Mobile body control device, mobile body control method, and storage medium

Abstract

Provided is a mobile body control device, a mobile body control method, and a storage medium that appropriately apply information, which is information in which an image captured by a camera is converted to an overhead view coordinate system, to travel of a mobile body. The mobile body control device includes a target trajectory generation section that generates a target trajectory that indicates a path along which the mobile body will travel in the future, based on division line information that is indicated on a space in which an image that indicates a surrounding situation of the mobile body, which is captured by a camera mounted on the mobile body, is converted to the overhead view coordinate system; a curvature estimation section that calculates a curvature of the target trajectory; a curvature correction section that corrects the curvature by applying a correction filter for correcting the curvature to the estimated curvature; a speed plan generation section that generates a speed plan that indicates a target speed of the mobile body in the future, based on the corrected curvature; and a travel control section that causes the mobile body to travel in accordance with the speed plan.

Description

Technical Field

[0001] This invention relates to a mobile body control device, a mobile body control method, and a storage medium. Background Technology

[0002] Previously, there were known technologies that transformed images of the vehicle's surroundings captured by an onboard camera into a bird's-eye view coordinate system, utilizing the information from the bird's-eye view coordinate system to provide driving support for the vehicle. For example, Japanese Patent Application Publication No. 2020-77126 disclosed a technology for displaying a bird's-eye view image of a road, created from images from an onboard camera, on a display screen. Summary of the Invention

[0003] Patent Document 1 describes a technique for generating a bird's-eye view image of the approach area of ​​a vehicle and displaying it on a monitor. However, there is a limitation: when transforming an image captured by a camera into a bird's-eye view coordinate system, the greater the distance from the camera, the lower the accuracy of the information in the bird's-eye view coordinate system. As a result, there are situations where the information in the bird's-eye view coordinate system cannot be appropriately utilized for vehicle movement.

[0004] The present invention was made with regard to such circumstances, and one of its objectives is to provide a mobile body control device, a mobile body control method, and a storage medium capable of appropriately utilizing information that is information obtained by transforming images captured by a camera into a bird's-eye view coordinate system.

[0005] The mobile body control device, mobile body control method, and storage medium of the present invention adopt the following structure.

[0006] (1): One aspect of the present invention relates to a mobile body control device, wherein the mobile body control device comprises: a target track generation unit that generates a target track representing the future travel path of the mobile body based on dividing line information represented in a space after transforming an image representing the surrounding conditions of the mobile body captured by a camera mounted on the mobile body into a bird's-eye view coordinate system; a curvature estimation unit that calculates the curvature of the target track; a curvature correction unit that corrects the curvature by applying a correction filter to the estimated curvature; a speed plan generation unit that generates a speed plan representing the future target speed of the mobile body based on the corrected curvature; and a travel control unit that causes the mobile body to travel according to the speed plan.

[0007] (2): Based on the above (1) scheme, the correction filter sets the upper limit of the curvature.

[0008] (3): Based on the above (2) scheme, the correction filter sets the upper limit of the curvature with the following tendency, which means that the greater the distance between the moving body and the point on the target track, the smaller the upper limit of the curvature at the point on the target track.

[0009] (4): Based on any of the above schemes (1) to (3), the speed plan generation unit uses the modified curvature as a condition to generate the speed plan in such a way that the lateral acceleration of the moving body becomes a predetermined value.

[0010] (5): Based on any of the above schemes (1) to (4), when the speed of the moving body is greater than the target speed, the driving control unit calculates the distance required to decelerate from the speed to the target speed, so as to decelerate the moving body in such a way that the moving body reaches the target speed within the calculated distance.

[0011] (6): Another aspect of the present invention relates to a mobile body control method, wherein the mobile body control method causes a computer to perform the following processing: generating a target track representing the future path of the mobile body based on dividing line information obtained by transforming an image representing the surrounding conditions of the mobile body captured by a camera mounted on the mobile body into a bird's-eye view coordinate system; calculating the curvature of the target track; correcting the curvature by applying a correction filter to the estimated curvature; generating a speed plan representing the future target speed of the mobile body based on the corrected curvature; and causing the mobile body to travel according to the speed plan.

[0012] (7): Another aspect of the present invention relates to a storage medium storing a program that causes a computer to perform the following processing: generating a target track representing the future path of the mobile body based on dividing line information obtained by transforming an image representing the surrounding conditions of the mobile body captured by a camera mounted on the mobile body into a bird's-eye view coordinate system; calculating the curvature of the target track; correcting the curvature by applying a correction filter to the estimated curvature; generating a speed plan representing the future target speed of the mobile body based on the corrected curvature; and causing the mobile body to travel according to the speed plan.

[0013] According to the schemes (1) to (7), the information after the images captured by the camera are transformed into the bird's-eye view coordinate system can be appropriately used for the movement of the moving body.

[0014] According to scheme (2) or (3), outliers of curvature generated when the image captured by the camera is transformed into the bird's-eye view coordinate system can be eliminated.

[0015] According to scheme (4) or (5), the mobile vehicle can be driven without causing discomfort to the occupants. Attached Figure Description

[0016] Figure 1 This is a structural diagram of a vehicle system utilizing the mobile body control device of the implementation method.

[0017] Figure 2 This diagram illustrates an example of a method for an object recognition device to extract information about dividing lines.

[0018] Figure 3 It is a line graph used to illustrate the characteristics of a group of points that serve as dividing line information obtained by an object recognition device.

[0019] Figure 4 This is a functional structure diagram of the first control unit and the second control unit included in the automatic driving control device.

[0020] Figure 5 This is a diagram illustrating an example of a method for generating a target orbit by a target orbit generation unit.

[0021] Figure 6 This is a line graph showing an example of the estimated curvature of the target trajectory calculated by the curvature estimation unit.

[0022] Figure 7 This is a line graph showing an example of the corrected curvature of the target trajectory after correction by the curvature correction unit.

[0023] Figure 8 This is a diagram showing an example of a speed plan generated by the speed plan generation department.

[0024] Figure 9 This is a line diagram showing an example of the corrected curvature of the target track after correction by the curvature correction unit when the vehicle is traveling on a curve.

[0025] Figure 10 This is a diagram illustrating an example of the processing flow performed by an autonomous driving control device. Detailed Implementation

[0026] Hereinafter, with reference to the accompanying drawings, embodiments of the mobile body control device, mobile body control method, and storage medium of the present invention will be described. The mobile body control device is a device for controlling the movement of a mobile body. Mobile bodies include three-wheeled or four-wheeled vehicles, two-wheeled vehicles, micro-mobile bodies, etc., and may also include all mobile bodies that are for carrying people (occupants) and are capable of moving on a road surface with lanes. In the following description, the mobile body is a four-wheeled vehicle, and the vehicle equipped with a driving support device is referred to as vehicle M.

[0027] [Overall Structure]

[0028] Figure 1 This is a structural diagram of a vehicle system 1 utilizing the mobile body control device of the embodiment. The drive source of the vehicle equipped with vehicle system 1 is an internal combustion engine such as a diesel engine or a gasoline engine, an electric motor, or a combination thereof. The electric motor operates using electricity generated by a generator connected to the internal combustion engine, or electricity discharged from a secondary battery or fuel cell.

[0029] Vehicle system 1 includes, for example, a camera 10, a radar device 12, an object recognition device 16, a communication device 20, an HMI (Human Machine Interface) 30, vehicle sensors 40, a navigation device 50, an MPU (Map Positioning Unit) 60, driving controls 80, an automatic driving control device 100, a driving force output device 200, a braking device 210, and a steering device 220. These devices and equipment are interconnected via CAN (Controller Area Network) communication lines, serial communication lines, wireless communication networks, etc. It should be noted that... Figure 1 The structure shown is just one example; you can omit part of the structure or add other structures.

[0030] Camera 10 is, for example, a digital camera utilizing a solid-state imaging element such as CCD (Charge Coupled Device) or CMOS (Complementary Metal-Oxide Semiconductor). Camera 10 is mounted anywhere on the vehicle equipped with vehicle system 1 (hereinafter referred to as the vehicle M). When taking pictures of the front, camera 10 is mounted on the upper part of the windshield, the back of the rearview mirror inside the vehicle, etc. Camera 10, for example, periodically and repeatedly takes pictures of the surroundings of the vehicle M. Camera 10 can also be a stereo camera.

[0031] Radar device 12 radiates millimeter-wave or other radio waves around the vehicle M and detects the radio waves reflected by objects (reflected waves) to detect at least the position (distance and orientation) of the objects. Radar device 12 can be installed at any location on the vehicle M. Radar device 12 can also detect the position and speed of objects using FM-CW (Frequency Modulated Continuous Wave) method.

[0032] The object recognition device 16 analyzes the image of the situation in front of the vehicle M captured by the camera 10 and extracts necessary information. Furthermore, the object recognition device 16 performs sensor fusion processing on the detection results from the camera 10 and the radar device 12 to identify the position, type, speed, etc., of objects, and outputs the identification results to the autonomous driving control device 100. In this invention, the radar device 12 can be omitted; in this case, the object recognition device 16 may only have the function of analyzing images. Alternatively, sensor fusion processing may be omitted, and the detection results from the radar device 12 may be directly output to the autonomous driving control device 100.

[0033] The object recognition device 16 extracts information related to the dividing line where the vehicle M is traveling (hereinafter referred to as "dividing line information") based on the image captured by the camera 10. Figure 2 This diagram illustrates an example of a method by which the object recognition device 16 extracts information about dividing lines. First, the object recognition device 16 inputs a learned model, such as a DNN (deep neural network), which takes an image captured by the camera 10 representing the situation ahead of the vehicle M as input and outputs dividing lines from the image as point groups. This process extracts point groups representing the dividing lines. The extracted point groups are defined in the camera coordinate system.

[0034] Next, the object recognition device 16 transforms the extracted point group in the camera coordinate system into a point group in the bird's-eye view coordinate system using an arbitrary method. The point group obtained through this transformation is irregularly arranged. Therefore, the object recognition device 16 transforms the irregularly arranged point group in the bird's-eye view coordinate system into a point group P with equal intervals (e.g., 1m intervals) by, for example, using function fitting such as a quadratic curve. Thus, the object recognition device 16 obtains the point group P with equal intervals representing the dividing line in the bird's-eye view coordinate system as dividing line information.

[0035] Figure 3 This is a line diagram used to illustrate the characteristics of the point group P, which serves as the dividing line information acquired by the object recognition device 16. Figure 3 In the line graph, the horizontal axis represents the distance from the vehicle M to each point that constitutes the point group P, and the vertical axis represents the curvature of the point group P. Figure 3 The dashed line represents the curvature of point group P in the bird's-eye view coordinate system. Figure 3 The solid line represents the actual curvature of the road. According to... Figure 3 It can be seen that the curvature of the point group P in the bird's-eye view coordinate system tends to be as follows: when the distance from the vehicle M is short, the deviation from the curvature of the actual road is small; on the other hand, when the distance from the vehicle M is long, the deviation from the curvature of the actual road is large.

[0036] Therefore, the following scenario is envisioned: In general, during automated driving or assisted driving with acceleration and deceleration, when the speed plan for vehicle M is generated based on a point group P transformed from the camera coordinate system to the bird's-eye view coordinate system, the curvature of the road is overestimated compared to reality, causing vehicle M to decelerate excessively. As a result, the occupants of vehicle M may experience discomfort or unease due to excessive deceleration. As described later, the automated driving control device 100 of this embodiment addresses this problem. It should be noted that the image recognition function of the object recognition device 16 can also be incorporated into the automated driving control device 100.

[0037] The communication device 20 uses, for example, cellular networks, Wi-Fi networks, Bluetooth (registered trademark), DSRC (Dedicated Short Range Communication), etc., to communicate with other vehicles in the vicinity of the vehicle M, or communicates with various server devices via wireless base stations.

[0038] The vehicle sensor 40 includes a vehicle speed sensor for detecting the speed of the vehicle M, an acceleration sensor for detecting acceleration, a yaw rate sensor for detecting angular velocity about the vertical axis, and an orientation sensor for detecting the orientation of the vehicle M.

[0039] The navigation device 50 includes, for example, a GNSS (Global Navigation Satellite System) receiver 51, a navigation HMI 52, and a route determination unit 53. The navigation device 50 stores first map information 54 in a storage device such as an HDD (Hard Disk Drive) or flash memory. The GNSS receiver 51 determines the position of the vehicle M based on signals received from GNSS satellites. The position of the vehicle M can also be determined or supplemented by an INS (Inertial Navigation System) utilizing the output of the vehicle sensors 40. The navigation HMI 52 includes a display device, a speaker, a touch panel, buttons, etc. The navigation HMI 52 can also be partially or entirely shared with the aforementioned HMI 30. The route determination unit 53, for example, refers to the first map information 54 to determine the route (hereinafter referred to as the map path) from the position of the vehicle M determined by the GNSS receiver 51 (or any input position) to the destination input by the occupant using the navigation HMI 52. The first map information 54 is, for example, information representing the shape of a road by indicating road segments and nodes connecting the road segments. The first map information 54 may also include road curvature, POI (Point of Interest) information, etc. The path on the map is output to the MPU 60. The navigation device 50 can also provide route guidance using the navigation HMI 52 based on the path on the map. The navigation device 50 can also be implemented, for example, through the functions of a terminal device such as a smartphone or tablet held by the occupant. The navigation device 50 can also send its current location and destination to the navigation server via the communication device 20, and obtain the path equivalent to the path on the map from the navigation server.

[0040] MPU 60 includes, for example, a lane recommendation unit 61, and stores second map information 62 in a storage device such as an HDD or flash memory. The lane recommendation unit 61 divides the path on the map provided by the navigation device 50 into multiple blocks (e.g., every 100m along the vehicle's direction of travel), and determines a recommended lane for each block based on the second map information 62. The lane recommendation unit 61 determines which lane to drive in from the left. When the path on the map has branching points, the lane recommendation unit 61 determines the recommended lane in a manner that allows the vehicle M to travel on a reasonable path to the branch destination.

[0041] The second map information 62 is higher precision map information than the first map information 54. The second map information 62 may include, for example, information about the center of a lane or the boundaries of a lane. Additionally, the second map information 62 may include road information, traffic restriction information, residential information (address, postal code), facility information, telephone number information, etc. The second map information 62 can be updated in real time by communicating with other devices through the communication device 20.

[0042] The driving control unit 80 includes, for example, an accelerator pedal, a brake pedal, a gear shift lever, a steering wheel, a special-shaped steering gear, a joystick, and other control components. Sensors are installed on the driving control unit 80 to detect the amount or presence of operation, and the detection results are output to some or all of the automatic driving control unit 100, the driving force output device 200, the braking device 210, and the steering device 220.

[0043] Before describing the automatic driving control device 100, the driving force output device 200, the braking device 210, and the steering device 220 will be described. The driving force output device 200 outputs the driving force (torque) for the vehicle M to drive to the drive wheels. The driving force output device 200 includes, for example, a combination of an internal combustion engine, an electric motor, and a transmission, as well as a power ECU (Electronic Control Unit) that controls them. The power ECU controls the above-mentioned structure according to information input from the automatic driving control device 100 or from the driving operation device 80.

[0044] The braking device 210 includes, for example, a brake caliper, a hydraulic cylinder that transmits hydraulic pressure to the brake caliper, an electric motor that generates hydraulic pressure in the hydraulic cylinder, and a braking ECU. The braking ECU controls the electric motor according to information input from the automatic driving control device 100 or from the driving operation device 80, so that braking torque corresponding to the braking operation is output to each wheel.

[0045] The steering device 220 includes, for example, a steering ECU and an electric motor. The electric motor, for example, applies force to a rack and pinion mechanism to change the direction of the steering wheels. The steering ECU drives the electric motor to change the direction of the steering wheels according to information input from the automatic driving control device 100 or from the driving operation device 80.

[0046] The autonomous driving control device 100 includes, for example, a first control unit 120 and a second control unit 160. The first control unit 120 and the second control unit 160 are implemented by executing programs (software) using hardware processors such as CPUs (Central Processing Units). Furthermore, some or all of these components can be implemented using hardware (including circuitry) such as LSIs (Large Scale Integration), ASICs (Application Specific Integrated Circuits), FPGAs (Field-Programmable Gate Arrays), and GPUs (Graphics Processing Units), or through a combination of software and hardware. The program can be pre-stored in a storage device such as an HDD or flash memory (a storage device with a non-transitory storage medium) of the autonomous driving control device 100, or stored in a removable storage medium such as a DVD or CD-ROM, and installed in the HDD or flash memory of the autonomous driving control device 100 by mounting the storage medium (a non-transitory storage medium) to a drive unit. The autonomous driving control device 100 is an example of a "mobile control device".

[0047] [Structure of the automatic driving control device 100]

[0048] Figure 4 This is a functional structure diagram of the first control unit 120 and the second control unit 160 included in the automatic driving control device 100. The first control unit 120 includes, for example, an identification unit 130 and an action plan generation unit 140. The action plan generation unit 140 includes, for example, a target trajectory generation unit 142, a curvature estimation unit 144, a curvature correction unit 146, and a speed plan generation unit 148.

[0049] The recognition unit 130 identifies the position, speed, acceleration, and other states of objects surrounding the vehicle M based on information input from the camera 10 and radar device 12 via the object recognition device 16. In particular, the recognition unit 130 obtains a group of points P representing road markings from the object recognition device 16 and identifies the area enclosed by the obtained group of points P as the lane (driving lane) in which the vehicle M is traveling.

[0050] The target track generation unit 142 generates a target track TT representing the future path of the vehicle M based on the point group P obtained from the object recognition device 16. Figure 5This diagram illustrates an example of the method by which the target track generation unit 142 generates the target track TT. First, the target track generation unit 142 calculates a vector V1. This vector V1 takes the point P1, representing the road dividing line on one side, closest to the vehicle M, as its starting point, and the point P2, representing the road dividing line on the other side, closest to the vehicle M, as its ending point. Figure 5 In the example, the target track generation unit 142 calculates a vector V1 that takes the point P1 closest to the vehicle M in the point group P representing the road dividing line on the left as the starting point and the point P2 closest to the vehicle M in the point group P representing the road dividing line on the other side as the ending point, but it can also be the opposite vector.

[0051] Next, the target track generation unit 142 obtains the second point P3 closest to the vehicle M from either the point group P representing the road dividing line on the left or the point group P representing the road dividing line on the right. Figure 5 In the process, the target track generation unit 142 obtains the second point P3 in the point group P representing the road dividing line on the left that is closest to the vehicle M. Next, the target track generation unit 142 calculates the unit vector V2' of vector V2 with point P1 as the starting point and point P3 as the ending point, and rotates the calculated unit vector V2' by -90 degrees to obtain the unit vector V2'". The target track generation unit 142 calculates the orthographic projection vector V3 of vector V1 relative to the unit vector V2', and estimates the magnitude of the orthographic projection vector V3 as the width w of the road on which the vehicle M travels. In other words, the target track generation unit 142 can be said to have calculated the orthographic projection vector of vector V1 relative to the unit vector in the normal direction of the road dividing line passing through point P1.

[0052] Next, the target track generation unit 142 determines whether the recognition accuracy of any point group P in the point group P representing the road dividing line, specifically the point group P representing the left road dividing line and the point group P representing the right road dividing line, is high. More specifically, the target track generation unit 142 determines the recognition accuracy of any point group P in the point group P representing the left road dividing line and the point group P representing the right road dividing line based on factors such as whether point group P was successfully tracked, the number of times point group P was recognized, and the length of the line connecting point group P. Figure 5 In the case shown on the left, it is detected that the line connecting the point group P representing the road dividing line on the right is longer than the line connecting the point group P representing the road dividing line on the left. Therefore, the target track generation unit 142 determines that the recognition accuracy of the point group P representing the road dividing line on the right is higher.

[0053] Next, the target orbit generation unit 142, as... Figure 5As shown on the right, using the road dividing line determined to have higher recognition accuracy as a reference, the target track TT is generated by offsetting half the estimated road width w by a length w / 2 along the normal direction of the road dividing line. More specifically, the target track generation unit 142 calculates points TP obtained from each point group P determined to have higher recognition accuracy by offsetting half the estimated road width w by a length w / 2 along the normal direction of the road dividing line, and connects the points TP to each other, thereby generating the target track TT.

[0054] It should be noted that, in Figure 5 The example illustrates the case where both point group P representing the left road dividing line and point group P representing the right road dividing line are identified. However, if the identification of either point group P representing the left road dividing line or point group P representing the right road dividing line fails, the target track TT is generated using the point group P obtained immediately before the identification failure, along with the estimated road width w, and based on the point group P representing the side that did not fail to identify, using the method described above. Therefore, even if the identification of either point group P representing the left road dividing line or point group P representing the right road dividing line fails, the target track TT can still be generated.

[0055] The curvature estimation unit 144 estimates the curvature of the target track TT generated by the target track generation unit 142. More specifically, the curvature estimation unit 144 estimates the curvature by calculating the curvature of each point TP of the target track TT according to the following equation (1), when the forward and backward direction of the vehicle M is defined as the x-axis, the left and right direction as the y-axis, and the distance from the vehicle M is defined as s. The curvature estimation unit 144 specifically calculates equation (1) using numerical analysis methods such as the central difference method. In equation (1), κ(s) represents the curvature of the point TP at a distance s from the vehicle M, and R(s) represents the radius of curvature of the point TP at a distance s from the vehicle M. As described above, the point group P representing the bird's-eye view coordinate system of the road dividing line is set to be equally spaced, so the points TP of the target track TT obtained by offsetting the point group P are also set to be equally spaced, and the application of numerical analysis methods such as the central difference method becomes effective.

[0056]

[0057] Figure 6 This is a line graph showing an example of the estimated curvature EC of the target orbit TT calculated by the curvature estimation unit 144. Figure 6In the diagram, the solid line represented by EC shows the estimated curvature of the target track TT, estimated by the curvature estimation unit 144, while the dashed line represented by TC shows the actual curvature of the road on which the vehicle M travels. Thus, the estimated curvature EC of the target track TT, set based on the point group P transformed from the camera coordinate system to the bird's-eye view coordinate system, tends to have a larger error the farther away from the vehicle M. As a result, if the vehicle M decelerates according to the speed plan obtained based on the estimated curvature EC, the occupants of the vehicle M may experience discomfort or a sense of unease due to the excessive deceleration.

[0058] Given the above situation, the curvature correction unit 146 corrects the estimated curvature EC by applying a correction filter for curvature correction to the estimated curvature EC estimated by the curvature estimation unit 144. More specifically, the curvature correction unit 146 applies a correction filter such that the upper limit of the estimated curvature EC is set based on the tendency that the greater the distance between the vehicle M and the target track TT, the smaller the upper limit of the curvature at point TP.

[0059] Figure 7 This is a line graph showing an example of the corrected curvature CC of the target trajectory TT after correction by the curvature correction unit 146. Figure 7 In the diagram, the double-dotted line represented by CF indicates the correction filter, and the solid line represented by CC indicates the corrected curvature CC of the target trajectory TT after correction by the curvature correction unit 146. For example... Figure 7 As shown, when the distance s from the vehicle M is within the specified value d1, the value of the estimated curvature EC is lower than the set value of the correction filter CF, and the value of the correction curvature CC is consistent with the value of the estimated curvature EC.

[0060] On the other hand, when the distance s from the vehicle M is greater than the predetermined value d1, the value of the estimated curvature EC is higher than the set value of the correction filter CF. Therefore, the curvature correction unit 146 applies the correction filter CF to limit the value of the estimated curvature EC to the upper limit value C1, thereby obtaining the corrected curvature CC. In this way, the greater the distance between the vehicle M and the point TP of the target track TT, the smaller the upper limit value of the estimated curvature EC is set, thereby enabling correction only for the estimated curvature EC, which is assumed to have a large error.

[0061] The speed plan generation unit 148 generates a speed plan representing the future target speed of the vehicle M based on the corrected curvature CC, which has been corrected by the curvature correction unit 146. More specifically, the speed plan generation unit 148 generates the speed plan by using the corrected curvature CC as a condition, ensuring that the lateral acceleration of the vehicle M is a predetermined value G that does not cause discomfort to the occupants. The speed plan generation unit 148 also generates a speed plan for the lateral acceleration V. 2 / R=V 2The relationship κ=G is transformed to generate a speed plan so that the vehicle M travels at the speed shown in the following formula (2). It should be noted that, in this embodiment, for the sake of simplicity, the lateral acceleration is calculated by establishing a relationship with the lateral acceleration of the vehicle M as a predetermined value G. However, the predetermined value G in this case is not limited to a specific value, and can be set to any value within the range that does not cause discomfort or incongruity to the occupants.

[0062]

[0063] Figure 8 This is a diagram showing an example of a speed plan generated by the speed plan generation unit 148. Figure 8 The speed plan shown is Figure 7 The corrected curvature CC shown is generated by the velocity planning generation unit 148. For example... Figure 8 As shown, when the distance s from vehicle M is below a specified value d1, the target speed of vehicle M decreases as the distance s increases. This is because, as the distance s from vehicle M increases... Figure 7 The corrected curvature CC also increases (i.e., imagine there is a curve in front of the vehicle M).

[0064] However, when the distance s from the vehicle M is greater than the specified value d1, Figure 7 The corrected curvature CC shown is taken as a constant value, therefore the target speed calculated based on the corrected curvature CC is also taken as a constant value. Through this processing, the following situation can be suppressed: the curvature of the point group P after transformation to the bird's-eye view coordinate system is evaluated as too large as the distance from the vehicle M increases, thus causing the vehicle M to decelerate excessively.

[0065] Figure 9 This is a line diagram illustrating an example of the corrected curvature CC of the target track TT after correction by the curvature correction unit 146 when the vehicle M is traveling on a curve. (Example:) Figure 9 As shown, the estimated curvature EC of the target track TT exceeds the aforementioned upper limit C1 when the distance s from the vehicle M is below the specified value d1. However, it is assumed that the estimated accuracy of the curvature is higher at positions close to the vehicle M. Therefore, the curvature correction unit 146 applies a higher upper limit C2 to the estimated curvature EC. That is, by applying a smaller upper limit as a correction filter when the distance s from the vehicle M is large, and applying a larger upper limit as a correction filter when the distance s from the vehicle M is small, it is possible to correct the estimated curvature EC, which is assumed to have a large error, while simultaneously utilizing the estimated curvature EC, which is assumed to have a small error, in the generation of the speed plan.

[0066] return Figure 4The second control unit 160 controls the driving force output device 200, the braking device 210 and the steering device 220 so that the vehicle M passes through the target track TT generated by the action plan generation unit 140 according to the speed plan generated by the speed plan generation unit 148.

[0067] The second control unit 160 includes, for example, an acquisition unit 162, a speed control unit 164, and a steering control unit 166. The acquisition unit 162 acquires information about the target track (track point) generated by the action plan generation unit 140 and stores this information in a memory (not shown). The speed control unit 164, when the current speed of the vehicle M is greater than the target speed generated by the speed plan generation unit 148, calculates the distance required to decelerate from the current speed to the target speed, and decelerates the vehicle M such that it reaches the target speed within the calculated distance range. The steering control unit 166 controls the steering device 220 based on the curvature of the target track stored in the memory.

[0068] [Processing flow]

[0069] Next, refer to Figure 10 This will explain the processing flow performed by the automatic driving control device 100. Figure 10 This diagram illustrates an example of the processing flow performed by the automatic driving control unit 100. First, the recognition unit 130 obtains a point group P representing the dividing lines in the bird's-eye view coordinate system from the object recognition device 16 (step S100). Next, the target track generation unit 142 generates the target track TT for the vehicle M based on the obtained point group P (step S101).

[0070] Next, the curvature estimation unit 144 estimates the curvature of the generated target track TT (step S102). Next, the curvature correction unit 146 corrects the estimated curvature by applying a correction filter (step S103). Next, the speed plan generation unit 148 generates a speed plan representing the future target speed of the vehicle M based on the corrected curvature (step S104). Next, the second control unit 160 causes the vehicle M to travel according to the target track TT generated by the target track generation unit 142 and the speed plan generated by the speed plan generation unit 148 (step S105). Thus, the processing of this flowchart ends.

[0071] It should be noted that the above embodiments describe an example where the automatic driving control device 100 drives the vehicle M automatically according to the speed plan generated by the speed plan generation unit 148. However, the present invention is not limited to this structure and can also be applied to assisted driving for manual driving by a driver. For example, when the driver applies the braking device 210 while the vehicle M is driving manually on a curve, the braking device 210 can be activated to assist in deceleration so that the current speed of the vehicle M reaches the target speed shown in the speed plan generated by the speed plan generation unit 148. Alternatively, for example, when the driver drives the vehicle M manually on a curve, if the deviation between the current speed and the target speed shown in the speed plan exceeds a threshold, the braking device 210 can be activated even if the driver does not apply it to bring the current speed closer to the target speed.

[0072] According to this embodiment as described above, a target track for the vehicle M is generated based on the dividing line information represented in space after the image captured by the camera is transformed into a bird's-eye view coordinate system. The curvature of the generated target track is estimated and corrected, and a speed plan for the vehicle M is generated based on the corrected curvature. The vehicle M is then driven according to the generated speed plan. Thus, information after the image captured by the camera is transformed into a bird's-eye view coordinate system can be appropriately used for the movement of a moving body.

[0073] The implementation methods described above can be performed as follows.

[0074] A mobile body control device, configured to include:

[0075] Storage device, which stores a program; and

[0076] Hardware processor,

[0077] The hardware processor executes the program stored in the storage device to perform the following processing:

[0078] Based on the dividing line information represented in the space after transforming the image of the surrounding conditions of the mobile body taken by the camera mounted on the mobile body into the bird's-eye view coordinate system, a target track representing the future path of the mobile body is generated.

[0079] Calculate the curvature of the target orbit;

[0080] The curvature is corrected by applying a correction filter to the estimated curvature.

[0081] A velocity plan representing the future target velocity of the moving body is generated based on the corrected curvature; and

[0082] The moving body is made to travel according to the speed plan.

[0083] The above description illustrates specific embodiments of the present invention, but the present invention is not limited to such embodiments in any way, and various modifications and substitutions can be made without departing from the spirit of the present invention.

Claims

1. A mobile body control device, wherein, The moving body control device includes: The target track generation unit generates a target track representing the future path of the mobile body based on the dividing line information represented in the space after transforming the image representing the surrounding conditions of the mobile body captured by the camera mounted on the mobile body into a bird's-eye view coordinate system. The curvature estimation unit calculates the curvature of the target trajectory; The curvature correction unit corrects the curvature by applying a correction filter to the estimated curvature. The speed plan generation unit generates a speed plan representing the future target speed of the moving body based on the corrected curvature. as well as The driving control unit causes the moving body to travel according to the speed plan. The correction filter is a filter that increases the degree of curvature correction at the point on the target track as the distance between the moving body and the point on the target track increases.

2. The moving body control device according to claim 1, wherein, The correction filter sets an upper limit on the curvature.

3. The moving body control device according to claim 2, wherein, The correction filter sets the upper limit of the curvature with the following tendency: the greater the distance between the moving body and a point on the target track, the smaller the upper limit of the curvature at the point on the target track.

4. The moving body control device according to any one of claims 1 to 3, wherein, The speed plan generation unit uses the corrected curvature as a condition to generate the speed plan in a manner that makes the lateral acceleration of the moving body a predetermined value.

5. The moving body control device according to any one of claims 1 to 3, wherein, When the speed of the moving body is greater than the target speed, the driving control unit calculates the distance required to decelerate from the speed to the target speed, and decelerates the moving body in such a way that the moving body reaches the target speed within the calculated distance range.

6. A method for controlling a moving body, wherein, The moving body control method causes the computer to perform the following processing: A target track representing the future path of the mobile body is generated based on the dividing line information obtained by transforming images representing the surrounding conditions of the mobile body captured by a camera mounted on the mobile body into a bird's-eye view coordinate system. Calculate the curvature of the target orbit; The curvature is corrected by applying a correction filter to the estimated curvature. Based on the corrected curvature, a speed plan representing the future target speed of the moving body is generated; as well as The moving body is made to travel according to the speed plan. The correction filter is a filter that increases the degree of curvature correction at the point on the target track as the distance between the moving body and the point on the target track increases.

7. A storage medium storing a program, The program causes the computer to perform the following processing: A target track representing the future path of the mobile body is generated based on the dividing line information obtained by transforming images representing the surrounding conditions of the mobile body captured by a camera mounted on the mobile body into a bird's-eye view coordinate system. Calculate the curvature of the target orbit; The curvature is corrected by applying a correction filter to the estimated curvature. Based on the corrected curvature, a speed plan representing the future target speed of the moving body is generated; as well as The moving body is made to travel according to the speed plan. The correction filter is a filter that increases the degree of curvature correction at the point on the target track as the distance between the moving body and the point on the target track increases.

8. A mobile body control device, wherein, The moving body control device includes: The target track generation unit generates a target track representing the future path of the mobile body based on the dividing line information represented in the space after transforming the image representing the surrounding conditions of the mobile body captured by the camera mounted on the mobile body into a bird's-eye view coordinate system. The curvature estimation unit calculates the curvature of the target trajectory; The curvature correction unit corrects the curvature by applying a correction filter to the estimated curvature to correct the error in the curvature that accompanies the transformation, and by presetting an upper limit value for the curvature. The speed plan generation unit generates a speed plan representing the future target speed of the moving body based on the corrected curvature. as well as The driving control unit causes the moving body to travel according to the speed plan.

9. A method for controlling a moving body, wherein, The moving body control method causes the computer to perform the following processing: A target track representing the future path of the mobile body is generated based on the dividing line information obtained by transforming images representing the surrounding conditions of the mobile body captured by a camera mounted on the mobile body into a bird's-eye view coordinate system. Calculate the curvature of the target orbit; The curvature is corrected by applying a correction filter to the estimated curvature to correct for errors in the curvature that accompany the transformation, and the upper limit of the curvature is preset. Based on the corrected curvature, a speed plan representing the future target speed of the moving body is generated; as well as The moving body is made to travel according to the speed plan.

10. A storage medium storing a program, The program causes the computer to perform the following processing: A target track representing the future path of the mobile body is generated based on the dividing line information obtained by transforming images representing the surrounding conditions of the mobile body captured by a camera mounted on the mobile body into a bird's-eye view coordinate system. Calculate the curvature of the target orbit; The curvature is corrected by applying a correction filter to the estimated curvature to correct for errors in the curvature that accompany the transformation, and the upper limit of the curvature is preset. Based on the corrected curvature, a speed plan representing the future target speed of the moving body is generated; as well as The moving body is made to travel according to the speed plan.

Images