Automatic parking control device

Abstract

To provide an automatic parking control device capable of executing accurate automatic parking control or parking assistance control even under a slippery road surface condition.SOLUTION: An automatic parking control device includes: a peripheral environment recognition device that acquires peripheral environment information of a vehicle; a parking control unit that searches for a parkable area on the basis of the peripheral environment information, generates a target path with the parkable area as a target arrival point and performs travel control of the vehicle along the target path; an image processing unit that estimates a distance to a recognized three-dimensional object and the degree of slipperiness of the road surface on the basis of the peripheral environment information; an image map generation unit that performs image synthesis of the estimated distance information, road surface slipperiness degree information, and peripheral environment information to generate a road surface μ-map; a wheel selection unit that predicts a path through which each of multiple wheels passes on the basis of the target path, overlays the predicted path of each wheel onto the road surface μ-map and selects the wheel that passes through the least slippery path; and a movement amount calculation unit that obtains a wheel speed pulse of the selected wheel and calculates a movement amount of the reference position of the vehicle.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] This invention relates to an automatic parking control device that is mounted on a vehicle such as an automobile and performs driving control to guide the vehicle to a parking area, and relates to technology that can perform accurate automatic parking control or parking assistance control even on slippery road conditions, for example. [Background technology]

[0002] In recent years, automatic driving control technology has been developed for vehicles such as automobiles, which allows the vehicle to travel automatically without the driver's operation. In addition, various driving control devices that can execute various driving controls to assist the driver's driving operation by utilizing this type of automatic driving control technology have been proposed and are being put into practical use.

[0003] In recent years, various types of conventional driving control devices of this type have been proposed, such as automatic parking control devices that include various parking control systems that perform driving control to guide a vehicle to a parking area.

[0004] Here, the parking control system is specifically referred to as, for example, a parking assistance system (APS; Assisted Parking System) or a partially automated parking system (PAPS; Partially Automated Parking System).

[0005] Automatic parking control or parking assistance control (hereinafter referred to as automatic parking control, etc.) executed in a conventional automatic parking control device includes, for example, the following control process. That is, first, information on the vehicle's surrounding environment (for example, road markings, three-dimensional structures such as car stops, etc.) is acquired using various sensors. Next, a parking area is searched for based on the acquired surrounding environment information. Next, a target route for moving the vehicle is generated with the searched parking area as a target destination. Then, various controls (steering, driving, braking, etc.) are appropriately executed to move the vehicle along the generated target route.

[0006] Various proposals have been made regarding automatic parking control devices that perform such automatic parking control, for example, in JP 2023-017467 A.

[0007] By the way, when executing such automatic parking control, it is important to accurately control the movement of the vehicle along the generated target route. For that purpose, it is necessary to accurately predict the movement amount of the vehicle when calculating each control value of feedback control and feedforward control of steering, driving, braking, etc.

[0008] In this case, conventional methods for predicting the amount of movement of a vehicle include, for example, the so-called GPS (Global Positioning System) method, which calculates the distance traveled from the vehicle's position using a GNSS (Global Navigation Satellite System) sensor, and the wheel speed pulse method, which integrates the distance traveled from the wheel speed pulse.

[0009] Here, the GPS method may experience unstable or difficult reception of radio waves from satellites in, for example, a multi-storey car park or a garage with a roof, etc. For this reason, it is considered inappropriate to use the GPS method for predicting the amount of movement of a vehicle when performing automatic parking control, etc.

[0010] Therefore, in order to predict the amount of movement of a vehicle when automatic parking control or the like is being executed, the wheel speed pulse method is currently generally used. [Prior art documents] [Patent documents]

[0011] [Patent Document 1] JP 2023-017467 A Summary of the Invention [Problem to be solved by the invention]

[0012] However, when predicting the amount of movement of a vehicle using the wheel speed pulse method, if the road conditions around the vehicle are slippery, such as a snowy road, the wheels may slip and spin. If the wheels spin in this way, an error will occur in the predicted amount of movement of the vehicle calculated based on the wheel speed pulse.

[0013] As a result, it becomes impossible to accurately time the steering, driving, braking, and other controls based on the calculated predicted movement amount, which causes a problem of reduced ability of the vehicle to track the target route in automatic parking control and the like.

[0014] If target path tracking ability decreases in this way, problems may occur such as a deviation in the vehicle's stopping position relative to the target parking area, or an increase in unnecessary operations such as turning operations, resulting in a decrease in the feel of vehicle control.

[0015] The present invention provides an automatic parking control device that is mounted on a vehicle such as an automobile and performs driving control to guide the vehicle to a parking area, and that can perform accurate automatic parking control or parking assistance control even on slippery road conditions such as snowy roads. [Means for solving the problem]

[0016] In order to achieve the above object, an automatic parking control device according to one aspect of the present invention is an automatic parking control device that performs driving control to guide a vehicle to a parking area, and includes a surrounding environment recognition device that acquires surrounding environment information of the vehicle, a parking control unit that searches for a parking area based on the surrounding environment information acquired by the surrounding environment recognition device, generates a target route for moving the vehicle with the searched parking area as a destination point, and performs driving control to move the vehicle along the generated target route, and a parking control unit that performs driving control to move the vehicle along the generated target route based on the surrounding environment information acquired by the surrounding environment recognition device. an image map generating unit that generates a road surface mu map by image-combining the distance information and the road surface slipperiness information estimated by the image processing unit with the surrounding environment information; a wheel selecting unit that predicts a path that each of a plurality of wheels of the vehicle will take based on the target path, overlays the predicted path of each wheel on the road surface mu map, and selects a wheel among the plurality of wheels that will take the least slippery path; and a movement amount calculating unit that obtains wheel speed pulses of the selected wheels and calculates a movement amount of a reference position of the vehicle. Effect of the Invention

[0017] According to the present invention, it is possible to provide an automatic parking control device that is mounted on a vehicle such as an automobile and performs driving control to guide the vehicle to a parking area, and that can perform accurate automatic parking control or parking assistance control even on slippery road conditions such as snow-covered roads. [Brief description of the drawings]

[0018] [Figure 1] FIG. 1 is a block diagram showing a schematic configuration of a vehicle driving control device including an automatic parking control device according to an embodiment of the present invention; [Diagram 2] 1 is a display example of a planar depth map generated by the automatic parking control device of the present embodiment; [Diagram 3] A display example of a planar μ map generated by the automatic parking control device of this embodiment. [Figure 4]A display example of a road surface μ map generated by the automatic parking control device of this embodiment. [Diagram 5] Fig. 4 shows an example of the target path and predicted wheel path superimposed on the road surface μ map. [Figure 6] A flowchart showing the operation of a vehicle driving control device including an automatic parking control device according to the present embodiment. [Figure 7] 7 is a flowchart showing a subroutine of the road surface μ map generation process of FIG. 6 (the process of step S6 of FIG. 6). DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0019] The present invention will be described below with reference to the illustrated embodiments. The drawings used in the following description are schematic, and the dimensional relationship and scale of each component may be different for each component in order to show each component at a size that can be recognized on the drawing. Therefore, the present invention is not limited to the illustrated form with respect to the quantity of each component, the shape of each component, the size ratio of each component, the relative positional relationship of each component, etc. shown in each drawing.

[0020] First, a schematic configuration of a vehicle driving control device including an automatic parking control device according to one embodiment of the present invention will be described below with reference to Fig. 1. Fig. 1 is a block diagram showing a schematic configuration of a vehicle driving control device including an automatic parking control device according to one embodiment of the present invention.

[0021] The basic configuration of the driving control device shown in Fig. 1 is substantially the same as that of a conventional driving control device of the same type. Therefore, in the following description, illustration of the general configuration of the driving control device and detailed description thereof are omitted. Then, the components related to the automatic parking control device of this embodiment will be described below.

[0022] The vehicle driving control device including the automatic parking control device 1 of this embodiment has a camera unit 10, which is an in-vehicle camera device fixed to the upper central part of the front interior of the vehicle (hereinafter referred to as the vehicle itself; not shown) in which the driving control device is installed.

[0023] The camera unit 10 includes a stereo camera 11, an image processing unit (IPU) 12, an image recognition unit 13, a control unit 14, and the like.

[0024] The stereo camera 11 is formed with two cameras, a main camera 11a and a sub camera 11b. The main camera 11a and the sub camera 11b are arranged, for example, in the vehicle interior of the vehicle at symmetrical positions with respect to the center of the vehicle width direction, facing the front (traveling direction) of the vehicle. Each of the main camera 11a and the sub camera 11b is composed of, for example, an imaging optical system, an imaging element such as a CMOS image sensor, and a processing circuit for processing imaging signals, etc.

[0025] With this configuration, the stereo camera 11 acquires two image data from two different viewpoints targeting a predetermined range of the surrounding environment in front of the vehicle using the main camera 11a and the sub camera 11b at a predetermined imaging period synchronized with each other. Then, stereo image data is generated based on the two image data acquired in this way. This stereo image data is surrounding environment information that represents the surrounding environment while the vehicle is traveling. The surrounding environment information (image data) generated by the stereo camera 11 is output to the image processing unit 12.

[0026] The image processing unit 12 is a configuration unit or circuit unit that performs predetermined image processing on the surrounding environment information (image data representing the surrounding environment while the vehicle is traveling) acquired by the stereo camera 11. The image processing unit 12 performs, for example, processing to detect edges of various objects (objects, lane markings, etc.) displayed on the image.

[0027] The image processing unit 12 also acquires distance information based on the amount of positional shift of corresponding edges on the left and right images based on the stereo image data, and generates image information including the distance information (distance image information). The distance image information generated in the image processing unit 12 is output to the image recognition unit 13.

[0028] The image recognition unit 13 calculates the road curvature [1 / m] of the left and right dividing lines of the road on which the vehicle is traveling (the vehicle's traveling path) and the width between the left and right dividing lines (lane width) based on the distance image information and the like input from the image processing unit 12. Various well-known means are used to calculate the road curvature and lane width.

[0029] In addition, the image recognition unit 13 performs predetermined pattern matching based on the distance image information acquired by the stereo camera 11 to recognize three-dimensional objects (such as guardrails, curbs, and other surrounding vehicles) extending along the road, parking frame lines marked by dividing lines on the road surface of a parking lot or the like, three-dimensional structures such as car stops that define parking space areas, or gap spaces between adjacent vehicles, etc. In addition, the image recognition unit 13 also recognizes the conditions of the road surface around the vehicle (hereinafter referred to as road surface conditions, etc.).

[0030] Here, the recognition of three-dimensional objects (object recognition) in the image recognition unit 13 recognizes, for example, the type of three-dimensional object, the height of the three-dimensional object, the width dimension of the three-dimensional object, the distance from the vehicle to the three-dimensional object, the moving speed of the three-dimensional object, the relative speed between the vehicle and the three-dimensional object, and the relative distance between three-dimensional objects (for example, the lateral distance between a curb on the side of the road and a dividing line nearby).

[0031] The road surface conditions recognized by the image recognition unit 13 include, for example, a condition in which the road surface is wet due to rain or melting snow, a rainfall condition, a snow accumulation condition, a packed snow condition, a frozen road condition, etc. These road surface conditions are estimated based on, for example, the brightness difference of the images.

[0032] Various pieces of information recognized by the image recognition unit 13 are output as surrounding environment information to the control unit 14. In this case, the camera unit 10 including the image recognition unit 13 functions as a surrounding environment recognition device that recognizes the surrounding environment of the vehicle.

[0033] Furthermore, the image recognition unit 13 performs image analysis using AI (Artificial Intelligence) using, for example, semantic segmentation technology based on the surrounding environment information (image data) acquired by the stereo camera 11. Here, the AI ​​performs depth estimation (distance estimation) for a three-dimensional object recognized based on the input image data, and generates a planar (2D) depth map that represents the depth distribution on a planar image. Figure 2 shows an example of the planar depth map generated at this time.

[0034] As shown in Fig. 2, a planar depth map (indicated as [Depth-MAP] in Fig. 2) is image data in the form of a normal image with depth distribution information (depth information) superimposed on it. In the example display in Fig. 2, the depth (distance) represents perspective depending on the type of hatching. Also, in Fig. 2, an index representing the depth (perspective) within the image is displayed in the margin of the image.

[0035] The AI ​​also estimates road surface conditions, etc. based on the input image data (road surface mu estimation). It then generates a planar (2D) mu map that displays areas on the road surface that indicate the degree of slipperiness (μ (mu); friction coefficient). Figure 3 shows an example of the planar mu map generated at this time.

[0036] As shown in FIG. 3, a planar mu map (denoted as [μ-MAP] in FIG. 3) is image data in the form of a normal image in which information on the degree of slipperiness of a road surface (mu information) is superimposed on an area corresponding to the road surface. In the display example of FIG. 3, slippery areas are indicated by hatching. Also, in the margin of the image in FIG. 3, an explanatory display [Low_μ] is displayed to indicate that the hatched areas indicate low mu. Note that, although the display example shown in FIG. 3 does not clearly display the degree of slipperiness, for example, by using different types of display (hatching display) indicating slippery areas, differences in the degree of slipperiness can be displayed.

[0037] Furthermore, the image recognition unit 13 combines the above-mentioned planar depth map (FIG. 2), planar mu map (FIG. 3), and object recognition data (image data) to generate a road surface mu map (FIG. 4) of a predetermined form. In this case, the image recognition unit 13 functions as an image map generator.

[0038] 4 is a display example of a road surface mu map generated in the image recognition unit 13. The road surface mu map is image data including depth information (distance information) and information on the degree of slipperiness of the road surface (mu information).

[0039] In the example of the road surface μ map shown in Fig. 4, the area near the target parking position including the vehicle is displayed in a bird's-eye view. The symbol M in Fig. 4 indicates the vehicle. The symbols M1 and M2 in Fig. 4 indicate other vehicles. In Fig. 4, the other vehicles M1 and M2 are parked in a specified parking space. The symbol 100 in Fig. 4 indicates a parking frame line. The symbol 101 in Fig. 4 indicates a car stopper installed in the parking space.

[0040] Reference numerals 111 and 112 in Fig. 4 indicate possible parking areas. Of these, reference numeral 111 in Fig. 4 indicates a first candidate parking area, and reference numeral 112 indicates a second candidate parking area. Note that the example in Fig. 4 shows a situation in which two possible parking areas are recognized as possible parking areas out of a plurality of possible parking areas.

[0041] The control unit 14 is included in the camera unit 10, and is a configuration unit or circuit unit that controls the camera unit 10 and also comprehensively controls the entire driving control device including the automatic parking control device 1 of this embodiment.

[0042] This control unit 14 is connected to various control units, such as a cockpit control unit (CP_ECU) 21, an engine control unit (E / G_ECU) 22, a transmission control unit (T / M_ECU) 23, a brake control unit (BK_ECU) 24, and a power steering control unit (PS_ECU) 25, via an in-vehicle communication line such as a CAN (Controller Area Network).

[0043] A human-machine interface (HMI) 31 arranged around the driver's seat is connected to the CP_ECU 21. The HMI 31 is configured to include, for example, a switch for instructing the execution of various driving assistance controls, a mode changeover switch for changing driving modes, a steering touch sensor for detecting the driver's steering state, a driver monitoring system (DMS) for detecting the driver's face recognition and line of sight, an in-vehicle monitor system including an in-vehicle camera for recognizing the riding conditions of the driver and other personnel, a touch panel type display device (visual display device), a combination meter, a sound device including a speaker, etc. (auditory display device), and the like.

[0044] When the CP_ECU 21 receives a control signal from the control unit 14, it appropriately notifies the driver of various warnings for the preceding vehicle, the implementation status of driving support control, and various information related to the surrounding environment of the vehicle by display, voice, etc. through the HMI 31. In addition, the CP_ECU 21 outputs various input information such as the on / off operation state of various driving support controls input by the driver through the HMI 31 to the control unit 14.

[0045] A throttle actuator 32 for an electronically controlled throttle and the like are connected to an output side of the E / G_ECU 22. In addition, various sensors such as an accelerator sensor (not shown) are connected to an input side of the E / G_ECU 22.

[0046] The E / G_ECU 22 is a drive device that generates a drive force for the vehicle by controlling the throttle actuator 32 based on a control signal from the control unit 14 or detection signals from various sensors. In this way, the E / G_ECU 22 adjusts the amount of intake air for the engine to generate a desired engine output. The E / G_ECU 22 also outputs signals such as the accelerator opening degree detected by the various sensors to the control unit 14.

[0047] An output side of the T / M_ECU 23 is connected to a hydraulic control circuit 33. In addition, an input side of the T / M_ECU 23 is connected to various sensors such as a shift position sensor (not shown).

[0048] The T / M_ECU 23 performs hydraulic control for the hydraulic control circuit 33 based on the engine torque signal estimated by the E / G_ECU 22 and detection signals from various sensors. As a result, the T / M_ECU 23 operates friction engagement elements, pulleys, and the like provided in the automatic transmission to shift the engine output at a desired gear ratio. The T / M_ECU 23 also outputs signals such as the shift position detected by the various sensors to the control unit 14.

[0049] A brake actuator 34 for adjusting the brake fluid pressure output to the brake wheel cylinders provided on the respective wheels is connected to the output side of the BK_ECU 24. In addition, various sensors such as a brake pedal sensor, a yaw rate sensor, a longitudinal acceleration sensor, and a vehicle speed sensor (not shown) are connected to the input side of the BK_ECU 24.

[0050] The BK_ECU 24 is a braking device that performs drive control of the brake actuator 34 based on a control signal from the control unit 14 or detection signals from various sensors to perform vehicle braking control. As a result, the BK_ECU 24 appropriately generates braking force on each wheel for performing forced braking control, yaw rate control, etc. on the host vehicle. The BK_ECU 24 also outputs signals of the brake operation state, yaw rate, longitudinal acceleration, vehicle speed (host vehicle speed), etc. detected by various sensors to the control unit 14.

[0051] An electric power steering motor 35 that applies a steering torque to the steering mechanism by the rotational force of the motor is connected to the output side of the PS_ECU 25. In addition, various sensors (not shown) such as a steering torque sensor and a steering angle sensor are connected to the input side of the PS_ECU 25.

[0052] The PS_ECU 25 is a steering device that performs drive control of the electric power steering motor 35 based on a control signal from the control unit 14 or detection signals from various sensors to perform steering control of the vehicle. In this way, the PS_ECU 25 generates a steering torque for the steering mechanism. The PS_ECU 25 also outputs signals such as the steering torque and steering angle detected by the various sensors to the control unit 14.

[0053] In addition, various sensors such as a locator unit 36, an on-board radar device 37, a rear sensor 38, a near-infrared sensor 39, an outside air temperature sensor 40, and a wheel speed sensor 41 are connected to the control unit 14.

[0054] The locator unit 36 ​​includes a GNSS sensor 36a and a high-precision road map database (road map DB) 36b.

[0055] The GNSS sensor 36a receives positioning signals transmitted from a plurality of positioning satellites to determine the position (latitude, longitude, altitude, etc.) of the vehicle.

[0056] The road map DB 36b is a large-capacity storage medium such as a hard disk drive (HDD) device or a solid state drive (SSD) device, and stores highly accurate three-dimensional road map information (dynamic map).

[0057] The road map DB36b contains lane data required for autonomous driving, such as lane width data, lane center position coordinate data, lane travel azimuth data, and speed limits. This lane data is stored at intervals of several meters for each lane on the road map. Furthermore, the road map DB36b contains dynamic information that changes from moment to moment, such as traffic regulations, road construction, accidents, and congestion.

[0058] Furthermore, the locator unit 36 ​​can acquire real-time information on the surrounding environment at the vehicle position measured by the GNSS sensor 36a (for example, traffic congestion information, weather information, and various information on parking lots, etc.) by communicating with an external system (not shown). In this case, the weather information includes, for example, fog occurrence information in the area including the vehicle position, rainfall information, snowfall information, snow accumulation information, temperature and humidity information, etc.

[0059] The road map DB 36b also holds information on various facilities, parking lots, etc. For example, based on a request signal from the control unit 14, the road map DB 36b outputs road map information of a set range based on the vehicle position measured by the GNSS sensor 36a as surrounding environment information to the control unit 14. Thus, in this embodiment, the road map DB 36b, together with the GNSS sensor 36a, functions as a surrounding environment recognition device that recognizes the surrounding environment of the vehicle.

[0060] The on-board radar device 37 is composed of a plurality of sensors, for example, a plurality of millimeter wave radars. Here, the plurality of millimeter wave radars detect three-dimensional objects such as pedestrians and vehicles traveling alongside, as well as structures (e.g., curbs, guard rails, walls of buildings, plants, and other three-dimensional objects) provided on the edge of the road (e.g., the edge on the shoulder side) by receiving and analyzing the reflected waves from objects in response to the output radio waves. Furthermore, the plurality of millimeter wave radars also detect three-dimensional obstacles present on the road. In this case, the plurality of millimeter wave radars detect the width of the three-dimensional object, the position of the representative point of the three-dimensional object (relative position and relative distance to the vehicle itself), the relative speed, and other specific information related to the three-dimensional object.

[0061] The multiple sensors (multiple millimeter wave radars, etc.) included in the on-board radar device 37 are disposed, for example, on the left and right sides of the front bumper (referred to as front left and right side sensors) and on the left and right sides of the rear bumper (referred to as rear left and right side sensors). The front left and right side sensors detect, as surrounding environment information, three-dimensional objects existing in areas diagonally forward and to the left and right and to the sides of the vehicle, which are difficult to recognize in the image from the stereo camera 11. The rear left and right side sensors detect, as surrounding environment information, three-dimensional objects existing in areas diagonally forward and to the left and right and to the rear of the vehicle, which are difficult to recognize with the front left and right side sensors.

[0062] In this manner, in this embodiment, the on-vehicle radar device 37 functions as a surrounding environment recognition device that recognizes the surrounding environment of the vehicle. Information acquired by each sensor of the on-vehicle radar device 37 is sent to the image recognition unit 13 via the control unit 14.

[0063] The rear sensor 38 is, for example, configured with a sonar device that uses ultrasonic waves to measure the distance to and shape of an object. At least one (or multiple) rear sensor 38 is provided, for example, on the rear bumper. The rear sensor 38 detects, as surrounding environment information, a three-dimensional object present in an area behind the vehicle that is difficult to recognize using the rear left and right side sensors. Thus, in this embodiment, the rear sensor 38 functions as a surrounding environment recognition device that recognizes the surrounding environment of the vehicle.

[0064] The coordinates of each object outside the vehicle contained in each of the surrounding environment information recognized by the image recognition unit 13, the surrounding environment information recognized by the locator unit 36, the surrounding environment information recognized by the on-board radar device 37, and the surrounding environment information recognized by the rear sensor 38 are all converted by the control unit 14 into coordinates of a three-dimensional coordinate system with the center of the vehicle as the origin.

[0065] The near-infrared sensor 39 is a sensor that recognizes the surrounding conditions of the vehicle, particularly road conditions such as the road surface temperature. The road surface temperature, the amount of moisture on the road surface, the amount of snow on the road surface, etc. are recognized based on the information acquired by the near-infrared sensor 39. The outside air temperature sensor 40 is a sensor that detects changes in the outside air temperature around the vehicle.

[0066] Information acquired by each sensor, such as the near-infrared sensor 39 and the outside air temperature sensor 40, is detected as surrounding environment information. In this embodiment, each sensor, such as the near-infrared sensor 39 and the outside air temperature sensor 40, functions as a surrounding environment recognition device that recognizes the surrounding environment of the vehicle.

[0067] The wheel speed sensor 41 is a sensor that detects the wheel rotation speed by detecting a pulse signal (wheel speed pulse) that is generated in proportion to the rotation speed of each wheel (generally four wheels) of the vehicle.

[0068] The control unit 14 executes vehicle running control based on the various information acquired by the various sensors. The running control includes, for example, engine output control by the E / G_ECU 22 and torque distribution control for each drive wheel, forward or reverse direction control by control of the transmission by the T / M_ECU 23, and individual braking control (brake control) for each wheel by the BK_ECU 24, thereby performing vehicle running control as required.

[0069] In addition to the above-mentioned sensors, various sensors for acquiring surrounding environmental information can also be used, such as a LiDAR (Light Detection And Ranging) device that uses laser light to measure the distance to and shape of an object.

[0070] The stereo camera 11 described above mainly observes a predetermined field of view in front of the vehicle. In addition, a plurality of camera devices of the same configuration may be provided to observe predetermined field of view in the sides and rear of the vehicle. In this way, the entire periphery of the vehicle can be observed.

[0071] Furthermore, the control unit 14 includes therein a parking control unit 15, a wheel selection unit 16, a movement amount calculation unit 17, and the like.

[0072] The parking control unit 15 is a configuration unit or a circuit unit that performs various processes when executing automatic parking control based on various information acquired by various sensors. Here, the various processes performed when executing automatic parking control include, for example, a process of searching for a parking position (i.e., a parking available area) as a parking target, a process of generating a parking target path for leading the vehicle to the searched parking position, and a process of calculating vehicle control values ​​(control values ​​for steering control, drive control, braking control, etc.) when moving the vehicle along the generated parking target path.

[0073] The wheel selection unit 16 is a configuration unit or circuit unit that performs a process of selecting and acquiring the most reliable wheel position information. The wheel selection unit 16 first calculates a predicted path for each wheel (usually four wheels) based on the parking target path generated by the parking control unit 15 and the vehicle's specification information (e.g., tread value, wheelbase value, etc.) previously stored in a predetermined storage memory or the like (not shown). Next, the wheel selection unit 16 performs a calculation process of superimposing the predicted path for each wheel thus calculated on the road surface μ map (see FIG. 5). Then, the wheel selection unit 16 selects the wheel that passes through the least slippery area (high μ area) from the predicted paths for each wheel.

[0074] Here, Fig. 5 is a display example in which the parking target route and the predicted route of each wheel are superimposed on the road surface mu map of Fig. 4. Reference symbol R1 in Fig. 5 indicates the first parking target route to the first parking candidate area 111 of the host vehicle M. Reference symbols R1R and R1L in Fig. 5 are the predicted wheel routes of each wheel of the host vehicle M corresponding to the first parking target route R1. Among these, reference symbol R1R indicates the predicted wheel route of the right wheel, and reference symbol R1L indicates the predicted wheel route of the left wheel.

[0075] Similarly, the reference symbol R2 in Fig. 5 indicates a second target route to the second parking candidate area 112 of the host vehicle M. The reference symbols R2R and R2L in Fig. 5 indicate predicted wheel routes of the respective wheels of the host vehicle M corresponding to the second parking target route R2. Among these, the reference symbol R2R indicates the predicted wheel route of the right wheel, and the reference symbol R2L indicates the predicted wheel route of the left wheel.

[0076] For example, a wheel predicted path exists for each of four wheels (front, rear, left and right wheels). However, in the display example of Fig. 5, in order to avoid cluttering the drawing, only two predicted paths for the left and right wheels are shown instead of all predicted paths. The display example is not limited to this, and predicted paths for all wheels may be displayed.

[0077] The movement amount calculation unit 17 is a component unit or a circuit unit that performs a calculation process of an estimated movement amount of the vehicle. The movement amount calculation unit 17 receives the output of the wheel speed sensor 41 to acquire the wheel speed pulse of each wheel, and calculates the movement amount (movement distance) of the reference position of the vehicle (for example, the center position of the vehicle or the center position of the rear axle of the vehicle) from the rotation amount of each wheel. Then, it performs a vehicle position estimation process (odometry process) that estimates the traveling trajectory from the calculated accumulated movement distance to estimate the vehicle position.

[0078] In addition, all or part of the image recognition unit 13, control unit 14, parking control unit 15, wheel selection unit 16, movement amount calculation unit 17, CP_ECU 21, E / G_ECU 22, T / M_ECU 23, BK_ECU 24, PS_ECU 25, locator unit 36, etc. are composed of a processor including hardware.

[0079] Here, the processor is configured by a well-known configuration including, for example, a central processing unit (CPU), a random access memory (RAM), a read only memory (ROM), a non-volatile memory, a non-volatile storage device, a non-transitory computer readable medium, and the like, and peripheral devices thereof.

[0080] Software programs executed by the CPU and fixed data such as data tables are stored in advance in ROM, non-volatile memory, non-volatile storage device, etc. Then, the CPU reads out the software programs stored in ROM, etc., expands them in RAM, and executes them, and the software programs appropriately refer to various data, etc., thereby realizing the functions of the above-mentioned components and components (13-17, 21-25, 36), etc.

[0081] The processor may be configured with a semiconductor chip such as a Field Programmable Gate Array (FPGA), etc. Each of the above components and components (13 to 17, 21 to 25, 36) may be configured with an electronic circuit.

[0082] Furthermore, the software program may be in a form in which the whole or part is recorded as a computer program product on a portable disk medium such as a flexible disk, CD-ROM, or DVD-ROM, or on a non-transitory computer readable medium such as a card-type memory, an HDD (Hard Disk Drive) device, or an SSD (Solid State Drive) device.

[0083] The operation of the automatic parking control device 1 of this embodiment configured as described above will be described below with reference to Figs. 6 and 7. Fig. 6 is a flowchart showing the operation of a vehicle driving control device including the automatic parking control device of this embodiment. Fig. 7 is a flowchart showing a subroutine of the road surface μ map generation process (the process of step S6 in Fig. 6) in the flowchart of Fig. 6. Note that Figs. 6 and 7 mainly explain the automatic parking control process.

[0084] When the driving control device of the vehicle M is started and the automatic parking control process by the automatic parking control device 1 starts, first, in step S1 of Fig. 6, the control unit 14 executes a process to initialize the road surface mu map information and the vehicle position information. This initialization process is a general process to erase the information from the previous driving from the memory and initialize the memory.

[0085] Next, in step S2, the control unit 14 executes a surrounding environment recognition process based on the surrounding environment information acquired by various sensors such as the camera unit 10, the locator unit 36, and the on-board radar device 37. This surrounding environment recognition process is a general process executed by a driving control device. The surrounding environment recognition process is executed continuously while the host vehicle M is traveling.

[0086] In step S3, the control unit 14 executes a vehicle position estimation process by the movement amount calculation unit 17. This vehicle position estimation process is a process that detects output signals from, for example, the wheel speed sensor 41 and the steering angle sensor (not shown), estimates the amount of movement from the initial position of the vehicle M, and calculates the current estimated position (odometry process). This vehicle position estimation process is also executed continuously while the vehicle M is traveling.

[0087] Next, in step S4, the control unit 14 executes a road surface μ map generation process by controlling the image recognition unit 13. This road surface μ map generation process will be described below with reference to FIG.

[0088] In step S21 of FIG. 7, the control unit 14 inputs, to the AI ​​included in the image recognition unit 13, image data that has been acquired by the stereo camera 11 and has been subjected to predetermined processing by the image processing unit 12.

[0089] Next, in step S22, the control unit 14 controls the image recognition unit 13 to execute a planar depth map generation process. This planar depth map generation process is a process of performing depth estimation (distance estimation) by image analysis of the image data input to the AI ​​to generate a planar depth map (see FIG. 2).

[0090] Next, in step S23, the control unit 14 controls the image recognition unit 13 to execute a planar mu map generation process. This planar mu map generation process is a process of estimating road surface conditions, etc. (road surface mu estimation) by image analysis of the image data input to the AI, and generating a planar mu map (see FIG. 3).

[0091] In step S24, the control unit 14 controls the image recognition unit 13 to perform object recognition processing by image analysis of the input image data.

[0092] In step S25, the control unit 14 controls the image recognition unit 13 to execute a fusion process. This fusion process is a process of fusing the generated planar depth map and planar mu map with object recognition data to generate a road surface mu map of a predetermined form (see FIG. 4).

[0093] In step S26, the control unit 14 controls the image recognition unit 13 to update the generated road surface μ map and the self-position information, and then returns to the original processing step (RETURN).

[0094] 6, in step S5, the control unit 14 controls the parking control unit 15 to execute a parking position search process based on surrounding environment information acquired by various sensors such as the camera unit 10, the locator unit 36, and the in-vehicle radar device 37. This parking position search process is a process for searching for a parking position (parking area) that is a parking target for the host vehicle M based on the object recognition results of a parking space, another vehicle, etc.

[0095] In step S6, the control unit 14 controls the parking control unit 15 to generate a parking target route connecting the vehicle position and the parking position based on the current estimated position information of the vehicle M obtained in the process of step S3 described above and the target parking position information obtained in the process of step S5 described above (parking target route generation process).

[0096] In step S7, the control unit 14 controls the wheel selection unit 16 to calculate the predicted paths of each of the four wheels from the parking target path information acquired in the processing of step S6 described above and the specification information of the host vehicle M (wheel predicted path calculation processing).

[0097] In step S8, the control unit 14 controls the wheel selection unit 16 to compare each wheel predicted path obtained in the processing of step S7 described above with the road surface mu map obtained in the processing of step S4 described above, and executes a wheel selection process to select the wheel that will take the least slippery path among the four wheels.

[0098] Here, the wheel passing through the least slippery path may be selected, for example, by comparing the total value of all paths for each wheel and selecting one wheel passing through the least slippery path. In addition, a wheel passing through a partially less slippery area may be selected according to the moving distance (moving area) of a reference position of the vehicle (for example, the center position of the vehicle or the center position of the rear axle of the vehicle) and switched for each area.

[0099] Specifically, for example, the left front wheel may be selected when the travel distance is between 1m and 5m, and the right rear wheel may be selected when the travel distance is between 6m and 10m, so that the selected wheel is switched for each region of the entire route.

[0100] In step S9, the control unit 14 controls the movement amount calculation section 17 to acquire the wheel speed pulse (the output of the wheel speed sensor 41) of the wheel selected in the process of step S8 described above. Then, based on the acquired data, the movement distance of the reference position of the vehicle (for example, the center position of the vehicle or the center position of the rear axle of the vehicle) is calculated. The calculation result is transmitted to the parking control section 15.

[0101] In step S10, the control unit 14 controls the parking control unit 15 to execute a vehicle control value calculation process. This vehicle control value calculation process is a process for calculating vehicle control values ​​(control values ​​for steering control, drive control, braking control, etc.) for automatically driving the host vehicle M along the set parking target route.

[0102] In step S11, the control unit 14 executes the automatic parking control process for the host vehicle M based on the vehicle control value calculated in the above-mentioned step S10. Then, when parking of the host vehicle M at the target parking position is completed, the series of processes ends (END).

[0103] As described above, according to the embodiment, in the automatic parking control device 1 mounted on a vehicle such as an automobile, The surrounding environment is recognized based on image data as environmental information acquired by the camera unit 10 as a surrounding environment recognition device, and road surface conditions, etc. are estimated. According to the estimated road surface conditions, the least slippery predicted wheel path is selected, and the movement amount of the host vehicle M is predicted based on the selected predicted wheel path, so that highly accurate vehicle movement amount information can be acquired, and therefore highly accurate vehicle control can be realized.

[0104] In addition, even though the vehicle movement amount is predicted using the wheel speed pulse when automatic parking control, etc. is executed, the tracking ability of the parking target path is not reduced even on slippery road conditions such as snowy roads. In other words, the number of turns and the amount of deviation of the final target position can be reduced, improving the quality of automatic parking control, etc.

[0105] In addition, when describing the configuration and operation of the automatic parking control device of the above embodiment, the automatic parking control is mainly performed as an example. However, the operation of the automatic parking control device of this embodiment is not limited to the above example. The control performed by the automatic parking control device of this embodiment can also be applied when performing parking assistance control that assists the driver in parking operations.

[0106] In addition, in the above embodiment, an example is shown in which a plurality of parking target routes (R1, R2) are generated and displayed. In this way, when a plurality of parking target routes are generated, it is necessary to determine which parking target route to select. In this case, for example, when displaying the generated plurality of parking target routes, it is more preferable to display the least slippery route among the plurality of parking target routes in a distinguishable form as a recommended route. In this case, for example, it is conceivable to display the recommended route in a visually distinguishable form, such as by displaying it in color. Then, on such a display screen displaying the plurality of parking target routes, the driver may manually select a desired parking target route. In this form, the driver can easily select a less slippery target parking route. Alternatively, a form may be adopted in which a predetermined judgment criterion is set and the control unit 14 performs automatic selection control according to the judgment criterion.

[0107] The present invention is not limited to the above-mentioned embodiment, and various modifications and applications can be implemented within the scope of the gist of the invention. Furthermore, the above-mentioned embodiment includes inventions at various stages, and various inventions can be extracted by appropriate combinations of the disclosed multiple constituent elements. For example, even if some constituent elements are deleted from all the constituent elements shown in the above-mentioned one embodiment, if the problem to be solved by the invention can be solved and the effect of the invention can be obtained, the configuration from which the constituent elements are deleted can be extracted as the invention. Furthermore, the constituent elements across different embodiments may be appropriately combined. The present invention is not restricted by its specific embodiment except as limited by the attached claims. [Explanation of symbols]

[0108] 1...Automatic parking control device 10...Camera unit 11…Stereo camera 11a…Main camera 11b…Sub camera 12...Image processing unit 13...Image recognition unit 14…Control unit 15...Parking control unit 16...Wheel selection section 17...Movement amount calculation section 21...Cockpit control unit (CP_ECU) 22…Engine control unit (E / G_ECU) 23...Transmission control unit (T / M_ECU) 24...Brake control unit (BK_ECU) 25…Power steering control unit (PS_ECU) 31…Human Machine Interface (HMI) 32...Throttle actuator 33...Hydraulic control circuit 34…Brake actuator 35...Electric power steering motor 36…Locator unit 36a…GNSS sensor 36b…High-precision road map database (road map DB) 37... Vehicle-mounted radar device 38…Rear sensor 39...Near infrared sensor 40...Outside air temperature sensor 41...Wheel speed sensor 100...Parking line 101...Car stop 111…First parking candidate area 112…Second parking candidate area M…Own vehicle M1,M2…Other vehicles R1: First parking target route R1L: Predicted wheel path of the left wheel corresponding to the first parking target path R1R: Predicted wheel path of the right wheel corresponding to the first parking target path R2: Second parking target route R2L: Predicted wheel path of the left wheel corresponding to the second parking target path R2R: Predicted wheel path of the right wheel corresponding to the second parking target path

Claims

1. An automatic parking control device that performs driving control to guide a vehicle to a parking area, A surrounding environment recognition device for acquiring surrounding environment information of the vehicle; a parking control unit that searches for a parking area based on the surrounding environment information acquired by the surrounding environment recognition device, generates a target route for moving the vehicle to the searched parking area as a destination point, and performs driving control to move the vehicle along the generated target route; an image processing unit that estimates a distance to a recognized three-dimensional object and a degree of slipperiness of a road surface based on the surrounding environment information acquired by the surrounding environment recognition device; an image map generating unit that generates a road surface μ map by image synthesis of the distance information and the road surface slipperiness degree information estimated by the image processing unit and the surrounding environment information; a wheel selection unit that predicts a path along which each of a plurality of wheels of the vehicle will travel based on the target path, overlays the predicted path of each wheel on the road surface μ map, and selects a wheel that will travel the least slippery path among the plurality of wheels; a movement amount calculation unit that acquires a wheel speed pulse of the selected wheel and calculates a movement amount of a reference position of the vehicle; An automatic parking control device comprising:

2. 2. The automatic parking control device according to claim 1, wherein the surrounding environment recognition device is an in-vehicle camera device that acquires surrounding environment information of the vehicle as image data.

3. The automatic parking control device according to claim 1, characterized in that the image processing unit estimates the distance to the recognized three-dimensional object and the degree of slipperiness of the road surface based on the image data obtained by imaging a predetermined range in front of the vehicle.

4. The image map generator includes: a planar depth map that estimates a depth of a recognized three-dimensional object based on the input image data and shows the estimated depth information as depth distribution information on a planar image; a planar mu map that estimates road surface conditions based on the input image data and displays the degree of slipperiness of the road surface in a form that can be distinguished for each predetermined area; object recognition data of a three-dimensional object recognized based on the input image data; Generate a road surface μ map by fusing the above 2. The automatic parking control device according to claim 1 .

5. The automatic parking control device according to claim 1, wherein the wheel selection unit selects one wheel based on a total value of the entire path, or selects a wheel that passes through a non-slip area for each area in the entire path.

Images