control device

Abstract

The present application provides a control device that achieves an improvement in safety. A control device (100) includes a processor that can acquire output information of a radar device (12) that can detect an object located in the vicinity of a vehicle (M) and a camera (10), the processor performs first processing that identifies a first range including a traffic cone among a plurality of ranges (AR) of a peripheral area (DA) set to the vehicle (M) based on the output information of the radar device (12) and second processing that identifies a second range including the traffic cone among the plurality of ranges (AR) based on the output information of the camera (10), selects a third range from among the plurality of ranges (AR) after the first range is removed based on the first range, and determines the reliability of the identification result of the first range based on the identification result of the second processing for the third range.

Description

Technical Field

[0001] This invention relates to a control device. Background Technology

[0002] In recent years, the adoption of autonomous and assisted driving technologies for vehicles has developed rapidly. As part of these technologies, technologies such as Auto Lane Changing (ALC) have been developed, allowing vehicles to change lanes even without the driver performing steering or other maneuvers.

[0003] Patent Document 1 describes a vehicle control device comprising: an external identification unit that identifies the surrounding conditions of the vehicle; an action planning unit that determines the action that the vehicle should take based on the identification result of the external identification unit; and a vehicle control unit that performs driving control of the vehicle based on the determination result of the action planning unit.

[0004] Existing technical documents

[0005] Patent documents

[0006] Patent Document 1: Japanese Patent Application Publication No. 2019-156192 Summary of the Invention

[0007] The problem that the invention aims to solve

[0008] As in Patent Document 1, identifying sections of the road where driving is restricted due to construction or accidents (in this specification, such sections are defined as driving restriction sections) is important for improving safety when controlling the vehicle's movement.

[0009] The purpose of this invention is to improve safety. Furthermore, it contributes to further improving traffic safety and enabling the development of sustainable transportation systems.

[0010] Methods for solving problems

[0011] One aspect of the present invention is a control device for controlling the driving of a vehicle, wherein the control device comprises: a processor capable of acquiring output information from a first sensor and a second sensor capable of detecting objects located around the vehicle; the processor performing the following operations: performing a first process and a second process, wherein the first process identifies a first range containing a specific object from a plurality of ranges defined in the periphery area of ​​the vehicle based on the output information of the first sensor; the second process identifies a second range containing the specific object from the plurality of ranges based on the output information of the second sensor; selecting a third range from the plurality of ranges after removing the first range based on the first range; and determining the reliability of the identification result of the first range based on the identification result of the second process for the third range.

[0012] Invention Effects

[0013] According to the present invention, vehicle safety can be improved. Attached Figure Description

[0014] Figure 1 This is a block diagram showing the overall structure of the vehicle system 1 equipped with the control device 100.

[0015] Figure 2 This is a schematic diagram showing an example of the external structure of the vehicle M included in the vehicle system 1.

[0016] Figure 3 This is a diagram showing an example of the structure of the first control unit 120 and the second control unit 160.

[0017] Figure 4 This is a diagram showing a specific example of a driving mode.

[0018] Figure 5 This is a schematic diagram showing the area around the vehicle M where the traffic cone can be identified by the identification unit 130.

[0019] Figure 6 This is a schematic diagram representing a segmentation example of the surrounding area DA.

[0020] Figure 7 This is a schematic diagram representing examples of the first and third ranges.

[0021] Figure 8 This is a schematic diagram representing examples of the second and fourth ranges.

[0022] Figure 9 This is a flowchart used to explain the operation of the control device 100.

[0023] Figure 10 It is used for explanation. Figure 9The flowchart shows the operation of the control device 100 after step S8.

[0024] Explanation of reference numerals in the attached figures

[0025] 100 Control device

[0026] 10 cameras

[0027] 12 Radar Devices

[0028] M vehicle Detailed Implementation

[0029] Hereinafter, a vehicle system 1 including a control device 100 as an embodiment of the present invention will be described with reference to the accompanying drawings. The drawings are viewed along the directions indicated by the reference numerals. In this specification, for the sake of simplicity and clarity, the front-back and left-right directions are indicated by the reference numerals from... Figure 2 The direction observed by the driver of vehicle M is recorded. In the attached diagram, the front of vehicle M is denoted as Fr, the rear as Rr, the left as L, and the right as R.

[0030] <Overall Structure of Vehicle System 1>

[0031] Figure 1 This is a block diagram showing the overall structure of the vehicle system 1 equipped with the control device 100. Figure 2 This is a schematic diagram illustrating the external structure of a vehicle M included in vehicle system 1. 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 gasoline engine, an electric motor, or a combination thereof. The electric motor operates using electricity generated by a generator connected to the internal combustion engine, or by discharge electricity from a secondary battery or fuel cell. Figure 2 The example shown is a four-wheeled vehicle, M.

[0032] Vehicle system 1 includes, for example, a camera 10, a radar device 12, a LiDAR (Light Detection and Range) system 14, a communication device 20, an HMI (Human Machine Interface) 30, vehicle sensors 40, a driver monitoring camera 50, a navigation device 60, an MPU (Map Positioning Unit) 70, driving controls 80, a control device 100, a driving force output device 200, a braking device 210, and a steering device 220. These devices and equipment are interconnected via CAN (Controller Area Network) communication lines, serial communication lines, wireless communication networks, etc.

[0033] Camera 10 is, for example, a digital camera utilizing imaging elements such as CCD (Charge Coupled Device) or CMOS (Complementary Metal Oxide Semiconductor). Camera 10 is mounted in any part of the vehicle M. For example, such as... Figure 2 As shown, camera 10 is located near the rearview mirror (not shown) inside the vehicle M, and at the front of the right door and the front of the left door outside the vehicle M. The image information (output information of camera 10) of the vehicle M in the direction of travel in front, to the right rear, and to the left rear, captured by camera 10, is sent to control device 100.

[0034] Radar device 12 radiates millimeter-wave and other radio waves around vehicle M, and obtains information on the distribution of reflection points (distance and orientation of each reflection point) by detecting radio waves reflected from objects (reflected waves). Lasers, microwaves, millimeter waves, and ultrasound can be appropriately used as radio waves. Radar device 12 can be installed at any location on vehicle M. For example, as... Figure 2 As shown, there are five radar devices 12, three on the front and two on the rear. The output information of the radar devices 12 is sent to the control device 100.

[0035] The LIDAR 14 illuminates the periphery of vehicle M with light (or electromagnetic waves of a wavelength close to light) and measures the scattered light. The LIDAR 14 detects the presence or absence of an object and its distance based on the time from emission to reception. The illuminated light can be, for example, a pulsed laser. The LIDAR 14 can be mounted at any location on vehicle M. For example, as... Figure 2 As shown, there are two LIDAR14s on the front and three on the rear, for a total of five. The output information of the LIDAR14s is sent to the control device 100.

[0036] The communication device 20 communicates with other vehicles in the vicinity of vehicle M, for example, using cellular networks, Wi-Fi networks, Bluetooth, DSRC (Dedicated Short Range Communication), etc., or communicates with various server devices via wireless base stations.

[0037] The HMI30 provides various information to the occupants of vehicle M and accepts their input. The HMI30 includes various display devices, speakers, buzzers, touch panels, switches, buttons, etc.

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

[0039] The driver monitoring camera 50 is, for example, a digital camera that utilizes imaging elements such as a CCD image sensor or a CMOS image sensor. The driver monitoring camera 50 is capable of capturing the position and orientation of the head of the occupant (hereinafter referred to as the driver) sitting in the driver's seat of the vehicle M from the front (with the face facing the camera), and can be installed at any location in the vehicle M.

[0040] The navigation device 60 includes, for example, a GNSS (Global Navigation Satellite System) receiver 61, a navigation HMI 62, and a path determination unit 63. The navigation device 60 stores the first map information 64 in a storage device such as an HDD (Hard Disk Drive) or flash memory.

[0041] The GNSS receiver 61 determines the position of vehicle M based on signals received from GNSS satellites. The position of vehicle M can also be determined or supplemented by using the INS (Inertial Navigation System) output from vehicle sensor 40.

[0042] The navigation HMI 62 includes a display device, speakers, a touch panel, buttons, etc. The navigation HMI 62 can also share some or all of the components with the aforementioned HMI 30.

[0043] The route determination unit 63, for example, refers to the first map information 64 to determine the route (hereinafter referred to as the map path) from the position of the vehicle M determined by the GNSS receiver 61 (or any input position) to the destination input by the occupant using the navigation HMI 62. The first map information 64 represents road shape information, for example, by indicating road lines and nodes connected by those lines. The first map information 64 may also include road curvature, POI (Point of Interest) information, etc. The map path is output to the MPU 70.

[0044] The navigation device 60 can also provide route guidance using the navigation HMI 62 based on the path on the map. The navigation device 60 can also send its current location and destination to the navigation server via the communication device 20, and obtain the path from the navigation server that is equivalent to the path on the map.

[0045] MPU 70 includes, for example, a lane recommendation decision unit 71 that stores second map information 72 in a storage device such as an HDD or flash memory. The lane recommendation decision unit 71 divides the path on the map provided by the navigation device 60 into multiple segments (e.g., every 100 [m] in the vehicle's direction of travel) and determines recommended lanes by segment by referring to the second map information 72. The lane recommendation decision unit 71, for example, determines which lane to drive in from the left. When the path on the map has branching points, the lane recommendation decision unit 71 determines the recommended lane in a way that allows the vehicle M to travel on a reasonable path to the branch destination.

[0046] The second map information 72 is map information with higher precision than the first map information 64. The second map information 72 may include, for example, information about the center of a lane or the boundaries of a lane. Furthermore, the second map information 72 may also include road information, traffic control information, residential information, facility information, telephone number information, etc. The second map information 72 can be updated in real time by communicating with other devices through the communication device 20.

[0047] In addition to the steering wheel 82, the driving control unit 80 also includes, for example, an accelerator pedal, a brake pedal, a gear shift lever, turn signals, and other controls. The driving control unit 80 is equipped with sensors that detect the amount of operation or the presence or absence of operation, and the detection results are output to some or all of the control device 100, the driving force output device 200, the braking device 210, and the steering device 220.

[0048] The steering wheel 82 does not necessarily have to be ring-shaped; it can also be an irregularly shaped steering wheel, a lever, a button, or other similar form. A steering grip sensor 84 is installed on the steering wheel 82. The steering grip sensor 84 is implemented using an electrostatic capacitive sensor or similar device, and outputs a signal to the control device 100 that detects whether the driver is holding the steering wheel 82.

[0049] The control device 100 includes at least a processor such as a CPU (Central Processing Unit) and a storage medium required for the operation of the processor. The processor functions as a first control unit 120 and a second control unit 160 by executing programs stored in the storage medium. The control device 100 is not limited to processing by a single processor; it may also utilize multiple processors to distribute the processing.

[0050] <Structure of the first control unit 120 and the second control unit 160>

[0051] Figure 3This diagram illustrates an example of the structure of the first control unit 120 and the second control unit 160. The first control unit 120, for example, includes an identification unit 130, an action plan generation unit 140, and a pattern determination unit 150. The first control unit 120, for example, implements AI (Artificial Intelligence) based functions and functions based on pre-provided models in parallel.

[0052] For example, the function of "intersection recognition" can be achieved by performing intersection recognition based on deep learning and other methods in parallel, as well as recognition based on pre-given conditions (the existence of signals, road signs, etc. that can be pattern matched), and then comprehensively evaluating both by adding scores to both. This ensures the reliability of autonomous driving.

[0053] The recognition unit 130 identifies, for example, the driving environment in which vehicle M is traveling. For instance, the recognition unit 130 identifies the driving lane of vehicle M by comparing the pattern of road markings (e.g., the arrangement of solid and dashed lines) obtained from the second map information 72 with the pattern of road markings surrounding vehicle M identified from the image captured by camera 10. Furthermore, the recognition unit 130 is not limited to recognizing road markings; it can also identify driving lanes by recognizing driving road boundaries (road boundaries) including road markings, shoulders, curbs, median strips, guardrails, etc. In this recognition, the position of vehicle M obtained from navigation device 60 and the processing results of INS (In-Site Management) can also be incorporated. In addition, the recognition unit 130 identifies temporary stop lines, obstacles, red lights, toll booths, and other road features.

[0054] When identifying a driving lane, the identification unit 130 identifies the position and orientation of the vehicle M relative to the driving lane. For example, the identification unit 130 may identify the deviation of the vehicle M's reference point from the center of the lane, and the angle formed by the vehicle M's direction of travel relative to the line connecting the centers of the lanes, as the relative position and orientation of the vehicle M relative to the driving lane. Alternatively, the identification unit 130 may identify the position of the vehicle M's reference point relative to either end of the driving lane (road markings or road boundaries) as the relative position of the vehicle M relative to the driving lane.

[0055] The recognition unit 130 identifies the surrounding environment of the vehicle M based on some or all of the output information from the camera 10, radar device 12, and LIDAR 14. For example, the recognition unit 130 identifies the position and type of objects located around the vehicle M (whether they are moving or stationary). The position of an object is identified, for example, as absolute coordinates with a representative point of the vehicle M (center of gravity, drive shaft center, etc.) as the origin (defined by the Y-axis passing through the representative point of the vehicle M and parallel to the left-right direction). Figure 6 The Y-axis (Ay) and the X-axis (Ay) passing through the representative point of vehicle M and parallel to the front-rear direction. Figure 6The X-axis (Ax) represents the position on the XY plane and is used for various controls.

[0056] As objects located around vehicle M, examples include dynamic objects (other vehicles traveling around the area, etc.) and stationary objects (objects that form the road boundary, such as plantings, walls, and central dividers, as well as special installations during construction or accidents, such as traffic cones, guardrails, signs, and temporary traffic lights). These installations include specific objects that can be distributed on the road (specifically, traffic cones). The identification unit 130 performs a first process based on the output of radar device 12 to identify traffic cones and a second process based on the output information of camera 10 to identify traffic cones as specific objects around vehicle M.

[0057] The identification unit 130 identifies whether the surrounding environment of vehicle M is within a restricted driving zone based on some or all of the output information from camera 10, radar device 12, and LIDAR 14. "The surrounding environment of vehicle M is within a restricted driving zone" refers to either the situation where vehicle M is driving within a restricted driving zone, or the situation where a restricted driving zone exists at a predetermined distance ahead of vehicle M. "The surrounding environment of vehicle M is not within a restricted driving zone" refers to the situation where vehicle M is not driving within a restricted driving zone and there is no restricted driving zone ahead of vehicle M.

[0058] The action plan generation unit 140 generates a target trajectory for the future automatic (driver-independent) travel of the vehicle M in a manner that allows it to travel in principle within the recommended lane determined by the recommended lane determination unit 71 and to adapt to the surrounding conditions of the vehicle M. The target trajectory includes, for example, a speed element. For instance, the target trajectory is represented as a track arranged sequentially with the locations (track points) that the vehicle M should reach. Track points are locations that the vehicle M should reach along the road at predetermined travel distances (e.g., approximately several meters). In addition, target speed and target acceleration are generated as part of the target trajectory at predetermined sampling times (e.g., approximately a fraction of a second). Alternatively, track points can be locations that the vehicle M should reach at each predetermined sampling time. In this case, the target speed and target acceleration information are represented by the intervals of the track points.

[0059] The action plan generation unit 140 can also set automatic driving events when generating the target track. Automatic driving events include constant speed driving events, low-speed following events, lane change events, branching events, merging events, and takeover events. The action plan generation unit 140 generates the target track corresponding to the initiation events.

[0060] The mode determination unit 150 determines the driving mode of the vehicle M as any one of multiple driving modes with different tasks applied to the driver. Furthermore, if the task of the determined driving mode (hereinafter referred to as the current driving mode) is not performed by the driver, the mode determination unit 150 changes the driving mode of the vehicle M to a more demanding driving mode. The mode determination unit 150 is an example of a control state setting unit that selects and sets at least one of the automatic modes controlling the vehicle M's speed and steering from multiple driving modes.

[0061] <Specific examples of driving modes>

[0062] Figure 4 This diagram illustrates specific examples of driving modes. Vehicle M has five driving modes, for example, from driving mode 1 to driving mode 5. In terms of the degree of automation of the driving control of vehicle M, driving mode 1 is the highest, followed by driving modes 2, 3, and 4 in that order, decreasing to driving mode 5 being the lowest. Conversely, the task imposed on the driver is easiest in driving mode 1, then becomes more demanding in driving modes 2, 3, and 4 in that order, with driving mode 5 being the most demanding. Furthermore, since driving modes other than driving mode 1 are not automatic driving control states, the control device 100 is obligated to terminate automatic driving control and transfer to assisted driving or manual driving. The contents of each driving mode are illustrated below.

[0063] In the first driving mode, the vehicle is in an automated driving state, and the driver is not required to monitor the road ahead or hold the steering wheel 82. However, even in the first driving mode, the driver is required to be able to quickly switch to a manual driving posture according to the request from the control device 100. In addition, automated driving here means that steering, acceleration and deceleration are controlled without the driver's operation. The road ahead refers to the space in the direction of travel of the vehicle M as visually confirmed through the windshield. The first driving mode is, for example, a driving mode that can be executed when the vehicle M is traveling at a speed below a prescribed speed (e.g., about 60 km / h) on a dedicated motor vehicle road such as a highway and when there is a vehicle ahead that is following.

[0064] In the second driving mode, which is a driver assistance mode, the driver is tasked with monitoring the area ahead of vehicle M (hereinafter referred to as "monitoring the area ahead"), but not with controlling the steering wheel 82. In the third driving mode, which is also a driver assistance mode, the driver is tasked with both monitoring the area ahead and controlling the steering wheel 82. The fourth driving mode requires some degree of driver input regarding at least one of the vehicle M's steering or acceleration / deceleration. For example, in the fourth driving mode, driver assistance features such as ACC (Adaptive Cruise Control) and LKAS (Lane Keeping Assist System) are used. In the fifth driving mode, which is a manual driving mode requiring driver input for both steering and acceleration / deceleration. Both the fourth and fifth driving modes require the driver to monitor the area ahead of vehicle M.

[0065] return Figure 3 The second control unit 160 controls the vehicle M to pass through the target track generated by the action plan generation unit 140 at a predetermined time. The second control unit 160 includes, for example, an acquisition unit 162, a speed control unit 164, and a steering control unit 166.

[0066] The acquisition unit 162 acquires information about the target track (track point) generated by the action plan generation unit 140 and stores it in a memory (not shown). The speed control unit 164 controls the driving force output device 200 (see reference) based on the speed elements associated with the target track stored in the memory. Figure 1 ) or braking device 210 (refer to Figure 1 The steering control unit 166 controls the steering device 220 (see reference) based on the curvature of the target track stored in the memory. Figure 1 The processing of the speed control unit 164 and the steering control unit 166 is achieved, for example, through a combination of feedforward control and feedback control.

[0067] In the control device 100, the structure combining the action plan generation unit 140 and the second control unit 160 constitutes the driving control unit 170. The driving control unit 170 performs automatic lane change control of the vehicle M based on the recognition results of the driving environment or 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 driver's operation of the driving operation element 80 (e.g., the turn signal lever).

[0068] The driving control unit 170 selects a lane-changing method from multiple lane-changing methods with varying levels of driver involvement in vehicle M, and performs driving control (also known as lane-changing control) according to the selected lane-changing method. These multiple lane-changing methods with varying levels of driver involvement in vehicle M can also be referred to as multiple lane-changing methods with varying degrees of automation. The lower the driver's involvement, the higher the degree of automation; conversely, the higher the driver's involvement, the lower the degree of automation.

[0069] For example, multiple lane-changing methods may include the following three automatic lane-changing methods. The first automatic lane-changing method is intentional automatic lane change (ALC - Category C), in which the driver of vehicle M intentionally changes lanes, and the driver of vehicle M instructs the start of the lane change. In intentional automatic lane change, the driver of vehicle M considers the driving conditions of other vehicles, the route to the destination, etc., to determine whether a lane change should be made. When a lane change is deemed necessary, the driver of vehicle M instructs the start of the lane change by operating the driving control unit 80. Based on this instruction, the driving control unit 170, while considering the surrounding driving conditions, initiates the automatic lane change at the appropriate moment.

[0070] The second type of automatic lane change is recommended automatic lane change (ALC - Category D), in which the driving control unit 170 recommends a lane change, and the driver of vehicle M approves the lane change. In recommended automatic lane change, the driving control unit 170 determines whether a lane change should be performed based on the driving conditions of other vehicles, the route to the destination, etc. If a lane change is required, the driving control unit 170 recommends the lane change to the driver. If the driver of vehicle M approves the lane change recommendation, they instruct vehicle M to begin the lane change by operating an approval switch. The approval switch can be a dedicated approval switch or an operating device that also has other functions (for example, driving operation device 80). Based on this instruction, the driving control unit 170, while considering the surrounding driving conditions, begins the automatic lane change at the appropriate time. Therefore, if the driver does not approve the lane change recommendation, i.e., does not operate driving operation device 80, the automatic lane change is not performed.

[0071] The third type of automatic lane change is Automated Lane Change Decision (ALC - Category E), in which the driving control unit 170 determines whether a lane change should be made and initiates the lane change. In the Automated Lane Change Decision, the driving control unit 170 determines whether a lane change should be made based on the driving conditions of other vehicles, the route to the destination, etc. If a lane change is deemed necessary, the driving control unit 170 considers the surrounding driving conditions and initiates the automatic lane change at a feasible moment. In the Automated Lane Change Decision, the driver of vehicle M does not participate in the lane change.

[0072] The control device 100 performs automatic lane changes corresponding to the driving mode. For example, the control device 100 can perform a decision-based automatic lane change in the first driving mode. The control device 100 can perform a suggested automatic lane change in the second, third, and fourth driving modes. The control device 100 can perform an intentional automatic lane change in the third and fourth driving modes. The control device 100 does not perform any automatic lane changes in the fifth driving mode.

[0073] return Figure 1 The driving force output device 200 outputs driving force (torque) to the drive wheels to propel the vehicle. The driving force output device 200 may include, for example, a combination of an internal combustion engine, an electric motor, and a transmission, and an ECU (Electronic Control Unit) that controls them. The ECU controls these components according to information input from the second control unit 160 or from the driving operation unit 80.

[0074] The braking device 210 includes, for example, a brake caliper, a hydraulic cylinder that transmits hydraulic pressure to the brake caliper, an electric motor that generates hydraulic pressure in the hydraulic cylinder, and a brake ECU. The brake ECU controls the electric motor according to information input from the second control unit 160 or from the driving operation unit 80, and outputs braking torque corresponding to the braking operation to each wheel.

[0075] The steering system 220 includes, for example, a steering ECU and an electric motor. The electric motor, for example, applies force to a rack and pinion mechanism to change the direction of the steering wheels. The steering ECU drives the electric motor and changes the direction of the steering wheels according to information input from the second control unit 160 or from the driving operation unit 80.

[0076] <Identification and processing of the area containing traffic cones>

[0077] Figure 5 This is a schematic diagram showing the area around the vehicle M where the traffic cone can be identified by the identification unit 130. Figure 5The diagram shows a range 10A where objects can be detected by camera 10 and a range 12A where objects can be detected by radar device 12. For example, the recognition unit 130 defines a peripheral region DA—a region encompassed in range 12A and partially overlapping with range 10A—that is, a region with sufficiently high object detection resolution detected by camera 10 and radar device 12, as the target area for traffic cone recognition. The peripheral region DA is set such that its width in the front-rear direction is greater than its width in the left-right direction. Furthermore, the peripheral region DA is set such that the position of vehicle M is offset towards the rear in the front-rear direction. That is, the width of the peripheral region DA in the front-rear direction forward of the position of vehicle M is greater than its width in the front-rear direction backward of the position of vehicle M.

[0078] The identification unit 130 divides the surrounding area DA into multiple ranges for management. Figure 6 This is a schematic diagram representing a segmentation example of the surrounding region DA. In Figure 6 In the example shown, the surrounding area DA is divided into 7 parts in the left-right direction and 18 parts in the front-back direction, resulting in 126 ranges AR (the elongated rectangles in the left-right direction in the figure). Hereinafter, to distinguish a specific range AR from other ranges, that range AR will be referred to as range AR* (* is any number). The position (center position) of each range AR is represented by coordinates on the XY plane. Figure 6 The range AR1 in the diagram represents the range containing vehicle M, and the position of range AR1 is consistent with the position of vehicle M.

[0079] The identification unit 130 obtains the output information of the radar device 12 in the surrounding area DA, identifies the position and orientation of the traffic cone based on the output information, and performs the first processing of identifying the range AR (hereinafter referred to as the first range) that includes the traffic cone in the range AR constituting the surrounding area DA. Figure 7 An example is shown where the six ranges from AR121 to AR126 are identified as the first range through the first processing.

[0080] In addition, the identification unit 130 obtains the output information of the camera 10 in the surrounding area DA, identifies the position and orientation of the traffic cone based on the output information, and performs a second process to identify the range AR containing the traffic cone (hereinafter referred to as the second range) in the range AR constituting the surrounding area DA. Figure 8 An example is shown where ranges AR10 and AR11 are identified as second ranges through a second process.

[0081] <Reliability determination of the recognition results of the first processing>

[0082] When the identification unit 130 identifies a first range, it selects at least one range AR as a third range from the remaining ranges AR after removing the first range from the surrounding area DA, based on the location of the first range. Specifically, the identification unit 130 selects a range AR that is at least adjacent to the first range.

[0083] For example, if the identification unit 130 has two first ranges that are equidistant in the left-right direction and arranged with one or two ranges AR separated in the front-back direction, it selects the entire range AR between these two first ranges as the third range. Figure 7 In the example, the range AR between range AR121 and range AR122, the two range ARs between range AR123 and range AR124, and the range AR between range AR125 and range AR126 (summarized as range AR121a) are selected as the third range.

[0084] Furthermore, when there are two first ranges that are adjacent in the left-right direction and separated by a distance of one or two ranges AR in the front-back direction, the identification unit 130 selects the range AR enclosed by the two first ranges as the third range. Figure 7 In the example, ranges AR122 and AR123 exist as the first ranges, which are adjacent in the left-right direction and separated by a range AR in the front-back direction. Therefore, the four ranges AR enclosed by ranges AR122 and AR123 (summarized as range AR121b in the diagram) are selected as the third range.

[0085] Furthermore, the identification unit 130 selects the range AR that is adjacent to the first range AR and the selected range AR in the left and right directions respectively from the remaining range AR after removing the first range and the selected range AR as the third range. Figure 7 In the example, the range AR adjacent to each other in the left and right directions of range AR121 to range AR126, range AR121a, and range AR121b (summarized as range AR121c) is selected as the third range.

[0086] Furthermore, the method for selecting the third range is just one example, and the present invention is not limited thereto. For example, the identification unit 130 may also select the range AR adjacent to each first range in the left-right direction as at least the third range, or select the range AR adjacent to each first range in at least the left-right direction and the front-back direction as at least the third range, or select all the range AR adjacent to each first range as at least the third range.

[0087] When the identification unit 130 completes the selection of the third range, it obtains the result of the second processing and performs a process to determine whether there exists a range among all the third ranges that is identified by the second processing as containing a traffic cone as a second range. In this process, if the determination result is "yes", the identification unit 130 determines that the reliability of the identification result of the first range is above a threshold; if the determination result is "no", the identification result of the first range is determined to be below the threshold. That is, the identification unit 130 determines the reliability of the identification result of the first range (the identification result of the first range containing a traffic cone) based on the identification result of the second processing for the third range adjacent to the first range (whether the third range contains a traffic cone).

[0088] exist Figure 7 In the example, if the identification unit 130 includes a range identified as a second range among the five third ranges adjacent to the range AR121, it determines that the reliability of the identification result of identifying ranges AR121 to AR125 as the first range is above the threshold. If no range identified as a second range is included among all the third ranges, it determines that the reliability of the identification result of the first process of identifying ranges AR121 to AR125 as the first range is less than the threshold.

[0089] In this way, even if a first range is identified through the first processing, the reliability of the identification result of the first range can be determined based on the identification result of the second processing for a third range selected from the vicinity of the first range. Therefore, even if the first range is incorrectly identified due to errors in the first sensor, etc., this result does not need to be used. Therefore, when the identification result of the first processing is used in subsequent control, the accuracy of the control can be improved.

[0090] <Reliability determination of the identification results of the second processing>

[0091] The identification unit 130 not only determines the reliability of the identification result from the first processing, but also determines the reliability of the identification result from the second processing. When a second range is identified, the identification unit 130 selects at least one range AR as a fourth range from the remaining range AR after removing the second range from the surrounding region DA, based on the position of the second range. Specifically, the identification unit 130 selects a range AR that is at least adjacent to the second range as the fourth range. Preferably, the identification unit 130 selects a range AR that is at least adjacent to the second range in the front-back direction as the fourth range.

[0092] For example, the identification unit 130 selects all ranges in range AR whose left-right positions are the same as the second range as the fourth range. Figure 8In the example, 17 ranges AR10a that are the same as range AR10 in the left and right directions are selected as the fourth range, and 17 ranges AR11a that are the same as range AR11 in the left and right directions are selected as the fourth range.

[0093] When the identification unit 130 completes the selection of the fourth range, it obtains the result of the first processing and determines whether there is a range among all the fourth ranges that was identified as the first range through the first processing. If the determination result is "yes", the reliability of the identification result determined by the identification unit 130 as the second range is above a threshold; if the determination result is "no", the reliability of the identification result determined by the identification unit 130 as the second range is less than the threshold. That is, the identification unit 130 determines the reliability of the identification result of the second range (the identification result that the second range includes traffic cones) based on the identification result of the first processing for the fourth range that is at the same position as the second range in the left-right direction (whether the fourth range includes traffic cones).

[0094] exist Figure 8 In the example, if the range AR10a and the range AR11a contain the range identified as the first range, the identification unit 130 determines that the reliability of the identification result of the second process that identifies the ranges AR10 and AR11 as the second range is above the threshold. If the range AR10a and the range AR11a do not contain the first range, the identification unit 130 determines that the reliability of the identification result of the second process that identifies the ranges AR10 and AR11 as the second range is less than the threshold.

[0095] In this way, even if a second range is identified through the second processing, the reliability of the identification result of the second range can be determined based on the identification result of the first processing for a fourth range selected from the vicinity of the second range. Therefore, even if the second range is incorrectly identified due to errors such as those of the second sensor, it is unnecessary to use that result. Therefore, when the identification result of the second processing is used in subsequent control, the accuracy of the control can be improved.

[0096] <Identification and processing of driving restriction zones>

[0097] When the identification unit 130 identifies the first range and the second range, and the reliability of the identification results of the first processing and the second processing is both above the threshold, it identifies the surrounding environment of vehicle M as a driving restriction zone. Thus, with high reliability of both the first and second processing results, by identifying the surrounding environment of vehicle M as a driving restriction zone, it can accurately identify driving restriction zones.

[0098] Furthermore, if the recognition unit 130 can identify both the first range and the second range, and the reliability of the recognition result in either the first range or the second range is above a threshold, then it can identify the surrounding environment of the vehicle M as a driving restriction zone. Even so, it can eliminate the influence caused by errors of the camera 10 and the radar device 12, and perform driving restriction zone recognition with high accuracy.

[0099] When the identification unit 130 determines that the driving environment is a restricted driving zone, the driving control unit 170 preferably restricts the driving control of the vehicle M. Specifically, the driving control unit 170 restricts lane change control. Restricting lane change control means prohibiting lane change control, or performing lane change control but prohibiting lane changes as part of the process. In this way, when the vehicle M is driving in a restricted driving zone or is approaching a restricted driving zone, by restricting the lane change control performed by the control device 100, the vehicle M can be driven safely.

[0100] The operation of the control device 100 will be explained below with reference to the flowchart. Figure 9 This is a flowchart used to explain the operation of the control device 100. Figure 9 The process shown is, for example, in Figure 4 The execution of any of the first to fourth driving modes shown is carried out.

[0101] If the identification unit 130 obtains the output information of the radar device 12, it performs a first process (step S1) based on the output information to identify the first range containing the traffic cone in the entire range AR constituting the surrounding area DA.

[0102] Furthermore, if the recognition unit 130 obtains the output information of the camera 10, it performs a second process (step S2) based on the output information to identify the second range containing the traffic cone in the entire range AR constituting the surrounding area DA.

[0103] If the identification unit 130 identifies a first range in step S1 (step S3: Yes), it sets a third range around the first range based on the identified first range (step S4). If the identification unit 130 does not identify a first range in step S1 (step S3: No), it determines that the driving environment is not a driving restriction zone (step S9) and ends the process.

[0104] If the identification unit 130 determines "yes" in step S3, and if the second range is identified in step S2 (step S5: yes), then based on the identified second range, a fourth range is set around the second range (step S6). If the identification unit 130 does not identify the second range in step S2 (step S5: no), it determines that the driving environment is not a driving restriction zone (step S9) and ends the process.

[0105] After step S6, the identification unit 130 determines whether there is a range identified as the second range in the third range, and whether there is a range identified as the first range in the fourth range (step S7). If the determination in step S7 is "yes", the identification unit 130 determines that the driving environment is a driving restriction zone, prohibits lane change control performed by the driving control unit 170 (step S8), and ends the process. If the determination in step S7 is "no", the identification unit 130 proceeds to step S9. The above process is repeated until step S8 is performed.

[0106] Figure 10 It is used to explain in Figure 9 The flowchart shows the operation of the control device 100 after step S8.

[0107] When the identification unit 130 is in either a first state where the first range is not identified through the first processing or a second state where the second range is not identified through the second processing (step S11: Yes), it starts counting the travel distance of vehicle M, and in step S12 determines whether the travel distance has reached the threshold TH1 (step S12). If the determination in step S12 is "No", the identification unit 130 returns the processing to step S11; and if the determination in step S12 is "Yes", it determines that the driving environment is not within the driving restriction range (step S13) and returns to... Figure 9 The processing shown.

[0108] If the identification unit 130 determines "yes" in step S11, that is, if a traffic cone is identified in at least one of the first and second processes, it restores the travel distance count to its initial value and determines whether the traffic cone was identified only through the second process (step S14). If the identification unit 130 determines "yes" in step S14, it starts counting the travel distance of vehicle M and determines whether the travel distance has reached the threshold TH2 (step S15). If the identification unit 130 determines "no" in step S15, it returns the process to step S14; if the identification unit 130 determines "yes" in step S15, it determines that the driving environment is not within the driving restriction zone (step S13) and returns to... Figure 9 The processing shown.

[0109] If the determination in step S14 is "No", the recognition unit 130 restores the travel distance count to its initial value and determines whether the traffic cone was only identified through the first process (step S16). If the determination in step S16 is "Yes", the recognition unit 130 starts counting the travel distance of vehicle M and determines whether the travel distance has reached the threshold TH3 (step S17). If the determination in step S17 is "No", the recognition unit 130 returns the process to step S16; if the determination in step S17 is "Yes", it determines that the driving environment is not within the driving restriction zone (step S13) and returns to... Figure 9 The process is as shown. If the identification unit 130 determines "no" in step S16, that is, if it is neither the first state nor the second state (where a traffic cone is identified in both the first and second processes), it restores the travel distance count to its initial value and returns the process to step S11. Thresholds TH2 and TH3 are larger than threshold TH1. Furthermore, threshold TH2 is larger than threshold TH3.

[0110] In this way, after determining that the surrounding environment is a driving restriction zone, if either or both of the following conditions persist—a first state where the first range is not identified through the first process and a second state where the second range is not identified through the second process—the identification unit 130 determines that the surrounding environment is not a driving restriction zone. Therefore, no complex processing is required from the moment it is determined to be a driving restriction zone until it is determined not to be a driving restriction zone, thus reducing the processing load.

[0111] Furthermore, the continuation of both the first and second states means that there is a high probability that traffic cones are not present around vehicle M. Therefore, in this case, by determining in advance that the area is not a restricted driving zone, the prohibition of lane change control can be lifted earlier. On the other hand, the continuation of only either the first or second state means that traffic cones are likely to be present around vehicle M. Therefore, in this case, by extending the time until it is determined that the area is not a restricted driving zone, lane change control can be appropriately prohibited, thereby improving safety.

[0112] The following are at least described in this specification. Furthermore, although the components corresponding to those in the above embodiments are shown in parentheses, the present invention is not limited thereto. (1)

[0114] A control device (control device 100) is used for driving control of a vehicle (vehicle M), wherein,

[0115] The control device includes:

[0116] The processor is capable of acquiring output information from a first sensor (radar device 12) and a second sensor (camera 10) that can detect objects located around the vehicle.

[0117] The processor described above performs the following actions:

[0118] The system performs a first processing and a second processing. The first processing identifies a first range (range AR121 to range AR126) containing a specific object (traffic cone) in a plurality of ranges (ranges AR) set in the surrounding area (surrounding area DA) of the vehicle based on the output information of the first sensor. The second processing identifies a second range (range AR10, range AR11) containing a specific object in the plurality of ranges based on the output information of the second sensor.

[0119] Based on the first range mentioned above, a third range (range AR121a, range AR121b, range AR121c) is selected from the plurality of ranges after removing the first range mentioned above.

[0120] The reliability of the identification result of the first range is determined based on the identification result of the second processing for the third range.

[0121] According to (1), even if the accuracy of the recognition result of the first processing decreases due to errors in the first sensor, the reliability of the recognition result of the first processing can be determined based on the recognition result of the second processing, and the recognition result of the first processing can be used in subsequent processing or detrimental to subsequent processing. Therefore, the accuracy of various controls based on the recognition result of a specific object can be improved. (2)

[0123] According to the control device described in (1), wherein,

[0124] When the processor determines that the reliability of the identification result of the first process (the identification result of the range AR121 to AR125 being the range containing the traffic cone) is above a threshold when the third range includes the second range (for example, when the range AR121c adjacent to the range AR121 is identified as the second range).

[0125] According to (2), for example, if a specific object is identified through the second processing in a third range close to the first range, it can be determined that the identification result of the first processing is highly reliable, and therefore the reliability is determined to be above the threshold. Therefore, the accuracy of various controls based on the identification result of the first processing can be improved. (3)

[0127] According to the control device described in (1) or (2), wherein,

[0128] The processor defines the third range as the range that is at least adjacent to the first range among the plurality of ranges.

[0129] According to (3), the reliability of the recognition result of the first processing can be determined with high accuracy. (4)

[0131] According to the control device described in (3), wherein,

[0132] When there are two first ranges that are in the same position in the left-right direction of the vehicle, the processor sets the range between the two first ranges as the third range.

[0133] According to (4), the reliability of the recognition result of the first processing can be determined with high accuracy. (5)

[0135] According to the control device described in (3) or (4), wherein,

[0136] The processor will set the range located on both sides of the first range in the left-right direction of the vehicle as the third range.

[0137] According to (5), the reliability of the recognition result of the first processing can be determined with high accuracy. (6)

[0139] According to any one of (1) to (5), the control device, wherein,

[0140] The processor described above performs the following actions:

[0141] Based on the second range mentioned above, a fourth range (range AR10a, range AR11a) is selected from the plurality of ranges after removing the second range mentioned above;

[0142] The reliability of the identification result of the second range is determined based on the identification result of the first processing for the fourth range.

[0143] According to (6), even if the accuracy of the recognition result of the second processing decreases due to errors in the second sensor, the reliability of the recognition result of the second processing can be determined based on the recognition result of the first processing, and the recognition result of the second processing can be used in subsequent processing or not used in subsequent processing. Therefore, the accuracy of various controls based on the recognition result of a specific object can be improved. (7)

[0145] According to the control device described in (6), wherein,

[0146] When the processor determines that the reliability of the identification result of the second processing (identification result of ranges AR10 and AR11 being ranges containing traffic cones) is above a threshold when the fourth range includes the first range (for example, when range AR10a adjacent to range AR10 is identified as the first range).

[0147] According to (7), for example, if a specific object is identified within a fourth range close to the second range, it can be determined that the recognition result of the second processing is highly reliable, and therefore the reliability is above the threshold. Thus, the accuracy of various controls based on the recognition result of the second processing can be improved. (8)

[0149] According to the control device described in (6) or (7), wherein,

[0150] The first sensor mentioned above is radar.

[0151] The second sensor mentioned above is a digital camera.

[0152] The processor selects all of the above ranges (range AR10a, range AR11a) whose positions in the left-right direction of the vehicle are the same as those in the second range as the fourth range.

[0153] The field of view of a camera in the front-back direction tends to be narrower than the field of view of a radar in the front-back direction. According to (8), the field of view in the front-back direction is selected as the fourth field of view relative to the second field of view identified based on the output of the camera. This allows the radar to supplement the field of view that the camera cannot detect, and the reliability of the identification result of the second field of view can be determined with high accuracy. (9)

[0155] The control device according to any one of (6) to (8), wherein,

[0156] The specific object mentioned above is a traffic cone.

[0157] When the processor identifies the first range and the second range, and the reliability of the identification results of the first processing and the second processing are both above the threshold, it determines that the surrounding environment of the vehicle is a restricted driving zone.

[0158] According to (9), if a specific object is identified in both the first and second processes, and the reliability of each identification result is high, it is determined to be a driving restriction zone. Therefore, it is possible to determine whether a driving restriction zone is entered with high precision. (10)

[0160] According to the control device described in (9), wherein,

[0161] After determining that the surrounding environment is within the driving restriction zone, if the processor fails to identify either or both of the first state of the first range through the first processing and the second state of the second range through the second processing, it determines that the surrounding environment is not within the driving restriction zone.

[0162] According to (10), no complicated processing is required from the time it is determined to be a driving restriction zone until it is determined not to be a driving restriction zone, thus reducing the processing load. (11)

[0164] According to the control device described in (10), wherein,

[0165] The processor described above performs the following actions:

[0166] If the first state and the second state are maintained during the period when the vehicle travels a first distance (threshold TH1), it is determined that the surrounding environment is not the driving restriction zone.

[0167] If either the first state or the second state described above persists during the period when the vehicle travels the second distance (threshold TH2, threshold TH3), it is determined that the surrounding environment is not within the driving restriction zone.

[0168] The second distance mentioned above is longer than the first distance mentioned above.

[0169] According to (11), the continuation of the first state and the second state means that there is a high probability that a specific object does not exist around the vehicle. Therefore, in this case, by determining in advance that it is not a driving restriction zone, the functions restricted in the driving restriction zone can be restored earlier, for example. On the other hand, the continuation of only one of the first state and the second state means that a specific object may exist around the vehicle. Therefore, in this case, by extending the time until it is determined that it is not a driving restriction zone, the functions restricted in the driving restriction zone can be continued, for example. (12)

[0171] The control device according to any one of (9) to (11), wherein,

[0172] The processor described above performs the following actions:

[0173] Perform lane change control for the aforementioned vehicles;

[0174] If the surrounding environment is determined to be within the aforementioned driving restriction zone, the aforementioned lane change control will be restricted.

[0175] According to (12), safety can be improved by restricting lane changes within the driving restriction zone. (13)

[0177] The control device according to any one of (1) to (12), wherein,

[0178] The width of the aforementioned surrounding area in the longitudinal direction of the vehicle is set to be greater than the width of the aforementioned surrounding area in the lateral direction of the vehicle.

[0179] The position of the aforementioned vehicle in the aforementioned surrounding area is set to be biased towards the rear side in the aforementioned front-rear direction.

Claims

1. A control device for controlling the movement of a vehicle, wherein, The control device includes: The processor is capable of acquiring output information from a first sensor and a second sensor that can detect objects located around the vehicle. The processor performs the following actions: The system performs a first processing step and a second processing step. The first processing step identifies a first range containing a specific object among multiple ranges set in the surrounding area of ​​the vehicle based on the output information of the first sensor. The second processing step identifies a second range containing a specific object among the multiple ranges based on the output information of the second sensor. Based on the first range, a third range is selected from the plurality of ranges after removing the first range; The reliability of the identification results for the first range is determined based on the identification results of the second processing for the third range. If the processor determines that the reliability of the identification result of the first processing is above a threshold when the third range includes the second range, The processor sets the range that is at least adjacent to the first range among the plurality of ranges as the third range.

2. The control device according to claim 1, wherein, If there are two first ranges that are in the same position in the left-right direction of the vehicle, the processor sets the range between the two first ranges as the third range.

3. The control device according to claim 1 or 2, wherein, The processor sets the range located on both sides of the first range in the left-right direction of the vehicle as the third range.

4. The control device according to claim 1 or 2, wherein, The processor performs the following actions: Based on the second range, a fourth range is selected from the plurality of ranges after removing the second range; The reliability of the identification result of the second range is determined based on the identification result of the first processing for the fourth range.

5. The control device according to claim 4, wherein, If the processor determines that the reliability of the identification result of the second processing is above a threshold when the fourth range includes the first range.

6. The control device according to claim 4, wherein, The first sensor is radar. The second sensor is a digital camera. The processor selects all the ranges whose position in the left-right direction of the vehicle is the same as that of the second range as the fourth range.

7. The control device according to claim 4, wherein, The specific object is a traffic cone. If the processor identifies the first range and the second range, and the reliability of the identification results of the first processing and the second processing are both above the threshold, then the processor determines that the surrounding environment of the vehicle is a restricted driving zone.

8. The control device according to claim 7, wherein, After determining that the surrounding environment is the driving restriction zone, if either or both of the first state of failing to identify the first range through the first processing and the second state of failing to identify the second range through the second processing continue, the processor determines that the surrounding environment is not the driving restriction zone.

9. The control device according to claim 8, wherein, The processor performs the following actions: If the first state and the second state continue during the period when the vehicle travels the first distance, it is determined that the surrounding environment is not the driving restriction zone; If either the first state or the second state persists during the period when the vehicle travels the second distance, it is determined that the surrounding environment is not within the driving restriction zone. The second distance is longer than the first distance.

10. The control device according to any one of claims 7 to 9, wherein, The processor performs the following actions: Perform lane change control on the vehicle; If the surrounding environment is determined to be within the driving restriction zone, the lane change control is restricted.

11. The control device according to claim 1 or 2, wherein, The width of the surrounding area in the longitudinal direction of the vehicle is set to be greater than the width of the surrounding area in the lateral direction of the vehicle. The position of the vehicle in the surrounding area is set to be biased towards the rear side in the front-rear direction.

Images