Control device

Abstract

To improve safety.SOLUTION: A control device 100 detects a right rear end MR and a left rear end ML in a left and right direction of a vehicle M, out of a rear end MRr on a near side to the vehicle M in a front and rear direction of the other vehicle MA, on the basis of output information of a camera 10, derives a first angle θR formed by a direction connecting the vehicle M and the right rear end MR relative to the front and rear direction, and a second angle θL formed by a direction connecting the vehicle M and the left rear ML relative to the front and rear direction, on the basis of the right rear end MR and the left rear end ML, derives a first distance L1 between the rear end MRr of the other vehicle MA and the vehicle M, on the basis of output information of a lader device 12, in order to determine a positional relationship between the vehicle M and the other vehicle MA, on the basis of the first angle θR, the second angle θL, and the first distance L1.SELECTED DRAWING: Figure 7

Description

[Technical field]

[0001] The present invention relates to a control device. [Background technology]

[0002] In recent years, the introduction of autonomous driving and driving assistance for vehicles has progressed rapidly. Patent Document 1 describes a vehicle control device that includes an external environment recognition unit that recognizes the surrounding state of the vehicle, an action planning unit that determines the action that the vehicle should take based on the recognition result of the external environment recognition unit, and a vehicle control unit that controls the driving of the vehicle based on the determination result of the action planning unit. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2019-156192 A Summary of the Invention [Problem to be solved by the invention]

[0004] Devices for recognizing the surrounding conditions of the vehicle include an imaging device and a radar device. From the images captured by the imaging device, it is possible to recognize detection target objects around the vehicle and determine the positional relationship between the vehicle and the detection target objects. Also, from the output of the radar device, it is possible to recognize detection target objects around the vehicle and determine the positional relationship between the vehicle and the detection target objects. By combining the results of these two determinations, it is possible to determine the positional relationship between the vehicle and the detection target objects with high accuracy.

[0005] For example, the lateral distance between the vehicle and the target object may be determined by using the lateral distance between the vehicle and the target object calculated from an image in preference to the lateral distance between the vehicle and the target object calculated from the output of a radar device. In this case, if there is a large error in the lateral distance between the vehicle and the target object calculated from an image, the error in the ultimately determined lateral distance will also be large.

[0006] The present invention aims to improve safety by enabling highly accurate determination of the positional relationship between the vehicle and a detection target object, thereby further improving traffic safety and contributing to the development of a sustainable transportation system. [Means for solving the problem]

[0007] A control device of one embodiment of the present invention is a control device that controls the driving of a vehicle, and includes a processor capable of acquiring output information of an imaging device and a radar device provided on the vehicle, and the processor detects one end and the other end in the left-right direction of the vehicle of a first end of a detection target object around the vehicle that is closer to the vehicle in the fore-and-aft direction of the vehicle based on the output information of the imaging device, derives a first angle formed in a direction connecting the vehicle and the one end with respect to the fore-and-aft direction and a second angle formed in a direction connecting the vehicle and the other end with respect to the fore-and-aft direction, derives a first distance between the first end of the detection target object and the vehicle based on the output information of the radar device, and determines a positional relationship between the vehicle and the detection target based on the first angle, the second angle, and the first distance. Effect of the Invention

[0008] According to the present invention, the positional relationship between the host vehicle and a detection target object can be determined with high accuracy. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a block diagram showing the overall configuration of a vehicle system 1 equipped with a control device 100. [Diagram 2] FIG. 2 is a schematic diagram showing an example of the external configuration of a vehicle M included in the vehicle system 1. As shown in FIG. [Diagram 3] FIG. 3 is a diagram showing an example of the configuration of the first control unit 120 and the second control unit 160. As shown in FIG. [Figure 4] FIG. 4 is a diagram showing a specific example of the operation mode. [Diagram 5] FIG. 5 is a diagram showing a schematic view of an area around the vehicle M that can be recognized by the recognition unit 130. As shown in FIG. [Figure 6] FIG. 6 is a schematic diagram for explaining a method for determining the positional relationship between the vehicle M and another vehicle MA. [Figure 7] FIG. 7 is a flowchart for explaining the operation of the first control unit 120 when determining the positional relationship between the vehicle and another vehicle. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] A vehicle system 1 including a control device 100 according to an embodiment of the present invention will be described below with reference to the drawings. The drawings are to be viewed according to the direction of the symbols. In this specification, for simplicity and clarity of explanation, the front, rear, left and right directions are described according to the direction as seen by the driver of the vehicle M shown in FIG. 2, and in the drawings, the front of the vehicle M is indicated as Fr, the rear as Rr, the left as L, and the right as R.

[0011] <Overall configuration of vehicle system 1> FIG. 1 is a block diagram showing the overall configuration of a vehicle system 1 equipped with a control device 100. FIG. 2 is a schematic diagram showing an example of the external configuration of a vehicle M included in the vehicle system 1. The vehicle M is, for example, a two-wheeled, three-wheeled, or four-wheeled vehicle, and its drive source is an internal combustion engine such as a diesel engine or a gasoline engine, an electric motor, or a combination of these. The electric motor operates using power generated by a generator connected to the internal combustion engine, or discharged power from a secondary battery or a fuel cell. FIG. 2 shows an example in which the vehicle M is a four-wheeled vehicle.

[0012] The vehicle system 1 includes, for example, a camera 10, a radar device 12, a LIDAR (Light Detection and Ranging) 14, a communication device 20, an HMI (Human Machine Interface) 30, a vehicle sensor 40, a driver monitor camera 50, a navigation device 60, an MPU (Map Positioning Unit) 70, a driving operator 80, a control device 100, a driving force output device 200, a brake device 210, and a steering device 220. These devices and equipment are connected to each other by multiple communication lines such as a CAN (Controller Area Network) communication line, serial communication lines, a wireless communication network, etc.

[0013] The camera 10 is a digital camera using an imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor). The camera 10 is attached to any location of the vehicle M. For example, as shown in FIG. 2, the camera 10 is provided near a rearview mirror (not shown) inside the cabin of the vehicle M, and in front of the right door and the left door outside the cabin of the vehicle M. Image information (output information of the camera 10) of the front, right rear side, and left rear side in the traveling direction of the vehicle M captured by the camera 10 is sent to the control device 100.

[0014] The radar device 12 emits radio waves such as millimeter waves around the vehicle M, detects radio waves reflected by an object (reflected waves), and acquires distribution information of the reflection points of the radio waves on the object (distance and direction of each of the multiple reflection points). Laser, microwave, millimeter wave, ultrasonic wave, etc. may be used as the radio waves as appropriate. The radar device 12 is attached to any location of the vehicle M. For example, as shown in FIG. 2, five radar devices 12 are provided, three on the front side and two on the rear side. Output information of the radar devices 12 is sent to the control device 100. Hereinafter, output information of the front radar device 12 is referred to as forward radar information.

[0015] The LIDAR 14 irradiates light (or electromagnetic waves with a wavelength close to that of light) around the vehicle M and measures the scattered light. The LIDAR 14 detects the presence or absence of an object and the distance to the object based on the time between emitting and receiving the light. The irradiated light is, for example, a pulsed laser light. The LIDAR 14 is attached to any position of the vehicle M. For example, as shown in FIG. 2, five LIDARs 14 are provided, two on the front side and three on the rear side. Output information from the LIDARs 14 is sent to the control device 100.

[0016] The communication device 20 communicates with other vehicles in the vicinity of the vehicle M, for example, using a cellular network, a Wi-Fi (registered trademark) network, Bluetooth (registered trademark), DSRC (Dedicated Short Range Communication), etc., or communicates with various server devices via a wireless base station.

[0017] The HMI 30 presents various information to an occupant of the vehicle M and accepts input operations by the occupant. The HMI 30 includes various display devices, a speaker, a buzzer, a touch panel, switches, keys, and the like.

[0018] The vehicle sensor 40 includes a vehicle speed sensor that detects the speed of the vehicle M, an acceleration sensor that detects the acceleration, a yaw rate sensor that detects the angular velocity around a vertical axis, a direction sensor that detects the direction of the vehicle M, and the like.

[0019] The driver monitor camera 50 is a digital camera using an imaging element such as a CCD image sensor or a CMOS image sensor. The driver monitor camera 50 is attached to an arbitrary location of the vehicle M in a position and orientation that allows the head of an occupant (hereinafter, driver) seated in the driver's seat of the vehicle M to be imaged from the front (in an orientation that images the face).

[0020] The navigation device 60 includes, for example, a Global Navigation Satellite System (GNSS) receiver 61, a navigation HMI 62, and a route determination unit 63. The navigation device 60 holds first map information 64 in a storage device such as a hard disk drive (HDD) or a flash memory.

[0021] The GNSS receiver 61 determines the position of the vehicle M based on signals received from GNSS satellites. The position of the vehicle M may be determined or supplemented by an Inertial Navigation System (INS) that uses outputs from the vehicle sensors 40.

[0022] The navigation HMI 62 includes a display device, a speaker, a touch panel, keys, etc. The navigation HMI 62 may be partially or entirely shared with the HMI 30 described above.

[0023] The route determination unit 63 determines, for example, a route (hereinafter, a route on a map) from the position of the vehicle M specified by the GNSS receiver 61 (or any input position) to a destination input by the occupant using the navigation HMI 62, with reference to the first map information 64. The first map information 64 is, for example, information in which road shapes are expressed by links indicating roads and nodes connected by the links. The first map information 64 may include information such as road curvature and POI (Point Of Interest) information. The route on the map is output to the MPU 70.

[0024] The navigation device 60 may provide route guidance based on the route on the map using the navigation HMI 62. The navigation device 60 may transmit the current position and the destination to a navigation server via the communication device 20, and obtain a route equivalent to the route on the map from the navigation server.

[0025] The MPU 70 includes, for example, a recommended lane determination unit 71, and holds second map information 72 in a storage device such as an HDD or a flash memory. The recommended lane determination unit 71 divides the route on the map provided by the navigation device 60 into a plurality of blocks (for example, divided into 100 m intervals in the vehicle travel direction), and determines a recommended lane for each block by referring to the second map information 72. The recommended lane determination unit 71 determines, for example, which lane from the left the vehicle should travel in. When a branch point is present on the route on the map, the recommended lane determination unit 71 determines a recommended lane so that the vehicle M can travel along a reasonable route to proceed to the branch point.

[0026] The second map information 72 is map information with higher accuracy than the first map information 64. The second map information 72 includes, for example, information on the center of lanes or information on boundaries of lanes. The second map information 72 may also include road information, traffic regulation information, address information, facility information, telephone number information, and the like. The second map information 72 may be updated as needed by the communication device 20 communicating with another device.

[0027] Driving operators 80 include, for example, a steering wheel 82 as well as an accelerator pedal, a brake pedal, a shift lever, a turn signal, and other operators. Driving operators 80 are fitted with sensors that detect the amount of operation or the presence or absence of operation, and the detection results are output to control device 100 or some or all of driving force output device 200, braking device 210, and steering device 220.

[0028] The steering wheel 82 does not necessarily have to be annular, and may be in the form of an irregular steering wheel, a joystick, buttons, etc. A steering grip sensor 84 is attached to the steering wheel 82. The steering grip sensor 84 is realized by a capacitance sensor or the like, and outputs a signal to the control device 100 that can detect whether the driver is gripping the steering wheel 82 or not.

[0029] The control device 100 includes at least a processor such as a CPU (Central Processing Unit) and a storage medium necessary for the operation of the processor. The processor executes a program stored in the storage medium to function as the first control unit 120 and the second control unit 160. The control device 100 is not limited to a device in which processing is performed by a single processor, and may be a device in which processing is shared among a plurality of processors.

[0030] <Configuration of First Control Unit 120 and Second Control Unit 160> 3 is a diagram showing an example of the configuration of the first control unit 120 and the second control unit 160. The first control unit 120 includes, for example, a recognition unit 130, an action plan generation unit 140, and a mode determination unit 150. The first control unit 120 realizes, for example, a function based on AI (Artificial Intelligence) and a function based on a pre-given model in parallel.

[0031] For example, the function of "recognizing intersections" may be realized by executing in parallel the recognition of intersections using deep learning etc. and the recognition based on pre-given conditions (such as traffic lights and road markings that can be pattern matched), and by scoring both and evaluating them comprehensively. This ensures the reliability of autonomous driving.

[0032] The recognition unit 130 recognizes, for example, the driving environment in which the vehicle M is driving. For example, the recognition unit 130 recognizes the driving lane of the vehicle M by comparing a pattern of road dividing lines (for example, an arrangement of solid lines and dashed lines) obtained from the second map information 72 with a pattern of road dividing lines around the vehicle M recognized from an image captured by the camera 10. Note that the recognition unit 130 may recognize the driving lane by recognizing road boundaries (road boundaries) including not only road dividing lines but also road dividing lines, shoulders, curbs, median strips, guardrails, etc. In this recognition, the position of the vehicle M obtained from the navigation device 60 and the processing results by the INS may be taken into consideration. In addition, the recognition unit 130 recognizes stop lines, obstacles, red lights, toll booths, and other road phenomena.

[0033] When recognizing the travel lane, the recognition unit 130 recognizes the position and attitude of the vehicle M with respect to the travel lane. For example, the recognition unit 130 may recognize the deviation of the reference point of the vehicle M from the center of the lane and the angle with respect to a line connecting the centers of the lanes in the traveling direction of the vehicle M as the relative position and attitude of the vehicle M with respect to the travel lane. Alternatively, the recognition unit 130 may recognize the position of the reference point of the vehicle M with respect to either side end of the travel lane (a road dividing line or a road boundary) as the relative position of the vehicle M with respect to the travel lane. In the following, as an example, the installation position of the camera 10 is taken as the reference point P.

[0034] The recognition unit 130 recognizes the surrounding environment of the vehicle M based on some or all of the output information of the camera 10, the radar device 12, and the LIDAR 14. For example, the recognition unit 130 recognizes the position of an object around the vehicle M, the type of the object (whether it is a moving object or a stationary object), and the like. The position of the object is recognized as a position on absolute coordinates (an XY plane indicated by a Y axis (Y axis Ay in FIG. 6) that passes through the representative point of the vehicle M and is parallel to the left-right direction, and an X axis (X axis Ax in FIG. 6) that passes through the representative point of the vehicle M and is parallel to the front-rear direction) with a representative point of the vehicle M (such as the center of gravity or the center of the drive shaft) as the origin, and is used for various controls.

[0035] Objects in the vicinity of vehicle M include moving objects (other vehicles traveling nearby, etc.) and stationary objects (objects that form road boundaries such as plants, walls, and median strips, as well as objects that are specifically installed during construction or accidents (cones, guardrails, signs, temporary traffic lights, etc.)). The recognition unit 130 performs a recognition process for moving objects in the vicinity of vehicle M, which includes a first process for recognizing moving objects based on the output of the radar device 12 and a second process for recognizing moving objects based on output information from the camera 10.

[0036] The action plan generating unit 140 generates a target trajectory along which the vehicle M will travel in the future automatically (without relying on the driver's operation) so that the vehicle M will travel in the recommended lane determined by the recommended lane determining unit 71 in principle and can further respond to the surrounding conditions of the vehicle M. The target trajectory includes, for example, a speed element. For example, the target trajectory is expressed as a sequence of points (trajectory points) to be reached by the vehicle M. The trajectory points are points to be reached by the vehicle M at every predetermined travel distance (for example, about several [m]) along the road, and separately, the target speed and target acceleration at every predetermined sampling time (for example, about a few tenths [sec]) are generated as part of the target trajectory. The trajectory points may also be positions to be reached by the vehicle M at the sampling time for every predetermined sampling time. In this case, the information on the target speed and target acceleration is expressed as the interval between the trajectory points.

[0037] The behavior plan generating unit 140 may set an event for autonomous driving when generating the target trajectory. The autonomous driving events include a constant speed driving event, a low speed following driving event, a lane change event, a branching event, a merging event, a takeover event, etc. The behavior plan generating unit 140 generates a target trajectory according to the activated event.

[0038] The mode determination unit 150 determines the driving mode of the vehicle M to be one of a plurality of driving modes that impose different tasks on the driver. Furthermore, when the task of the determined driving mode (hereinafter, the current driving mode) is not executed by the driver, the mode determination unit 150 changes the driving mode of the vehicle M to a driving mode with a heavier task. The mode determination unit 150 is an example of a control state setting unit that selects and sets an automation mode of at least one of the control of the traveling speed and steering of the vehicle M from a plurality of driving modes.

[0039] <Examples of operation modes> FIG. 4 is a diagram showing a specific example of the driving mode. The driving modes of the vehicle M include, for example, five modes, from the first driving mode to the fifth driving mode. The control state, i.e., the degree of automation of the driving control of the vehicle M, is highest in the first driving mode, followed by the second driving mode, the third driving mode, and the fourth driving mode, and is lowest in the fifth driving mode. Conversely, the task imposed on the driver is the lightest in the first driving mode, followed by the second driving mode, the third driving mode, and the fourth driving mode, and is the most severe in the fifth driving mode. Note that in driving modes other than the first driving mode, the control state is not automatic driving, so the responsibility of the control device 100 is to end the control of automatic driving and transition to driving assistance or manual driving. Below, the contents of each driving mode are illustrated.

[0040] In the first driving mode, the vehicle is in an automatic driving state, and the driver is not required to monitor the front or hold the steering wheel 82. However, even in the first driving mode, the driver is required to be in a position where he or she can quickly switch to manual driving in response to a request from the control device 100. Note that automatic driving here means that both steering and acceleration / deceleration are controlled without the driver's operation. The front means the space in the traveling direction of the vehicle M that is visible through the front windshield. The first driving mode is a driving mode that can be executed when conditions are met, such as when the vehicle M is traveling at a predetermined speed or less (for example, about 60 [km / h]) on a motorway such as an expressway, and there is a vehicle ahead to be followed.

[0041] In the second driving mode, the vehicle is in a driving assistance state, and the driver is tasked with monitoring the front of the vehicle M (hereinafter, forward monitoring), but is not tasked with gripping the steering wheel 82. In the third driving mode, the vehicle is in a driving assistance state, and the driver is tasked with the tasks of monitoring the front and gripping the steering wheel 82. The fourth driving mode is a driving mode in which the driver is required to perform some driving operation for at least one of steering and acceleration / deceleration of the vehicle M. For example, in the fourth driving mode, driving assistance such as ACC (Adaptive Cruise Control) and LKAS (Lane Keeping Assist System) is performed. In the fifth driving mode, the vehicle is in a manual driving state in which the driver is required to perform both steering and acceleration / deceleration. In both the fourth driving mode and the fifth driving mode, the driver is naturally tasked with the task of monitoring the front of the vehicle M.

[0042] 3, the second control unit 160 controls the vehicle M to pass the target trajectory generated by the action plan generating unit 140 at the scheduled time. The second control unit 160 includes, for example, an acquisition unit 162, a speed control unit 164, and a steering control unit 166.

[0043] The acquisition unit 162 acquires information on the target trajectory (trajectory points) generated by the action plan generation unit 140, and stores it in a memory (not shown). The speed control unit 164 controls the traveling driving force output device 200 (see FIG. 1) or the brake device 210 (see FIG. 1) based on the speed element associated with the target trajectory stored in the memory. The steering control unit 166 controls the steering device 220 (see FIG. 1) according to the degree of curvature of the target trajectory stored in the memory. The processing of the speed control unit 164 and the steering control unit 166 is realized, for example, by a combination of feedforward control and feedback control.

[0044] In the control device 100, the action plan generating unit 140 and the second control unit 160 together constitute a driving control unit 170. The driving control unit 170 executes control of an automobile lane change in the vehicle M based on the recognition result of the driving environment or the surrounding environment of the vehicle M recognized by the recognition unit 130. In addition, the driving control unit 170 detects the driver's intention to change lanes based on the operation of a driving operator 80 (e.g., a winker lever) by the driver.

[0045] The driving control unit 170 selects one lane change mode from among a plurality of lane change modes with different degrees of involvement by the driver of the vehicle M, and performs driving control (also called lane change control) according to the selected lane change mode. A plurality of lane change modes with different degrees of involvement by the driver of the vehicle M can also be referred to as a plurality of lane change modes with different degrees of automation. The lower the degree of involvement by the driver, the higher the degree of automation, and the greater the degree of involvement by the driver, the lower the degree of automation.

[0046] For example, the multiple lane change modes may include the following three automated lane change modes. The first automated lane change is an intentional automated lane change (ALC-category C) in which the driver of the vehicle M intends to change lanes himself / herself and issues an instruction to start the lane change. In an intentional automated lane change, the driver of the vehicle M determines whether or not to change lanes, taking into consideration the driving conditions of other vehicles, the route to the destination, and the like. If the driver of the vehicle M should change lanes, he / she issues an instruction to start the lane change to the vehicle M by operating the driving operator 80. Based on this instruction, the driving control unit 170 starts the automated lane change at a feasible timing while taking into consideration the surrounding driving conditions.

[0047] The second type of automated lane change is a proposed automated lane change (ALC-category D) in which the driving control unit 170 proposes a lane change and the driver of the vehicle M approves the lane change. In the proposed automated lane change, the driving control unit 170 determines whether or not the lane change should be made based on the driving conditions of other vehicles, the route to the destination, and the like. If the lane change should be made, the driving control unit 170 proposes the lane change to the driver. If the driver of the vehicle M approves the proposal for the lane change, the driver of the vehicle M gives an instruction to start the lane change to the vehicle M by operating an approval switch. The approval switch may be a switch dedicated to approval, or an operator (for example, the driving operator 80) that also serves other functions. Based on this instruction, the driving control unit 170 starts the automated lane change at an executable timing while taking into account the surrounding driving conditions. Therefore, if the driver does not approve the proposal for the lane change, that is, if the driver does not operate the driving operator 80, the automated lane change is not executed.

[0048] The third type of automated lane change is a determined automated lane change (ALC-category E) in which the driving control unit 170 determines a lane change and decides to start the lane change. In a determined automated lane change, the driving control unit 170 determines whether or not to change lanes based on the driving conditions of other vehicles, the route to the destination, and the like. If a lane change is to be made, the driving control unit 170 starts the automated lane change at an executable timing, taking into account the surrounding driving conditions. In the case of a determined automated lane change, the driver of the vehicle M is not involved in the lane change.

[0049] The control device 100 executes an automated lane change according to the driving mode. For example, the control device 100 may execute a judged automated lane change in the first driving mode. The control device 100 may execute a suggested automated lane change in the second driving mode, the third driving mode, and the fourth driving mode. The control device 100 may execute an intended automated lane change in the third driving mode and the fourth driving mode. The control device 100 does not execute any automated lane change in the fifth driving mode.

[0050] Returning to Fig. 1, driving force output device 200 outputs a driving force (torque) for the vehicle to travel to the driving wheels. Driving force output device 200 includes, for example, a combination of an internal combustion engine, an electric motor, a transmission, etc., and an ECU (Electronic Control Unit) that controls these. The ECU controls the above components according to information input from second control unit 160 or information input from driving operator 80.

[0051] Brake device 210 includes, for example, a brake caliper, a cylinder that transmits hydraulic pressure to the brake caliper, an electric motor that generates hydraulic pressure in the cylinder, and a brake ECU. The brake ECU controls the electric motor according to information input from second control unit 160 or information input from driving operator 80, so that a brake torque corresponding to a braking operation is output to each wheel.

[0052] The steering device 220 includes, for example, a steering ECU and an electric motor. The electric motor changes the direction of the steered wheels by applying a force to, for example, a rack and pinion mechanism. The steering ECU drives the electric motor in accordance with information input from the second control unit 160 or information input from the driving operator 80 to change the direction of the steered wheels.

[0053] <Determining the positional relationship with the detection target object> FIG. 5 is a diagram showing a schematic view of an area around the vehicle M that can be recognized by the recognition unit 130. FIG. 5 shows a range 10A in which an object can be detected by the camera 10 and a range 12A in which an object can be detected by the radar device 12. As shown in FIG. 5, the radar device 12 has a wide detection range in the front-rear direction, and the camera 10 has a wide detection range in the left-right direction. Therefore, the front-rear distance between the vehicle M and other vehicles as surrounding detection target objects may be derived more accurately by using the output information of the radar device 12 than by using the output information of the camera 10. Also, the left-right distance between the vehicle M and other vehicles may be derived more accurately by using the output information of the camera 10 than by using the output information of the radar device 12.

[0054] Fig. 6 is a schematic diagram for explaining a method for determining the positional relationship between the vehicle M and another vehicle MA. Fig. 6 shows a state in which a common vehicle MA is recognized based on both image information from the camera 10 and forward radar information from the front radar device 12.

[0055] The first control unit 120 detects one end (right rear end MR in the example of FIG. 6) and the other end (left rear end ML in the example of FIG. 6) in the left-right direction out of a first end (rear end MRr in the example of FIG. 6) on the side closer to the vehicle M in the fore-aft direction as a feature point of the other vehicle MA recognized based on the image information. The first control unit 120 detects a specific end (left front end MZ in the example of FIG. 6) on the side closer to the vehicle M in the left-right direction out of a second end (front end MFr in the example of FIG. 6) on the side farther from the vehicle M in the fore-aft direction as a feature point of the other vehicle MA.

[0056] The first control unit 120 derives a first angle θR (an angle between a straight line passing through the reference point P and extending in the longitudinal direction and a straight line connecting the reference point P and the right rear end MR) in the longitudinal direction in a direction connecting the vehicle M and the right rear end MR based on the right rear end MR detected based on the image information. The first control unit 120 derives a second angle θL (an angle between a straight line passing through the reference point P and extending in the longitudinal direction and a straight line connecting the reference point P and the left rear end ML) in the longitudinal direction in a direction connecting the vehicle M and the left rear end ML based on the left rear end ML detected based on the image information. The first control unit 120 derives a third angle θZ (an angle between a straight line passing through the reference point P and extending in the longitudinal direction and a straight line connecting the reference point P and the left front end MZ) in the longitudinal direction in a direction connecting the vehicle M and the left front end MZ based on the left front end MZ detected based on the forward image information.

[0057] Based on the forward radar information, the first control unit 120 acquires distance information in the longitudinal direction between the other vehicle MA and the vehicle M. The first control unit 120 acquires, as the distance information, a first distance L1 from the reference point P to the rear end MRr and a second distance L2 from the reference point P to the front end MFr.

[0058] The first control unit 120 uses the various information derived in this way to calculate the following formulas (A) and (B) to derive left-right distance information between vehicle M and other vehicle MA (distance YR to the left end of other vehicle MA and distance YL to the right end of other vehicle MA). Using the distance information derived in this way, it becomes possible to determine whether other vehicle MA is traveling in a lane adjacent to the lane in which vehicle M is traveling, or whether other vehicle MA is traveling in a lane adjacent to the adjacent lane, and so on, and driving control using this determination becomes possible. "Tan" indicates tangent.

[0059] YR = L1 × tan θR (A) YL = L1 × tan θL (B)

[0060] The first control unit 120 further performs the calculation of the following formula (C) to derive a distance YZ from the vehicle M to the right front end of the other vehicle MA. YZ = L2 × tan θZ (C)

[0061] Based on the derived distances YZ and YL, the first control unit 120 derives the angle between the traveling direction of the other vehicle MA and the traveling direction (synonymous with the forward / rearward direction) of the vehicle M. For example, if the angle is 0 degrees when the distances YZ and YL match, then when the distance YZ is less than the distance YL, the angle becomes larger in the positive direction as the distance YZ becomes smaller, and when the distance YZ is greater than the distance YL, the angle becomes larger in the negative direction as the distance YZ becomes larger.

[0062] For example, when the first control unit 120 recognizes that the other vehicle MA is traveling in the adjacent lane based on the distance YR and the distance YL, it further uses the above angle to determine whether or not the other vehicle MA is entering the lane in which the vehicle M is traveling from the adjacent lane. For example, if the above angle is equal to or greater than a threshold value greater than 0, it determines that the other vehicle MA is entering in front of the vehicle M, and if the above angle is less than the above threshold value, it determines that the other vehicle MA is not entering in front of the vehicle M. By making the entry determination of the other vehicle MA in this way, for example, when it is determined that the other vehicle MA is entering, it becomes possible to perform driving control such as reducing the speed so as to maintain a distance between the vehicles.

[0063] 7 is a flowchart for explaining the processing of the first control unit 120 when determining the positional relationship between the vehicle and another vehicle. This flowchart shows the operation when the same vehicle MA is recognized based on both the image information and the forward radar information.

[0064] The first control unit 120 judges whether the recognition result of the other vehicle MA recognized based on the image information is normal or not (step S1). For example, the first control unit 120 judges that the recognition result is abnormal when the moving speed of the other vehicle MA exceeds a threshold value or the width of the other vehicle MA in the left-right direction exceeds a threshold value.

[0065] When the first control unit 120 determines that the recognition result is abnormal (step S1: NO), it ends the process. When the first control unit 120 determines that the recognition result is normal (step S1: YES), it detects both ends of the first end of the other vehicle MA (the right rear end MR and the left rear end ML in FIG. 6) and a specific end of the second end of the other vehicle MA (the left front end MZ in FIG. 6) based on the image information (step S2).

[0066] Next, the first control unit 120 judges whether or not both ends of the first end have been detected in step S2 (step S3). For example, the left rear end or right rear end of the other vehicle MA in the image of the other vehicle MA included in the image information may become invisible due to sunlight or an obstacle, and in such a case, the left rear end or right rear end of the other vehicle MA cannot be detected. In such a case, the judgment in step S3 is NO. If the judgment in step S3 is NO (at least one of the ends cannot be detected), the processing is terminated.

[0067] If the first control unit 120 can detect both ends of the first end (step S3: YES), it derives the above-mentioned first angle θR, second angle θL, and third angle θZ based on both ends of the first end and a specific end of the second end (step S4).

[0068] Next, the first control unit 120 judges whether the first angle θR and the second angle θL derived in step S4 are within a predetermined range (step S5). This predetermined range is determined in advance as a range expected when there is another vehicle traveling in a lane adjacent to the lane in which the vehicle M is traveling or in a lane further adjacent thereto. Therefore, when at least one of the first angle θR and the second angle θL exceeds the predetermined range, the first control unit 120 judges that the reliability of at least one of the first angle θR and the second angle θL is low due to some abnormality, and stops judging the positional relationship using these angles. That is, when at least one of the first angle θR and the second angle θL exceeds the predetermined range (step S5: NO), the first control unit 120 ends the process.

[0069] If the first angle θR and the second angle θL are each within a predetermined range (step S5: YES), the first control unit 120 acquires distance information (first distance L1 and second distance L2 in Figure 6) between the other vehicle MA and vehicle M in the forward / backward direction based on the forward radar information (step S6).

[0070] Then, the first control unit 120 determines the positional relationship between the vehicle M and the other vehicle MA as described above based on the distance information acquired in step S6 and the angle information derived in step S4 (step S7). After that, the driving control unit 170 performs driving control of the vehicle M based on the determined positional relationship.

[0071] The first distance L1 and the second distance L2 shown in FIG. 6 can also be derived based on image information. For example, the longitudinal distance to the other vehicle MA can be estimated based on the vertical position of the other vehicle MA in the captured image. However, if there is a gradient on the road on which the vehicle M and the other vehicle MA are traveling, the longitudinal distance to the other vehicle MA that can be estimated from the captured image may include an error. On the other hand, the distance to the other vehicle MA recognized based on the radar device 12 can be obtained with high accuracy even if there is a gradient on the road. In this embodiment, the first control unit 120 derives the distance YL and the distance YR based on the angle information (first angle θR and second angle θL) derived based on the image information and the distance information (first distance L1) derived based on the forward radar information. Since the distance information is not directly obtained from the image information, the distance YL and the distance YR can be derived with high accuracy even if there is a gradient on the road.

[0072] In this embodiment, the first control unit 120 derives the distance YZ based on the angle information (third angle θZ) derived based on the image information and the distance information (second distance L2) derived based on the forward radar information, and can derive the approach angle of the other vehicle MA by comparing the distance YZ with the distance YL. Since the distance YZ is not directly obtained from the image information, it can be derived with high accuracy even if the road has a gradient. As a result, the approach angle can also be derived with high accuracy, improving the reliability of the driving control.

[0073] In this embodiment, the first control unit 120 performs the determination in step S7 only when the first angle θR and the second angle θL are within a predetermined range, thereby making it possible to determine the positional relationship with other vehicles with higher accuracy.

[0074] In this embodiment, the first control unit 120 does not perform the determination in step S7 if it cannot detect at least one of the left and right rear ends of the other vehicle MA, thereby making it possible to determine the positional relationship with the other vehicle with higher accuracy.

[0075] This specification describes at least the following items. Note that, in parentheses, components corresponding to those in the above-mentioned embodiment are shown, but the present invention is not limited to these.

[0076] (1) A control device (control device 100) that controls driving of a vehicle (vehicle M), A processor capable of acquiring output information of an imaging device (camera 10) and a radar device (radar device 12) provided on the vehicle, The processor detects one end (right rear end MR) and the other end (left rear end ML) in a left-right direction of the vehicle of a first end (rear end MRr) of a detection target object (another vehicle MA) around the vehicle that is closer to the vehicle in a front-rear direction of the vehicle based on output information of the imaging device; deriving a first angle (first angle θR) formed in a direction connecting the vehicle and the one end with respect to the longitudinal direction, and a second angle (second angle θL) formed in a direction connecting the vehicle and the other end with respect to the longitudinal direction, based on the one end and the other end; deriving a first distance (first distance L1) between the first end of the detection target object and the vehicle based on output information of the radar device; a control device that determines a positional relationship between the vehicle and the detection target object based on the first angle, the second angle, and the first distance.

[0077] According to (1), the positional relationship with respect to a detection target object can be determined with high accuracy, thereby improving the safety of driving control.

[0078] (2) The control device according to (1), The processor detects a specific end (left front end MZ) that is an end closer to the vehicle in the left-right direction out of a second end (front end MFr) of the detection target object that is farther from the vehicle in the front-rear direction based on output information of the imaging device, Deriving a third angle (third angle θZ) between the vehicle and the specific end portion relative to the longitudinal direction based on the specific end portion; deriving a second distance (second distance L2) between the second end of the detection target object and the vehicle based on output information of the radar device; A control device that determines the positional relationship based on the first angle, the second angle, the first distance, the third angle, and the second distance.

[0079] According to (2), the positional relationship with the detection target object can be determined with higher accuracy.

[0080] (3) The control device according to (2), The processor determines the angle between the direction of travel of the detected object and the direction of travel of the vehicle as the positional relationship, and determines that the detected object will enter the first lane from a second lane adjacent to the first lane in which the vehicle is traveling, based on the angle.

[0081] According to (3), it is possible to determine with high accuracy whether another vehicle traveling in an adjacent lane will enter in front of the vehicle, thereby improving the reliability of driving control.

[0082] (4) A control device according to any one of (1) to (3), The processor performs the determination when the first angle and the second angle are within a predetermined range.

[0083] According to (4), the positional relationship with the detection target object can be determined with higher accuracy.

[0084] (5) A control device according to any one of (1) to (4), The processor stops the determination when at least one of the one end and the other end cannot be detected.

[0085] According to (5), the positional relationship with the detection target object can be determined with higher accuracy. [Explanation of symbols]

[0086] 100 Control device 10. Camera 12 Radar equipment M Vehicle

Claims

1. A control device for controlling vehicle running, A processor capable of acquiring output information of an imaging device and a radar device provided in the vehicle, The processor, detecting one end and another end in a left-right direction of the vehicle of a first end portion of a detection target object in the vicinity of the vehicle in a front-rear direction of the vehicle based on output information of the imaging device; Based on the one end and the other end, a first angle θR formed by a direction connecting the one end and a straight line passing through a reference point of the vehicle with respect to the longitudinal direction and extending in the longitudinal direction, and a second angle θL formed by a direction connecting the other end and a straight line passing through a reference point of the vehicle with respect to the longitudinal direction and extending in the longitudinal direction, deriving a first distance L1 in the front-rear direction between the first end of the detection target object and the vehicle based on output information of the radar device; Based on the first angle θR, the second angle θL, and the first distance L1, deriving, as information indicating a positional relationship between the vehicle and the detection target object, distance information YR in the left-right direction between the vehicle and the one end of the detection target object and distance information YL in the left-right direction between the vehicle and the other end of the detection target object using the following equations (A) and (B): YR=L1×tanθR...(A) YL=L1×tanθL...(B) Control device.

2. The control device according to claim 1 , The processor detects a specific end portion of the second end portion of the detection target object that is farther from the vehicle in the front-rear direction based on output information of the imaging device, the specific end portion being an end portion closer to the vehicle in the left-right direction; Deriving a third angle θZ between a line passing through a reference point of the vehicle with respect to the longitudinal direction and extending in the longitudinal direction and a direction connecting the specific end portion, based on the specific end portion; deriving a second distance L2 in the front-rear direction between the second end of the detection target object and the vehicle based on output information of the radar device; Based on the first angle θR, the second angle θL, the first distance L1, the third angle θZ, and the second distance L2, distance information YZ in the left-right direction between the vehicle and the specific end of the detection target object is derived using the following formula (C) as information indicating the positional relationship. YZ=L2×tanθZ...(C) Control device.

3. The control device according to claim 2, The processor determines the angle between the direction of travel of the detected object and the direction of travel of the vehicle as the positional relationship, and determines that the detected object will enter the first lane from a second lane adjacent to the first lane in which the vehicle is traveling based on the angle.

4. The control device according to claim 1 or 2, The processor derives information indicating the positional relationship when the first angle and the second angle are within a predetermined range.

5. The control device according to claim 1 or 2, When at least one of the one end and the other end cannot be detected, The control device stops deriving the information indicating the positional relationship.

Images