Control device, control method therefor, vehicle, storage medium, and program product

By generating an imaginary straight driving lane and setting a risk search area, the problem of reduced risk calculation accuracy for vehicles on curved roads is solved, and risk calculation and reporting on curved roads are simplified and accelerated.

CN120663942APending Publication Date: 2025-09-19HONDA MOTOR CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202510149388.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2024-03-18
Filing Date
2025-02-11
Publication Date
2025-09-19

AI Technical Summary

Technical Problem

When a vehicle travels on a road with curves, the accuracy of risk calculation in the prior art is easily reduced, resulting in increased complexity in risk determination and reporting.

Method used

By generating information on a virtual driving lane that is a straight driving lane, a search area for calculating risk is set using object recognition and driving lane recognition means, and the risk in the area is calculated.

Benefits of technology

Even when traveling on a road shape including curves, it is possible to suppress a decrease in the accuracy of risk calculation, simplifying and accelerating the risk calculation and reporting process to the driver.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120663942A_ABST
    Figure CN120663942A_ABST
Patent Text Reader

Abstract

The invention provides a control device, a control method thereof, a vehicle, a storage medium, and a program product. The control device is provided with: a target recognition means for recognizing the state of a target outside the moving body; a travel lane recognition means for recognizing a travel lane on a travel path on which the moving body travels; a generation means for generating virtual travel lane information, which is a straight travel lane, on the basis of the recognized travel lane information and the recognized state of the target; a setting means for setting, on the virtual travel lane, a search region for calculating a risk, which is an index value indicating the degree to which the moving body should be prevented from entering; and a calculation means for calculating the risk in the set search area. At this time, when the travel lane has a road shape including a curved shape, the generation means generates information on a virtual travel lane by changing the positions of the travel lane so that the curved portion of the travel lane becomes a straight travel lane along the direction of travel.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to a control device, a control method thereof, a vehicle, a storage medium, and a program product. Background Art

[0002] Conventionally, as a technology for generating an appropriate driving trajectory corresponding to the driving environment when a mobile object such as a vehicle is traveling, the following technology is known: when the driving road is a curved road, a target object potential area is set so that the target object potential area set on a straight road is different based on the curvature radius of the curved road (Patent Document 1).

[0003] Prior art literature Patent Literature Patent Document 1: Japanese Patent Application Publication No. 2019-46161 Summary of the Invention Problems to be solved by the invention The technology disclosed in Patent Document 1 utilizes high-precision curvatures of curved roads, pre-included in map information. However, there are cases where map information does not include the curvatures of each curve on the road, or where a vehicle travels while recognizing its surroundings without sufficient map information. The accuracy of calculating the curvature of the road can decrease due to vehicle behavior. Therefore, estimating the curvature of the road and using this estimated curvature to determine the risk associated with a curve (an indicator indicating the degree to which a vehicle should avoid entering the curve) and reporting the corresponding risk can complicate the process and reduce the accuracy of risk determination and reporting.

[0004] The present invention has been made in view of the above-mentioned problems, and an object of the present invention is to realize a technology capable of suppressing a decrease in accuracy in risk calculation even when traveling on a movement path having a curved road shape.

[0005] Means used to solve problems According to the present invention, a control device is provided, characterized in that: The control device has: an object recognition mechanism for recognizing the state of an object outside the mobile body; a driving lane recognition mechanism for recognizing a driving lane on a moving path of the moving object; a generating unit for generating information of a virtual driving lane that is a straight driving lane based on the recognized driving lane information and the recognized state of the target object; a setting unit that sets a search area on the virtual driving lane for calculating a risk, the risk being an index value indicating a degree to which the moving object should avoid entering the lane; and a calculation unit that calculates the risk in the set search area, When the driving lane has a road shape including a curve, the generating unit generates the information of the virtual driving lane by transforming each position of the driving lane so that the curved portion of the driving lane becomes a straight driving lane along the traveling direction.

[0006] Furthermore, according to the present invention, there is provided a vehicle characterized in that: The vehicle has: An object recognition mechanism that recognizes the state of an object outside the vehicle; a driving lane recognition mechanism for recognizing a driving lane on a moving path of the vehicle; a generating unit for generating information of a virtual driving lane that is a straight driving lane based on the recognized driving lane information and the recognized state of the target object; a setting unit that sets a search area on the virtual driving lane for calculating a risk, the risk being an index value indicating a degree to which the vehicle should avoid entering the lane; a calculation unit that calculates the risk in the set search area; and a decision unit that determines, based on the risk calculated in the set search area, an action of the vehicle including automatic driving of the vehicle that does not require a driving operation by a driver or automatic driving for assisting a driving operation performed by the driver, When the driving lane has a road shape including a curve, the generating unit generates the information of the virtual driving lane by transforming each position of the driving lane so that the curved portion of the driving lane becomes a straight driving lane along the traveling direction.

[0007] Furthermore, according to the present invention, a control method for a control device is provided, characterized in that: The control method of the control device comprises: a target object recognition step, in which the state of a target object outside the mobile body is recognized; a driving lane identification step, in which a driving lane on a moving path of the moving object is identified; a generating step of generating information of a virtual driving lane as a straight driving lane based on the recognized driving lane information and the recognized state of the target object; a setting step of setting a search area on the virtual driving lane for calculating a risk, the risk being an index value indicating a degree to which the moving object should avoid entering the lane; and a calculation step, in which the risk in the set search area is calculated, In the generating step, when the driving lane has a road shape including a curve, each position of the driving lane is transformed so that the curved portion of the driving lane becomes a straight driving lane along the traveling direction, thereby generating the information of the virtual driving lane.

[0008] Furthermore, according to the present invention, there is provided a storage medium storing a program for causing a computer to function as each mechanism of a control device, wherein: The control device has: an object recognition mechanism for recognizing the state of an object outside the mobile body; a driving lane recognition mechanism for recognizing a driving lane on a moving path of the moving object; a generating unit for generating information of a virtual driving lane that is a straight driving lane based on the recognized driving lane information and the recognized state of the target object; a setting unit that sets a search area on the virtual driving lane for calculating a risk, the risk being an index value indicating a degree to which the moving object should avoid entering the lane; and a calculation unit that calculates the risk in the set search area, When the driving lane has a road shape including a curve, the generating unit generates the information of the virtual driving lane by transforming each position of the driving lane so that the curved portion of the driving lane becomes a straight driving lane along the traveling direction.

[0009] Furthermore, according to the present invention, there is provided a program product for causing a computer to function as each mechanism of a control device, characterized in that: The control device has: an object recognition mechanism for recognizing the state of an object outside the mobile body; a driving lane recognition mechanism for recognizing a driving lane on a moving path of the moving object; a generating unit for generating information of a virtual driving lane that is a straight driving lane based on the recognized driving lane information and the recognized state of the target object; a setting unit that sets a search area on the virtual driving lane for calculating a risk, the risk being an index value indicating a degree to which the moving object should avoid entering the lane; and a calculation unit that calculates the risk in the set search area, When the driving lane has a road shape including a curve, the generating unit generates the information of the virtual driving lane by transforming each position of the driving lane so that the curved portion of the driving lane becomes a straight driving lane along the traveling direction.

[0010] Effects of the Invention According to the present invention, even when traveling on a movement route having a road shape including a curve, it is possible to suppress a decrease in accuracy in the calculation of risk. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a diagram showing a configuration example of a vehicle as an example of a mobile object according to the embodiment.

[0012] Figure 2 This is a block diagram showing an example of the functional configuration of a control device according to the embodiment.

[0013] Figure 3 This is a diagram explaining the outline of risk calculation according to the embodiment.

[0014] Figure 4 This is a flowchart showing a series of operations of the driving assistance process according to the embodiment.

[0015] Figure 5 This is a diagram for explaining an example of a process of determining a road shape including a curve according to an embodiment.

[0016] Figure 6 This is a diagram for explaining an example of a process of determining a relationship with a travel road boundary according to the embodiment.

[0017] Figure 7 This is a diagram for explaining an example of a process for estimating the curvature of a curve according to the embodiment.

[0018] Figure 8 This is a diagram for explaining an example of a process of changing the position of an object according to the embodiment.

[0019] Figure 9 This is a diagram illustrating an example of risk to a target object according to the embodiment.

[0020] Description of Reference Numerals 1: Vehicle; 2: Control device; 21-29: ECU. DETAILED DESCRIPTION

[0021] The following embodiments are described in detail with reference to the accompanying drawings. The following embodiments do not limit the inventions described herein. Furthermore, not all combinations of features described in the embodiments are essential to the invention. Any combination of two or more of the multiple features described in the embodiments may be used. Identical or similar components are denoted by the same reference numerals, and duplicate descriptions are omitted.

[0022] <Example of Vehicle Configuration> Figure 1 FIG. 1 is a block diagram of a vehicle 1 as an example of a mobile body according to the present invention. Figure 1 , a vehicle 1 is schematically shown in top and side views. As an example, vehicle 1 is a four-wheeled passenger car, but may also be a two-wheeled vehicle or another type of vehicle. Furthermore, the mobile object of the present invention is not limited to vehicles but may also include various mobile objects such as autonomous robots.

[0023] Vehicle 1 includes a vehicle control device (hereinafter referred to as control device 2) that controls vehicle 1. Control device 2 includes multiple ECUs (Electronic Control Units) 20 to ECU 29 that are communicatively connected via an in-vehicle network. Each ECU includes a processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), a memory such as a semiconductor memory, and an interface with external devices. The memory stores programs executed by the processor and data used by the processor during processing. Each ECU may also include multiple processors, memories, and interfaces. For example, ECU 20 includes a processor 20a and a memory 20b. The processing performed by ECU 20 is performed by processor 20a executing instructions contained in the program stored in memory 20b. Alternatively, ECU 20 may include a dedicated integrated circuit such as an ASIC (Application Specific Integrated Circuit) for executing the processing performed by ECU 20. The same applies to other ECUs.

[0024] The following describes the functions of each of ECUs 20 through 29. The number of ECUs and their assigned functions can be designed appropriately, allowing for further refinement or integration beyond the scope of this embodiment. For example, a single ECU (e.g., ECU 22) can also perform the functions of other ECUs.

[0025] The ECU 20 performs controls related to manual and automated driving of the vehicle 1. Automated driving automatically controls at least one of the steering, acceleration, and deceleration of the vehicle 1. Automated driving performed by the ECU 20 can include both automated driving that eliminates the need for driver control (also referred to as automated driving) and automated driving that assists the driver's control (also referred to as driving assistance). For example, the ECU 20's driving control can include automatically stopping or steering the vehicle to avoid a collision, replacing the driver's control.

[0026] The ECU 21 controls the electric power steering system 3. The electric power steering system 3 includes a mechanism that steers the front wheels in response to the driver's steering operation (steering operation) of the steering wheel 31. The electric power steering system 3 also includes a motor that generates driving force to assist the steering operation or automatically steer the front wheels, and a sensor that detects the steering angle. When the vehicle 1 is in automatic driving mode, the ECU 21 automatically controls the electric power steering system 3 in response to instructions from the ECU 20 to control the direction of travel of the vehicle 1.

[0027] ECU 22 and ECU 23 control the detection unit that detects the vehicle's surrounding conditions and processes the detection results. Vehicle 1, for example, includes a standard camera 40 and four fisheye cameras 41 through 44 as detection units for detecting the vehicle's surrounding conditions. Standard camera 40, fisheye cameras 42, and fisheye cameras 44 are connected to ECU 22. Fisheye cameras 41 and 43 are connected to ECU 23. By analyzing images captured by standard camera 40 and fisheye cameras 41 through 44, ECU 22 and ECU 23 can identify the type, position, speed, and other state of an object, as well as lane areas on the travel path, road boundaries (white lines), and lane demarcation lines (dashed lines, etc.). The type, number, and mounting locations of the cameras in vehicle 1 are not limited to those in this embodiment and may also be configured differently. Furthermore, as a detection unit for detecting a target object around the vehicle 1 or measuring the distance to the target object, an optical radar (Light Detection and Ranging) or a millimeter-wave radar may be included.

[0028] The standard camera 40 is installed at the front center of the vehicle 1 to capture the surrounding conditions in front of the vehicle 1. The fisheye camera 41 is installed at the front center of the vehicle 1 to capture the surrounding conditions in front of the vehicle 1. Figure 1In the figure, the standard camera 40 and the fisheye camera 41 are shown arranged horizontally. However, the arrangement of the standard camera 40 and the fisheye camera 41 is not limited to this; for example, they may be arranged vertically. Furthermore, at least one of the standard camera 40 and the fisheye camera 41 may be mounted on the front portion of the roof of the vehicle 1 (for example, on the interior side of the front window). The fisheye camera 42 is mounted in the center of the right side of the vehicle 1 to capture images of the surroundings to the right of the vehicle 1. The fisheye camera 43 is mounted in the center of the rear of the vehicle 1 to capture images of the surroundings to the rear of the vehicle 1. The fisheye camera 44 is mounted in the center of the left side of the vehicle 1 to capture images of the surroundings to the left of the vehicle 1.

[0029] ECU 22 controls the standard camera 40, fisheye cameras 42, and fisheye cameras 44, and processes the detection results. ECU 23 controls the fisheye cameras 41 and 43, and processes the detection results. By separating the detection unit responsible for detecting the vehicle's surroundings into two systems, the reliability of the detection results can be improved. Furthermore, ECU 22 can detect the driver's head orientation and line of sight using images captured by a fisheye camera (not shown) installed inside the vehicle cabin.

[0030] ECU 24 controls the gyro sensor 5, GPS sensor 24b, and communication device 24c, and processes information on detection and communication results. Gyro sensor 5 detects the rotational motion of vehicle 1. The vehicle 1's route can be determined based on the detection results of gyro sensor 5, wheel speed, and other factors. GPS sensor 24b detects the vehicle 1's current location. Communication device 24c wirelessly communicates with a server that provides map information and traffic information to obtain this information. ECU 24 can access a map information database 24a stored in memory, and perform tasks such as searching for a route from the current location to the destination. ECU 24, map database 24a, and GPS sensor 24b constitute a so-called navigation system.

[0031] The ECU 25 includes a communication device 25a for inter-vehicle communication. The communication device 25a performs wireless communication with other surrounding vehicles, for example, to exchange information between the vehicles.

[0032] The ECU 26 controls the power unit 6. The power unit 6 is a mechanism that outputs driving force to rotate the drive wheels of the vehicle 1 and includes, for example, an engine and a transmission. For example, the ECU 26 controls the engine output in response to the driver's driving operation (accelerator operation or accelerator operation) detected by the operation detection sensor 7a provided on the accelerator pedal 7A, or switches the transmission gears based on information such as the vehicle speed detected by the vehicle speed sensor 7c.

[0033] The ECU 27 controls the lighting devices (headlights, taillights, etc.) including the direction indicator 8 (turn indicator). Figure 1 In the example of FIG, the direction indicators 8 are provided at the front, door mirrors, and rear of the vehicle 1.

[0034] ECU28 controls the input-output device 9. The input-output device 9 outputs information to passengers (e.g., the driver) and receives input of information from the driver. The sound output device 91 reports information to the driver, for example, by sound including a predetermined sound or speech. For example, ECU22 performs the driving assistance processing described later, determines the execution of the report, and sends it to ECU28, thereby outputting the content of the report. The driving assistance processing will be described later. The display device 92 reports information to the driver by displaying an image. The display device 92 is, for example, arranged in front of the driver's seat to constitute an instrument panel, etc. In addition, here, sound and display are shown as examples, but information can also be reported by vibration or light. In addition, it is also possible to combine multiple of sound, display, vibration or light to report information. The input device 93 is a switch group arranged in a position that can be operated by the driver to indicate the vehicle 1, but it can also include a sound input device.

[0035] ECU29 controls the braking device 10 and the parking brake (not shown). The braking device 10 is, for example, a disc brake device, which is provided on each wheel of the vehicle 1 and decelerates or stops the vehicle 1 by applying resistance to the rotation of the wheel. ECU29 controls the operation of the braking device 10 in accordance with the driver's driving operation (brake operation) detected by the operation detection sensor 7b provided on the brake pedal 7B. When the driving state of the vehicle 1 is automatic driving, ECU29 automatically controls the braking device 10 in accordance with the instructions from ECU20 to control the deceleration and stopping of the vehicle 1. The braking device 10 and the parking brake can also be operated to maintain the stopped state of the vehicle 1. In addition, when the transmission of the power unit 6 is equipped with a parking lock mechanism, it can also be operated to maintain the stopped state of the vehicle 1.

[0036] <Example of Functional Configuration Implemented in ECU 22> Next, refer to Figure 2 , a functional configuration example implemented in the ECU 22 will be described. Note that part or all of the contents described below as functions implemented in the ECU 22 may also be implemented in another ECU (for example, the ECU 20). Figure 2 The functional configuration example shown is an example of a functional configuration implemented by executing a program stored in an internal memory by the ECU 22. Figure 2The functional configuration example shown focuses on the configuration related to the driving assistance process described later. Therefore, the functions implemented in the ECU 22 are not limited to Figure 2 The functions shown may also include other functions.

[0037] The object recognition unit 201 identifies the state of objects outside of vehicle 1 based on at least one of images obtained from the detection unit and sensor information such as optical radar. Examples of objects include moving objects (such as surrounding vehicles, pedestrians, and cyclists) or fallen objects around vehicle 1. The state of an object includes, for example, its type, position, speed, and trajectory. The position of an object can be its relative position relative to vehicle 1. The object recognition unit 201 can use, for example, one or more neural networks to identify the state of external objects, but other learning models may also be used.

[0038] The driving lane recognition unit 202 identifies the driving lane on the moving path of the vehicle 1 based on at least one of the images obtained from the detection unit and the sensor information such as the optical radar. The information of the identified driving lane includes, for example, information on the driving road boundary, dividing line and lane area on the moving path. The information on the driving road boundary and dividing line can also be given by the position information of a discrete point group at predetermined intervals (for example, every 1 meter). The driving lane recognition unit 202 can identify the driving lane on the moving path through, for example, one or more neural networks, but other learning models can also be used. In addition, the functions of the target object recognition unit 201 and the functions of the driving lane recognition unit 202 can also be implemented by a neural network or a learning model.

[0039] The lane recognition unit 202 also uses the lane boundary information to determine whether the lane has a predetermined road shape including a curve. The determination of whether the lane has a predetermined road shape will be described later.

[0040] Figure 3 The overview of the driving assistance process according to this embodiment is shown. Figure 3 In the illustrated example, a vehicle 301 (ie, vehicle 1 ) serving as the host vehicle is traveling in a driving lane 302 on a movement path, and a vehicle 303 is stopped in the driving lane 302 . Figure 3 The driving lane 302 shown is a driving lane having a road shape including a curved shape. Figure 3 The example shown depicts the curvature of the driving lane 302 in an exaggerated manner for the sake of explanation. However, as will be described later, the driving assistance processing of this embodiment mainly executes processing when the vehicle is traveling in a driving lane with a smooth curvature having a curvature radius of 100R or more.

[0041] When vehicle 301 is traveling in lane 302 , object recognition unit 201 recognizes the state of the object including the position, speed, and movement trajectory of vehicle 303 . Lane recognition unit 202 recognizes the road boundary, dividing lines, and lane area of ​​lane 302 .

[0042] The virtual driving lane generating unit 203 generates information on a virtual driving lane that is a straight driving lane based on the driving lane information recognized by the object recognizing unit 201 and the state of the object recognized by the driving lane recognizing unit 202 .

[0043] exist Figure 3 In the example shown, the virtual lane generation unit 203 generates virtual lane information by transforming each position of the driving lane 302 so that the curved portion of the driving lane 302 becomes a straight driving lane (i.e., the driving lane 304) along the direction of travel. As described above, the driving lane 302 curves with a gentle curvature, for example, with a radius of curvature of 100R or greater. Therefore, it is possible to perform processing to approximate the driving lane 302 information to a straight driving lane. The virtual lane generation unit 203 generates the straight lines constituting the virtual driving lane 304 by, for example, drawing straight lines in the direction of travel from the average position of a cluster of points within a predetermined range of the road boundary on the left (or right) side of the vehicle 301. The transformation of each position of the driving lane 302 may also involve shifting (reflecting) each position in a direction perpendicular to the direction of travel. However, shifting each position of the driving lane 302 in a direction perpendicular to the direction of travel may result in a distance on the virtual driving lane 304 being shorter than the actual distance on the driving lane 302. Therefore, it is possible not only to shift each position perpendicular to the direction of travel but also to offset the position of the target object on virtual lane 304 so that it moves away from the position of vehicle 301 in the direction of travel. This allows the positional relationship between vehicle 301 and the target object on lane 302 to be reflected in virtual lane 304 with greater accuracy through simple calculations. By generating a virtual lane as a straight line, the risk calculation and driver notification processes described later, which are inherent to curved roads, need not be processed to match the curvature. This simplifies and accelerates the risk calculation and driver notification processes. Furthermore, since no transformation using the estimated curvature is performed, a decrease in processing accuracy can be minimized.

[0044] The risk calculation unit 204 calculates risk, an indicator value indicating the degree to which the vehicle should avoid entering. The risk for a specific object becomes more negative (the degree to which the vehicle should avoid entering increases) as the object approaches the identified object, and decreases as the object moves away, eventually reaching zero. The risk calculation unit 204 sets a search area on a hypothetical driving lane for calculating this risk. For example, the search area includes a first observation point set in the direction of travel of vehicle 301 and one or more second observation points (two in the example described below) to the left and right of the first observation point, as viewed from vehicle 301. These observation points are grouped together, and risk is calculated for each observation point in the search area. The lowest risk among the calculated risks is then searched for, thereby obtaining the lowest-risk driving trajectory. While the illustrated example shows a single observation point set at a predetermined position in the direction of travel from vehicle 301, multiple observation points may be arranged in the direction of travel, with multiple observation points set to the left and right of each observation point. This allows the risk to be determined in a specific direction or position on the driving lane. In the following description, calculating the risk at each observation point in the search area is also referred to as simply calculating the risk in the search area.

[0045] The risk calculation unit 204 sets a risk potential for the hypothetical driving lane. The risk potential can also be set using known techniques. The risk potential can be a combination of the risk potential set for the driving lane and the risk potential resulting from the presence of the target object. Alternatively, only the risk potential resulting from the presence of the target object may be used.

[0046] Figure 9 The diagram schematically illustrates an example of the potential risk resulting from the presence of a target object (e.g., vehicle 303). The vertical axis represents the level of risk, and the horizontal axis represents the left-right position of vehicle 303. In range 902 close to vehicle 303, the potential risk represents the highest value among the risks set for vehicle 303. Furthermore, within ranges 901 and 902, the risk decreases as the distance from the center of vehicle 303 increases. The same potential risk can also be set in front of and behind vehicle 303. The potential risk set for a target object is also referred to as the target object potential. If the search area for calculating risk falls within ranges 901 to 903, the risk increases due to the presence of vehicle 303. On the other hand, if the search area does not overlap with ranges 901 to 903, the risk does not increase due to the presence of vehicle 303.

[0047] The risk potential assigned to a lane is, for example, set so that it is lowest in the center of the lane and increases as it moves away from the center (closer to the road boundary). This risk potential is also referred to as an inductive risk potential. When using this risk potential, the risk is lowest near the center of the lane within the search area. Furthermore, the risk increases near the road boundary within the search area.

[0048] Refer again Figure 3 .exist Figure 3 In the example, an observation point 310 in the search area is set at a predetermined distance from vehicle 301. When vehicle 301 is traveling in a hypothetical driving lane, observation point 310 on the left side of the search area is within the risk potential 306 of vehicle 305 (i.e., vehicle 303). In this case, the risk calculation unit 204 combines the risks of risk potential 306 to calculate the risk in the search area. This allows the risk calculated in the search area to include the impact of the target object. Furthermore, if there are multiple targets, the risk potentials of the targets are combined. If the distance between two targets from observation point 310 on the left side of the search area is close and the risk potential of each target is not zero at observation point 310, the risk potential of each target is combined. In other words, the risk calculation unit 204 calculates the risk in the search area based on this combined risk potential. This allows vehicle actions such as autonomous driving and reporting to the driver to be determined based on the risk calculated in the search area.

[0049] The driving control unit 205 determines the vehicle's behavior based on the risk calculated in the search area. For example, the driving control unit 205 determines the driving path of the vehicle 301 so that the vehicle 301 drives along the observation point where the lowest risk is calculated. Furthermore, the driving control unit 205 controls at least one of the speed and steering of the vehicle 301 so that the vehicle 301 automatically drives along the determined driving path. Of course, in addition to speed and steering, the driving control unit 205 can also perform various controls required for automatic driving along the determined driving path. Automatic driving can include automatic driving of the vehicle 301 that does not require driving operations performed by the driver, or automatic driving that assists the driving operations performed by the driver.

[0050] The notification unit 206 reports to the driver based on the risk calculated within the search area. If the risk within the search area (at any observation point) exceeds a predetermined value, the notification unit 206 issues a predetermined warning sound or a natural language audio notification (including a description of the identified object). For example, the notification unit 206's audio notification may include at least one of the following: the presence, position, direction, distance, and time until a collision with a potentially collisionable object. The notification unit 206 may also display the content of the notification on the display device 92. For example, the notification unit 206 may include at least one of the following: the presence, position, direction, distance, and time until a collision with a potentially collisionable object on the display device 92. The notification unit 206 may also issue a notification to the driver if the distance from the vehicle 301 to the object is less than a predetermined distance, or if the arrival time at the object is less than a predetermined time.

[0051] Furthermore, the aforementioned risk may correspond to the possibility of collision between the vehicle 301 and another object (vehicle 303). In this case, the driving control unit 205 or the reporting unit 206 determines the behavior of the mobile object based on the possibility of collision between the vehicle 301 and another object (vehicle 303).

[0052] Next, refer to Figure 4 The following describes a series of operations for the driving support process in the vehicle. This process is implemented, for example, by the processor 20a of the ECU 22 of the control device 2 executing a program in the memory 20b.

[0053] In S401, the object recognition unit 201 recognizes the state of an object outside the vehicle 1 based on at least one of the image obtained from the detection unit and sensor information such as an optical radar. Furthermore, the lane recognition unit 202 recognizes the lane on the path of the vehicle 1 based on at least one of the image obtained from the detection unit and sensor information such as an optical radar.

[0054] Next, through the processes of S402 to S405 , the driving lane recognition unit 202 determines whether the driving lane has a predetermined road shape including a curved shape. First, in S402 , the driving lane recognition unit 202 determines whether the driving lane has a curved shape.

[0055] Figure 5 An example of a curved driving lane is shown schematically. Figure 5The example shown shows an example where a road boundary exists in the direction of travel of vehicle 301 (because the lane includes a curve). In this example, the road boundary exists at position 502, which is a distance 501 (e.g., 20 meters) from vehicle 301. If the road boundary exists in the direction of travel, lane recognition unit 202 determines that the lane is curved. If the lane is determined to be curved, the process proceeds to S403; otherwise, the process returns to S401.

[0056] In S403 , the lane recognition unit 202 determines whether the positional relationship between the boundary of the travel road and the vehicle is in a specific state. Figure 6 The example in which the relationship with the travel road boundary is in a specific state is schematically shown. Figure 6 In the example shown, a road boundary exists at a distance of less than 501 from the vehicle. This state may indicate that the vehicle is straying from the road, such as when making a left or right turn or entering a parking lot. Therefore, in this embodiment, the driving assistance process ends when such a specific state occurs. If a road boundary exists at a distance of less than 501 from the vehicle, the lane recognition unit 202 determines that the specific state exists and ends the process. Otherwise, the process proceeds to S404.

[0057] In S404 , the lane recognition unit 202 estimates the curvature of the road boundary of the lane by fitting the road boundary of the lane to an arc. Figure 7 The diagram schematically illustrates the fitting of a road boundary to an arc. In this example, the road boundary of lane 302 is given by discrete point cluster position information 701 at predetermined intervals (e.g., every 1 meter). Lane recognition unit 202 estimates the parameters of the arc that best matches point cluster position information 701 using, for example, the least squares method. By estimating the arc parameters, the arc's curvature can be determined.

[0058] In S405, the lane recognition unit 202 determines whether the estimated curvature is below a predetermined value. If so, the process proceeds to S406; otherwise, the process ends. If the curvature of the road boundary is large, the risk calculation using the virtual lane may be inappropriate, so the lane recognition unit 202 does not continue the driving assistance process.

[0059] In S406 , the virtual driving lane generation unit 203 converts the driving lane information recognized by the object recognition unit 201 and the state of the object recognized by the driving lane recognition unit 202 into a virtual driving lane that is a straight driving lane.

[0060] Figure 8FIG. 2 shows an example of generating information of a virtual driving lane based on information of a driving lane and the position of a target object (vehicle 303). The virtual driving lane generating unit 203 refers to, for example, Figure 3 Through the above-described method, the position of the road boundary of lane 302 and the position of the target object are mapped to the road boundary of lane 304. In this embodiment, when transforming the target object's position onto the virtual lane, the position of the identified target object is offset using geometric operations such as trigonometric functions. For example, a right triangle may be formed connecting the intersection of the position of vehicle 301 and the road boundary ((0, y) in the vehicle coordinate system) and the position of vehicle 303, and the position of vehicle 305 may be offset to form a triangle similar to this right triangle. This allows for simple and high-speed calculations, and by offsetting the target object's position, the target object's position on the virtual lane can be determined with greater accuracy.

[0061] In S407, the risk calculation unit 204 sets a search area for risk calculation on the virtual driving lane as described above, and calculates the risk of the impact of the target object within the search area on the virtual driving lane. As described above, the risk calculation unit 204 calculates the risk using, for example, the risk value of the risk potential within the search area on the virtual driving lane to set the risk potential on the virtual driving lane.

[0062] In S408 , if the calculated risk is equal to or greater than a predetermined value, the risk calculation unit 204 proceeds to S409 . Otherwise, the risk calculation unit 204 ends the process without issuing a report.

[0063] In S409, the notification unit 206, for example, based on an instruction from the risk calculation unit 204, notifies the driver. As described above, the notification unit 206 notifies the driver using a predetermined warning sound or a natural language sound (including a description of the recognized object). After the notification unit 206 completes the notification, the series of driving assistance processing operations ends.

[0064] Furthermore, in the above-described series of driving assistance processing operations, a case where a notification is performed when the calculated risk is greater than a predetermined value is described as an example, but either automatic driving by the driving control unit 205 or the like may be performed. Furthermore, both the notification by the notification unit 206 and the automatic driving by the driving control unit 205 may be performed.

[0065] As described above, in the above-described embodiment, vehicle 1 generates information about a virtual lane, which is a straight lane, based on information about the recognized lane and the state of the recognized object. In this case, if the lane has a predetermined curve, vehicle 1 generates information about the virtual lane by changing the lane's position so that the curved portion of the lane becomes a straight lane along the direction of travel. Furthermore, vehicle 1 sets a search area on the virtual lane for risk calculation and calculates the risk within the set search area as an indicator indicating the degree to which a moving object should avoid entering. This eliminates the need for processing specific to curved roads in risk calculation and driver notification, simplifying and speeding up the risk calculation and driver notification processes. Furthermore, it minimizes any degradation in processing accuracy. In other words, even when traveling on a curved road, it minimizes any degradation in risk calculation accuracy.

[0066] <Summary of Implementation Methods> (Item 1) A control device (such as 22), characterized in that The control device has: An object recognition mechanism (e.g., 201 ) that recognizes the state of an object outside the mobile body (e.g., 1 ); A driving lane identification mechanism (e.g., 202 ) that identifies a driving lane on a moving path of the moving object; a generating unit (e.g., 203) for generating information of a virtual driving lane as a straight driving lane based on the information of the recognized driving lane and the recognized state of the target object; a setting unit (e.g., 204) that sets a search area on the virtual driving lane for calculating a risk, wherein the risk is an index value indicating the degree to which the moving object should avoid entering the lane; and A calculation unit (e.g., 204) calculates the risk in the set search area, When the driving lane has a road shape including a curve, the generating unit generates the information of the virtual driving lane by transforming each position of the driving lane so that the curved portion of the driving lane becomes a straight driving lane along the traveling direction.

[0067] According to this embodiment, even when traveling on a movement route having a road shape including a curve, it is possible to suppress a decrease in accuracy in the calculation of risk.

[0068] (Item 2) The control device according to item 1 is characterized in that The target object recognition mechanism recognizes the position of the target object. The generating unit generates information on the virtual driving lane by converting the recognized position of the target object onto the virtual driving lane.

[0069] According to this embodiment, even when traveling on a movement route having a road shape including a curve, it is possible to suppress a decrease in accuracy in calculating the risk to the target object.

[0070] (Item 3) The control device according to item 1 is characterized in that when the curvature of the travel road boundary of the travel lane is greater than a predetermined value, the generating unit does not generate the information of the virtual travel lane (for example, S405).

[0071] According to this embodiment, when it is not appropriate to generate a virtual driving lane that is a straight driving lane, the generation of the virtual driving lane can be suppressed.

[0072] (Item 4) The control device according to item 1 is characterized in that the control device further includes a decision unit (for example, 205 , 206 ) that decides the behavior of the mobile object based on the calculated risk.

[0073] According to this embodiment, vehicle control corresponding to the risk can be achieved.

[0074] (Item 5) The control device according to item 4 is characterized in that The risk corresponds to the possibility of collision between the mobile object in the search area and the identified target object. The decision unit decides the behavior of the mobile body based on the possibility of collision between the mobile body and the identified target object.

[0075] According to this embodiment, it is possible to suppress a decrease in accuracy in the calculation of the probability of collision with the target object.

[0076] (Item 6) The control device according to item 4 is characterized in that the behavior of the mobile body includes a report to a driver of the mobile body.

[0077] According to this embodiment, when traveling on a movement route including a curve, it is possible to suppress a decrease in the accuracy of risk-based reporting.

[0078] (Item 7) The control device according to item 4 is characterized in that the behavior of the mobile body includes automatic driving of the mobile body that does not require a driving operation by a driver, or automatic driving for assisting a driving operation by the driver.

[0079] According to this embodiment, when the vehicle is traveling on a movement path including a curve, it is possible to suppress a decrease in the accuracy of risk-based automatic driving.

[0080] (Item 8) The control device according to Item 7 is characterized in that the decision mechanism determines the driving path of the moving body based on the calculated risk when the moving body is automatically driving without requiring driving operations by the driver, and controls at least either the speed and steering of the moving body according to the driving path.

[0081] According to this embodiment, various controls related to the automatic travel of the mobile object can be performed according to the travel route based on the calculated risk.

[0082] (Item 9) The control device according to item 1 is characterized in that The control device further includes a determination unit that uses information on a road boundary of the driving lane to determine whether the driving lane has a road shape including a curve (for example, S402). When the driving lane does not have a road shape including a curve, the generating unit does not generate the information of the virtual driving lane.

[0083] According to this embodiment, risk calculation using a virtual driving lane can be applied to an appropriate curve.

[0084] (Item 10) The control device according to item 9 is characterized in that the determination unit determines whether the driving lane has a road shape including a curve based on a curvature of a driving road boundary of the driving lane (eg, S405 ).

[0085] According to this embodiment, the curvature of the curved road can be taken into consideration when determining whether the road is an appropriate curved road.

[0086] (Item 11) The control device according to item 10 is characterized in that when the curvature of the travel road boundary of the travel lane is within a predetermined range, the determination unit determines that the travel lane has a road shape including a curve (for example, S405 ).

[0087] According to this embodiment, it is possible to prevent the risk calculation using a virtual driving lane from being applied to a curved road with a large curvature.

[0088] (Item 12) The control device according to item 10 is characterized in that the determination unit estimates the curvature of the driving road boundary of the driving lane by fitting the driving road boundary of the driving lane with an arc (for example, S404 ).

[0089] According to this embodiment, the curvature of the travel road boundary of the travel lane can be dynamically acquired.

[0090] (Item 13) The control device according to item 2 is characterized in that when the generating mechanism transforms the position of the identified target object to the imaginary driving lane, the generating mechanism offsets the position of the identified target object on the imaginary driving lane in such a manner that the position of the identified target object moves away from the position of the moving body in the direction of travel of the moving body.

[0091] According to this embodiment, when traveling on a movement path including a curve, the positional relationship between the vehicle 301 and the target object in the driving lane 302 can be reflected on the virtual driving lane 304 with higher accuracy through simple calculations.

[0092] (Item 14) The control device according to item 13 is characterized in that the generating means shifts the position of the recognized object using a geometric calculation when converting the position of the recognized object to the virtual driving lane.

[0093] According to this embodiment, when the vehicle is traveling on a movement path including a curve, simpler and faster calculations can be achieved.

[0094] The present invention is not limited to the above-described embodiment, and various modifications and changes can be made within the scope of the gist of the present invention.

Claims

1. A control device, characterized in that: The control device has: an object recognition mechanism for recognizing the state of an object outside the mobile body; a driving lane recognition mechanism for recognizing a driving lane on a moving path of the moving object; a generating unit for generating information of a virtual driving lane that is a straight driving lane based on the recognized driving lane information and the recognized state of the target object; a setting unit that sets a search area on the virtual driving lane for calculating a risk, the risk being an index value indicating a degree to which the moving object should avoid entering; as well as a calculation unit that calculates the risk in the set search area, When the driving lane has a road shape including a curve, the generating unit generates the information of the virtual driving lane by transforming each position of the driving lane so that the curved portion of the driving lane becomes a straight driving lane along the traveling direction.

2. The control device according to claim 1, characterized in that The target object recognition mechanism recognizes the position of the target object. The generating unit generates information on the virtual driving lane by converting the recognized position of the target object onto the virtual driving lane.

3. The control device according to claim 1, characterized in that The generating unit does not generate the information of the virtual driving lane when the curvature of the driving road boundary of the driving lane is larger than a predetermined value.

4. The control device according to claim 1, characterized in that The control device further includes a decision unit that determines an action of the mobile body based on the calculated risk.

5. The control device according to claim 4, characterized in that The risk corresponds to the possibility of collision between the mobile object in the search area and the identified target object. The decision unit decides the behavior of the mobile body based on the possibility of collision between the mobile body and the identified target object.

6. The control device according to claim 4, characterized in that The behavior of the mobile object includes a report to the driver of the mobile object.

7. The control device according to claim 4, characterized in that The behavior of the mobile body includes automatic driving of the mobile body that does not require a driving operation by a driver, or automatic driving for assisting a driving operation by the driver.

8. The control device according to claim 7, characterized in that: The decision mechanism determines a travel path of the mobile body based on the calculated risk when the mobile body is automatically traveling without requiring a driving operation by a driver, and controls at least one of a speed and a steering of the mobile body according to the travel path.

9. The control device according to claim 1, characterized in that The control device further includes a determination unit that uses information on a travel road boundary of the travel lane to determine whether the travel lane has a road shape including a curve. When the driving lane does not have a road shape including a curve, the generating unit does not generate the information of the virtual driving lane.

10. The control device according to claim 9, characterized in that: The determination unit determines whether the driving lane has a road shape including a curve based on a curvature of a driving road boundary of the driving lane.

11. The control device according to claim 10, characterized in that: The determination unit determines that the driving lane has a road shape including a curve when the curvature of the driving road boundary of the driving lane is within a predetermined range.

12. The control device according to claim 10, characterized in that The determination unit estimates the curvature of the travel road boundary of the travel lane by fitting the travel road boundary of the travel lane with an arc.

13. The control device according to claim 2, characterized in that When the generating mechanism transforms the position of the identified target object onto the virtual driving lane, the generating mechanism shifts the position of the identified target object onto the virtual driving lane so that the position of the identified target object moves away from the position of the moving body in the direction of travel of the moving body.

14. The control device according to claim 13, characterized in that: The generating unit shifts the position of the recognized object using a geometric calculation when converting the position of the recognized object onto the virtual driving lane.

15. A vehicle, characterized in that: The vehicle has: An object recognition mechanism that recognizes the state of an object outside the vehicle; a driving lane recognition mechanism for recognizing a driving lane on a moving path of the vehicle; a generating unit for generating information of a virtual driving lane that is a straight driving lane based on the recognized driving lane information and the recognized state of the target object; a setting unit that sets a search area on the virtual driving lane for calculating a risk, the risk being an index value indicating a degree to which the vehicle should avoid entering the lane; a calculation unit configured to calculate the risk in the set search area; as well as a decision unit that determines, based on the risk calculated in the set search area, an action of the vehicle including automatic driving of the vehicle that does not require a driving operation by a driver or automatic driving for assisting a driving operation performed by the driver, When the driving lane has a road shape including a curve, the generating unit generates the information of the virtual driving lane by transforming each position of the driving lane so that the curved portion of the driving lane becomes a straight driving lane along the traveling direction.

16. A control method for a control device, characterized in that: The control method of the control device comprises: a target object recognition step, in which the state of a target object outside the mobile body is recognized; a driving lane identification step, in which a driving lane on a moving path of the moving object is identified; a generating step of generating information of a virtual driving lane as a straight driving lane based on the recognized driving lane information and the recognized state of the target object; a setting step of setting a search area on the virtual driving lane for calculating a risk, the risk being an index value indicating a degree to which the moving object should avoid entering the lane; as well as a calculation step, in which the risk in the set search area is calculated, In the generating step, when the driving lane has a road shape including a curve, each position of the driving lane is transformed so that the curved portion of the driving lane becomes a straight driving lane along the traveling direction, thereby generating the information of the virtual driving lane.

17. A storage medium storing a program for causing a computer to function as each mechanism of a control device, characterized in that: The control device has: an object recognition mechanism for recognizing the state of an object outside the mobile body; a driving lane recognition mechanism for recognizing a driving lane on a moving path of the moving object; a generating unit for generating information of a virtual driving lane that is a straight driving lane based on the recognized driving lane information and the recognized state of the target object; a setting unit that sets a search area on the virtual driving lane for calculating a risk, the risk being an index value indicating a degree to which the moving object should avoid entering; as well as a calculation unit that calculates the risk in the set search area, When the driving lane has a road shape including a curve, the generating unit generates the information of the virtual driving lane by transforming each position of the driving lane so that the curved portion of the driving lane becomes a straight driving lane along the traveling direction.

18. A program product for causing a computer to function as each mechanism of a control device, characterized in that: The control device has: an object recognition mechanism for recognizing the state of an object outside the mobile body; a driving lane recognition mechanism for recognizing a driving lane on a moving path of the moving object; a generating unit for generating information of a virtual driving lane that is a straight driving lane based on the recognized driving lane information and the recognized state of the target object; a setting unit that sets a search area on the virtual driving lane for calculating a risk, the risk being an index value indicating a degree to which the moving object should avoid entering; as well as a calculation unit that calculates the risk in the set search area, When the driving lane has a road shape including a curve, the generating unit generates the information of the virtual driving lane by transforming each position of the driving lane so that the curved portion of the driving lane becomes a straight driving lane along the traveling direction.

Citation Information

Patent Citations

  • Vehicle controller, vehicle control method, and program

    JP2019046161A