Vehicle control device and vehicle control method

Abstract

A vehicle control device and a vehicle control method, the vehicle control device comprising: a lane detection unit (31) for detecting a lane in which a vehicle (10) is traveling; a path setting unit (32) for setting a predetermined path for the vehicle (10) to travel along the detected lane; a detection unit (33) for detecting a lane dividing line dividing the lane in which the vehicle (10) is traveling and obstacles existing around the vehicle (10); a valid interval determination unit (34) for determining a valid interval in the predetermined path that is consistent with the detected lane dividing line; and a control unit (36) for controlling the behavior of the vehicle (10) in a manner to avoid a collision between the obstacle and the vehicle (10) when the position of the obstacle is included in the valid interval and the obstacle is located on the predetermined path.

Description

Technical Field

[0001] The present invention relates to a vehicle control device and a vehicle control method. Background Art

[0002] Research is underway to develop technologies that enable automated driving of vehicles or assist the driver in driving. These technologies set a predetermined path for the vehicle and control its movement to ensure it follows that path. However, depending on the situation, obstacles may exist that pose a risk of collision with the vehicle. Therefore, technologies have been proposed for controlling the vehicle to prevent it from colliding with such obstacles (see Japanese Patent Application Laid-Open No. 2019-91325).

[0003] In the technology described in Japanese Patent Gazette No. 2019-91325, a driving assistance device performs driving assistance for a vehicle based on obstacle avoidance assistance processing derived based on information related to obstacles present on the vehicle's planned driving path and lane network information, wherein the lane network information includes at least one of information indicating whether a lane change to an adjacent lane of the vehicle's driving lane is possible and width information of the vehicle's driving lane. Summary of the Invention

[0004] When determining whether an obstacle is present in a vehicle's planned travel path and controlling the vehicle based on the determination, it is necessary to appropriately set the planned travel path for proper vehicle control. If the planned travel path is not appropriately set, the vehicle may be controlled to avoid the obstacle, even though the risk of collision with the obstacle is low. This may cause occupants of the vehicle to feel uneasy or uncomfortable.

[0005] Therefore, an object of the present invention is to provide a vehicle control device that can suppress unnecessary collision avoidance maneuvers.

[0006] According to one embodiment, a vehicle control device is provided. The vehicle control device includes: a storage unit storing map information; a lane detection unit detecting the lane in which the vehicle is traveling by comparing the map information with an image representing the vehicle's surroundings generated by a vehicle-mounted imaging unit or a position measured by a position measurement unit for measuring the vehicle's position; a path setting unit setting a predetermined path for the vehicle to travel along the detected lane; a detection unit detecting lane dividing lines dividing the lanes based on the image and detecting obstacles around the vehicle; a valid section determination unit determining a valid section within the predetermined path that coincides with the detected lane dividing lines; and a control unit controlling the behavior of the vehicle to avoid collision with the obstacle when the position of the obstacle is within the valid section and the obstacle is on the predetermined path.

[0007] In the vehicle control device, preferably, the effective interval determination unit determines the first interval as the effective interval, wherein the first interval is an interval from the current position of the vehicle to a curved position where the difference between the curvature of the planned path for the vehicle to travel and the curvature of the detected lane dividing line becomes greater than a predetermined value.

[0008] Alternatively, in the vehicle control device, preferably, the effective section determination unit determines a second section from the current position of the vehicle to an intersection position where the planned route of vehicle travel intersects the detected lane dividing line as the effective section.

[0009] Alternatively, in addition, in the vehicle control device, preferably, the effective interval determination unit determines the shorter of the first interval and the second interval as the effective interval, the first interval being an interval from the current position of the vehicle to a curved position where the difference between the curvature of the planned path for the vehicle to travel and the curvature of the detected lane dividing line becomes greater than a predetermined value, and the second interval being an interval from the current position of the vehicle to an intersection position where the planned path intersects the detected lane dividing line.

[0010] In this case, when neither the curved position nor the intersecting position can be detected, the effective section determination unit preferably determines a third section from the current position of the vehicle to the farthest position where the lane dividing line is detected as the effective section.

[0011] Furthermore, preferably, even if the position of the obstacle is outside the effective range, when the distance from the current position of the vehicle to the obstacle is below a predetermined distance threshold and the obstacle is located on a predetermined path for the vehicle to travel, the control unit controls the vehicle's behavior in a manner to avoid a collision between the obstacle and the vehicle.

[0012] According to another technical solution of the present invention, a vehicle control method is provided. The method includes: detecting a lane in which a vehicle is traveling by comparing map information with an image representing the vehicle's surroundings generated by a vehicle-mounted imaging unit or a position measured by a position measurement unit that measures the vehicle's position; setting a predetermined path for the vehicle to travel along the detected lane; detecting lane dividing lines dividing the lanes based on the image and detecting obstacles around the vehicle; determining a valid section of the predetermined path that coincides with the detected lane dividing lines; and, if the position of an obstacle is within the valid section and the obstacle is on the predetermined path, controlling the vehicle's behavior to avoid collision with the obstacle.

[0013] The traveling vehicle control device according to the present invention achieves the effect of suppressing unnecessary collision avoidance maneuvers. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a schematic diagram of the vehicle control system in which the vehicle control device is installed.

[0015] Figure 2 This is a hardware configuration diagram of an electronic control device as one embodiment of a vehicle control device.

[0016] Figure 3 This is a functional block diagram of a processor in an electronic control device related to vehicle control processing.

[0017] Figure 4A This is a diagram showing an example of a valid period.

[0018] Figure 4B This is a diagram showing an example of a valid period.

[0019] Figure 4C This is a diagram showing an example of a valid period.

[0020] Figure 4D This is a diagram showing an example of a valid period.

[0021] Figure 5 This is a flowchart of the vehicle control process. DETAILED DESCRIPTION

[0022] The following describes a vehicle control device and a vehicle control method implemented in the vehicle control device with reference to the accompanying drawings. The vehicle control device detects the lane in which the vehicle is traveling (hereinafter referred to as the host lane) and sets a planned driving path along the detected host lane. The planned driving path is the planned path for the vehicle to travel in the interval from the current position to a predetermined distance ahead. Furthermore, the vehicle control device detects lane dividing lines that separate the host lane from lanes adjacent to the host lane (hereinafter referred to as adjacent lanes) based on an image representing the vehicle's surrounding area generated by a camera mounted on the vehicle. Furthermore, based on the detected lane dividing lines, the vehicle control device determines, as sections of the planned driving path that coincide with the detected lane dividing lines, as sections of the planned driving path that are effective for determining collisions with obstacles, i.e., valid sections. Furthermore, when an obstacle detected by a sensor mounted on the vehicle is located on the planned driving path and is included in the valid section, the vehicle control device controls the vehicle's behavior to avoid collision with the obstacle. Thus, even when an adjacent lane is mistakenly recognized as the vehicle's own lane and a planned travel path is mistakenly set along the adjacent lane, the vehicle control device can prevent unnecessary vehicle behavior control.

[0023] Figure 1 This is a schematic diagram of the vehicle control system equipped with the vehicle control device. Figure 2This is a hardware configuration 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, the storage device 4, and the ECU 5 are connected in a manner that allows communication via an in-vehicle network based on 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 (laser radar) or radar that measures the distance from the vehicle 10 to objects existing around the vehicle 10. Furthermore, the vehicle control system 1 may also have a navigation device (not shown) for searching for a planned route to a destination. In addition, the vehicle control system 1 may also have a wireless communicator (not shown) for wireless communication with other devices.

[0024] The GPS receiver 2 is an example of a positioning unit. It receives GPS signals from GPS satellites at predetermined intervals and measures the vehicle 10's own position based on the received GPS signals. Furthermore, the GPS receiver 2 outputs positioning information indicating the positioning result of the vehicle 10's own position based on the GPS signals to the ECU 5 via the in-vehicle network at predetermined intervals. Alternatively, the vehicle 10 may include a receiver based on a satellite positioning system other than the GPS receiver 2. In this case, the receiver only needs to measure the vehicle 10's own position.

[0025] The camera 3 is an example of a photographing unit, 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 in the interior of the vehicle 10, for example, in a manner facing the front of the vehicle 10. The camera 3 photographs the area in front of the vehicle 10 at predetermined shooting periods (for example, 1 / 30 second to 1 / 10 second) to generate an image reflecting the area in front. The image obtained by the camera 3 can be a color image or a grayscale image. In addition, a plurality of cameras with different shooting directions or focal distances can also be provided in the vehicle 10.

[0026] Every time the camera 3 generates an image, it outputs the generated image to the ECU 5 via the in-vehicle network.

[0027] 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 its access device. Furthermore, the storage device 4 stores a high-precision map, which is an example of map information. For example, a high-precision map includes information indicating the presence or absence of lane dividing lines and the positions of lane dividing lines at various locations on roads within a predetermined area represented by the high-precision map. Furthermore, the high-precision map may also include information indicating road markings other than lane dividing lines, such as stop lines, and information indicating road signs.

[0028] Furthermore, the storage device 4 may also include a processor for executing high-precision map update processing and processing related to the readout request of the high-precision map from the ECU 5. In addition, the storage device 4 may also send a high-precision map acquisition request and the current position of the vehicle 10 to the map server via a wireless communicator (not shown) each time the vehicle 10 moves a predetermined distance, and 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. In addition, when the storage device 4 receives a high-precision map readout request from the ECU 5, it extracts a high-precision map that includes the current position of the vehicle 10 and represents a relatively narrow range compared to the above-mentioned predetermined area from the stored high-precision map, and outputs it to the ECU 5 via the in-vehicle network.

[0029] The ECU 5 controls the travel of the vehicle 10 so that the vehicle 10 performs automatic driving.

[0030] 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 independent circuits, or may be integrally configured as a single integrated circuit.

[0031] The communication interface (I / F) 21 includes an interface circuit for connecting the ECU 5 to the in-vehicle network. Each time the communication interface 21 receives positioning information from the GPS receiver 2, it transmits the positioning information to the processor 23. Furthermore, each time 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.

[0032] 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 of the vehicle 10's surroundings, positioning results of the vehicle's own position, high-precision maps, internal parameters indicating the camera 3's focal length, field of view, shooting direction, and installation position, 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.

[0033] 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 logical 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.

[0034] Figure 3 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 route setting unit 32, a detection unit 33, a valid range determination unit 34, a determination unit 35, and a vehicle control unit 36. Each of the aforementioned components of the processor 23 is, for example, a functional module implemented by a computer program running on the processor 23. Alternatively, each of the aforementioned components of the processor 23 may be a dedicated arithmetic circuit provided in the processor 23.

[0035] The lane detection unit 31 detects the lane in which the vehicle 10 is traveling (hereinafter sometimes referred to as the host lane). For example, the lane detection unit 31 refers to the current position of the vehicle 10, as determined by the GPS receiver 2, and a high-precision map to determine the road on which the vehicle 10 is traveling. Within the determined road, the lane in which the vehicle 10 can travel is detected as the host lane. For example, if the road at the vehicle 10's current position is a single-lane road with left-hand traffic, the lane detection unit 31 detects the lane to the left of the vehicle 10's direction of travel as the host lane.

[0036] Alternatively, the lane detection unit 31 can detect the vehicle's lane by comparing the image captured by the camera 3 with a high-precision map. In this case, the lane detection unit 31 detects features on or around the road represented in the image by, for example, inputting the image into a recognizer. As such a recognizer, the lane detection unit 31 can use, for example, a deep neural network (DNN) with a convolutional neural network (CNN) architecture, such as the Single Shot MultiBox Detector (SSD) or Faster R-CNN. Such a recognizer is pre-trained to detect features from the image. Furthermore, the lane detection unit 31 assumes the position and posture of the vehicle 10 by projecting features detected from the image onto the high-precision map, or by projecting features on or around the road surrounding the vehicle 10 on the high-precision map onto the image, using the internal parameters of the camera 3. The lane detection unit 31 infers the vehicle 10's current position and posture from the features detected from the image that best match the features shown on the high-precision map. Then, the lane detection unit 31 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] The lane detection unit 31 notifies the route setting unit 32 and the vehicle control unit 36 of information indicating the detected own lane and information indicating the current position of the vehicle 10 .

[0038] Upon receiving information indicating the detected host lane and information indicating the current position of the vehicle 10 from the lane detection unit 31, the route setting unit 32 sets a planned driving route along the host lane, extending from the current position of the vehicle 10 to a predetermined distance ahead. For example, the route setting unit 32 sets the planned driving route by referring to a high-precision map so that the planned driving route passes through the center of the host lane.

[0039] The route setting unit 32 notifies the set planned travel route to the effective section specifying unit 34 , the determining unit 35 , and the vehicle control unit 36 .

[0040] The detection unit 33 detects lane lines of the vehicle's lane and obstacles around the vehicle 10 based on the image obtained by the camera 3. The detection unit 33 detects lane lines represented by the image and obstacles such as parked vehicles or fallen objects on the road that become obstacles during the travel of the vehicle 10, for example, by inputting the image into a recognizer. As such a recognizer, the detection unit 33 can use, for example, an SSD or Faster R-CNN, which is similar to the recognizer described in the lane detection unit 31. Alternatively, as such a recognizer, the detection unit 33 can use a DNN for semantic segmentation that recognizes the category of the object represented by each pixel, such as a Fully Convolutional Network (FCN) or U-Net. Such a recognizer is learned in advance in order to detect lane lines and obstacles that become detection targets from the image.

[0041] Furthermore, if the vehicle 10 is equipped with a distance sensor, the detection unit 33 can also detect obstacles based on the ranging signal obtained by the distance sensor. In this case, the detection unit 33 detects obstacles by inputting the ranging signal into an identifier that has been pre-trained to detect obstacles based on the ranging signal. In this case, the identifier determines the direction of the obstacle in the ranging signal. Therefore, the detection unit 33 can estimate the distance to the detected obstacle by referring to the distance value of the ranging signal at the determined direction.

[0042] The detection unit 33 notifies the effective section determination unit 34 of information indicating the position of the lane dividing line on the image, and notifies the determination unit 35 of information indicating the position of the obstacle on the image or information indicating the distance and direction to the obstacle detected by the distance sensor.

[0043] Based on the lane dividing line between the host lane and the adjacent lane detected by the detection unit 33 , the effective section determination unit 34 determines, as an effective section, a section in the entire planned travel route that coincides with the detected lane dividing line.

[0044] Figures 4A to 4D Each of them is a diagram showing an example of a valid period.

[0045] exist Figure 4AIn the example shown, planned driving path 401 curves midway relative to the original lane 400 due to, for example, an adjacent lane being mistakenly detected as the vehicle's lane. Furthermore, the difference between the curvature of planned driving path 401 and the curvature of lane dividing line 411 between the vehicle's lane and the adjacent lane increases as the vehicle moves away from the vehicle 10. In this case, effective section determination unit 34 determines the section (first section) of planned driving path 401 from the current position of vehicle 10 to the position (hereinafter referred to as the curvature position) P where the difference between the curvature of planned driving path 401 and the curvature of lane dividing line 411 exceeds a predetermined threshold value as effective section 421. Furthermore, planned driving path 401 itself is set along the detected lane with reference to a high-precision map, and therefore can be set farther than the range recognizable by camera 3 or the like. Therefore, when the section from the current position of the vehicle 10 to the curved position P becomes the effective section, the effective section determination unit 34 can set a longer effective section, so the vehicle control unit 36 can start controlling the behavior of the vehicle 10 earlier to avoid collision between the vehicle 10 and the obstacle.

[0046] exist Figure 4BIn the example shown, planned driving path 402 intersects lane line 412 on the left side of host lane 400 midway due to, for example, an adjacent lane being mistakenly detected as the host lane. In this case, effective section determination unit 34 determines the section (second section) of planned driving path 402 from the current position of vehicle 10 to the position Q where planned driving path 402 intersects lane line 412 (hereinafter, referred to as the intersection position for ease of explanation) as effective section 422. Furthermore, to reduce the impact of errors in the recognition of the position of lane line 412 on vehicle 10 control, effective section determination unit 34 may also detect a position (indicated by dashed line 412a) that intersects planned driving path 402 at a predetermined distance inside the host lane relative to lane line 414 as intersection position Q. Furthermore, the greater the curvature of the lane line or the further away from the vehicle 10, the greater the error in the position of the lane line. Therefore, the effective interval determination unit 34 may also set the predetermined deviation distance such that the greater the curvature of the lane dividing line on the side intersecting the planned driving path, or the further away from the position of the vehicle 10, the larger the predetermined deviation distance. Alternatively, the effective interval determination unit 34 may also determine the specifications of the road on which the vehicle 10 is traveling by referring to the current position of the vehicle 10 indicated by the high-precision map and the latest positioning information, and set the predetermined deviation distance based on the specifications. Generally, the higher the specification of the road, the less likely it is to have curves with large curvatures. Therefore, the higher the specification of the road on which the vehicle 10 is traveling, the shorter the predetermined deviation distance may be set by the effective interval determination unit 34. In this case, the effective interval determination unit 34 can appropriately set the deviation distance without relying on the detection results of the lane dividing lines based on the image.

[0047] exist Figure 4C In the example shown, planned driving path 403 is set to end at a position farther than lane dividing line 413 between the vehicle's lane and the adjacent lane, detected by detection unit 33. Furthermore, neither intersection position P nor curve position Q exists. Therefore, if neither intersection position P nor curve position Q is detected, effective section determination unit 34 determines the section (third section) in planned driving path 403 from the vehicle 10's current position to the farthest point R on the detected lane dividing line 413 as effective section 423. In other words, the length of effective section 423 is equal to the length of the section from the vehicle 10's current position to the farthest point R on the detected lane dividing line 411. Furthermore, if the farthest points detected on the left lane dividing line and the right lane dividing line of the vehicle's lane are different, effective section determination unit 34 may determine the effective section based on the lane dividing line detected at the farther position from the vehicle 10's current position.

[0048] exist Figure 4DIn the example shown, the lane dividing line between the host lane and the adjacent lane is not detected. Therefore, no valid section is determined for the planned driving route 404. In other words, the length of the valid section is zero.

[0049] Furthermore, the position of each pixel in the image corresponds one-to-one with the direction to the object represented by that pixel from camera 3. Therefore, for each pixel representing a lane dividing line in the image, the valid interval determination unit 34 can estimate the actual position of the lane dividing line represented by that pixel in real space, represented by a coordinate system based on a predetermined point on vehicle 10 (e.g., the center of the front end of vehicle 10), by referring to the pixel's position and internal parameters such as the focal length and installation position of camera 3. This allows the valid interval determination unit 34 to estimate the position of the lane dividing line detected from the image in real space. Based on this estimated position, the valid interval determination unit 34 can then determine the position of the farthest end of the detected lane dividing line or the position where the planned travel path intersects the lane dividing line. Furthermore, to calculate the difference between the curvature of the planned travel path and the curvature of the detected lane dividing line, the valid interval determination unit 34 divides the planned travel path and the detected lane dividing line into sub-intervals of predetermined lengths, for example. Furthermore, the effective section determination unit 34 may simply determine the curvature of the planned driving path within each divided subsection based on the positions of the planned driving path at both end points of the subsection and the position of the planned driving path at the midpoint of the subsection. Similarly, the effective section determination unit 34 may simply determine the curvature of the lane dividing line within each divided subsection based on the positions of the lane dividing line at both end points of the subsection and the position of the lane dividing line at the midpoint of the subsection.

[0050] The effective interval determination unit 34 obtains Figure 4A The bending position P and Figure 4B In the case of both intersection positions Q shown in FIG, the interval between the position of the position with the shorter distance from the vehicle 10 and the current position of the vehicle 10 can be set as the effective interval. Figure 4A , the planned travel path 401 intersects the lane dividing line 411 at a position farther from the vehicle 10 than the curved position P. Therefore, as described above, the effective section 421 is determined as the section from the current position of the vehicle 10 to the curved position P. Figure 4B At a position farther from the vehicle 10 than the intersection position Q, the difference between the curvature of the planned travel path 402 and the curvature of the lane dividing line 412 becomes greater than the threshold. Therefore, as described above, the effective section 422 is determined to be the section from the current position of the vehicle 10 to the intersection position Q.

[0051] The valid section specifying unit 34 notifies the determining unit 35 of information indicating the valid section in the planned travel route.

[0052] The determination unit 35 determines whether the obstacle detected by the detection unit 33 is located within the valid section of the planned travel route and whether the planned travel route and the obstacle overlap.

[0053] When an obstacle is detected in an image generated by camera 3, determination unit 35 estimates the actual position of the obstacle represented by each pixel in the image, in a real-world coordinate system based on a predetermined point on vehicle 10, by referring to the pixel's position and internal parameters such as the camera 3's focal length and installation position. Furthermore, when an obstacle is detected based on a ranging signal generated by a distance sensor, the direction and distance from the location on vehicle 10 where the distance sensor is installed are known, allowing estimation of the obstacle's actual position based on this direction and distance. Determination unit 35 then compares the estimated obstacle's position in real-world space with the valid interval to determine whether the obstacle's position is within the valid interval.

[0054] If the determination unit 35 determines that an obstacle is located within the valid section of the planned travel route, it then determines whether the obstacle's position overlaps with the planned travel route. If the two overlap, the determination unit 35 determines that the obstacle is located on the planned travel route. If no obstacle is detected, the determination unit 35 determines that the obstacle is not located on the planned travel route.

[0055] Alternatively, the determination unit 35 may first determine whether the position of the obstacle overlaps with the planned driving route, and if so, determine whether the position of the obstacle is included in the valid section of the planned driving route.

[0056] Furthermore, even if the obstacle's position is not within the valid section of the planned travel route, if the distance from vehicle 10 to the obstacle's position falls below a predetermined distance threshold, determination unit 35 may determine whether the obstacle's position overlaps the planned travel route. Furthermore, the predetermined distance threshold may be, for example, the shortest distance that can be avoided by vehicle 10 performing actions to avoid collision with the obstacle, or a distance obtained by multiplying the shortest distance by a predetermined safety factor (e.g., a distance corresponding to a Time to Collision (TTC) of 1.4 seconds). Therefore, determination unit 35 may set the predetermined distance threshold to a larger value as the vehicle 10's speed, as measured by its speed sensor (not shown), increases.

[0057] The determination unit 35 notifies the vehicle control unit 36 of the determination results of whether the obstacle is located within the valid section of the planned driving route and whether the planned driving route and the obstacle overlap. Furthermore, the determination unit 35 may also notify the vehicle control unit 36 of the determination result of whether the distance from the vehicle 10 to the obstacle is less than or equal to a predetermined distance threshold.

[0058] The vehicle control unit 36 automatically controls the vehicle 10 so that it travels along the planned route. For example, the vehicle control unit 36 refers to the current position of the vehicle 10 and the planned route to determine the steering angle required to control the vehicle 10 along the planned route. The unit then 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 vehicle control unit 36 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 as measured by a speed sensor (not shown), and sets the accelerator position or braking force to achieve the target acceleration. Furthermore, the vehicle control unit 36 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 vehicle control unit 36 outputs a control signal corresponding to the set braking force to the brakes of the vehicle 10. Furthermore, the vehicle control unit 36 may determine the legal speed for the road on which the vehicle 10 is traveling by referring to a high-precision map and set the target speed of the vehicle 10 based on the legal speed. Alternatively, the vehicle control unit 36 may set the target speed of the vehicle 10 so that the inter-vehicle distance between the vehicle 10 and other vehicles traveling ahead of the vehicle 10 remains constant.

[0059] Furthermore, upon receiving a determination from the determination unit 35 that an obstacle is within the valid section of the planned travel path and that the planned travel path overlaps with the obstacle, the vehicle control unit 36 controls the behavior of the vehicle 10 to prevent the vehicle 10 from colliding with the obstacle. For example, the vehicle control unit 36 sets a braking amount to stop the vehicle 10 before colliding with the obstacle and outputs a control signal corresponding to the set braking amount to the brakes of the vehicle 10, thereby decelerating the vehicle 10. Alternatively, the vehicle control unit 36 may determine a steering angle to change the vehicle 10's course before colliding with the obstacle and output a control signal corresponding to the steering angle to an actuator (not shown) that controls the steering wheels of the vehicle 10.

[0060] By setting the situation where the obstacle is located within the effective section of the planned travel route as one of the conditions for controlling the behavior of the vehicle 10 to avoid a collision between the vehicle 10 and the obstacle, the vehicle control unit 36 can prevent the situation where the behavior of the vehicle 10 is controlled to avoid a collision even though the risk of the vehicle 10 colliding with the obstacle is low. Figure 4A, although the detected obstacle 430 is located on the planned driving path 401, the position of the obstacle 430 is outside the effective interval 421. Therefore, the behavior control of the vehicle 10 for collision avoidance is not executed. Figure 4B , although the detected obstacle 430 is located on the planned driving path 402, the position of the obstacle 430 is outside the effective interval 422. Therefore, the behavior control of the vehicle 10 for collision avoidance is not executed. Figure 4A or Figure 4B In the case shown, if the vehicle 10 correctly identifies its own lane and resets its planned driving path along the original own lane while approaching the obstacle, the obstacle will be outside the planned driving path. Therefore, the behavior control of the vehicle 10 for collision avoidance will not be executed. Figure 4C In the example shown, obstacle 430 is located outside of effective zone 423, so the behavior of vehicle 10 is not controlled for collision avoidance. However, in this case, planned travel path 403 is set along the original host lane, and obstacle 430 is located on planned travel path 403. Therefore, when vehicle 10 approaches obstacle 430 and the position of obstacle 430 is within effective zone 423, the behavior of vehicle 10 is controlled for collision avoidance.

[0061] Furthermore, when the vehicle control unit 36 obtains a determination result from the determination unit 35 that the distance from the vehicle 10 to the obstacle is less than a predetermined distance threshold and the planned driving path overlaps with the obstacle, the vehicle control unit 36 can control the behavior of the vehicle 10 in a manner to avoid a collision between the vehicle 10 and the obstacle.

[0062] 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.

[0063] The lane detection unit 31 of the processor 23 detects the lane in which the vehicle 10 is traveling, that is, the host lane (step S101). The path setting unit 32 of the processor 23 sets a planned travel path from the current position of the vehicle 10 to a predetermined distance ahead along the determined host lane (step S102).

[0064] The detection unit 33 of the processor 23 detects the lane dividing line between the vehicle's own lane and the adjacent lane and any obstacles present around the vehicle 10 based on the image acquired by the camera 3 or the ranging signal from the distance sensor (step S103). Furthermore, the valid section determination unit 34 of the processor 23 determines, based on the lane dividing line between the vehicle's own lane and the adjacent lane, the sections of the planned driving route that coincide with the detected lane dividing line as valid sections (step S104).

[0065] The determination unit 35 of the processor 23 determines whether the obstacle is within the valid section of the planned travel route (step S105). If the obstacle is not within the valid section (step S105 - No), the determination unit 35 determines whether the distance from the vehicle 10 to the obstacle is less than a predetermined distance threshold (step S106).

[0066] When the obstacle is located within the valid interval of the planned driving path (step S105-Yes), or when the distance from the vehicle 10 to the obstacle is less than the predetermined distance threshold (step S106-Yes), the vehicle control unit 36 determines whether the obstacle is located on the planned driving path (step S107).

[0067] When the obstacle is located on the planned travel path (step S107 —Yes), the vehicle control unit 36 of the processor 23 controls the behavior of the vehicle 10 so as to avoid a collision between the vehicle 10 and the obstacle (step S108 ).

[0068] On the other hand, if the distance between the vehicle 10 and the obstacle is greater than the predetermined distance threshold (step S106—No), or if the obstacle is not located on the planned travel path (step S107—No), the vehicle control unit 36 controls the behavior of the vehicle 10 so that the vehicle 10 travels along the planned travel path (step S109). After step S108 or step S109, the processor 23 ends the vehicle control process.

[0069] As described above, the vehicle control device detects the vehicle's own lane and sets a planned driving path along the detected lane. Furthermore, the vehicle control device detects lane dividing lines that separate the vehicle's own lane from adjacent lanes based on an image representing the vehicle's surrounding area generated by a vehicle-mounted camera. Furthermore, based on the detected lane dividing lines, the vehicle control device determines as valid sections the sections of the overall planned driving path that coincide with the detected lane dividing lines. Furthermore, when an obstacle detected by the vehicle-mounted sensors is located on the planned driving path and is included in the valid section, the vehicle control device controls the vehicle's behavior in a manner that avoids a collision between the obstacle and the vehicle. Thus, even if a planned driving path is incorrectly set along an adjacent lane due to misidentification of the adjacent lane as the vehicle's own lane, and a collision object with a low risk of collision is located on the incorrectly set planned driving path, the vehicle control device can prevent unnecessary vehicle behavior control.

[0070] According to a modified example, if the position of an obstacle is not included in the valid section of the planned travel route and the distance from vehicle 10 to the obstacle is below a predetermined distance threshold, determination unit 35 may predict the trajectory of vehicle 10 from the present time until a predetermined time later by performing a predetermined prediction process on the trajectory of vehicle 10 calculated based on information indicating vehicle 10's behavior, such as its yaw rate, acceleration, and speed, obtained during the most recent predetermined period. In this case, determination unit 35 may obtain information indicating vehicle 10's behavior from sensors that measure vehicle 10's behavior, such as a yaw rate sensor (not shown), an acceleration sensor (not shown), and a speed sensor (not shown). Determination unit 35 may then determine whether the predicted trajectory of vehicle 10 overlaps with the position of the obstacle. In this case, if the predicted trajectory of vehicle 10 overlaps with the position of the obstacle, vehicle control unit 36 may control the behavior of vehicle 10 to avoid a collision between vehicle 10 and the obstacle.

[0071] Furthermore, the computer program that realizes the functions of the processor 23 of the ECU 5 according to 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.

[0072] As described above, those skilled in the art can make various modifications according to the embodiments within the scope of the present invention.

Claims

1. A vehicle control device comprising: A storage unit for storing map information; a lane detection unit that detects the lane in which the vehicle is traveling by comparing an image representing the surroundings of the vehicle generated by an imaging unit mounted on the vehicle or a position measured by a position measurement unit that measures the position of the vehicle with the map information; a route setting unit that sets a planned route for the vehicle to travel along the detected lane indicated by the map information; a detection unit that detects lane dividing lines dividing the lanes based on the image and detects obstacles existing around the vehicle; an effective section determining unit for determining an effective section in the planned path that coincides with the detected lane dividing line, the effective section being a section from the current position of the vehicle to an intersection position where the planned path intersects the detected lane dividing line; as well as Control Department, The control unit is configured as follows: When the position of the obstacle is within the effective interval and the obstacle is on the predetermined path, the behavior of the vehicle is controlled so as to avoid a collision between the vehicle and the obstacle. When the obstacle is located on the predetermined path but the position of the obstacle is outside the effective section, the behavior of the vehicle is controlled so that the vehicle travels along the predetermined path. Even if the position of the obstacle is outside the effective range, the behavior of the vehicle is controlled in a manner to avoid a collision between the vehicle and the obstacle when the distance from the current position of the vehicle to the obstacle is below a predetermined distance threshold and the obstacle is located on the predetermined path.

2. A vehicle control method, comprising: detecting the lane in which the vehicle is traveling by comparing map information with an image representing the surroundings of the vehicle generated by an imaging unit mounted on the vehicle or a position measured by a position measuring unit that measures the position of the vehicle; setting a predetermined path for the vehicle to travel along the detected lane indicated by the map information; detecting lane dividing lines dividing the lane based on the image, and detecting obstacles existing around the vehicle; determining a valid section of the planned path that coincides with the detected lane dividing line, the valid section being a section from a current position of the vehicle to an intersection position where the planned path intersects the detected lane dividing line; When the position of the obstacle is within the effective range and the obstacle is on the predetermined path, controlling the behavior of the vehicle in a manner to avoid a collision between the vehicle and the obstacle; When the obstacle is located on the predetermined path but the position of the obstacle is outside the effective section, controlling the behavior of the vehicle so that the vehicle travels along the predetermined path; and Even if the position of the obstacle is outside the effective range, the behavior of the vehicle is controlled in a manner to avoid a collision between the vehicle and the obstacle when the distance from the current position of the vehicle to the obstacle is below a predetermined distance threshold and the obstacle is located on the predetermined path.

Images