Vehicle control device, vehicle control method, and recording medium

Abstract

The vehicle control device comprises: a detection unit (31) for detecting the type of a lane dividing line dividing the lane in which the vehicle (10) is traveling from a sensor signal representing a condition around the vehicle (10) generated by a sensor (3) mounted on the vehicle (10); and a control unit (33) for determining whether the type of a lane dividing line between the vehicle (10) and the adjacent lane at the current position of the vehicle (10) indicated by map information is consistent with the type of the detected lane dividing line, and controlling the vehicle (10) in such a manner as to start a lane change to the adjacent lane when a lane change to an adjacent lane adjacent to the vehicle (10) is requested.

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] Research is underway on technologies for autonomous vehicle driving or driver assistance. In particular, technologies have been proposed for automatically changing a vehicle from its own lane to an adjacent lane, or for assisting in lane changes (see Japanese Patent Application Publication No. 2016-177622 and International Publication No. 2016 / 110732).

[0003] The information processing device described in Japanese Patent Publication No. 2016-177622 detects multiple lanes including at least a driving lane and adjacent lanes adjacent to the driving lane, and displays information indicating the positional relationship between the driving lane and the adjacent lanes corresponding to the detection result to an information prompting unit capable of prompting the information to passengers of the vehicle.

[0004] Furthermore, the target path generation device disclosed in International Publication No. 2016 / 110732 determines whether a lane change exists based on acquired map information. If so, it then determines whether there is an obstacle near the lane change. If so, the target path generation device generates a target path for the vehicle so that the vehicle's driving direction in the lane change area differs from that in the lane change area if no obstacle is determined. Summary of the Invention

[0005] To determine the location at which a vehicle should perform a lane change, the vehicle references an image representing the vehicle's surrounding environment or map information showing the structure of the roads surrounding the vehicle. However, this map information does not always represent the most up-to-date structure of the roads surrounding the vehicle. After the map information is generated for use by the vehicle to perform a lane change, the road structure shown in the map information may differ from the actual road structure due to, for example, construction near the location where the lane change is to be performed.

[0006] Therefore, an object of the present invention is to provide a vehicle control device that can cause a vehicle to change lanes at an appropriate position.

[0007] According to one embodiment, a vehicle control device is provided. The vehicle control device includes: a storage unit storing map information indicating the types of lanes provided on a road and lane dividing lines provided between lanes; a detection unit detecting the type of lane dividing lines dividing a lane in which the vehicle is traveling from sensor signals indicating conditions surrounding the vehicle, generated by sensors mounted on the vehicle; and a control unit that, when a lane change to an adjacent lane adjacent to the vehicle's lane is requested, determines whether the type of the lane dividing line between the vehicle's lane and the adjacent lane at the vehicle's current position, as indicated by the map information, matches the type of the detected lane dividing line, and controls the vehicle to initiate a lane change to the adjacent lane if the type of the lane dividing line indicated by the map information matches the type of the detected lane dividing line.

[0008] In the vehicle control device, preferably, the control unit controls the vehicle so that the vehicle continues traveling in its own lane when the type of the lane dividing line indicated by the map information is different from the type of the detected lane dividing line.

[0009] According to another embodiment, a vehicle control method is provided. The method includes detecting the type of a lane dividing line dividing a lane in which the vehicle is traveling from a sensor signal representing a condition surrounding the vehicle generated by a sensor mounted on the vehicle, determining whether the type of the lane dividing line between the vehicle's lane and the adjacent lane at the vehicle's current position, as indicated by map information indicating the types of lane dividing lines provided for each lane of a road and provided between lanes, matches the type of the detected lane dividing line when a lane change is requested to the adjacent lane, and controlling the vehicle to initiate a lane change to the adjacent lane if the type of the lane dividing line indicated by the map information matches the type of the detected lane dividing line.

[0010] According to yet another embodiment, a vehicle control computer program is provided. The vehicle control computer program includes instructions for causing a processor to: detect the type of a lane dividing line that demarcates a lane in which the vehicle is traveling from sensor signals representing conditions surrounding the vehicle, generated by sensors mounted on the vehicle; determine, when a lane change to an adjacent lane adjacent to the vehicle's lane is requested, whether the type of the lane dividing line between the vehicle's lane and the adjacent lane at the vehicle's current position, as indicated by map information indicating the types of lane dividing lines provided for each lane of the road and between lanes, matches the type of the detected lane dividing line; and control the vehicle to initiate a lane change to the adjacent lane if the type of the lane dividing line indicated by the map information matches the type of the detected lane dividing line.

[0011] The traveling vehicle control device of the present invention has the effect of being able to cause the vehicle to change lanes at an appropriate position. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 This is a schematic diagram of the vehicle control system in which the vehicle control device is installed.

[0013] Figure 2 This is a hardware configuration diagram of an electronic control device as one embodiment of a vehicle control device.

[0014] Figure 3 This is a functional block diagram of a processor in an electronic control device related to vehicle control processing.

[0015] Figure 4 This is a diagram showing an overview of vehicle control according to the present embodiment.

[0016] Figure 5 This is a flowchart of the vehicle control process. DETAILED DESCRIPTION

[0017] The following describes a vehicle control device, a vehicle control method implemented in the vehicle control device, and a vehicle control computer program, with reference to the accompanying figures. The vehicle control device detects the type of lane dividing lines that demarcate the lane in which the vehicle is traveling (hereinafter referred to as the host lane) from sensor signals generated by sensors mounted on the vehicle and indicating the vehicle's surrounding conditions. Specifically, the vehicle control device detects the type of lane dividing lines between the host lane and an area on the road adjacent to the host lane (hereinafter referred to as an adjacent section). Examples of adjacent sections include lanes adjacent to the host lane (hereinafter referred to as adjacent lanes), road cliffs, or roadside strips. Lane dividing lines that demarcate the host lane include not only lane dividing lines between the host lane and adjacent lanes, but also lane dividing lines between the host lane and adjacent sections other than adjacent lanes (for example, road cliffs or roadside strips). Furthermore, when a lane change is requested to either the left or right adjacent lane, the vehicle control device determines the type of lane dividing line between the host lane and the adjacent lane at the vehicle's current position as indicated by map information. The vehicle control device then determines whether the type of lane dividing line indicated by the map information matches the type of lane dividing line actually detected on the lane change destination side relative to the vehicle's own lane. If the type of lane dividing line indicated by the map information matches the type of the detected lane dividing line, the vehicle control device determines that an adjacent lane capable of lane change actually exists on the lane change destination side relative to the vehicle's own lane and controls the vehicle to initiate a lane change to the adjacent lane. On the other hand, if the type of lane dividing line indicated by the map information differs from the type of the detected lane dividing line, the adjacent area on the lane change destination side is an area outside of a lane, such as a road cliff or roadside strip, or lane changes to the adjacent lane prior to the lane change are prohibited. In this case, the vehicle control device does not initiate a lane change. Thus, the vehicle control device determines whether to initiate a lane change by referring not only to the map information but also to the actual road structure surrounding the vehicle as indicated by sensor signals, enabling lane changes to be made at appropriate locations. As a result, the vehicle control device can prevent a lane change to an adjacent lane from being performed at a position where a lane change to the adjacent lane is actually impossible because the map information does not reflect the latest road structure around the current position of the vehicle.

[0018] Figure 1 This is a schematic diagram of the vehicle control system in which the vehicle control device is installed. Figure 2This 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 that is mounted on a vehicle 10 and controls the vehicle 10 has a GPS receiver 2, a camera 3, a storage device 4, and an electronic control unit (ECU) 5 as an example of a vehicle control device. The GPS receiver 2, the camera 3, and the storage device 4 are communicatively connected to the ECU 5 via an in-vehicle network that complies with a standard such as a controller area network. In addition, the vehicle control system 1 may also have a distance sensor (not shown) such as LiDAR or radar that measures the distance from the vehicle 10 to an object existing around the vehicle 10. Furthermore, the vehicle control system 1 may also have a navigation device (not shown) for searching for a planned driving route to a destination. Furthermore, the vehicle control system 1 may also have a wireless communicator (not shown) for wirelessly communicating with other devices.

[0019] The GPS receiver 2 is an example of a positioning unit. It receives GPS signals from GPS satellites at predetermined intervals and determines the position of the vehicle 10 based on the received GPS signals. The GPS receiver 2 then outputs positioning information indicating the position of the vehicle 10 based on the GPS signals to the ECU 5 at predetermined intervals via the in-vehicle network. Alternatively, the vehicle 10 may include a receiver that complies with a satellite positioning system other than the GPS receiver 2. In this case, the receiver alone may determine the position of the vehicle 10.

[0020] The camera 3 is an example of a sensor that generates a sensor signal indicating the surrounding conditions of the vehicle 10, and has a two-dimensional detector composed of an array of photoelectric conversion elements sensitive to visible light, such as CCD or C-MOS, and an imaging optical system that forms an image of the area to be photographed on the two-dimensional detector. The camera 3 is installed, for example, in the interior of the vehicle 10, facing the front of the vehicle 10. The camera 3 photographs the area in front of the vehicle 10 at predetermined shooting intervals (for example, 1 / 30 second to 1 / 10 second), and generates an image of the area in front. The image obtained by the camera 3 is an example of a sensor signal, and can be a color image or a gray image. In addition, a plurality of cameras with different shooting directions or focal lengths can be provided for the vehicle 10.

[0021] Whenever the camera 3 generates an image, it outputs the generated image to the ECU 5 via the in-vehicle network.

[0022] The storage device 4 is an example of a storage unit and includes, for example, at least one of a hard disk drive, a nonvolatile semiconductor memory, or an optical recording medium, and an access device therefor. Furthermore, the storage device 4 stores a high-precision map, which is an example of map information. The high-precision map includes, for example, information indicating each lane at each point on a road within a predetermined area represented by the high-precision map, the presence or absence of lane dividing lines dividing each lane, and the type of each lane dividing line.

[0023] Furthermore, the storage device 4 may also have a processor for executing high-precision map update processing and processing related to the read-out request of the high-precision map from the ECU5. In this case, the storage device 4 sends a request to obtain the high-precision map together with the current position of the vehicle 10 to the map server via a wireless communicator (not shown), for example, every time the vehicle 10 moves a specified distance. Then, the storage device 4 receives a high-precision map of a specified area around the current position of the vehicle 10 from the map server via the wireless communicator. In addition, when the storage device 4 receives a read-out request for the high-precision map from the ECU5, it cuts out a high-precision map representing a range that includes the current position of the vehicle 10 and is relatively narrower than the above-mentioned specified area from the stored high-precision map, and outputs it to the ECU5 via the in-vehicle network.

[0024] The ECU 5 controls the travel of the vehicle 10 so that the vehicle 10 is automatically driven.

[0025] like Figure 2 As shown, the ECU 5 includes a communication interface 21, a memory 22, and a processor 23. The communication interface 21, the memory 22, and the processor 23 may be configured as separate circuits, or may be integrally configured as a single integrated circuit.

[0026] The communication interface 21 includes an interface circuit for connecting the ECU 5 to the in-vehicle network. Furthermore, whenever the communication interface 21 receives positioning information from the GPS receiver 2, it transmits this positioning information to the processor 23. Furthermore, whenever the communication interface 21 receives an image from the camera 3, it transmits the received image to the processor 23. Furthermore, the communication interface 21 transmits a high-precision map read from the storage device 4 to the processor 23.

[0027] The memory 22 is another example of a storage unit, and may include, for example, volatile semiconductor memory and non-volatile semiconductor memory. Furthermore, the memory 22 stores various data used in the vehicle control processing executed by the processor 23 of the ECU 5. For example, the memory 22 stores images representing the surroundings of the vehicle 10, positioning results of the vehicle's own position, high-precision maps, internal parameters such as the focal length, field of view, shooting direction, and installation position of the camera 3, and parameter sets used to determine the identifier used to detect lane markings, etc. Furthermore, the memory 22 temporarily stores various data generated during the vehicle control processing.

[0028] 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 predetermined intervals.

[0029] Figure 3 This is a functional block diagram of the processor 23 related to vehicle control processing. The processor 23 includes a detection unit 31, a lane change necessity determination unit 32, and a control unit 33. 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.

[0030] Based on the images acquired by the ECU 5 from the camera 3, the detection unit 31 detects the categories of the lane dividing lines on the left and right sides of the vehicle's lane, that is, the categories of the lane dividing lines between the vehicle's lane and its adjacent sections on the left and right. For example, the detection unit 31 detects the lane dividing lines represented in the latest image and determines the categories of the detected lane dividing lines by inputting the latest image into a pre-trained recognizer that detects lane dividing lines from an image and determines the categories of the detected lane dividing lines. The detection unit 31 can use, for example, a deep neural network (DNN) for object detection with a convolutional neural network (CNN) architecture, such as a Single Shot MultiBox Detector (SSD) or Faster R-CNN. Alternatively, the detection unit 31 can use a DNN for semantic segmentation, such as a fully convolutional network (FCN) or U-net, as a recognizer that identifies the category of the object represented by each pixel. Such a recognizer is pre-trained using a large number of teacher images, including images representing lane dividing lines, according to a prescribed learning method, such as back propagation of the error.

[0031] The detection unit 31 determines that the lane dividing line among the detected lane dividing lines is located to the right of a reference position (for example, the midpoint of the lower end of the image in the horizontal direction) corresponding to the direction of travel of the vehicle 10 itself on the image and is closest to the reference position as the lane dividing line on the right side of the host lane. Then, the detection unit 31 uses the category of the lane dividing line output by the identifier as the category of the lane dividing line on the right side of the host lane. Similarly, the detection unit 31 determines that the lane dividing line among the detected lane dividing lines is located to the left of the reference position and is closest to the reference position as the lane dividing line on the left side of the host lane. Then, the detection unit 31 uses the category of the lane dividing line output by the identifier as the category of the lane dividing line on the left side of the host lane.

[0032] The detection unit 31 may also detect lane lines from an image using other techniques and determine the type of the detected lane lines. For example, the detection unit 31 may detect lane lines by matching a template prepared in advance for each lane line type with the image template. In this case, the detection unit 31 may simply determine that a lane line of that type is present in an area where the degree of consistency with the template for any type exceeds a predetermined threshold. In this case, the detection unit 31 may simply calculate the normalized cross-correlation value between the template and its corresponding area in the image as the degree of consistency between the template and the corresponding area.

[0033] The detection unit 31 notifies the control unit 33 of the types of the lane dividing lines on the right and left sides of the host lane.

[0034] The lane change necessity determination unit 32 determines whether the vehicle 10 needs to change from its own lane to any adjacent lane on the left or right. For example, the lane change necessity determination unit 32 refers to a high-precision map and determines whether the section from the current position of the vehicle 10 to a predetermined distance ahead includes a branch point where the road on which the vehicle 10 is currently traveling branches off. Then, if there is a branch point within the section, the lane change necessity determination unit 32 refers to the route to the destination of the vehicle 10 received from the navigation device (not shown) mounted on the vehicle 10, and determines the lane that the vehicle 10 should travel in at the branch point in order to reach the destination. Furthermore, if the determined lane is different from the own lane, the lane change necessity determination unit 32 determines that the vehicle 10 needs to change lanes to the determined lane.

[0035] In this case, to determine the host lane, the lane change necessity determination unit 32 refers to the current position of the vehicle 10 indicated by the latest positioning information obtained from the GPS receiver 2 and the high-precision map. The lane change necessity determination unit 32 then determines the lane that includes the current position of the vehicle 10 among the lanes indicated on the high-precision map as the host lane.

[0036] Alternatively, the lane change necessity determination unit 32 may detect the vehicle's lane by comparing the latest image captured by the camera 3 with a high-precision map. In this case, the lane change necessity determination unit 32, for example, inputs the image into a recognizer to detect features on or around the road depicted in the image. As such a recognizer, the lane change necessity determination unit 32 may use, for example, a DNN with a CNN-type architecture, as described in the detection unit 31. Alternatively, the recognizer for lane line detection used in the detection unit 31 may be pre-trained to detect not only lane lines but also other features. The lane change necessity determination unit 32 then assumes the position and posture of the vehicle 10 and, referring to the internal parameters of the camera 3, projects the features detected from the image onto the high-precision map, or projects the features on or around the road surrounding the vehicle 10 on the high-precision map onto the image. The lane change necessity determination unit 32 infers the vehicle 10's current position and posture from the position and posture of the vehicle 10 when the features detected from the image best match the features depicted on the high-precision map. Then, the lane change necessity determination unit 32 may detect the lane including the estimated current position of the vehicle 10 among the lanes indicated by the high-precision map as the own lane.

[0037] Alternatively, when the driver operates a direction indicator (not shown) provided in the cabin of the vehicle 10, the lane change necessity determination unit 32 may determine that the vehicle 10 needs to change lanes to an adjacent lane in a direction specified by an operation signal from the direction indicator corresponding to the operation.

[0038] When the lane change necessity determination unit 32 determines that a lane change is necessary, it notifies the control unit 33 of the request for a lane change and the direction in which the lane change should be made (left or right relative to the host lane). Furthermore, if a lane change is requested for the vehicle 10 to proceed to the destination, the lane change necessity determination unit 32 notifies the control unit 33 of the desired location for the lane change (e.g., the location where the host lane diverges from an adjacent lane leading to the destination).

[0039] When a lane change request is received to either the left or right adjacent lane, the control unit 33 reads from the memory 22 the type of lane dividing line between the vehicle's own lane and its adjacent lane at the vehicle's current position, as shown on the high-precision map (hereinafter referred to as the on-map dividing line type). The control unit 33 then determines whether the on-map dividing line type matches the type of the lane dividing line actually detected on the left and right sides of the vehicle's own lane, located on the lane change destination side. If the on-map dividing line type matches the type of the detected lane dividing line, the control unit 33 determines that a lane change-enabled adjacent lane actually exists on the lane change destination side. The control unit 33 then controls the vehicle 10 to initiate a lane change to the adjacent lane. On the other hand, it is assumed that the on-map dividing line type differs from the type of the detected lane dividing line, and the lane change destination side is an area outside of lanes such as a road ledge or roadside strip, or lane changes to the adjacent lane on the lane change destination side are prohibited. In this case, the control unit 33 does not initiate a lane change, but instead controls the vehicle 10 to continue traveling in the vehicle's own lane. Furthermore, the control unit 33 may notify the driver of not starting the lane change and the reason thereof (inconsistency in the types of lane dividing lines) via a notification device such as a display device or a speaker provided in the cabin of the vehicle 10 .

[0040] Figure 4 FIG. 1 is a diagram showing an overview of vehicle control according to this embodiment. Figure 4 On the left side, the actual road structure 400 around the vehicle 10 is shown. Figure 4 To the right of is a high-precision map 401 showing an area corresponding to structure 400, as represented by the high-precision map. In this example, it is assumed that vehicle 10 is requested to change lanes from lane 410, currently traveling, to lane 411, which branches off to the left. Furthermore, after high-precision map 401 is distributed to vehicle 10, the location where lane 411 branches off from lane 410 in road structure 400 changes from point A to point B. In other words, it is assumed that the change in the branching location is not reflected in high-precision map 401.

[0041] In area 430 near location A, the type of lane dividing line 421 between lanes 410 and 411 on high-precision map 401 is a dashed line. In contrast, in the corresponding area 431 of the actual road structure 400, lane 411 has not yet branched near location A, so the type of lane dividing line 422 on the left side of lane 410 is a solid line. Therefore, when vehicle 10 is traveling near location A, the type of lane dividing line 422 on the left side of lane 410 detected from the image generated by camera 3 differs from the type of lane dividing line 421 between lanes 410 and 411 at the corresponding location on high-precision map 401. Therefore, control unit 33 does not perform a lane change.

[0042] On the other hand, near point B, in the actual road structure 400, lane 411 also branches off from lane 410. Therefore, the type of the lane dividing line on the left side of lane 410, that is, lane dividing line 422 between lanes 410 and 411, is also a dashed line. Therefore, when vehicle 10 is traveling near point B, the type of lane dividing line 422 on the left side of lane 410 detected from the image generated by camera 3 is the same as the type of lane dividing line 421 between lanes 410 and 411 at the corresponding position in high-precision map 401. Therefore, control unit 33 controls vehicle 10 to initiate a lane change.

[0043] Thus, the control unit 33 controls the vehicle 10 to start a lane change only when the type of the detected lane dividing line matches the type of the corresponding lane dividing line on the map. Therefore, the control unit 33 can prevent the vehicle 10 from performing a lane change to an adjacent lane at a position where a lane change to the adjacent lane is actually impossible.

[0044] When performing a lane change, the control unit 33 sets the planned travel path for the vehicle 10 so that the vehicle 10 moves from its own lane to an adjacent lane. In this case, the control unit 33 sets the planned travel path so that the distance between the vehicle 10 and other vehicles traveling in the adjacent lane is greater than a predetermined distance when the vehicle 10 moves to the adjacent lane. Therefore, the control unit 33 detects other vehicles traveling in the adjacent lane based on, for example, a time-series series of images generated by the camera 3 or a time-series series of ranging signals generated by a ranging sensor (not shown) installed on the vehicle 10. The control unit 33 detects other vehicles by inputting the images or ranging signals into a recognition unit such as that described in the detection unit 31. The control unit 33 then determines whether the other vehicles are traveling in the adjacent lane based on the positional relationship between the left and right lane dividing lines of the own lane and the detected other vehicles. The control unit 33 then applies a predetermined prediction filter to the recent predetermined period of time obtained by tracking the detected other vehicles to predict the other vehicles' trajectories from the current time until a predetermined time in the past. The control unit 33 may refer to the predicted travel trajectory of another vehicle and set a planned travel route so that the other vehicle and the vehicle 10 are at least a predetermined distance apart in the adjacent lane.

[0045] When a planned travel route is set, the control unit 33 automatically controls the vehicle 10 so that it travels along the planned travel route. For example, the control unit 33 refers to the current position of the vehicle 10 and the planned travel route to determine the steering angle for the vehicle 10 to travel along the planned travel route, and outputs a control signal corresponding to the steering angle to an actuator (not shown) that controls the steering wheels of the vehicle 10. Furthermore, the control unit 33 determines the target acceleration of the vehicle 10 based on the target speed of the vehicle 10 and the current speed of the vehicle 10 measured by a vehicle speed sensor (not shown), and sets the accelerator position or brake application amount to achieve the target acceleration. The control unit 33 then determines the fuel injection amount based on the set accelerator position and outputs a control signal corresponding to the fuel injection amount to the fuel injection device of the vehicle 10 engine. Alternatively, the control unit 33 determines the power supplied to the vehicle 10 motor based on the set accelerator position and outputs a control signal corresponding to the power to the motor drive device. Furthermore, the control unit 33 outputs a control signal corresponding to the set braking amount to the brakes of the vehicle 10 .

[0046] Figure 5 This is an operational flowchart of the vehicle control process executed by the processor 23. The processor 23 may execute the vehicle control process according to the following operational flowchart at every predetermined period.

[0047] The detection unit 31 of the processor 23 detects the type of the own lane and the left and right lane dividing lines that divide the own lane based on the image acquired by the ECU 5 from the camera 3 (step S101 ).

[0048] The lane change necessity determination unit 32 of the processor 23 determines whether it is necessary to change lanes of the vehicle 10 from the own lane to any adjacent lane on the left or right (step S102 ).

[0049] If a lane change is not necessary (step S102 - No), the processor 23 ends the vehicle control process. On the other hand, if a lane change is necessary (step S102 - Yes), the control unit 33 of the processor 23 determines the type of the lane dividing line detected on the lane change destination side, among the left and right lane dividing lines of the host lane. The control unit 33 then determines whether the type of the determined lane dividing line matches the type of the corresponding lane dividing line indicated on the high-precision map (i.e., the type of the lane dividing line on the map) (step S103).

[0050] If the lane dividing line type on the map matches the type of the detected lane dividing line (step S103 - YES), the control unit 33 determines that an adjacent lane capable of lane change actually exists on the lane change destination side. The control unit 33 then controls the vehicle 10 to initiate a lane change to the adjacent lane (step S104).

[0051] On the other hand, if the lane dividing line type on the map is different from the detected lane dividing line type (step S103 - No), the control unit 33 does not initiate a lane change and controls the vehicle 10 so that the vehicle 10 continues to travel in the lane (step S105). After step S104 or step S105, the processor 23 ends the vehicle control process.

[0052] As described above, the vehicle control device detects the type of lane dividing lines that demarcate the vehicle's lane from sensor signals indicating the vehicle's surrounding conditions. Furthermore, when a lane change is requested from the vehicle's lane to any adjacent lane on the left or right, the vehicle control device determines whether the detected type of the lane dividing line on the lane change destination side of the vehicle's lane matches the type of the corresponding lane dividing line indicated by map information. If the type of the lane dividing line indicated by the map information matches the type of the detected lane dividing line, the vehicle control device determines that a lane-changeable adjacent lane exists on the lane change destination side and controls the vehicle to initiate a lane change to the adjacent lane. On the other hand, if the type of the lane dividing line indicated by the map information differs from the type of the detected lane dividing line, the vehicle control device does not initiate a lane change. Thus, the vehicle control device determines whether to initiate a lane change by referring not only to the map information but also to the actual road structure surrounding the vehicle as indicated by the sensor signals, enabling lane changes to be made at appropriate locations. As a result, the vehicle control device can prevent a lane change to an adjacent lane from being performed at a position where a lane change to the adjacent lane is actually impossible because the map information does not reflect the latest road structure around the current position of the vehicle.

[0053] According to a modified example, the detection unit 31, like the control unit 33, may be limited to determining the type of lane dividing line between the vehicle's lane and an adjacent segment when the lane change necessity determination unit 32 determines that a lane change is necessary. This eliminates the need to perform the processing of the detection unit 31 when a lane change is not necessary, thereby reducing the overall computational complexity of the vehicle control process.

[0054] Alternatively, the detection unit 31 may detect the type of each of the left and right lane dividing lines in the vehicle's lane based on sensor signals representing the surrounding conditions of the vehicle 10, generated by sensors mounted on the vehicle 10 other than the camera 3. In this case, as in the aforementioned embodiment, the detection unit 31 can detect the type of each of the left and right lane dividing lines in the vehicle's lane by inputting the sensor signals into a pre-learned identifier that detects lane dividing lines from the sensor signals and determines the type of the lane dividing lines. Such a sensor can be, for example, a FOT camera, which displays different features for each lane dividing line type in its sensor signals.

[0055] According to another variation, the control unit 33 may perform the same processing as the above-described embodiment only when the adjacent lane (hereinafter referred to as the target lane) that is the target of the requested lane change is a lane that branches off from the host lane within a specified distance from the current position of the vehicle 10. Specifically, the control unit 33 refers to the high-precision map and the current position of the vehicle 10 to determine whether the target lane is a lane that branches off from the host lane within the specified distance from the current position of the vehicle 10. If the target lane is not a lane that branches off from the host lane within the specified distance from the current position of the vehicle 10, the control unit 33 does not determine whether the detected lane dividing line between the host lane and the target lane matches the lane indicated on the high-precision map. In other words, even if the detected lane dividing line category differs from the lane indicated on the high-precision map, the control unit 33 controls the vehicle 10 to initiate a lane change. This prevents the control unit 33 from failing to execute a lane change when a lane change is requested for safety reasons, such as when the driver notices an obstacle in the host lane and requests a lane change to avoid it.

[0056] Furthermore, the computer program for realizing the functions of the processor 23 of the ECU 5 in the above-described embodiment or modification may be provided in the form of a computer-readable portable recording medium such as a semiconductor memory, a magnetic recording medium, or an optical recording medium.

[0057] As described above, those skilled in the art can make various modifications in accordance with the embodiments within the scope of the present invention.

Claims

1. A vehicle control device comprising: a storage unit storing map information indicating the types of lanes provided on the road and lane dividing lines provided between the lanes; a detection unit that detects a type of a lane dividing line that demarcates a lane in which the vehicle is traveling, from a sensor signal representing a condition surrounding the vehicle, generated by a sensor mounted on the vehicle; and The control unit, when a lane change is requested to an adjacent lane adjacent to the host lane, determines whether the adjacent lane that is the target of the requested lane change, that is, the target lane, is a lane that branches off from the host lane within a specified distance from the current position of the vehicle, and when the target lane is a lane that branches off from the host lane within the specified distance from the current position of the vehicle, determines whether the type of the lane dividing line between the host lane and the adjacent lane at the current position of the vehicle indicated by the map information is consistent with the type of the detected lane dividing line, and whether the type of the lane dividing line indicated by the map information is consistent with the type of the detected lane dividing line. When the category of the lane dividing line indicated by the map information is consistent with the category of the detected lane dividing line, the vehicle is controlled so as to start a lane change to an adjacent lane; when the category of the lane dividing line indicated by the map information is different from the category of the detected lane dividing line, the vehicle is controlled so as to continue traveling in the host lane; when the target lane is not a lane branching from the host lane within a specified distance from the current position of the vehicle, the vehicle is controlled so as to start a lane change to the adjacent lane even when the category of the lane dividing line indicated by the map information is different from the category of the detected lane dividing line.

2. A vehicle control method, comprising: detecting the type of a lane dividing line that demarcates a lane in which the vehicle is traveling from a sensor signal representing a condition surrounding the vehicle generated by a sensor mounted on the vehicle, When a lane change is requested to an adjacent lane adjacent to the host lane, determining whether the adjacent lane, i.e., the target lane, that is, the target lane of the requested lane change is a lane that branches off from the host lane within a predetermined distance from the current position of the vehicle; If the target lane is a lane that branches off from the host lane within a specified distance from the current position of the vehicle, determining whether the type of the lane dividing line between the host lane and the adjacent lane at the current position of the vehicle, as indicated by map information indicating the types of lanes and lane dividing lines provided on the road, is consistent with the type of the detected lane dividing line; When the type of the lane dividing line indicated by the map information is consistent with the type of the detected lane dividing line, the vehicle is controlled so as to start a lane change to an adjacent lane; and when the type of the lane dividing line indicated by the map information is different from the type of the detected lane dividing line, the vehicle is controlled so as to continue traveling in the own lane. In a case where the target lane is not a lane that branches off from the host lane within a specified distance from the current position of the vehicle, the vehicle is controlled in such a manner as to start a lane change to the adjacent lane even if the category of the lane dividing line represented by the map information is different from the category of the detected lane dividing line.

3. A recording medium having a vehicle control computer program recorded thereon, the vehicle control computer program causing a processor to execute: detecting the type of a lane dividing line that demarcates a lane in which the vehicle is traveling from a sensor signal representing a condition surrounding the vehicle generated by a sensor mounted on the vehicle, In a case where a lane change is requested to an adjacent lane adjacent to the own lane, determining whether the adjacent lane that is the target of the requested lane change, i.e., the target lane, is a lane that branches off from the own lane within a specified distance from the current position of the vehicle, and in a case where the target lane is a lane that branches off from the own lane within the specified distance from the current position of the vehicle, determining whether the category of the lane dividing line between the own lane and the adjacent lane at the current position of the vehicle, as indicated by map information indicating the categories of lanes set on the road and of lane dividing lines set between lanes, is consistent with the category of the detected lane dividing line, When the type of the lane dividing line indicated by the map information is consistent with the type of the detected lane dividing line, the vehicle is controlled so as to start a lane change to an adjacent lane; and when the type of the lane dividing line indicated by the map information is different from the type of the detected lane dividing line, the vehicle is controlled so as to continue traveling in the own lane. In a case where the target lane is not a lane that branches off from the host lane within a specified distance from the current position of the vehicle, the vehicle is controlled in such a manner as to start a lane change to the adjacent lane even if the category of the lane dividing line represented by the map information is different from the category of the detected lane dividing line.

Images