding feature on the high-precision map, it is assumed that the estimated position of the vehicle 10 is incorrect, and as a result, the estimated position of the own lane may be erroneous. It should be noted that the false detection determination unit 32 can simply project the feature detected from the image onto the high-precision map using the same method as the estimation of the vehicle position described in the own lane detection unit 31, thereby comparing the position of the feature on the image with the position of the corresponding feature on the high-precision map.

[0075] Furthermore, if the confidence level of a predetermined feature detected from the image generated by the camera 2 is below a predetermined confidence threshold, the false detection determination unit 32 determines that the detected position of the own lane may differ from the actual position. In this case, the confidence level can be the confidence level output by the identifier used by the own lane detection unit 31. Furthermore, the predetermined confidence threshold is preferably set to a value higher than the detection threshold used by the own lane detection unit 31 to detect features from the image. This is because insufficient accuracy in detecting features around the vehicle 10 may result in an inaccurate estimated position of the own lane.

[0076] Furthermore, the false detection determination unit 32 detects other vehicles traveling within the range shown in the image generated by the camera 2, which corresponds to the area where the vehicle 10 can travel on the high-precision map, based on the detected position of the own lane. Furthermore, if such other vehicles cannot be detected within a certain period of time, the false detection determination unit 32 determines that the detected position of the own lane may differ from the actual position. In the area where the vehicle 10 can travel on the high-precision map, it is generally assumed that other vehicles are traveling. Therefore, if no other vehicles are detected within the range on the image corresponding to this area, the estimated position of the vehicle 10 is incorrect, and as a result, the position of the own lane may be incorrect. It should be noted that the false detection determination unit 32 can project the area where the vehicle 10 can travel on the high-precision map onto the image using the same method as the estimation of the vehicle position described in the own lane detection unit 31, thereby determining the range on the image corresponding to this area.

[0077] Furthermore, the high-precision map may also include information indicating locations where detection of the own lane is likely to fail (hereinafter referred to as misdetection risk locations). In this case, if the current position of the vehicle 10 is within a predetermined range from the misdetection risk locations pre-specified in the high-precision map, the misdetection determination unit 32 determines that the detected location of the own lane may differ from the actual location.

[0078] The false detection determination unit 32 notifies the control unit 34 of a determination result as to whether the detected position of the own lane is likely to be different from the actual position.

[0079] The determination unit 33 determines a first control of the vehicle 10 that is required to be executed in the detected own lane. Furthermore, the determination unit 33 determines a second control of the vehicle 10 that is required to be executed in an adjacent lane adjacent to the detected own lane. In this case, the determination unit 33 may determine the first and second controls based on at least one of a predetermined behavior of the vehicle 10 that the vehicle 10 is required to achieve before reaching a predetermined location a predetermined distance ahead of the vehicle 10's current position, an image, and a high-precision map. It should be noted that the second control may be independently set for the adjacent lane adjacent to the left of the own lane and the adjacent lane adjacent to the right of the own lane. Furthermore, the first and second controls may include, for example, at least one of maintaining the vehicle speed according to the speed limit, suppressing lane changes to a no-entry lane, maintaining the vehicle's lane, changing lanes to a specific lane, maintaining steering and a HandsOn notification for steering maintenance, and manual driving and a notification of a drive transition request for manual driving. Furthermore, the predetermined action includes traveling along a lane to a destination, traveling at a speed specified by the driver or specified by regulations, and traveling in compliance with regulations prescribed for roads or lanes.

[0080] For example, the determination unit 33 refers to the driving route received from the navigation device 4 and determines that the vehicle 10 completes its move to the lane leading to the destination before reaching a point a predetermined distance ahead as a predetermined action. In this case, the determination unit 33 refers to the high-precision map and the detected own lane to determine whether the lane leading to the destination matches the detected own lane. If the lane leading to the destination is different from the detected own lane, the determination unit 33 determines a lane change to the lane leading to the destination as the first control. If the lane adjacent to the detected own lane matches the lane leading to the destination, the determination unit 33 determines a lane change to the lane leading to the destination as the second control. Furthermore, if the lane leading to the destination is the same as the detected own lane, the determination unit 33 determines a lane change to the lane leading to the destination as the first control. If the lane adjacent to the detected own lane is different from the lane leading to the destination, the determination unit 33 determines a lane change to the lane leading to the destination as the second control.

[0081] Alternatively, the determination unit 33 may refer to information indicating control set for the detected own lane, included in the high-precision map, and determine the control indicated by the information as the first control. Similarly, the determination unit 33 may refer to information indicating control set for an adjacent lane, included in the high-precision map, and determine the control indicated by the information as the second control.

[0082] Alternatively, the determination unit 33 may determine the first or second control by detecting road signs or road markers indicating the detected control of the own lane or adjacent lane from the image generated by the camera 2. In this case, the determination unit 33 detects the road signs or road markers by inputting the image into a recognizer that has been pre-trained to detect road signs or road markers. The determination unit 33 can utilize the same recognizer as that described for feature detection by the own lane detection unit 31. Thus, the recognizer outputs identification information indicating the type of the detected road sign or road marker and information indicating the object area containing the road sign or road marker. Alternatively, the features detected by the recognizer used by the own lane detection unit 31 may also include road signs or road markers. In this case, the determination unit 33 simply receives the identification information of the detected road sign or road marker and information indicating the object area containing the detected road sign or road marker in the image from the own lane detection unit 31.

[0083] The determination unit 33 determines whether the detected road sign or road sign represents the first or second control based on the position of the object region containing the detected road sign or road sign on the image and its positional relationship with the lane dividing lines on the image. Therefore, the determination unit 33 projects the vehicle's lane and adjacent lanes on the high-precision map onto the image using the same method used to estimate the vehicle's position as described in the lane detection unit 31, thereby determining the range representing the vehicle's lane and the range representing the adjacent lanes on the image. If the object region containing the detected road sign is included in the range representing the vehicle's lane, or if the degree of overlap with the range representing the vehicle's lane exceeds a predetermined threshold, the determination unit 33 determines that the road sign is located in the vehicle's lane. The determination unit 33 then determines the control corresponding to the road sign located in the vehicle's lane by referring to a reference table that indicates the relationship between the road sign type and the control specified for that road sign, and sets the determined control as the first control. Similarly, when the object area including the detected road sign is included in the range representing the adjacent lane, or the degree of overlap with the range representing the adjacent lane is greater than a predetermined threshold, the determination unit 33 determines that the road sign is located in the adjacent lane. Then, the determination unit 33 determines the control corresponding to the road sign located in the adjacent lane by referring to a reference table representing the relationship between the type of road sign and the control specified by the road sign, and sets the determined control as the second control. In addition, the determination unit 33 determines the sign for each lane represented by the detected road sign that has the same positional relationship as the detected own lane in each lane on the road on which the vehicle 10 is traveling as the sign for the own lane. For example, when the detected own lane is the second lane from the right, the determination unit 33 determines the second sign from the right among the signs represented by the detected road sign as the sign for the own lane. Similarly, the determination unit 33 may simply determine, among the detected lane markings indicated by the road markings, the marking having the same positional relationship as the adjacent lane among the lanes on the road on which the vehicle 10 is traveling, as the marking for the adjacent lane. As in the case of determining the first and second controls based on the road markings, the determination unit 33 may simply determine the control corresponding to the road marking located in the vehicle's lane or the adjacent lane by referencing a reference table indicating the relationship between the road marking type and the control specified by the road marking. The determination unit 33 may then set the determined control as the first control or the second control.

[0084] Furthermore, the determination unit 33 may determine the first control required for the vehicle's lane based on the conditions surrounding the vehicle 10 as depicted in the image. For example, the determination unit 33 may detect other vehicles traveling around the vehicle 10 from a series of images using a method similar to that described for the false detection determination unit 32, and track the detected other vehicles. Furthermore, the determination unit 33 may determine a lane change to an adjacent lane as the first control if the other vehicle being tracked is traveling ahead of the vehicle 10 in the vehicle's lane, the distance between the other vehicle and the vehicle 10 decreases over time, and at a certain point in time, the distance falls below a predetermined distance threshold.

[0085] The determination unit 33 notifies the control unit 34 of the determined first and second controls. If neither the first nor the second control is detected at the current position of the vehicle 10, the determination unit 33 may notify the control unit 34 of the undetected control.

[0086] If the detected own lane is unlikely to differ from the actual position, the control unit 34 executes the first control. On the other hand, if the detected own lane is likely to differ from the actual position, the control unit 34 determines whether executing either the first or second control would compromise the safety of the vehicle 10 or prevent the vehicle 10 from performing the intended action. If executing either the first or second control would compromise the safety of the vehicle 10 or prevent the vehicle 10 from performing the intended action, the control unit 34 transfers control of the vehicle 10 to the driver.

[0087] Therefore, when the detected position of the own lane differs from the actual position, the control unit 34 determines whether the safety of the vehicle 10 may be compromised or the intended action may 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 lane in which the vehicle 10 is traveling and the behavior such as the speed of the vehicle 10 when the first control is executed. The control unit 34 then refers to the driving path, high-precision map, image, etc. to determine whether either of the estimated lane and behavior satisfies a danger condition that would compromise the safety of the vehicle 10 and an unattainable condition that would make the intended action unattainable. If the danger condition is met, the control unit 34 determines that the safety of the vehicle 10 may be compromised. If the unattainable condition is met, the control unit 34 determines that the intended action may not be achieved.

[0088] Similarly, when the position of the detected own lane is correct, the control unit 34 determines whether the safety of the vehicle 10 may be compromised or the predetermined action may 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 lane in which the vehicle 10 is traveling and the behavior such as the speed of the vehicle 10 when the second control is executed. Then, the control unit 34 refers to the driving path, high-precision map, image, etc. to determine whether any of the estimated lanes and behaviors meets the danger condition and the inability to achieve condition. If the danger condition is met, the control unit 34 determines that the safety of the vehicle 10 may be compromised. In addition, if the inability to achieve condition is met, the control unit 34 determines that the predetermined action may not be achieved.

[0089] Through the above-described processing, if the control unit 34 determines that executing either the first or second control could compromise the safety of the vehicle 10 or prevent the intended action from being achieved, it determines to hand over control of the vehicle 10 to the driver. In this case, the control unit 34 notifies the driver of the handover of control of the vehicle 10 via the user interface 6. Then, after a predetermined time has passed since this notification, the control unit 34 hands over control of the vehicle 10 to the driver. After handing over control of the vehicle 10 to the driver, the control unit 34 controls the driving of the vehicle 10 in accordance with the driver's operations on the accelerator, brakes, steering wheel, and other controls.

[0090] It should be noted that, if the detected own lane may differ from the actual position, and if any of the dangerous conditions and unattainable conditions are not satisfied by executing the first control, the control unit 34 may simply execute the first control. Similarly, if the detected own lane may differ from the actual position, and if any of the dangerous conditions and unattainable conditions are not satisfied by executing the second control, the control unit 34 may simply execute the second control.

[0091] Figure 9 This is an operational flowchart of the vehicle control process executed by the processor 23. The processor 23 only needs to execute the vehicle control process according to the following operational flowchart at a predetermined cycle.

[0092] The host lane detection unit 31 of the processor 23 detects the host lane in which the vehicle 10 is traveling (step S101). The false detection determination unit 32 of the processor 23 also determines whether the position of the detected host lane relative to one end of the road on which the vehicle 10 is traveling may be different from the actual position (step S102).

[0093] Furthermore, the determination unit 33 of the processor 23 determines the first control required to be executed in the own lane and the second control required to be executed in the adjacent lane (step S103 ).

[0094] The control unit 34 of the processor 23 determines whether the determination result notified from the false detection determination unit 32 indicates that the detected position of the host lane may differ from the actual position (step S104). If the determination result indicates that the detected position of the host lane may not differ from the actual position (step S104 - "No"), the control unit 34 executes the determined first control (step S105). The control unit 34 then terminates the vehicle control process.

[0095] On the other hand, when the determination result indicates that the detected position of the own lane may be different from the actual position (step S104-"Yes"), the control unit 34 determines whether there is any adverse situation that may occur by executing any of the first control and the second control. That is, the control unit 34 determines whether the safety of the vehicle 10 may be compromised or the predetermined action may not be achieved by executing any of the first control and the second control (step S106). When the safety of the vehicle 10 may be compromised or the predetermined action may not be achieved regardless of which 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, when the safety of the vehicle 10 is not compromised and the predetermined action is achieved regardless of which control is executed (step S106-"No"), the control unit 34 executes the control (step S108). After step S107 or step S108, the processor 23 ends the vehicle control processing.

[0096] As described above, the vehicle control device determines whether the position of the detected own lane relative to one end of the road on which the vehicle is traveling is likely to be different from the actual position. In addition, the vehicle control device determines the first control of the vehicle required to be executed in the detected own lane and the second control of the vehicle required to be executed in the adjacent lane adjacent to the detected own lane. Then, in the case where the detected own lane is likely to be different from the actual position, the vehicle control device determines whether there is any adverse condition that occurs in the vehicle 10 when the first control and the second control are executed. That is, in the case where the safety of the vehicle 10 is likely to be compromised or the predetermined action cannot be achieved regardless of which of the first control and the second control is executed, the vehicle control device transfers control of the vehicle 10 to the driver. Thus, even if the position of the detected own lane is inaccurate, the vehicle control device can suppress the automatic execution of a control that should not have been executed.

[0097] The computer program that realizes the functions of the processor 23 of the ECU 8 in the above-described embodiment or modification 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.

[0098] As described above, those skilled in the art can make various changes in the embodiments within the scope of the present invention.

Claims

1. A vehicle control device, wherein: The vehicle control device has: a detection unit that detects a lane in which the vehicle is traveling among the plurality of lanes by comparing sensor signals indicating the surroundings of the vehicle obtained by sensors mounted on the vehicle with a map including information related to a plurality of lanes provided on the road in which the vehicle is traveling; a false detection determination unit that determines whether the detected position of the own lane relative to the one end of the road may be different from the actual position; a determination unit that determines, based on at least one of a predetermined behavior of the vehicle, the sensor signal, and the map, a first control of the vehicle that is required to be performed in the host lane and a second control of the vehicle that is required to be performed in an adjacent lane adjacent to the host lane, the predetermined behavior of the vehicle being a behavior that the vehicle is required to achieve before reaching a predetermined location a predetermined distance ahead of a current position of the vehicle; as well as The control unit transfers control of the vehicle to the driver when the detected position of the own lane may be different from the actual position and no matter which of the first control and the second control is executed, the safety of the vehicle may be damaged or the predetermined action cannot be achieved.

2. The vehicle control device according to claim 1, wherein: In the following circumstances, the control unit determines that regardless of which of the first control and the second control is executed, the safety of the vehicle may be compromised or the predetermined action cannot be achieved, namely: by executing the first control, the safety of the vehicle will be compromised or the predetermined action cannot be performed when the vehicle is actually traveling in the adjacent lane, and by executing the second control, the safety of the vehicle will be compromised or the predetermined action cannot be performed when the vehicle is actually traveling in the own lane.

3. The vehicle control device according to claim 1 or 2, wherein: When construction information received from other equipment indicates that road construction is being carried out within a predetermined period including the current moment in an interval from the current position of the vehicle to a predetermined distance ahead, the false detection determination unit determines that the detected position of the own lane relative to one end of the road may be different from the actual position.

4. The vehicle control device according to claim 1 or 2, wherein: In a case where the last update date of the map is earlier than the current time by more than a predetermined period, or in a case where the structure of the road in the section from the current position of the vehicle to a predetermined distance ahead in the map and the route search map used by the navigation device in searching the driving route of the vehicle is different, the false detection determination unit determines that the detected position of the own lane relative to one end of the road is likely to be different from the actual position.

5. The vehicle control device according to claim 1 or 2, wherein: When the driving trajectory of other vehicles in the section from the current position of the vehicle to a predetermined distance ahead passes through an area in the map where the vehicle cannot drive, the false detection determination unit determines that the detected position of the own lane relative to one end of the road may be different from the actual position.

6. The vehicle control device according to claim 1 or 2, wherein: The false detection determination unit determines that the detected position of the own lane relative to one end of the road may be different from the actual position before a certain time has passed since the start of detection of the own lane, or during a period from the start of detection of the own lane until the vehicle travels a certain distance.

7. The vehicle control device according to claim 1 or 2, wherein: When the number of lanes shown on the map or the sensor signal at the current position of the vehicle is greater than a predetermined number, and the detected own lane is located within a predetermined range from the center of multiple lanes of the road located at the current position of the vehicle, the false detection determination unit determines that the detected position of the own lane relative to one end of the road is likely to be different from the actual position.

8. The vehicle control device according to claim 1 or 2, wherein: When the number of lanes at the current position changes by more than a predetermined number relative to the number of lanes at the position of the vehicle a predetermined time ago, the false detection determination unit determines that the detected position of the own lane relative to one end of the road may be different from the actual position.

9. The vehicle control device according to claim 1 or 2, wherein: When the position of a predetermined ground feature detected based on the sensor signal is different from the position of the corresponding ground feature on the map based on the detected position of the own lane, the false detection determination unit determines that the detected position of the own lane relative to one end of the road may be different from the actual position.

10. The vehicle control device according to claim 1 or 2, wherein: When the accuracy of the predetermined feature detected based on the sensor signal is equal to or less than a predetermined confidence threshold, the false detection determination unit determines that the detected position of the host lane relative to the one end of the road may be different from the actual position.

11. The vehicle control device according to claim 1 or 2, wherein: When other vehicles traveling within the range indicated by the sensor signal, which is equivalent to the area in which the vehicle can travel on the map and based on the detected position of the own lane, cannot be detected within a certain period of time, the false detection determination unit determines that the detected position of the own lane relative to one end of the road may be different from the actual position.

12. The vehicle control device according to claim 1 or 2, wherein: When the current position of the vehicle is within a predetermined range from a misdetection risk point specified in advance in the map, the misdetection determination unit determines that the detected position of the own lane relative to one end of the road may differ from the actual position.

13. A vehicle control method, wherein: The vehicle control method includes: By comparing sensor signals indicating the surroundings of the vehicle obtained by sensors mounted on the vehicle with a map containing information on a plurality of lanes provided on the road on which the vehicle is traveling, a lane in which the vehicle is traveling is detected among the plurality of lanes. determining whether the detected position of the own lane relative to one end of the road may be different from the actual position, determining, based on at least one of a predetermined action of the vehicle, the sensor signal, and the map, a first control of the vehicle required to be performed in the host lane and a second control of the vehicle required to be performed in an adjacent lane adjacent to the host lane, the predetermined action of the vehicle being an action required to be performed by the vehicle before the vehicle reaches a predetermined location a predetermined distance ahead from a current position of the vehicle, When the detected position of the own lane may be different from the actual position and executing either the first control or the second control may damage the safety of the vehicle or fail to achieve the predetermined action, control of the vehicle is handed over to the driver.

14. A computer program for controlling a vehicle, wherein: The vehicle control computer program is configured to cause a processor mounted on a vehicle to execute the following operations: By comparing sensor signals indicating the surroundings of the vehicle obtained by sensors mounted on the vehicle with a map including information on a plurality of lanes provided on the road on which the vehicle is traveling, a lane in which the vehicle is traveling is detected among the plurality of lanes; determining whether the detected position of the own lane relative to one end of the road may be different from the actual position, determining, based on at least one of a predetermined action of the vehicle, the sensor signal, and the map, a first control of the vehicle required to be performed in the host lane and a second control of the vehicle required to be performed in an adjacent lane adjacent to the host lane, the predetermined action of the vehicle being an action required to be performed by the vehicle before the vehicle reaches a predetermined location a predetermined distance ahead from a current position of the vehicle, When the detected position of the own lane may be different from the actual position and executing either the first control or the second control may damage the safety of the vehicle or fail to achieve the predetermined action, control of the vehicle is handed over to the driver.

Images