Vehicle control device, control method, and control program product

Abstract

The invention provides a vehicle control device, a control method, and a control program product, which can perform appropriate control of a traffic light corresponding to a travel road on which a vehicle travels without preparing position information of the traffic light in advance. A control device (30) for controlling a vehicle (1) is provided with: a recognition unit (31) that recognizes the surroundings of the vehicle (1); a deviation amount calculation unit (32) that, when the traffic light is recognized by the recognition unit (31), calculates a deviation amount of the traffic light with respect to a travel road on which the vehicle (1) travels; a determination unit (34) that determines, on the basis of the deviation amount calculated by the deviation amount calculation unit (32), whether the traffic light recognized by the recognition unit (31) is a traffic light corresponding to the travel road; and a vehicle control unit (35) that controls the vehicle (1) on the basis of the determination result of the determination unit (34).

Description

Technical Field

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

[0002] In recent years, efforts to provide access to sustainable transportation systems that take vulnerable road users into consideration have become increasingly active. As part of this effort, research and development of driver assistance and autonomous driving technologies in vehicles such as automobiles is being conducted to further improve traffic safety and convenience.

[0003] As an example of driving assistance technology, the following technology is disclosed in the following patent document 1: based on map information including position information of traffic lights around a vehicle and the vehicle's own position, two or more traffic lights are predicted to appear in an image obtained by photographing the area around the vehicle; based on the possibility of the traffic lights being blocked, a priority is set between the two or more determined traffic lights; and the traffic light with the highest priority among the two or more traffic lights is detected from the above-mentioned image.

[0004] Prior art literature

[0005] Patent Literature

[0006] Patent Document 1: Japanese Patent No. 6337961 Summary of the Invention

[0007] Problems to be solved by the invention

[0008] However, in the above-mentioned prior art, the use of map information including the location information of traffic lights around the vehicle is a prerequisite. Therefore, in a vehicle for which the location information of traffic lights is not prepared in advance, it may not be possible to perform appropriate control of traffic lights corresponding to the road on which the vehicle is traveling.

[0009] The present invention provides a vehicle control device, control method, and control program product that can appropriately control traffic lights according to the road on which the vehicle is traveling, even without pre-prepared traffic light location information. This can improve traffic safety and contribute to the development of a sustainable transportation system.

[0010] Means for solving problems

[0011] One aspect of the present invention relates to a vehicle control device for controlling a vehicle, comprising:

[0012] an identification unit that identifies a surrounding condition of the vehicle;

[0013] a deviation amount calculation unit that calculates a deviation amount of the traffic light relative to the road on which the vehicle is traveling, when the traffic light is recognized by the recognition unit;

[0014] a determination unit that determines whether the traffic light is a traffic light corresponding to the travel road based on the deviation amount calculated by the deviation amount calculation unit; and

[0015] A vehicle control unit controls the vehicle based on a determination result of the determination unit.

[0016] Another aspect of the present invention relates to a control method, in which a computer controlling a vehicle performs the following processing:

[0017] identifying surrounding conditions of the vehicle;

[0018] When a traffic light is identified, calculating a deviation of the traffic light from the road on which the vehicle is traveling;

[0019] determining, based on the deviation, whether the traffic light is a traffic light corresponding to the driving road; and

[0020] The vehicle is controlled based on a determination result of the determination.

[0021] Another aspect of the present invention relates to a control program product storing a control program that causes a computer controlling a vehicle to perform the following processing:

[0022] identifying surrounding conditions of the vehicle;

[0023] When a traffic light is identified, calculating a deviation of the traffic light from the road on which the vehicle is traveling;

[0024] determining, based on the deviation, whether the traffic light is a traffic light corresponding to the driving road; and

[0025] The vehicle is controlled based on a determination result of the determination.

[0026] Effects of the Invention

[0027] According to the present invention, a vehicle control device, a control method, and a control program product can be provided that can perform appropriate control of traffic lights corresponding to a road on which a host vehicle is traveling, even without preparing traffic light position information in advance. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 This is a block diagram showing a schematic configuration of a vehicle 1 including a control device 30 as one embodiment of the vehicle control device of the present invention.

[0029] Figure 2 This is a diagram showing a first example of processing implemented by the functional units included in the control device 30 .

[0030] Figure 3 1 is a diagram showing a second example of processing implemented by the functional units of the control device 30 .

[0031] Figure 4 3 is a diagram showing a third example of processing implemented by the functional units of the control device 30 .

[0032] Figure 5 1 is a diagram showing an example of the first evaluation value derived by the evaluation value deriving unit 33 .

[0033] Figure 6 1 is a diagram showing an example of a traffic light Sn.

[0034] Figure 7 This is a flowchart (part 1) showing an example of a processing procedure of the control device 30 .

[0035] Figure 8 This is a flowchart (part 2) showing an example of the processing procedure of the control device 30 .

[0036] Description of Reference Numerals

[0037] 1 vehicle

[0038] 24 Map Information Database (Map Information)

[0039] 30 Control device (vehicle control device)

[0040] 31 Identification Department

[0041] 32 Deviation calculation unit

[0042] 33 Evaluation value export unit

[0043] 34 Judgment Department

[0044] 35 Vehicle Control Unit. DETAILED DESCRIPTION

[0045] Hereinafter, an embodiment of the vehicle control device, control method and control program of the present invention will be described with reference to the accompanying drawings. The accompanying drawings are viewed from the direction of the figure numerals. In addition, the following embodiments do not limit the present invention, and all elements described in the following embodiments are not limited to the elements necessary for the present invention. In addition, two or more elements described in the following embodiments may be arbitrarily combined without departing from the scope of the present invention. In the following, the same or similar elements are marked with the same or similar figure numerals, and their descriptions may be appropriately omitted or simplified.

[0046] In addition, in this specification, in order to make the description simple and clear, unless otherwise specified, the front, back, left, right, up and down directions are recorded according to the directions observed by the occupant, i.e., the driver, of a vehicle (i.e., the vehicle 1 described later) controlled by a control device (i.e., the control device 30 described later) which is an embodiment of the vehicle control device of the present invention.

[0047] [1. Vehicle]

[0048] Figure 1 This is a block diagram showing a schematic configuration of a vehicle 1 including a control device 30 as one embodiment of the vehicle control device of the present invention. Figure 1 The vehicle 1 of the present embodiment shown (hereinafter also referred to as the "present vehicle") is an automobile having a drive source and wheels (neither of which are shown), the wheels including drive wheels driven by power from the drive source and steerable wheels. As an example, the vehicle 1 may be a four-wheeled automobile having a pair of left and right front wheels and a pair of left and right rear wheels.

[0049] The driving source of vehicle 1 may be an electric motor, an internal combustion engine such as a gasoline engine or a diesel engine, or a combination of an electric motor and an internal combustion engine. Furthermore, the driving source of vehicle 1 may drive a pair of left and right front wheels, a pair of left and right rear wheels, or four wheels: a pair of left and right front wheels and a pair of left and right rear wheels. Of the front and rear wheels of vehicle 1, either one may be a steerable wheel, or both may be steerable wheels.

[0050] Vehicle 1 includes a sensor group 10 , a navigation device 20 , a control device 30 as an example of a vehicle control device according to the present invention, an electric power steering (EPS) system 40 , a driving force control system 50 , a braking force control system 60 , a communication unit 70 , an operation input unit 80 , and an alarm device 90 .

[0051] The sensor group 10 includes an external sensor 11 that acquires information about the surroundings of the vehicle 1 (hereinafter referred to as "surrounding information") and a vehicle sensor 12 that acquires information about the vehicle 1 (hereinafter referred to as "vehicle information"). The information acquired by each sensor included in the sensor group 10 (in other words, detection values) is output to the control device 30 and used by the control device 30 to control the vehicle 1 (hereinafter referred to as "vehicle control").

[0052] The external sensor 11 includes, for example, a camera 111, a sonar 112, and a radar 113. The camera 111 is an imaging device that captures the surroundings of the vehicle 1, including the front of the vehicle 1, and outputs image data of the obtained surrounding images to the control device 30. For example, a digital camera using an imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor) can be used as the camera 111.

[0053] The sonar 112 emits sound waves around the vehicle 1 (e.g., in front of, behind, and to the sides of the vehicle 1) and receives reflected sound from objects around the vehicle 1, thereby detecting the distance and direction of the objects. The radar 113 emits radio waves around the vehicle 1, including in front of the vehicle 1, and receives reflected waves from objects around the vehicle 1, thereby detecting the distance and direction of the objects. For example, a millimeter-wave radar can be used as the radar 113.

[0054] Furthermore, the external sensor 11 may include a LiDAR (Light Detection and Ranging) instead of or in addition to the sonar 112 or radar 113. In this case, the LiDAR emits laser light around the vehicle 1, including the front of the vehicle 1, and receives reflected light from objects around the vehicle 1 to detect the distance to the object, the direction of the object, and other information.

[0055] The vehicle sensor 12 includes, for example, a wheel sensor 121 , a vehicle speed sensor 122 , an inertial measurement unit (IMU) 123 , an occupant camera 124 , an operation detection unit 125 , and a steering touch sensor 126 .

[0056] The wheel sensor 121 detects the rotation angle of one or more wheels of the vehicle 1. As an example, the wheel sensor 121 detects the rotation angle of each of the left rear wheel and the right rear wheel. As the wheel sensor 121, for example, an angle sensor, a displacement sensor, etc. can be used.

[0057] The vehicle speed sensor 122 detects the vehicle speed VP, which is the running speed of the vehicle 1 (in other words, the moving speed of the vehicle body). For example, the vehicle speed sensor 122 detects the vehicle speed VP based on the rotation speed of a counter shaft (not shown) included in the vehicle 1 .

[0058] The inertial measurement device 123 detects the angular velocities in the pitch, roll, and yaw directions of the vehicle 1, and the accelerations in the front-back, left-right, and up-down directions of the vehicle 1. Alternatively, the vehicle sensor 12 may include an acceleration sensor that detects the acceleration of the vehicle 1 in a predetermined direction, or a gyroscopic sensor that detects the angular velocity of the vehicle 1 in a predetermined direction, in place of the inertial measurement device 123.

[0059] The passenger camera 124 is a digital camera that captures the interior of the vehicle 1 and outputs the resulting image data to the control device 30. For example, the passenger camera 124 can be a so-called "driver monitoring camera" capable of capturing a frontal image of the head (in other words, the face) of a passenger (hereinafter also referred to as the "driver") seated in the driver's seat of the vehicle 1. Similar to the camera 111, a digital camera utilizing an imaging element such as a CCD or CMOS can be employed as the passenger camera 124.

[0060] The operation detection unit 125 detects operations performed using the operation input unit 80, which is provided so that the driver can operate it. In this embodiment, the operation input unit 80 may include, for example, an operation button (not shown) that receives an operation to switch a predetermined driving assistance control between on (in other words, operative) and off (in other words, inoperative). In this case, the operation detection unit 125 can detect the operation of turning the predetermined driving assistance control on or off.

[0061] The steering device touch sensor 126 detects whether the steering device 46 of the vehicle 1 is properly gripped. For example, the steering device touch sensor 126 is implemented by an electrostatic capacitance sensor, etc. In this case, the electrostatic capacitance sensor is provided at the portion that the driver touches when the steering device 46 is properly gripped.

[0062] The navigation device 20 is configured to include, for example, a GNSS (Global Navigation Satellite System) receiver 21, a touch panel 22, and a speaker 23. The navigation device 20 also includes a storage unit (not shown) such as a flash memory. The storage unit of the navigation device 20 stores a map information database (DB) 24, which is an example of map information.

[0063] The map information database 24 is configured to include road network information. Road network information represents each road through a combination of nodes and the links connecting them (also called "paths"). Each node in the road network information represents a characteristic point on the road, such as an intersection, a corner, or an end point. In the road network information, each node is assigned information indicating the location corresponding to the node (e.g., coordinates such as latitude and longitude that can identify a point on a map). Furthermore, each link in the road network information is assigned information indicating the nodes at both ends of the link, the road corresponding to the link, the link length, the number of lanes, the direction of travel, and the type of road.

[0064] The GNSS receiver 21 determines the current position of the vehicle 1 (e.g., the latitude and longitude of the location of the vehicle 1) based on signals received from GNSS satellites. Furthermore, the navigation device 20 may obtain detection results from the vehicle sensors 12 (e.g., the wheel sensors 121 and the vehicle speed sensor 122) via the control device 30, for example, and determine or supplement the current position of the vehicle 1 using an inertial navigation system (INS) that utilizes the detection values ​​of the vehicle sensors 12.

[0065] The touch panel 22 is formed by combining a display device such as a liquid crystal display or an OLED (Organic Light Emitting Diode) and a pointing device (such as a touchpad). The speaker 23 is configured to output sound to an occupant of the vehicle 1 (such as the driver).

[0066] For example, the navigation device 20 searches for a route from the current location of the vehicle 1 to a destination set by the driver using the touch panel 22, referring to the map information database 24. The navigation device 20 then provides route guidance based on the searched route using the touch panel 22 and the speaker 23. Furthermore, the navigation device 20 may cause the touch panel 22 to display a specified display in response to instructions from the control device 30. Furthermore, the navigation device 20 may output, for example, information indicating the determined current location of the vehicle 1 and specified information (e.g., information indicating an operation received via the touch panel 22) to the control device 30.

[0067] Furthermore, in this embodiment, the control device 30 is configured to be able to refer to the map information database 24 (i.e., map information) of the navigation device 20. However, the present invention is not limited thereto, and map information including road network information similar to that in the map information database 24 may be stored separately in the control device 30, and the control device 30 may refer to this map information.

[0068] The control device 30 is, for example, a computer that centrally controls the entire vehicle 1. It includes a processor that performs various calculations, a storage unit with a non-transitory storage medium (e.g., flash memory) that stores various information, and an input / output unit that controls the input and output of data within and outside the control device 30 (none of which are shown). For example, the control device 30 may be implemented as a single ECU (Electronic Control Unit) or through the collaboration of multiple ECUs. Specific control examples of the control device 30 will be described later, and therefore are omitted here.

[0069] The EPS system 40 is configured to include, for example, a steering angle sensor 41 , a torque sensor 42 , an EPS motor 43 , a resolver 44 , and an EPS ECU 45 .

[0070] The steering angle sensor 41 detects the steering angle θst of the steering device 46 and outputs information indicating the detected steering angle θst to the EPS ECU 45. The torque sensor 42 detects the steering torque TQ applied to the steering device 46 of the vehicle 1 and outputs information indicating the detected steering torque TQ to the EPS ECU 45.

[0071] EPS motor 43 assists the driver in operating steering device 46 by applying driving force or reaction force to steering column 47 connected to steering device 46 in accordance with instructions from EPS ECU 45. Resolver 44 detects rotation angle θm of EPS motor 43 and outputs information indicating the detected rotation angle θm to EPS ECU 45.

[0072] The EPS ECU 45 is, for example, a computer that controls the EPS system 40 (e.g., the EPS motor 43). It includes a processor that performs various calculations, a storage unit with a non-transitory storage medium that stores various information, and an input / output unit that controls the input and output of data within and outside the EPS ECU 45 (none of which are shown). The EPS ECU 45 is implemented as one or more ECUs. For example, the EPS ECU 45 controls the EPS system 40 (e.g., the EPS motor 43) based on the steering angle θst detected by the steering angle sensor 41, the steering torque TQ detected by the torque sensor 42, and the rotation angle θm detected by the resolver 44.

[0073] The EPS system 40 (e.g., the EPS ECU 45) may also output information indicating the steering angle θst detected by the steering angle sensor 41, the steering torque TQ detected by the torque sensor 42, the rotation angle θm detected by the resolver 44, and the like to the control device 30. Furthermore, the EPS system 40 (e.g., the EPS ECU 45) may also output information indicating the steering speed ω of the steering device 46 to the control device 30. In this case, the steering speed ω is obtained, for example, by performing a time differentiation on the steering angle θst.

[0074] The driving force control system 50 includes a drive ECU 51 and is configured to control the driving force of the vehicle 1. The drive ECU 51 is, for example, a computer that controls the driving force control system 50. It includes a processor that performs various calculations, a storage unit with a non-transitory storage medium for storing various information, and an input / output unit that controls the input and output of data within and outside the drive ECU 51 (none of which are shown). This unit is implemented as one or more ECUs. For example, the drive ECU 51 controls the power output from the vehicle 1's drive source based on operation of an accelerator pedal 52 provided on the vehicle 1. Furthermore, the drive ECU 51 can also control the driving force control system 50 (e.g., the drive source) in accordance with instructions from the control device 30.

[0075] The braking force control system 60 includes a brake ECU 61 and is configured to control the braking force of the vehicle 1. The brake ECU 61 is, for example, a computer that controls the braking force control system 60. It includes a processor that performs various calculations, a storage unit with a non-transitory storage medium that stores various information, and an input / output unit that controls the input and output of data within and outside the brake ECU 61 (none of which are shown). This unit is implemented as one or more ECUs. For example, the brake ECU 61 controls the braking force of the vehicle 1 by controlling a brake device (not shown) provided in the vehicle 1 based on an operation of a brake pedal 62 provided in the vehicle 1. The brake device, for example, includes a brake caliper, a hydraulic cylinder that transmits hydraulic pressure to the caliper, and an electric motor that generates hydraulic pressure in the hydraulic cylinder. The brake ECU 61 controls the electric motor of the brake device to generate a braking force corresponding to the operation of the brake pedal 62. Furthermore, the brake ECU 61 can also control the braking force control system 60 (e.g., the brake device) in accordance with instructions from the control device 30.

[0076] The communication unit 70 is a communication interface for communicating with the external device 2 under the control of the control device 30. Specifically, the control device 30 can communicate with the external device 2 via the communication unit 70. Examples of the external device 2 include a driver's terminal device (e.g., a smartphone) and a server managed by the manufacturer of the vehicle 1. Furthermore, communication between the vehicle 1 and the external device 2 can employ, for example, mobile communication networks such as cellular lines, Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0077] The warning device 90 is a device that issues a warning to the driver under the control of the control device 30. The warning device 90 is configured to include, for example, an MID (Multi-Information Display) 91 and a buzzer 92.

[0078] The MID 91 is comprised of a display device such as a liquid crystal display (LCD) or an OLED, and is located in a location visually accessible to the driver (e.g., within the instrument panel of the vehicle 1). For example, the MID 91 displays a predetermined warning image in response to instructions from the control device 30. Furthermore, the MID 91 can also be used in conjunction with the aforementioned touch panel 22. In other words, the "MID 91" in the following description may be referred to as the "touch panel 22."

[0079] The buzzer 92 is configured to output a predetermined alarm sound. For example, the buzzer 92 outputs the predetermined alarm sound in accordance with an instruction from the control device 30. Furthermore, the buzzer 92 can also be used in conjunction with the aforementioned speaker 23. In other words, the "buzzer 92" in the following description may be referred to as the "speaker 23."

[0080] [2. Control device]

[0081] Next, the control device 30 will be described in more detail. The control device 30 includes, for example, an identification unit 31 , a deviation amount calculation unit 32 , a determination unit 34 , and a vehicle control unit 35 as functional units implemented by a processor executing a program stored in a storage unit of the control device 30 .

[0082] The recognition unit 31 recognizes the surrounding conditions of the vehicle 1. For example, the recognition unit 31 performs sensor fusion processing on some or all of the detection results of the camera 111, sonar 112, and radar 113 included in the external sensor 11, and recognizes the surrounding conditions of the vehicle 1 based on the processing results.

[0083] The recognition unit 31 identifies the position, type, speed, acceleration, and other information of objects surrounding the vehicle 1 as the surrounding conditions of the vehicle 1. For example, the recognition unit 31 identifies the object's position as a position in absolute coordinates with a representative point of the vehicle 1 (e.g., the center of gravity or the center of the drive shaft) as the origin. This allows the relative positions of the vehicle 1 and surrounding objects to be identified. Furthermore, the object's position can be expressed in absolute coordinates using a representative point such as the object's center of gravity or a corner, or as a region.

[0084] Examples of objects that can be recognized by the recognition unit 31 include traffic participants such as other vehicles and pedestrians; lane dividing lines, curbs, medians; and road structures such as guardrails and road shoulders. Furthermore, the recognition unit 31 can also recognize other road events such as traffic lights, stop signs, crosswalks, road signs, branching roads, merges, interchanges, and toll booths on toll roads. For example, the recognition unit 31 identifies traffic lights around the vehicle 1 based on any one of the multiple illuminated components (e.g., illuminated components 611 to 613 described below) typically included in a traffic light, as detected from the surrounding image captured by the camera 111.

[0085] Such a recognition unit 31 can recognize, for example, not only the shape of the lane in which the vehicle 1 is traveling, but also traffic lights and traffic participants (eg, other vehicles) around the vehicle 1 .

[0086] In the following description, a road having a host lane, i.e., the road on which vehicle 1 is traveling, is referred to as "traveling road Rd1." Traveling road Rd1 may include other lanes traveling in the same direction as the host lane, but does not include other lanes traveling in the opposite direction (hereinafter also referred to as "opposing lanes"). Furthermore, a road having an opposing lane, i.e., a road traveling in the opposite direction to traveling road Rd1, is referred to as "opposing road Rd2." Typically, traveling road Rd1 and opposing road Rd2 are often arranged parallel to each other.

[0087] Furthermore, when a traffic light is identified as being located near the vehicle 1, the recognition unit 31 may also determine the location corresponding to the traffic light (e.g., the latitude and longitude of the location where the traffic light is located). In this case, for example, the recognition unit 31 may determine the location corresponding to the traffic light by referencing map information such as the map information database 24 based on the relative position between the identified traffic light and the vehicle 1 and the current location of the vehicle 1 determined by the navigation device 20 (e.g., the GNSS receiver 21).

[0088] When the recognition unit 31 recognizes a traffic light, the deviation calculation unit 32 calculates the deviation of the traffic light from the travel road Rd1. Details will be described later, so a detailed explanation is omitted here. However, the deviation calculation unit 32 calculates the deviation of the traffic light from the travel road Rd1 by, for example, calculating the distance between the point corresponding to the traffic light recognized by the recognition unit 31 and the travel road boundary of the travel road Rd1. This allows an appropriate value to be calculated as the deviation of the traffic light from the travel road Rd1.

[0089] The determination unit 34 determines whether the traffic light identified by the recognition unit 31 is the traffic light corresponding to the travel road Rd1 based on the deviation calculated by the deviation calculation unit 32. Here, the traffic light corresponding to the travel road Rd1 is, for example, a traffic light that indicates "go" (e.g., green light) or "stop" (e.g., red light) to the vehicle 1 traveling on the travel road Rd1.

[0090] In addition, in this embodiment, in order to enable the determination unit 34 to determine with higher accuracy whether the identified traffic light is the traffic light corresponding to the driving road Rd1, the control device 30 also has an evaluation value derivation unit 33 as a functional unit, which is implemented by the processor executing a program stored in the storage unit of the control device 30.

[0091] The evaluation value deriving unit 33 derives a first evaluation value indicating the degree of association between the traffic light recognized by the recognition unit 31 and the travel road Rd1 based on the deviation calculated by the deviation calculating unit 32. A larger first evaluation value indicates a higher degree of association between the traffic light recognized by the recognition unit 31 and the travel road Rd1. As will be described later, the first evaluation value reaches its maximum value when the deviation is "0," for example.

[0092] In this manner, when the control device 30 includes the evaluation value derivation unit 33, the determination unit 34 determines whether the recognized traffic light is the traffic light corresponding to the travel road Rd1 based on the first evaluation value derived by the evaluation value derivation unit 33. For example, if the first evaluation value derived by the evaluation value derivation unit 33 is greater than or equal to a threshold value, the determination unit 34 determines that the recognized traffic light is the traffic light corresponding to the travel road Rd1. On the other hand, if the first evaluation value is less than the threshold value, the determination unit 34 determines that the recognized traffic light is not the traffic light corresponding to the travel road Rd1.

[0093] In this way, by determining whether the traffic light corresponds to the driving road Rd1 based on the first evaluation value derived by the evaluation value derivation unit 33, it is possible to determine whether the traffic light corresponds to the driving road Rd1 with high accuracy, compared to a case where whether the traffic light corresponds to the driving road Rd1 is determined only based on the deviation calculated by the deviation calculation unit 32.

[0094] The evaluation value derivation unit 33 is not an essential component and may not be provided. In such a case, for example, if the deviation calculated by the deviation calculation unit 32 is less than a threshold value, the determination unit 34 may determine that the recognized traffic light is the traffic light corresponding to the travel road Rd1. On the other hand, if the deviation is greater than the threshold value, the determination unit 34 may determine that the recognized traffic light is not the traffic light corresponding to the travel road Rd1.

[0095] The vehicle control unit 35 controls the vehicle 1 based on the determination result of the determination unit 34. The vehicle control unit 35 is used to reflect the determination result of the determination unit 34 to the vehicle control, and the vehicle control is not particularly limited. For example, when the determination unit 34 determines that the identified traffic light is the traffic light corresponding to the driving road Rd1 and the traffic light indicates "stop", the vehicle control unit 35 controls the vehicle 1 so that the vehicle 1 stops in front of the specified stop line on the driving road Rd1. In addition, when the determination unit 34 determines that the identified traffic light is the traffic light corresponding to the driving road Rd1 and the traffic light indicates "stop", if the vehicle 1 does not slow down when the distance from the vehicle 1 to the traffic light becomes less than a specified value, the vehicle control unit 35 issues an alarm via the alarm device 90 to call the driver's attention.

[0096] [3. Example of Processing Implemented by Functional Units of the Control Device]

[0097] An example of processing implemented by the functional units of the control device 30 will be described below. Figure 2 This is a diagram showing a first example of processing implemented by the functional units included in the control device 30 .

[0098] exist Figure 2 In the example shown, vehicle 1 is Figure 2 The vehicle 1 is traveling on the travel road Rd1 with the lower portion in the figure facing upward. The travel road Rd1 in this example is a single-lane road having only the own lane Lo in which the vehicle 1 is traveling.

[0099] Nodes Nd1, Nd2, Nd3, and Nd4 are nodes corresponding to the travel road Rd1 in this example, as shown in the map information database 24 or other similar information. Furthermore, links Lk1, Lk2, and Lk3 are links corresponding to the travel road Rd1 in this example, as shown in the map information database 24 or other similar information. In this example, link Lk1 connects node Nd1 and node Nd2, link Lk2 connects node Nd2 and node Nd3, and link Lk3 connects node Nd3 and node Nd4.

[0100] like Figure 2As shown, when the vehicle 1 is traveling on the driving road Rd1, the recognition unit 31, for example, recognizes a dividing line that divides one side of the own lane Lo in the width direction (for example, the left side of the vehicle 1) and a dividing line that divides the other side of the own lane Lo in the width direction (for example, the right side of the vehicle 1), and based on these recognition results, recognizes the shape of the own lane Lo including the length of the own lane Lo in the width direction, that is, the own lane width w.

[0101] Furthermore, when a traffic light Sn exists in front of the vehicle 1 traveling on the travel road Rd1, the recognition unit 31 recognizes the traffic light Sn and specifies the location corresponding to the traffic light Sn. Figure 2 In FIG. 1 , a circle denoted by the reference symbol Sn indicates a location corresponding to the traffic light Sn.

[0102] When the recognition unit 31 recognizes the traffic light Sn, the deviation calculation unit 32 calculates the deviation of the traffic light Sn from the travel road Rd1. To calculate the deviation of the traffic light Sn from the travel road Rd1, the deviation calculation unit 32 first calculates the length of a perpendicular line PL drawn from the point corresponding to the traffic light Sn to the segment connecting the node closest to the traffic light Sn and the second-closest node among the nodes on the travel road Rd1 (in other words, the segment passing through the node closest to the traffic light Sn and the second-closest node) as the traffic light offset with respect to the traffic light Sn.

[0103] In this case, if Figure 2 As shown, the node closest to the traffic light Sn is node Nd3 (refer to Figure 2 The second closest node is node Nd2 (see Figure 2 (arrow denoted by reference symbol β in the figure). Therefore, the deviation calculation unit 32 calculates the length "y" of the perpendicular line PL drawn from the location corresponding to the traffic light Sn to the road link Lk2 connecting the nodes Nd2 and Nd3 as the traffic light offset with respect to the traffic light Sn. Here, the traffic light offset "y" with respect to the traffic light Sn can also be considered as the minimum distance from the road link Lk2 connecting the node Nd3 closest to the traffic light Sn and the node Nd2 second closest to the traffic light Sn among the nodes of the travel road Rd1 to the location corresponding to the traffic light Sn.

[0104] Next, the deviation calculation unit 32 calculates the deviation of the traffic light Sn from the travel road Rd1 based on the thus calculated traffic light offset and the boundary distance of the travel road Rd1. The boundary distance and deviation are described in more detail below. The following description of parts that are identical to those in the above example will be omitted or simplified as appropriate.

[0105] Figure 3 2 is a diagram showing a second example of processing implemented by the functional unit of the control device 30. Figure 3In the example shown, traffic lights Sn1 and Sn2 are located ahead of vehicle 1 traveling on road Rd1, and both traffic lights Sn1 and Sn2 are recognized by recognition unit 31. Furthermore, in this example, it is assumed that the node closest to traffic lights Sn1 and Sn2 is node Nd11, the second closest node is node Nd12, and the road segment connecting nodes Nd11 and Nd12 is road segment Lk10.

[0106] In this example, when calculating the deviation of traffic light Sn1 from travel road Rd1, the deviation calculation unit 32 first calculates the traffic light offset with respect to traffic light Sn1 by, for example, calculating the length "y1" of a perpendicular line PL (not shown) drawn from the point corresponding to traffic light Sn1 to road link Lk10. Here, the traffic light offset with respect to traffic light Sn1, or "y1," can also be considered the minimum distance from road link Lk10, which connects node Nd11, the closest node to traffic light Sn1, and node Nd12, the second closest node, to the point corresponding to traffic light Sn1.

[0107] Next, the deviation amount calculation unit 32 sets a line obtained by offsetting the link Lk10 connecting the node Nd11 closest to the traffic light Sn1 and the second-closest node Nd12 to one side, i.e., the left side, in the width direction of the driving road Rd1 by a predetermined first boundary distance d1, as the left side driving road boundary L1 of the driving road Rd1. Furthermore, the deviation amount calculation unit 32 sets a line obtained by offsetting the link Lk10 connecting the node Nd11 closest to the traffic light Sn1 and the second-closest node Nd12 to the other side, i.e., the right side, in the width direction of the driving road Rd1 by a predetermined second boundary distance dr, as the right side driving road boundary L2 of the driving road Rd1.

[0108] The deviation calculation unit 32 then calculates the deviation dist1 of traffic light Sn1 as the difference between the traffic light offset for traffic light Sn1 (in other words, the minimum distance from link Lk10 to the point corresponding to traffic light Sn1) and the boundary distance corresponding to the road boundary closest to the point corresponding to traffic light Sn1, either the left road boundary L1 or the right road boundary L2. Specifically, in this example, the road boundary closest to the point corresponding to traffic light Sn1, either the left road boundary L1 or the right road boundary L2, is the left road boundary L1. Therefore, the deviation calculation unit 32 calculates the deviation dist1 of traffic light Sn1 as the value obtained by subtracting the first boundary distance d1, which is the boundary distance corresponding to the left road boundary L1, from the traffic light offset "y1" for traffic light Sn1.

[0109] Therefore, if Figure 3As shown, if the location corresponding to traffic light Sn1 is located closer to link Lk10 than left-side road boundary L1, the deviation dist1 of traffic light Sn1 takes a negative value. On the other hand, if the location corresponding to traffic light Sn1 is farther from left-side road boundary L1 than link Lk10, the deviation dist1 of traffic light Sn1 takes a positive value. In other words, the further the location corresponding to traffic light Sn1 is from link Lk10 beyond left-side road boundary L1, the greater the value of the deviation dist1 of traffic light Sn1.

[0110] Furthermore, in this example, when calculating the deviation of traffic light Sn2 from the travel road Rd1, the deviation calculation unit 32 first calculates the traffic light offset with respect to traffic light Sn2 by, for example, calculating the length "y2" of a perpendicular line PL (not shown) drawn from the point corresponding to traffic light Sn2 to the road link Lk10. Here, the traffic light offset with respect to traffic light Sn2, i.e., "y2," can also be considered the minimum distance from the road link Lk10 connecting the node Nd11 closest to traffic light Sn2 and the second-closest node Nd12 to the point corresponding to traffic light Sn2.

[0111] Next, the deviation amount calculation unit 32 sets the line obtained by offsetting the link Lk10 connecting the node Nd11 closest to the traffic light Sn2 and the second-closest node Nd12 to the left of the driving road Rd1 by the first boundary distance d1 as the left driving road boundary L1 of the driving road Rd1. Furthermore, the deviation amount calculation unit 32 sets the line obtained by offsetting the link Lk10 connecting the node Nd11 closest to the traffic light Sn2 and the second-closest node Nd12 to the right of the driving road Rd1 by the second boundary distance dr as the right driving road boundary L2 of the driving road Rd1.

[0112] The deviation calculation unit 32 then calculates the deviation dist2 of traffic light Sn2 as the difference between the traffic light offset for traffic light Sn2 (in other words, the minimum distance from link Lk10 to the point corresponding to traffic light Sn2) and the boundary distance corresponding to the road boundary closest to the point corresponding to traffic light Sn2, either the left road boundary L1 or the right road boundary L2. Specifically, in this example, the road boundary closest to the point corresponding to traffic light Sn2, either the left road boundary L1 or the right road boundary L2, is the right road boundary L2. Therefore, the deviation calculation unit 32 calculates the deviation dist2 of traffic light Sn2 as the value obtained by subtracting the second boundary distance dr, which is the boundary distance corresponding to the right road boundary L2, from the traffic light offset "y2" for traffic light Sn2.

[0113] Therefore, if Figure 3As shown, if the location corresponding to traffic light Sn2 is located closer to the road segment Lk10 than the right-side road boundary L2, the deviation dist2 of traffic light Sn2 takes a negative value. On the other hand, if the location corresponding to traffic light Sn2 is located beyond the right-side road boundary L2 and further from the road segment Lk10, the deviation dist2 of traffic light Sn2 takes a positive value. In other words, the further the location corresponding to traffic light Sn2 is from the right-side road boundary L2 and further from the road segment Lk10, the larger the value of the deviation dist2 of traffic light Sn2.

[0114] The deviation amount calculator 32 sets the first boundary distance dl and the second boundary distance dr based on, for example, the lane width w (i.e., the widthwise length of the lane Lo) identified by the recognition unit 31 and the number of lanes of the travel road Rd1 as indicated by map information such as the map information database 24. For example, the deviation amount calculator 32 uses the values ​​obtained by the equation (number of lanes n1 of the travel road Rd1 × lane width w) / 2 as the first boundary distance dl and the second boundary distance dr. The number of lanes n1 of the travel road Rd1 can be, for example, the number of lanes specified for the link used in calculating the deviation amount (link Lk10 in the above example). Specifically, the deviation amount calculator 32 sets the first boundary distance dl and the second boundary distance dr based on the lane width w identified by the recognition unit 31 and the number of lanes n1 of the travel road Rd1 as indicated by map information such as the map information database 24.

[0115] In this manner, by setting the first boundary distance d1 and the second boundary distance dr based on the lane width w and the number of lanes n1 of the travel road Rd1 in the map information such as the map information database 24, even if the recognition unit 31 cannot recognize the entire width direction of the travel road Rd1, it is possible to set appropriate first boundary distance d1 and second boundary distance dr. Furthermore, even if the map information such as the map information database 24 does not include information indicating the first boundary distance d1 and the second boundary distance dr, it is possible to set appropriate first boundary distance d1 and second boundary distance dr.

[0116] Furthermore, for example, if the recognition unit 31 can recognize the entire width direction of the travel road Rd1, the deviation amount calculation unit 32 may set the first boundary distance d1 and the second boundary distance dr based on the recognition result of the recognition unit 31. Furthermore, if map information such as the map information database 24 includes information indicating the first boundary distance d1 and the second boundary distance dr, the deviation amount calculation unit 32 may set the first boundary distance d1 and the second boundary distance dr based on the map information.

[0117] However, some traffic lights Sn, while corresponding to the travel road Rd1, are located on the opposite side of the opposing road Rd2 (e.g., on the opposing road Rd2), which has an opposite travel direction from the travel road Rd1. Therefore, even if the traffic light Sn is located on the opposite road Rd2, if it corresponds to the travel road Rd1, it is desirable to determine that it is a traffic light corresponding to the travel road Rd1. Therefore, the control device 30 may also perform the following processing, for example.

[0118] Figure 4 3 is a diagram showing a third example of processing implemented by the functional units of the control device 30. Figure 4 In the example shown, the travel road Rd1 on which the vehicle 1 travels is a four-lane road having a first lane Ln11 , a second lane Ln12 , a third lane Ln13 , and a fourth lane Ln14 as the host lane Lo on which the vehicle 1 travels.

[0119] In this example, there is an oncoming road Rd2 running parallel to the traveling road Rd1. Like the traveling road Rd1, the oncoming road Rd2 is also a four-lane road, comprising a first lane Ln21, a second lane Ln22, a third lane Ln23, and a fourth lane Ln24. In the third lane Ln23 of the oncoming road Rd2, another vehicle OV is traveling in the opposite direction of the vehicle 1. Furthermore, a central median Ms exists between the traveling road Rd1 and the oncoming road Rd2.

[0120] Assuming that the values ​​calculated by the above-mentioned formula (number of lanes n1 of the traveling road Rd1 × width w of the current lane) / 2 are set as the first boundary distance dl and the second boundary distance dr, if the traffic light Sn corresponding to the traveling road Rd1 is set on the side of the opposite road Rd2, a larger value will be calculated as the deviation, making it difficult to determine that the traffic light Sn is the traffic light corresponding to the traveling road Rd1.

[0121] Therefore, when an opposing road Rd2, which travels in an opposite direction to the driving road Rd1, exists around the vehicle 1, the deviation amount calculation unit 32 may make the boundary distance corresponding to the driving road boundary closer to the opposing road Rd2, between the left driving road boundary L1 (one driving road boundary in the width direction of the driving road Rd1) and the right driving road boundary L2 (the other driving road boundary) in the width direction of the driving road Rd1, longer than when there is no opposing road Rd2. In this way, even if the traffic light Sn corresponding to the driving road Rd1 is located on the opposite road Rd2 side, the traffic light Sn can be easily determined to be the traffic light corresponding to the driving road Rd1.

[0122] Specifically, in the case of this example, the driving road boundary on the side closer to the opposite road Rd2 between the left driving road boundary L1 and the right driving road boundary L2 is the right driving road boundary L2. Therefore, the deviation amount calculation unit 32 makes the boundary distance corresponding to the right driving road boundary L2, that is, the second boundary distance dr, greater than the case where the opposite road Rd2 does not exist.

[0123] For example, the deviation amount calculation unit 32 sets the first boundary distance d1 corresponding to the left side driving road boundary L1 which is the driving road boundary away from the oncoming road Rd2 to the value obtained by the formula (number of lanes n1 of the driving road Rd1×own lane width w) / 2 as described above.

[0124] Meanwhile, the deviation calculation unit 32 sets the second boundary distance dr corresponding to the right-side driving road boundary L2, which is the driving road boundary closest to the oncoming road Rd2, to a value calculated, for example, by the formula: r + (number of lanes n2 of the oncoming road Rd2 × lane width w) / 2. Here, the number of lanes n2 of the oncoming road Rd2 can be the number of lanes set for the road segment Lk30 corresponding to the oncoming road Rd2. Specifically, the deviation calculation unit 32 increases the boundary distance corresponding to the driving road boundary closest to the oncoming road Rd2 based on the lane width w of the oncoming road Rd2 identified by the recognition unit 31 and the number of lanes n2 of the oncoming road Rd2 indicated in the map information database 24 or other information.

[0125] In addition, r is, for example, the distance between the section Lk20 corresponding to the traveling road Rd1 and the section Lk30 corresponding to the opposite road Rd2, and can be calculated as the distance between the line segment connecting the nodes at both ends of the section Lk20 and the line segment connecting the nodes at both ends of the section Lk30.

[0126] In this way, Figure 4 As shown, the right driving road boundary L2 can be shifted toward the opposite road Rd2. Thus, even if the traffic light Sn corresponding to the driving road Rd1 is located on the opposite road Rd2, a large value can be suppressed from being calculated as the amount of deviation, making it easier to determine that the traffic light Sn is the traffic light corresponding to the driving road Rd1.

[0127] In addition, when the oncoming road Rd2 exists around the vehicle 1, the deviation amount calculation unit 32 increases the boundary distance corresponding to the boundary of the driving road on the side close to the oncoming road Rd2 based on the lane width w recognized by the recognition unit 31 and the lane number n2 of the oncoming road Rd2 indicated by the map information such as the map information database 24. Therefore, even if the recognition unit 31 cannot recognize the oncoming road Rd2, the boundary distance corresponding to the boundary of the driving road on the side close to the oncoming road Rd2 can be appropriately set.

[0128] Next, an example of the first evaluation value derived by the evaluation value deriving unit 33 will be described. Figure 5 : is a diagram showing an example of the first evaluation value derived by the evaluation value deriving unit 33. Figure 5 In FIG, the vertical axis represents the magnitude of the first evaluation value, and the horizontal axis represents the magnitude of the deviation.

[0129] When the deviation calculated by the deviation calculation unit 32 is equal to or less than "0", the evaluation value deriving unit 33 derives the first evaluation value as "1", for example. Here, "1" is the maximum value of the first evaluation value. Figure 5 In FIG. 1 , the illustration of the first evaluation value when the deviation amount is in a negative region is omitted.

[0130] On the other hand, when the deviation calculated by the deviation calculation unit 32 does not take a negative value (in other words, takes a value greater than or equal to "0"), the evaluation value derivation unit 33 converts the deviation calculated by 1 / exp(DEV×dist 2 ) is derived as the first evaluation value. In this formula, dist is the deviation calculated by the deviation calculation unit 32. In addition, DEV is the standard deviation preset by the manufacturer of the vehicle 1.

[0131] According to such evaluation value deriving unit 33, as shown in FIG. Figure 5 As shown, when the deviation calculated by the deviation calculation unit 32 is within the first range 501 close to "0", the decrease in the first evaluation value per unit deviation (for example, 1 [m]) can be reduced. Figure 5 As shown, when the deviation calculated by the deviation calculation unit 32 is within the second range 502 which is further from “0” than the first range 501 , the amount of decrease in the first evaluation value per unit deviation can be increased.

[0132] Therefore, for example, even if the deviation calculated by the deviation calculation unit 32 deviates from the first range 501 (i.e., near "0") due to errors in the recognition accuracy of the recognition unit 31, a first evaluation value with a larger value can be derived, making it easier to identify the traffic light as corresponding to the travel road Rd1. Furthermore, if the deviation is excessively large, exceeding the first range 501, a first evaluation value with a smaller value can be derived, making it harder to identify the traffic light as corresponding to the travel road Rd1. In other words, an appropriate first evaluation value can be obtained regardless of whether the deviation is within the first range 501 or not.

[0133] Alternatively, the recognition unit 31 may identify a traffic light Sn located at the intersection of the travel road Rd1 and a road other than the travel road Rd1. When a traffic light Sn located at the intersection of the travel road Rd1 and another road is identified, the deviation calculation unit 32 may calculate the deviation of the traffic light Sn from the other road in the same manner as the deviation of the traffic light Sn from the travel road Rd1. However, it should be noted that in this case, the road segments used for calculating the traffic light offset and deviation need to be those corresponding to the other road, not the road segments corresponding to the travel road Rd1. Furthermore, in this case, the evaluation value derivation unit 33 may derive a second evaluation value, similar to the first evaluation value, indicating the degree of association between the traffic light Sn and the other road, based on the deviation of the traffic light Sn from the other road.

[0134] Furthermore, in this case, if the first evaluation value is greater than the second evaluation value, the determination unit 34 may determine that the identified traffic light Sn is the traffic light corresponding to the travel road Rd1. In this way, even if a traffic light Sn is installed at the intersection of the travel road Rd1 and another road, it is possible to accurately determine whether the traffic light Sn is the traffic light corresponding to the travel road Rd1.

[0135] Figure 6 : is a diagram showing an example of a traffic light Sn. Figure 6 As shown, the traffic light Sn may include a main body 610 having a plurality of lighting parts 611 to 613 and a support part 620 that supports the main body 610 .

[0136] The lighting portion 611 is a portion of the traffic light Sn that lights up (in other words, emits light) in a green lighting color, for example, corresponding to the "go" indication, and is provided to the left of the center position 610c of the main body 610. Here, the center position 610c of the main body 610 is, for example, the center in the width direction of the housing that implements the main body 610.

[0137] The lighting portion 612 is a portion of the traffic light Sn that is illuminated, for example, in a yellow color corresponding to the instruction "Stop if safe to stop," and is provided so as to overlap with the center position 610c of the main body 610 when the traffic light Sn is viewed from the front. Furthermore, the lighting portion 613 is a portion of the traffic light Sn that is illuminated, for example, in a red color corresponding to the instruction "Stop," and is provided to the right of the center position 610c of the main body 610.

[0138] The traffic light Sn can be constructed such that the light emitting devices (eg, LEDs) of the lighting parts 611 to 613 are mounted on a housing serving as a main body 610 , and the main body 610 is supported by a support part 620 such as a support column extending vertically from the ground Gd.

[0139] The recognition unit 31 can recognize a traffic light Sn having a main body 610 and a support 620. Furthermore, the recognition unit 31 can also distinguish between the main body 610 and the support 620. Furthermore, if the recognition unit 31 can distinguish between the main body 610 and the support 620, the recognition unit 31 can also determine the location corresponding to the traffic light Sn based on the center position 610c of the main body 610. As an example, the recognition unit 31 can also determine the latitude and longitude of the location corresponding to the center position 610c of the main body 610 as the location corresponding to the traffic light Sn. In this way, even if the traffic light Sn includes a support 620 that supports the main body 610 (for example, if the support 620 is large), the location corresponding to the traffic light Sn can be appropriately determined.

[0140] In addition, the identification unit 31 may determine the location corresponding to the traffic light Sn based on the center position 610c of the main body 610 when the main body 610 can be identified; on the other hand, when the main body 610 cannot be identified and only any one of the multiple lighting units 611 to 613 can be identified, determine the location corresponding to the traffic light Sn based on the position and lighting color of the identified lighting unit.

[0141] For example, suppose the recognition unit 31 fails to recognize the main body 610 and only recognizes the lighting portion 611, which is illuminated in green. In this case, the recognition unit 31 may determine the location corresponding to the position offset to the right by a predetermined distance x1 from the center position 611c of the lighting portion 611 (e.g., the center in the width direction of the lighting portion 611) as the location corresponding to the traffic light Sn. The predetermined distance x1 is predetermined by the manufacturer of the vehicle 1, for example, taking into account the typical spacing between the center position 610c of the main body 610 and the center position 611c of the lighting portion 611.

[0142] As another example, suppose the recognition unit 31 fails to recognize the main body 610 and only recognizes the lighting portion 613, which is illuminated in red. In this case, the recognition unit 31 may also identify the location corresponding to a position offset to the left by a predetermined distance x2 from the center position 613c of the lighting portion 613 (e.g., the center in the width direction of the lighting portion 613) as the location corresponding to the traffic light Sn. The predetermined distance x2 is predetermined by the manufacturer of the vehicle 1, for example, taking into account the typical spacing between the center position 610c of the main body 610 and the center position 613c of the lighting portion 613.

[0143] As another example, assume that the recognition unit 31 cannot recognize the main body 610 and can only recognize the lighting unit 612 that is illuminated in yellow. In this case, the recognition unit 31 may also determine the location corresponding to the center position of the lighting unit 612 (for example, the center position 610c of the main body 610) as the location corresponding to the traffic light Sn.

[0144] In this way, when the main body 610 cannot be identified and only any one of the multiple lighting parts 611~613 can be identified, the location corresponding to the traffic light Sn is determined based on the position and lighting color of the identified lighting part. Therefore, even if the main body 610 of the traffic light Sn cannot be identified by the identification unit 31, the location corresponding to the traffic light Sn can be appropriately determined.

[0145] Alternatively, the recognition unit 31 may correct the point corresponding to the traffic light Sn based on the lane position of the own lane Lo in the travel road Rd1. In this case, the deviation amount calculation unit 32 calculates the deviation amount, etc., using the point corresponding to the corrected traffic light Sn.

[0146] As an example, assume that the driving road Rd1 is a three-lane road, and the leftmost lane of the three lanes is the driver's lane Lo. In this case, the recognition unit 31 may use a location offset to the right by a predetermined distance (e.g., 3 m) from the location corresponding to the traffic light Sn determined above as the location corresponding to the corrected traffic light Sn.

[0147] As another example, assume that the driving road Rd1 is a three-lane road, and the rightmost lane of the three lanes is the driver's lane Lo. In this case, the recognition unit 31 may also use a location offset to the left by a predetermined distance (e.g., 3 m) from the location corresponding to the traffic light Sn determined above as the location corresponding to the corrected traffic light Sn.

[0148] Furthermore, as another example, assume that the travel road Rd1 is a three-lane road, and the center lane between the left lane and the right lane is the own lane Lo. In this case, the recognition unit 31 may use the location corresponding to the traffic light Sn determined as described above as the location corresponding to the traffic light Sn without correction.

[0149] By correcting the point corresponding to the traffic light Sn based on the lane position of the own lane Lo on the travel road Rd1 in this manner, an appropriate position can be obtained as the point corresponding to the traffic light Sn regardless of the lane position of the own lane Lo on the travel road Rd1.

[0150] [4. Example of Processing Procedures of the Control Device]

[0151] Next, an example of the processing procedure of the control device 30 will be described. Figure 7 This is a flowchart (part 1) showing an example of a processing procedure of the control device 30 . Figure 8 This is a flowchart (part 2) showing an example of the processing procedure of the control device 30. For example, when the ignition power of the vehicle 1 is turned on, the control device 30 executes the following in a predetermined cycle: Figure 7 and Figure 8 A series of processing is shown.

[0152] like Figure 7 As shown, the control device 30 first determines whether the traffic light Sn existing around the vehicle 1 is recognized (step S1). If it is determined that the traffic light Sn is not recognized (step S1: No), the control device 30 directly ends the process. Figure 7 and Figure 8 A series of processing shown.

[0153] When it is determined that the traffic light Sn is recognized (step S1: yes), the control device 30 identifies the lane position of the own lane Lo (i.e., the lane in which the vehicle 1 is traveling) on ​​the driving road Rd1 (step S2), and corrects the location corresponding to the traffic light Sn based on the recognized lane position of the own lane Lo (step S3), and enters the processing of step S4.

[0154] Next, the control device 30 derives a first boundary distance dl corresponding to the left road boundary L1 and a second boundary distance dr corresponding to the right road boundary L2 based on the number of lanes n1 and the lane width w of the road Rd1 (step S4 ).

[0155] Next, the control device 30 determines whether the oncoming road Rd2 exists around the vehicle 1 (step S5 ). If it is determined that the oncoming road Rd2 does not exist around the vehicle 1 (step S5 : No), the control device 30 directly proceeds to the process of step S7 .

[0156] On the other hand, when it is determined that there is an oncoming road Rd2 nearby (step S5: Yes), the control device 30 makes the boundary distance corresponding to the driving road boundary on the side close to the oncoming road Rd2 longer than when there is no oncoming road Rd2 (step S6), and enters the processing of step S7.

[0157] Next, the control device 30 derives the deviation amount of the traffic light Sn from the travel road Rd1 based on the derived first boundary distance d1 or second boundary distance dr, and derives a first evaluation value for the traffic light Sn based on the deviation amount (step S7 ).

[0158] Next, the control device 30 determines whether the recognized traffic light Sn is a traffic light located at the intersection of the travel road Rd1 and another road (step S8). If the traffic light Sn is determined not to be a traffic light located at the intersection of the travel road Rd1 and another road (step S8: No), the control device 30 determines whether the derived first evaluation value is equal to or greater than a threshold value (step S9).

[0159] Then, when it is determined that the first evaluation value is greater than the threshold value (step S9: Yes), the control device 30 determines that the recognized traffic light Sn is the traffic light corresponding to the travel road Rd1 (step S10), and ends the process. Figure 7 and Figure 8 On the other hand, if it is determined that the first evaluation value is less than the threshold value (step S9: No), the control device 30 determines that the identified traffic light Sn is not the traffic light corresponding to the driving road Rd1 (step S11), and ends. Figure 7 and Figure 8 A series of processing shown.

[0160] In addition, in the process of step S8, if it is determined that the traffic light Sn is a traffic light installed at the intersection of the travel road Rd1 and another road (step S8: Yes), the control device 30 enters Figure 8 The process of step S12 shown in the figure derives the deviation of the traffic light Sn from the other roads and, based on this deviation, derives a second evaluation value for the traffic light Sn (step S12). It should be noted that the process of step S12 can be basically the same as the process of step S7, but the road segments used to calculate the traffic light offset and deviation need to be segments corresponding to the other roads.

[0161] Next, the control device 30 compares the first evaluation value derived by the process of step S7 with the second evaluation value derived by the process of step S12 , and determines whether the first evaluation value is greater than the second evaluation value (step S13 ).

[0162] If it is determined that the first evaluation value is greater than the second evaluation value (step S13: Yes), the control device 30 determines that the recognized traffic light Sn is the traffic light corresponding to the travel road Rd1 (step S14), and ends the process. Figure 7 and Figure 8 In this case, the control device 30 may further determine whether the first evaluation value is equal to or greater than a threshold value, and determine that the recognized traffic light Sn is the traffic light corresponding to the travel road Rd1 based on the condition that the first evaluation value is equal to or greater than the threshold value.

[0163] On the other hand, if it is determined that the first evaluation value is less than the second evaluation value (step S13: No), the control device 30 determines that the recognized traffic light Sn is a traffic light corresponding to another road (step S15), and ends the process. Figure 7 and Figure 8 A series of processing shown.

[0164] As described above, the control device 30 of this embodiment can appropriately determine whether a traffic light Sn located near the vehicle 1 corresponds to the travel road Rd1, taking into account the amount of deviation of the traffic light Sn from the travel road Rd1. Therefore, even without pre-requisite traffic light location information, the vehicle 1 can be appropriately controlled based on the traffic light corresponding to the travel road Rd1. This can improve traffic safety and contribute to the development of a sustainable transportation system.

[0165] Furthermore, the control method described in this embodiment can be implemented by executing a pre-prepared program (control program) on a computer. This control program is stored, for example, in a computer-readable storage medium and executed by reading from the storage medium. Furthermore, this control program can be provided in the form of a non-volatile (non-temporary) storage medium such as a flash memory, or provided via a network such as the Internet. Furthermore, in this embodiment, the computer that executes this control program is the control device 30 (e.g., the processor of the control device 30), but this is not limiting. For example, the computer that executes this control program can be included in the vehicle 1 or in an external device 2 that can communicate with the vehicle 1.

[0166] While one embodiment of the present invention has been described above, the present invention is not limited to the aforementioned embodiment. It is apparent that those skilled in the art will be able to devise various variations or modifications within the scope of the technical solution, and it should be understood that these variations and modifications also fall within the technical scope of the present invention.

[0167] For example, the methods for calculating the deviation amount and deriving the first evaluation value described in the above embodiments are merely examples and are not limited to the methods described in the examples. Specifically, for example, the deviation amount can be calculated without particular limitation, as long as the degree to which the recognized traffic light Sn deviates from the travel road Rd1 can be quantified. Similarly, the first evaluation value can be derived without particular limitation, as long as the degree of correlation between the recognized traffic light Sn and the travel road Rd1 can be quantified.

[0168] This specification includes at least the following items: In addition, the components corresponding to those in the above-mentioned embodiment are shown in parentheses, but the present invention is not limited thereto.

[0169] (1) A vehicle control device (control device 30) for controlling a vehicle (vehicle 1), comprising:

[0170] an identification unit (identification unit 31 ) for identifying a surrounding condition of the vehicle;

[0171] a deviation amount calculation unit (deviation amount calculation unit 32 ) for calculating a deviation amount of the traffic light relative to the road on which the vehicle is traveling, when the traffic light is recognized by the recognition unit;

[0172] a determination unit (determination unit 34 ) that determines whether the traffic light is a traffic light corresponding to the travel road based on the deviation amount calculated by the deviation amount calculation unit; and

[0173] A vehicle control unit (vehicle control unit 35 ) controls the vehicle based on the determination result of the determination unit.

[0174] According to (1), it is possible to consider the amount of deviation of traffic lights around the vehicle relative to the road on which it is traveling, and thus appropriately determine whether the traffic light corresponds to the road on which it is traveling. Therefore, even without pre-prepared traffic light location information, it is possible to appropriately control the vehicle based on the traffic light corresponding to the road on which it is traveling. This can improve traffic safety and contribute to the development of a sustainable transportation system.

[0175] (2) The vehicle control device according to (1), wherein:

[0176] The deviation amount calculation unit calculates a distance between a point corresponding to the traffic light and a travel road boundary of the travel road as the deviation amount.

[0177] According to (2), an appropriate value can be calculated as the deviation amount of the traffic light relative to the travel road.

[0178] (3) The vehicle control device according to (2), wherein:

[0179] The vehicle control device is configured to be able to refer to map information (map information database 24) including road network information representing each road by a combination of nodes and links connecting the nodes.

[0180] The deviation amount calculation unit sets a line obtained by offsetting a target road segment by a first boundary distance toward one side in a width direction of the driving road as a driving road boundary on one side of the driving road, and sets a line obtained by offsetting a target road segment by a second boundary distance toward the other side in the width direction of the driving road as a driving road boundary on the other side of the driving road, wherein the target road segment connects a node closest to the traffic light and a node second closest to the traffic light among nodes of the driving road.

[0181] The deviation amount calculation unit calculates the deviation amount as the difference between the minimum distance from the target road section to the location corresponding to the traffic light and a boundary distance corresponding to the driving road boundary on the one side and the driving road boundary on the other side that is close to the location corresponding to the traffic light.

[0182] According to (3), the further the location corresponding to the recognized traffic light is from the target link beyond the travel road boundary, the larger the deviation can be calculated. Therefore, an appropriate value can be calculated as the deviation.

[0183] (4) The vehicle control device according to (3), wherein:

[0184] The map information includes information indicating the number of lanes on each road.

[0185] The deviation amount calculation unit sets the first boundary distance and the second boundary distance based on the widthwise length of the own lane recognized by the recognition unit and the number of lanes of the travel road indicated by the map information.

[0186] According to (4), even when the recognition unit cannot recognize the entire width of the road, it is possible to set appropriate first and second boundary distances. In addition, even when the map information does not include information indicating the first and second boundary distances, it is possible to set appropriate first and second boundary distances.

[0187] (5) The vehicle control device according to (3), wherein:

[0188] When an opposite road whose travel direction is opposite to that of the driving road exists around the vehicle, the deviation amount calculation unit makes the boundary distance corresponding to the driving road boundary close to the opposite road among the driving road boundary on the one side and the driving road boundary on the other side larger than when the opposite road does not exist.

[0189] According to (5), even when the traffic light corresponding to the travel road is installed on the opposite road side, it is possible to suppress a large value from being calculated as the deviation amount, thereby making it easier to determine that the traffic light is the traffic light corresponding to the travel road.

[0190] (6) The vehicle control device according to (5), wherein:

[0191] The map information includes information indicating the number of lanes on each road.

[0192] The deviation amount calculation unit increases a boundary distance corresponding to a travel road boundary close to the oncoming road based on the widthwise length of the own lane recognized by the recognition unit and the number of lanes of the oncoming road indicated by the map information.

[0193] According to (6), even when the recognition unit cannot recognize the oncoming road, the boundary distance corresponding to the boundary of the traveling road close to the oncoming road can be appropriately set.

[0194] (7) The vehicle control device according to any one of (1) to (6), wherein:

[0195] The vehicle control device further comprises:

[0196] an evaluation value deriving unit (evaluation value deriving unit 33 ) for deriving a first evaluation value indicating a degree of association between the traffic light and the travel road based on the deviation amount calculated by the deviation amount calculating unit;

[0197] The determination unit determines whether the traffic light is a traffic light corresponding to the driving road based on the first evaluation value derived by the evaluation value deriving unit.

[0198] According to (7), whether or not the traffic light corresponds to the travel route can be determined with high accuracy, compared to a case where whether or not the traffic light corresponds to the travel route is determined based solely on the deviation amount calculated by the deviation amount calculation unit.

[0199] (8) The vehicle control device according to (7), wherein:

[0200] The larger the first evaluation value is, the higher the degree of association is. When the deviation is 0, the first evaluation value takes the maximum value.

[0201] When the deviation is within a first range close to 0, the evaluation value deriving unit reduces the amount of decrease in the first evaluation value per unit deviation.

[0202] When the deviation is within a second range further from 0 than the first range, the evaluation value deriving unit increases the amount of decrease in the first evaluation value per unit deviation.

[0203] According to (8), for example, even if the deviation calculated by the deviation calculation unit deviates from the first range (i.e., near 0) due to errors in the recognition accuracy of the recognition unit, a first evaluation value with a larger value that is easily determined to be a traffic light corresponding to the travel route can be derived. In addition, if the deviation is too large and exceeds the first range, a first evaluation value with a smaller value that is difficult to determine to be a traffic light corresponding to the travel route can be derived. In other words, regardless of whether the deviation is within the first range, an appropriate value can be obtained as the first evaluation value.

[0204] (9) The vehicle control device according to (7) or (8), wherein:

[0205] When the traffic light provided at the intersection of the travel road and another road is recognized, the deviation amount calculation unit further calculates the deviation amount of the traffic light relative to the other road.

[0206] The evaluation value deriving unit further derives a second evaluation value indicating a degree of association between the traffic light and the other road based on the amount of deviation of the traffic light from the other road.

[0207] When the first evaluation value is greater than the second evaluation value, the determination unit determines that the traffic light is a traffic light corresponding to the travel road.

[0208] According to (9), even when a traffic light is installed at an intersection between a traveling road and another road, it is possible to accurately determine whether the traffic light is a traffic light corresponding to the traveling road.

[0209] (10) The vehicle control device according to (2), wherein:

[0210] The recognition unit can recognize the traffic light including a main body (main body 610) having a plurality of lighting units (lighting units 611 to 613) and a support unit (support unit 620) supporting the main body, and can distinguish and recognize the main body from the support unit.

[0211] The recognition unit specifies the location corresponding to the traffic light based on the recognized center position of the main body (center position 610 c ).

[0212] According to (10), even when the traffic light has a support portion that supports the main body (for example, when the support portion is large), the location corresponding to the traffic light can be appropriately determined.

[0213] (11) The vehicle control device according to (10), wherein:

[0214] When the main body is recognized, the recognition unit determines the location corresponding to the traffic light based on the center position of the main body.

[0215] When the main body cannot be recognized and only one of the plurality of lighting units is recognized, the recognition unit specifies the location corresponding to the traffic light based on the position and lighting color of the recognized lighting unit.

[0216] According to (11), even when the main body of the traffic light cannot be recognized by the recognition unit, the location corresponding to the traffic light can be appropriately specified.

[0217] (12) The vehicle control device according to (2), wherein:

[0218] The recognition unit corrects the point corresponding to the traffic light based on a lane position of a host lane on the driving road.

[0219] According to (12), regardless of the lane position of the own lane on the travel road, an appropriate position can be obtained as the point corresponding to the traffic light Sn.

[0220] (13) A control method in which a computer (control device 30) for controlling a vehicle performs the following processing:

[0221] Identifying the surrounding conditions of the vehicle (step S1);

[0222] When a traffic light is identified, calculating a deviation of the traffic light from the road on which the vehicle is traveling (step S7);

[0223] Based on the deviation, determining whether the traffic light is a traffic light corresponding to the driving road (steps S9, S10); and

[0224] The vehicle is controlled based on a determination result of the determination.

[0225] According to (13), it is possible to consider the amount of deviation of traffic lights around the vehicle relative to the road on which it is traveling, and thus appropriately determine whether the traffic light corresponds to the road on which it is traveling. Therefore, even without pre-prepared traffic light location information, it is possible to appropriately control the vehicle based on the traffic light corresponding to the road on which it is traveling. This can improve traffic safety and contribute to the development of a sustainable transportation system.

[0226] (14) A control program product storing a control program that causes a computer (control device 30) for controlling a vehicle to perform the following processing:

[0227] Identifying the surrounding conditions of the vehicle (step S1);

[0228] When a traffic light is identified, calculating a deviation of the traffic light from the road on which the vehicle is traveling (step S7);

[0229] Based on the deviation, determining whether the traffic light is a traffic light corresponding to the driving road (steps S9, S10); and

[0230] The vehicle is controlled based on a determination result of the determination.

[0231] According to (14), it is possible to consider the amount of deviation of traffic lights around the vehicle relative to the road on which it is traveling, and thus appropriately determine whether the traffic light corresponds to the road on which it is traveling. Therefore, even without pre-prepared traffic light location information, it is possible to appropriately control the vehicle based on the traffic light corresponding to the road on which it is traveling. This can improve traffic safety and contribute to the development of a sustainable transportation system.

Claims

1. A vehicle control device for controlling a vehicle, comprising: an identification unit that identifies a surrounding condition of the vehicle; a deviation amount calculation unit that calculates a deviation amount of the traffic light relative to the road on which the vehicle is traveling, when the traffic light is recognized by the recognition unit; a determination unit that determines whether the traffic light is a traffic light corresponding to the travel road based on the deviation amount calculated by the deviation amount calculation unit; as well as A vehicle control unit controls the vehicle based on a determination result of the determination unit.

2. The vehicle control device according to claim 1, wherein: The deviation amount calculation unit calculates a distance between a point corresponding to the traffic light and a travel road boundary of the travel road as the deviation amount.

3. The vehicle control device according to claim 2, wherein: The vehicle control device is configured to be able to refer to map information including road network information representing each road by a combination of nodes and links connecting the nodes. The deviation amount calculation unit sets a line obtained by offsetting a target road segment by a first boundary distance toward one side in a width direction of the driving road as a driving road boundary on one side of the driving road, and sets a line obtained by offsetting a target road segment by a second boundary distance toward the other side in the width direction of the driving road as a driving road boundary on the other side of the driving road, wherein the target road segment connects a node closest to the traffic light and a node second closest to the traffic light among nodes of the driving road. The deviation amount calculation unit calculates the deviation amount as the difference between the minimum distance from the target road section to the location corresponding to the traffic light and a boundary distance corresponding to the driving road boundary on the one side and the driving road boundary on the other side that is close to the location corresponding to the traffic light.

4. The vehicle control device according to claim 3, wherein: The map information includes information indicating the number of lanes on each road. The deviation amount calculation unit sets the first boundary distance and the second boundary distance based on the widthwise length of the own lane recognized by the recognition unit and the number of lanes of the travel road indicated by the map information.

5. The vehicle control device according to claim 3, wherein: When an opposite road whose travel direction is opposite to that of the driving road exists around the vehicle, the deviation amount calculation unit makes the boundary distance corresponding to the driving road boundary close to the opposite road among the driving road boundary on the one side and the driving road boundary on the other side larger than when the opposite road does not exist.

6. The vehicle control device according to claim 5, wherein: The map information includes information indicating the number of lanes on each road. The deviation amount calculation unit increases a boundary distance corresponding to a travel road boundary close to the oncoming road based on the widthwise length of the own lane recognized by the recognition unit and the number of lanes of the oncoming road indicated by the map information.

7. The vehicle control device according to any one of claims 1 to 6, wherein: The vehicle control device further comprises: an evaluation value deriving unit that derives a first evaluation value indicating a degree of association between the traffic light and the travel road based on the deviation amount calculated by the deviation amount calculating unit, The determination unit determines whether the traffic light is a traffic light corresponding to the driving road based on the first evaluation value derived by the evaluation value deriving unit.

8. The vehicle control device according to claim 7, wherein: The larger the first evaluation value is, the higher the degree of association is. When the deviation is 0, the first evaluation value takes the maximum value. When the deviation is within a first range close to 0, the evaluation value deriving unit reduces the amount of decrease in the first evaluation value per unit deviation. When the deviation is within a second range further from 0 than the first range, the evaluation value deriving unit increases the amount of decrease in the first evaluation value per unit deviation.

9. The vehicle control device according to claim 7, wherein: When the traffic light provided at the intersection of the travel road and another road is recognized, the deviation amount calculation unit further calculates the deviation amount of the traffic light relative to the other road. The evaluation value deriving unit further derives a second evaluation value indicating a degree of association between the traffic light and the other road based on the amount of deviation of the traffic light from the other road. When the first evaluation value is greater than the second evaluation value, the determination unit determines that the traffic light is a traffic light corresponding to the travel road.

10. The vehicle control device according to claim 2, wherein: The recognition unit can recognize the traffic light including a main body having a plurality of lighting units and a support unit supporting the main body, and can distinguish and recognize the main body from the support unit. The recognition unit specifies a location corresponding to the traffic light based on the recognized center position of the main body.

11. The vehicle control device according to claim 10, wherein: When the main body is recognized, the recognition unit determines the location corresponding to the traffic light based on the center position of the main body. When the main body cannot be recognized and only one of the plurality of lighting units is recognized, the recognition unit specifies the location corresponding to the traffic light based on the position and lighting color of the recognized lighting unit.

12. The vehicle control device according to claim 2, wherein: The recognition unit corrects the point corresponding to the traffic light based on a lane position of a host lane on the driving road.

13. A control method, wherein a computer controlling a vehicle performs the following processing: identifying surrounding conditions of the vehicle; When a traffic light is identified, calculating a deviation of the traffic light from the road on which the vehicle is traveling; determining, based on the deviation, whether the traffic light is a traffic light corresponding to the driving road; as well as The vehicle is controlled based on a determination result of the determination.

14. A control program product comprising a control program, the control program causing a computer controlling a vehicle to perform the following processing: identifying surrounding conditions of the vehicle; When a traffic light is identified, calculating a deviation of the traffic light from the road on which the vehicle is traveling; determining, based on the deviation, whether the traffic light is a traffic light corresponding to the driving road; as well as The vehicle is controlled based on a determination result of the determination.

Images