Vehicle control devices

Abstract

The present invention provides a vehicle control device comprising: a camera; a detector for acquiring positional information of a target object based on reflected waves; a position estimating unit for estimating the position of the target object based on the positional information acquired by the camera and the detector; an actuator control unit for controlling a travel actuator based on the estimated position of the target object; and a slope detection unit for detecting a predetermined slope state, i.e., a state in which the slope of a road ahead of a vehicle is an upward slope of a predetermined degree or greater relative to the road surface at the vehicle's current position. Upon detecting the predetermined slope state, the position estimating unit reduces the reliability of positional information along the vehicle's travel direction acquired by the camera, among the positional information of the target object captured on the road surface in the predetermined slope state, and estimates the target object's position.

Description

Technical Field

[0001] The present invention relates to a vehicle control device for controlling a vehicle based on information from a sensor that detects the outside world. Background Art

[0002] As such a device, there is a known device that uses sensor fusion of radar and a camera to identify a preceding vehicle traveling ahead of the vehicle and controls the automatic braking system based on the identification result.

[0003] However, if the road surface ahead of the host vehicle is inclined at an uphill slope relative to the road surface on which the host vehicle is located, it may be impossible to accurately recognize an object such as a preceding vehicle by sensor fusion.

[0004] Prior art literature

[0005] Patent Literature

[0006] Patent Document 1: Japanese Patent Application Publication No. 2005-329779 (JP 2005-329779 A). Summary of the Invention

[0007] A vehicle control device according to one embodiment of the present invention includes: a camera for capturing images of the surrounding environment surrounding a host vehicle and acquiring positional information of a target object; a detector for acquiring the positional information of the target object based on reflected waves from a detection target within the camera's capturing area; a position estimating unit for estimating the position of the target object based on the positional information acquired by the camera and the positional information acquired by the detector; an actuator control unit for controlling a driving actuator mounted on the host vehicle based on the position of the target object estimated by the position estimating unit; and a slope detecting unit for detecting a predetermined slope state, i.e., an upward slope of a predetermined degree or greater relative to the road surface at the vehicle's current position. When the slope detecting unit detects the predetermined slope state, the position estimating unit reduces the reliability of the positional information of the host vehicle along the travel direction acquired by the camera, among the positional information of the target object captured on the road surface in the predetermined slope state, and estimates the position of the target object. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The objects, features and advantages of the present invention will be further clarified through the following description of the embodiments in conjunction with the accompanying drawings.

[0009] Figure 1 This is a block diagram schematically showing the overall configuration of a vehicle control system of an autonomous driving vehicle including a vehicle control device according to an embodiment of the present invention.

[0010] Figure 2 This is a block diagram showing a main configuration of a vehicle control device according to an embodiment of the present invention.

[0011] Figure 3 This is a diagram schematically showing an example of the operation of the vehicle control device according to the embodiment of the present invention.

[0012] Figure 4 It is shown by Figure 2 A flowchart of an example of processing performed by the controller. DETAILED DESCRIPTION

[0013] The following reference Figures 1 to 4 The embodiments of the present invention are described. The vehicle control device according to the embodiments of the present invention can be applied to both vehicles with autonomous driving capabilities, i.e., autonomous vehicles, and manually driven vehicles without autonomous driving capabilities. Below, an example of applying the vehicle control device to an autonomous vehicle is described. It should be noted that a vehicle to which the vehicle control device of this embodiment is applied is sometimes referred to as the "vehicle," as distinguished from other vehicles.

[0014] The present vehicle may be any of an engine vehicle having an internal combustion engine (engine) as a driving source, an electric vehicle having a travel motor as a driving source, or a hybrid vehicle having an engine and a travel motor as driving sources. The present vehicle (autonomous driving vehicle) can be driven not only in an autonomous driving mode that does not require a driver's driving operation, but also in a manual driving mode in which the driver performs a driving operation.

[0015] First, the outline structure of autonomous driving is explained. Figure 1 1 is a block diagram schematically showing the overall configuration of a vehicle control system 100 including a vehicle control device according to an embodiment of the present invention. Figure 1 As shown, the vehicle control system 100 mainly includes a controller 10 and an external sensor group 1, an internal sensor group 2, an input and output device 3, a positioning unit 4, a map database 5, a navigation device 6, a communication unit 7, and an actuator AC for driving, which are communicatively connected to the controller 10 via CAN communication lines, etc.

[0016] External sensor group 1 is a collective term for multiple sensors (external sensors) that detect external conditions as information about the vehicle's surroundings. For example, external sensor group 1 includes laser radar (LIDAR), radar, and cameras. Lidar detects the position (distance and direction) of objects around the vehicle by emitting laser beams and detecting reflected light. Radar detects the position of objects around the vehicle by emitting electromagnetic waves and detecting reflected waves. Cameras use imaging elements such as CCDs (charge-coupled devices) and CMOS (complementary metal oxide semiconductors) to capture images of the vehicle's surroundings. Lidar and radar can detect objects within the camera's imaging area.

[0017] The internal sensor group 2 is a collective term for multiple sensors (internal sensors) that detect the vehicle's driving state. For example, the internal sensor group 2 includes a vehicle speed sensor that detects the vehicle's speed, an acceleration sensor that detects the vehicle's acceleration in the front-to-back and left-to-right directions, and a rotational speed sensor that detects the rotational speed of the driving source. Sensors that detect driver operations in manual driving mode, such as those on the accelerator pedal, brake pedal, and steering wheel, are also included in the internal sensor group 2.

[0018] The input / output device 3 is a general term for devices that allow the driver to input commands and output information to the driver. For example, the input / output device 3 includes various switches for the driver to input various commands by operating operating members, a microphone for the driver to input commands by voice, a display that provides information to the driver by displaying images, and a speaker that provides information to the driver by voice.

[0019] The positioning unit (GNSS unit) 4 includes a positioning sensor that receives positioning signals transmitted from positioning satellites. This positioning sensor may also be included in the internal sensor group 2. Positioning satellites are artificial satellites such as GPS satellites and Quasi-Zenith Satellites. The positioning unit 4 uses the positioning information received by the positioning sensor to determine the current position (latitude, longitude, and altitude) of the vehicle.

[0020] The map database 5 stores general map information used by the navigation system 6 and is comprised of, for example, a hard disk or semiconductor devices. This map information includes road location information, road shape information (such as curvature), and the location information of intersections and forks. It should be noted that the map information stored in the map database 5 is different from the high-precision map information stored in the storage unit 12 of the controller 10.

[0021] The navigation device 6 searches for a target route on the road leading to a destination input by the driver and provides guidance along the target route. Destination input and guidance along the target route are performed via the input / output device 3. The target route is calculated based on the current position of the vehicle measured by the positioning unit 4 and the map information stored in the map database 5. The current position of the vehicle can also be measured using detection values ​​from the external sensor group 1, and the target route can be calculated based on this current position and the high-precision map information stored in the storage unit 12.

[0022] Communication unit 7 communicates with various servers (not shown) via a network, including wireless communication networks such as the Internet and mobile phone networks, and obtains map information, travel history information, and traffic information from the servers periodically or at random. Networks include not only public wireless communication networks but also closed communication networks established within each designated administrative area, such as wireless LANs, Wi-Fi (registered trademark), and Bluetooth (registered trademark). The obtained map information is output to map database 5 and storage unit 12, and the map information is updated.

[0023] Actuator AC is a driving actuator used to control the vehicle's travel. If the driving source is an engine, actuator AC includes a throttle actuator that adjusts the opening of the engine's throttle valve (throttle opening). If the driving source is a driving motor, the driving motor is included in actuator AC. Actuator AC also includes a brake actuator that activates the vehicle's braking system and a steering actuator that drives the steering system.

[0024] The controller 10 is composed of an electronic control unit (ECU). More specifically, the controller 10 includes a computer having a computing unit 11 such as a CPU (microprocessor), a storage unit 12 such as a ROM (read-only memory) and a RAM (random access memory), and other peripheral circuits not shown in the figure, such as an I / O (input / output) interface. It should be noted that multiple ECUs with different functions, such as an engine control ECU, a travel motor control ECU, and a brake device ECU, can be set separately, but for convenience, Figure 1 Controller 10 is shown in FIG as a collection of these ECUs.

[0025] The storage unit 12 stores highly accurate and detailed road map information. This road map information includes information on road locations, road shapes (such as curvature), road slopes, intersections, forks, lane numbers, lane widths, and the location of each lane (including lane center positions and lane boundary lines), map landmarks (such as traffic lights, signs, and buildings), and road surface conditions such as surface roughness. Landmark information (landmark information) includes information on the shape (outline), characteristics, and location of the landmarks.

[0026] The calculation unit 11 includes a vehicle position recognition unit 13 , an outside world recognition unit 14 , an action plan generation unit 15 , and a travel control unit 16 as functional components.

[0027] The vehicle position recognition unit 13 identifies the vehicle's position on the map (vehicle position) based on the vehicle's position information acquired by the positioning unit 4 and the map information in the map database 5. Alternatively, the vehicle's position may be identified using map information stored in the storage unit 12 and information about the vehicle's surroundings detected by the external sensor group 1, thereby enabling high-precision identification of the vehicle's position. It should be noted that if the vehicle's position can be measured using external sensors located on or near the road, the vehicle's position can also be identified by communicating with these sensors via the communication unit 7.

[0028] The external recognition unit 14 identifies the external conditions surrounding the vehicle based on signals from the external sensor group 1, such as a laser radar, radar, and camera. For example, it identifies the position, speed, and acceleration of surrounding vehicles (vehicles in front and behind) traveling around the vehicle, the position of surrounding vehicles parked or stopped around the vehicle, and the position and status of other objects. Other objects include signs, traffic lights, road dividing lines or stop lines, buildings, railings, utility poles, billboards, pedestrians, bicycles, tunnel entrances, etc. The status of other objects includes the color of the traffic light (red, green, yellow), the speed and direction of pedestrians and bicycles, etc.

[0029] The object that is the detection target of the external sensor group 1 is called a target object. Target objects include both people and objects, as well as both moving objects and stationary objects. The external recognition unit 14 performs comprehensive processing (fusion processing) on ​​the detection data of different types of sensors (such as cameras and radars) that constitute the external sensor group 1, determines whether the same target object is detected by each sensor, and derives the position data of the target object. For example, when the same target object is detected, fusion processing such as coordinate transformation, data supplementation, and averaging are performed on the detection data to derive the position data of the target object. In this way, the position of the target object can be accurately identified. It should be noted that the position data not only includes data showing a single position, but also includes data showing the change in position per unit time, that is, speed.

[0030] The action plan generation unit 15 generates a driving trajectory (target trajectory) for the vehicle from the current time point until a predetermined time has passed, based on, for example, the target route calculated by the navigation device 6, the map information stored in the storage unit 12, the vehicle's position identified by the vehicle position recognition unit 13, and the external conditions (objects) identified by the external environment recognition unit 14. If multiple candidate trajectories exist on the target route as target trajectories, the action plan generation unit 15 selects the optimal trajectory that complies with the law and meets criteria such as efficient and safe driving, and sets the selected trajectory as the target trajectory. The action plan generation unit 15 then generates an action plan corresponding to the generated target trajectory. Specifically, the action plan generation unit 15 generates various action plans corresponding to overtaking (passing a preceding vehicle), lane change (changing lanes), following (following a preceding vehicle), lane keeping (maintaining the lane without departing), deceleration, or acceleration. When generating the target trajectory, the action plan generation unit 15 first determines a driving mode and generates the target trajectory based on the driving mode.

[0031] The driving control unit 16 controls each actuator AC so that the vehicle travels along the target trajectory generated by the action plan generation unit 15 in the automatic driving mode. More specifically, the driving control unit 16 calculates the required driving force for obtaining the target acceleration per unit time calculated by the action plan generation unit 15, taking into account the driving resistance determined by the road slope, etc. in the automatic driving mode. The actuator AC is then feedback-controlled so that the actual acceleration detected by the internal sensor group 2, for example, reaches the target acceleration. In other words, the actuator AC is controlled so that the vehicle travels at the target speed and target acceleration. It should be noted that in the manual driving mode, the driving control unit 16 controls each actuator AC based on the driving instructions (steering operation, etc.) from the driver obtained by the internal sensor group 2.

[0032] However, in this embodiment, the position data for the same target object is obtained based on the detection values ​​of different types of external sensor groups 1, such as cameras and radars. However, when the host vehicle is traveling on flat ground with an upward slope ahead, the accuracy of the target object's position detected by the camera, which detects the preceding vehicle, decreases as the preceding vehicle begins to travel uphill. Specifically, the accuracy of distance measurement by a camera is inferior to that of radar and lidar, making it difficult to accurately detect the position of the preceding vehicle when the preceding vehicle is traveling uphill. Therefore, this embodiment configures the vehicle control device as follows to accurately detect the position of the target object even when the preceding vehicle is traveling at an upward slope relative to the host vehicle (e.g., traveling uphill).

[0033] Figure 2 This is a block diagram showing the main structure of the vehicle control device 50 according to the embodiment of the present invention. Figure 1 As part of the vehicle control system 100. Figure 2 As shown, the vehicle control device 50 includes a camera 1 a , a detector 1 b , a controller 10 , and an actuator AC.

[0034] The camera 1a is a single-lens reflex camera having an image sensor (image sensor) such as a CCD (charge coupled device) or a CMOS (complementary metal oxide semiconductor). Figure 1 Part of the external sensor group 1. The camera 1a can also be a stereo camera. For example, the camera 1a is installed at a predetermined position in front of the vehicle, continuously captures the space in front of the vehicle, and obtains images of target objects (camera images). The target objects include the front vehicle, people, buildings, etc. traveling in front of the vehicle. The position and type of the target object can be identified based on the camera image. That is, when the horizontal direction of the two-dimensional camera image is set to the x direction and the vertical direction is set to the y direction, the position of the target object in the vehicle width direction can be obtained based on the position in the x direction on the camera image, and the position of the target object in the height direction and the travel direction can be obtained based on the position in the y direction. In other words, the position data (position information) of the target object can be obtained by the camera 1a.

[0035] Detector 1b is a detector that detects the distance from the vehicle to the target object (target object) based on the reflected wave from the detection object (target object), and includes one or both of radar and lidar. Detector 1b can obtain the position data (position information) of the target object with respect to the vehicle. The position data includes data on the position and speed of the target object. The detection range of detector 1b is included in the shooting area of ​​camera 1a. Therefore, when the target object detected by camera 1a is the same as the target object detected by detector 1b, the position and speed of the target object can be derived by performing sensor fusion processing. Hereinafter, the target object detected by camera 1a will be referred to as a camera target object, and the target object detected by detector 1b will be referred to as a radar target object.

[0036] Figure 2 The controller 10 includes a slope detection unit 14a, a position estimation unit 14b, and a travel control unit 16 as a calculation unit 11 ( Figure 1 The slope detection unit 14a and the position estimation unit 14b are configured to identify the external conditions around the vehicle, such as Figure 1 The external world recognition unit 14 is composed of.

[0037] The slope detection unit 14a determines whether the road ahead of the vehicle is in a specified slope state based on the camera image captured by the camera 1a. This determines the specified slope state of the road ahead of the vehicle. A specified slope state refers to an upward slope of at least a specified degree relative to the road surface at the vehicle's current position. Therefore, if the road surface at the vehicle's current position is in an upward slope, this refers to a steep upward slope exceeding the specified degree. The slope detection unit 14a is capable of detecting the specified slope state (determining the presence or absence of the specified slope state) based on a camera image that includes the vehicle ahead.

[0038] Figure 3 1 is a diagram showing an example of a driving scene of the vehicle 101. Figure 3 FIG2 schematically shows a scene in which a front vehicle 102 is traveling on an uphill slope in front of a host vehicle 101 traveling on flat ground. Figure 3 As shown, when the front vehicle 102 is traveling on an uphill slope, when looking at the y-direction length (height) from the own vehicle 101 to the front vehicle 102 on the two-dimensional camera image, that is, the length starting from the lower end of the camera image, the y-direction length up to the rear end of the front vehicle 102 (the lower end in the image) is the minimum height h1, and the y-direction length up to the front end of the front vehicle 102 (the upper end in the image) is the maximum height h2.

[0039] In this case, the greater the slope of the uphill slope, the greater the difference Δh (= h2-h1) between the maximum height h2 and the minimum height h1. In addition, the greater the slope of the uphill slope, the greater the ratio α (= h2 / h1) of the maximum height h2 to the minimum height h1. Taking this into consideration, the slope detection unit 14a detects (determines) the specified slope state when the height difference Δh is greater than a specified value or the height ratio α is greater than a specified value. It should be noted that when the front vehicle 102 is traveling on an uphill slope, the minimum height h1 becomes larger. Therefore, as a simpler method, the specified slope state can also be detected when the minimum height h1 is greater than a specified value. When the slope detection unit 14a detects the specified slope state, it assigns a ramp mark to the camera object mark detected within the specified range AR centered on the front vehicle 102. For example, for the front vehicle 102, Figure 3 The landmark A is assigned to the ramp. Figure 3 In the example, a portion of the object A is out of the predetermined range AR, but most of the object A is within the predetermined range AR. It should be noted that a ramp mark may be assigned to the object that is entirely within the predetermined range AR.

[0040] When the slope detection unit 14a detects a predetermined slope, the position estimation unit 14b reduces the reliability of the y-direction position data of the camera object marked with a ramp sign. Rather than always reducing the reliability of the camera object marked with a ramp sign, the reliability of the camera object may be reduced when the difference between the y-direction position of the camera object and the y-direction position of the radar object when capturing the same detection target exceeds a predetermined value. It should be noted that the y-direction position of the camera object refers to the position of the object in the vehicle's travel direction, as determined based on the y-direction position of the camera image. The y-direction position of the radar object refers to the position of the object in the vehicle's travel direction (distance from the vehicle), as determined by the detector 1b, corresponding to the y-direction position of the camera image.

[0041] When the reliability of the camera object decreases, the position estimating unit 14b uses only the radar object, not the camera object, to estimate the y-position of the vehicle control object (control object), that is, its relative position relative to the vehicle's direction of travel. This allows accurate determination of the position of the preceding vehicle 102 while traveling on a slope. It should be noted that when the difference between the y-position of the camera object and the y-position of the radar object is less than a specified value, the position estimating unit 14b uses both the camera object and the radar object to estimate the object's position. As for the object's x-position, the difference between the camera object and the radar object is small even when traveling uphill, so both the camera object and the radar object are used to estimate the object's position.

[0042] On the other hand, sometimes a radar object corresponding to a camera object assigned a slope sign cannot be found. In this case, the position estimating unit 14b determines whether the camera object and the radar object have been associated within a specified period of time due to the camera 1a and the detector 1b detecting the same object. Specifically, it determines whether a radar object corresponding to the camera object has been found within the specified period of time. In this case, when the camera object and the radar object are associated and fused, this information is stored for at least a specified period of time to determine whether the camera object and the radar object have been associated within the specified period of time. If the camera object and the radar object are determined to be associated, the current object position is estimated using the detection values ​​of the previous radar object. If the camera object and the radar object are determined to have not been associated within the specified period of time, the position estimating unit 14b uses, for example, the camera object to estimate the object position, after setting an unstable flag. Specifically, because the detection values ​​of the camera object in a specified slope state have significant errors, the unstable flag is set, and driving control differs from normal.

[0043] The driving control unit 16 controls the driving actuator AC based on the position of the object (control object) estimated by the position estimation unit 14b. For example, when the vehicle is following the vehicle ahead by automatic driving through constant inter-vehicle distance control, the inter-vehicle distance from the vehicle ahead is calculated based on the position data of the control object indicating the vehicle ahead, and the actuator AC is controlled so that the inter-vehicle distance reaches the specified target inter-vehicle distance. However, when an unstable flag is established, the driving control unit 16 delays the timing of acceleration and deceleration during following driving compared to when the unstable flag is not established. In other words, the acceleration and deceleration of the vehicle are slowed down. On the other hand, when the automatic braking operation that requires the vehicle to stop urgently is in operation, the driving control unit 16, considering safety, advances the timing of automatic braking when an unstable flag is established compared to when the unstable flag is not established.

[0044] Figure 4 It is shown by Figure 2 The flowchart illustrates an example of processing executed by the controller 10, particularly the processing by the position estimation unit 14b. The processing illustrated in this flowchart begins, for example, when the slope detection unit 14a detects a predetermined slope and a camera object is assigned a slope mark. The process is then repeated at a predetermined cycle corresponding to the computer's operating cycle as long as this state persists. The controller 10 acquires position information obtained from the camera object and position information obtained from the radar object at each predetermined cycle.

[0045] like Figure 4 As shown, first, in S1 (S: Processing Step), it is determined whether the radar object corresponding to the camera object assigned a slope sign has been detected by detector 1b. In other words, it is determined whether the object detected by camera 1a has also been detected by detector 1b. If S1 is affirmative (S1: Yes), the process proceeds to S2, where it is determined whether the difference between the y-direction position of the camera object and the y-direction position of the radar object is greater than a specified value. This determination is based on whether the position of the camera object and the position of the radar object deviate by more than a specified amount, based on the detection of a specified slope. If S2 is negative (S2: No), the process proceeds to S3; if it is positive (S2: Yes), the process proceeds to S4.

[0046] In S3, the target object's position is estimated using the detection values ​​from camera 1a and detector 1b. Specifically, the camera target object and the radar target object are fused to estimate the target object's position. Meanwhile, in S4, the reliability of the camera target object is lowered, for example, to 0. The target object's position is then estimated based on the radar target object detected by detector 1b. In other words, the target object's position in the vehicle's travel direction is estimated using only the detection values ​​from detector 1b, not the camera 1a.

[0047] If S1 is negative (S1: No) because detector 1b does not detect the radar object corresponding to the camera object with the ramp sign, the process proceeds to S5. In S5, a determination is made as to whether the difference between the y-direction position of the camera object detected by camera 1a in the previous process (predetermined period ago) and the y-direction position of the camera object detected in the current process is greater than or equal to a predetermined value. If S5 is positive (S5: Yes), the process proceeds to S6; if it is negative (S5: No), the process ends. In S6, a determination is made as to whether the radar object detected by detector 1b in the past (e.g., in the previous process) and the camera object have been fused, that is, whether camera 1a and detector 1b have been previously linked. If S6 is positive (S6: Yes), the process proceeds to S7; if it is negative (S6: No), the process proceeds to S8.

[0048] In S7, the position of the target object is estimated using past detection values ​​from detector 1b. When estimating the target object's position, reference is made to the detection values ​​of internal sensor group 2 (vehicle speed sensor, yaw rate sensor, etc.). Meanwhile, in S8, a stability flag is set, and the target object's position is estimated based on the camera target object. When the instability flag is set, the driving control unit 16 controls actuator AC differently than when the instability flag is not set. For example, actuator AC is controlled to delay the timing of acceleration and deceleration when performing constant vehicle speed control or when performing inter-vehicle distance control to control the inter-vehicle distance between the host vehicle 101 and the preceding vehicle 102 to a specified value. Alternatively, actuator AC is controlled to advance the automatic braking action.

[0049] The operation of vehicle control device 50 according to this embodiment is summarized as follows. When vehicle 101 is following vehicle 102 ahead using inter-vehicle distance control, the predetermined slope is not detected unless both vehicle 101 and vehicle 102 are traveling on the same road slope. In this case, the position of the target object is estimated through a fusion process using the camera object detected by camera 1a and the radar object detected by detector 1b, and actuator AC is then controlled.

[0050] On the other hand, Figure 3 As shown, when a predetermined slope is detected ahead of the host vehicle 101, a camera object is assigned a slope flag, and the difference between the camera object and the radar object exceeds a predetermined value, the radar object is used instead of the camera object to estimate the object's position (S4). This allows the detection value from the detector 1b to accurately estimate the object's position, even when the preceding vehicle 102 is traveling uphill. In this case, the object is the preceding vehicle 102. As a result, smooth following travel is possible.

[0051] If detector 1b fails to detect an object detected by camera 1a, and the difference between the camera object's last detection value and the camera 1a and detector 1b have been associated within a specified period of time (e.g., during a previous process), the object's position is estimated using the previous detection value of detector 1b (S7). This allows accurate estimation of the object's position without using the camera object's less reliable detection value, even if detector 1b fails to detect the object at the current time. On the other hand, if camera 1a and detector 1b have not been associated within a specified period of time, the object's position is estimated using the camera object, with an unstable flag set (S8). If the unstable flag is set, actuator AC is controlled differently than usual. This allows vehicle 101's driving behavior to be appropriately controlled based on the object's position.

[0052] The present embodiment can achieve the following effects.

[0053] (1) The vehicle control device 50 includes: a camera 1a, which captures the surrounding environment of the vehicle 101 and obtains the position information of the target object; a detector 1b, which obtains the position information of the target object based on the reflected wave from the detection object in the capturing area of ​​the camera 1a; a position estimation unit 14b, which estimates the position of the target object based on the position information obtained by the camera 1a and the position information obtained by the detector 1b; a driving control unit (actuator control unit) 16, which controls the driving actuator AC mounted on the vehicle 101 based on the position of the target object estimated by the position estimation unit 14b; and a slope detection unit 14a, which detects whether the slope of the road ahead of the vehicle 101 is an upward slope of a predetermined degree or more based on the road surface at the current position of the vehicle 101, that is, a predetermined slope state ( Figure 2 、 Figure 3 When the slope detection unit 14a detects a predetermined slope, the position estimation unit 14b estimates the position of the target object by reducing the reliability (e.g., setting the reliability to 0) of the position information of the target object (target object with a ramp mark) captured on the road surface with the predetermined slope along the travel direction of the host vehicle 101 acquired by the camera 1a. This allows the target object's position to be accurately estimated under the predetermined slope.

[0054] (2) The position estimating unit 14b calculates the difference between the position information along the travel direction of the vehicle 101 obtained by the camera 1a and the position information along the travel direction of the vehicle 101 obtained by the detector 1b, among the position information of the target object captured on the road surface with a predetermined slope. If the difference is greater than a predetermined value, the position of the target object is estimated based on the position information along the travel direction of the vehicle 101 obtained by the detector 1b, not the position information along the travel direction of the vehicle 101 obtained by the camera 1a (S4). In other words, in this case, considering that the error in the detection value of the camera 1a is large, the camera target object is not used. Thus, even if the road ahead of the vehicle is an uphill slope, the position of the target object can be accurately estimated.

[0055] (3) The detector 1b is configured to acquire the position information of the target object at each predetermined time. When the camera 1a acquires the position information of the target object (camera target object) on the road surface with a predetermined slope at the current time, and the detector 1b does not acquire the position information of the target object (radar target object) on the road surface with a predetermined slope at the current time, the position estimating unit 14b estimates the position of the target object along the travel direction of the host vehicle 101 based on the position information of the target object acquired by the detector 1b within the past predetermined time corresponding to the target object captured by the camera 1a (S7). Thus, even when the radar target object is not detected at the current time, the position of the target object can be accurately estimated.

[0056] (4) When the slope detection unit 14a detects a predetermined slope, and the detector 1b fails to detect the same target object as the target object detected by the camera 1a, the position estimation unit 14b estimates the target object's position based on the position information along the travel direction of the host vehicle 101 obtained by the camera 1a, after setting an unstable flag (S8). At this time, the driving control unit 16 controls the actuator AC so that the acceleration and deceleration of the host vehicle 101 differs when the unstable flag is set by the position estimation unit 14b and when the unstable flag is not set. This allows for optimal control of the actuator AC even when no radar target object is detected, contributing to improved traffic safety.

[0057] (5) For example, when performing inter-vehicle distance control to keep the inter-vehicle distance between the host vehicle 101 and the preceding vehicle 102 at a predetermined value, the driving control unit 16 controls the actuator AC so that when the unstable flag is set by the position estimating unit 14b, the timing of the acceleration and deceleration operations is delayed compared to when the unstable flag is not set. Thus, even when the unstable flag is set, following driving can be performed while the inter-vehicle distance is well controlled.

[0058] (6) The driving actuators AC include a brake actuator for braking the vehicle 101. When the automatic brake is activated in an emergency, the driving control unit 16 controls the actuators (brake actuators) AC so that, when the position estimating unit 14b sets an unstable flag, the automatic brake is activated earlier than when the unstable flag is not set. This allows the automatic brake to be properly activated even when the unstable flag is set.

[0059] The above-mentioned embodiment can be modified in various ways. Several modified examples are described below. In the above-mentioned embodiment, the difference between the position information of the object captured on the road surface with a specified slope state, the position information in the vehicle's travel direction obtained based on the camera object and the position information in the vehicle's travel direction obtained based on the radar object is obtained. When the difference is greater than a specified value, the position information obtained based on the camera object is not used, but the position of the object is estimated based on the position information obtained based on the radar object. However, as long as the reliability of the position information obtained based on the camera object is reduced and the position of the object is estimated, the camera object can be used to estimate the position of the object. Therefore, the structure of the position estimation unit is not limited to the above. It should be noted that the position information includes not only the position of the object but also the speed information.

[0060] In the above embodiment, the prescribed slope state is detected based on the length (height) h1 and h2 of the front vehicle 102 in the y direction on the camera image, but the prescribed slope state can also be detected based on the reflected wave from the road surface of, for example, a radar or a laser radar. The slope can also be detected using map information. Therefore, the structure of the slope detection unit is not limited to the above. It should be noted that the slope detection unit is a component that determines whether the road surface in front of the vehicle is in a prescribed slope state, and can also serve as a slope determination unit. In the above embodiment, a radar or a laser radar is used as the detector 1b, but as long as it is configured to obtain the position information of the target object based on the reflected wave from the detection object within the shooting area of ​​the camera, the structure of the detector (position detector) can be in any form.

[0061] In the above embodiment, the driving control unit 16 is described as an example of inter-vehicle distance control and automatic braking control when the unstable flag is set. However, the actuator control unit can also perform other controls to cause the acceleration and deceleration of the host vehicle to differ when the unstable flag is set and when the unstable flag is not set. In the above embodiment, the vehicle control device 50 is used in a driving scenario with the preceding vehicle 102, but the vehicle control device 50 can also be used even when the preceding vehicle 102 is not moving.

[0062] In the above embodiment, an example in which the vehicle control device 50 is applied to an autonomous vehicle has been described. However, the present invention can also be similarly applied to a manually driven vehicle with or without a driving assistance function.

[0063] The present invention can also be used as a vehicle control method, including: a step of obtaining position information of an object by photographing the outside world around the vehicle with a camera; a step of obtaining position information of the object by a detector based on a reflected wave from a detection object within the photographing area of ​​the camera; a step of estimating the position of the object based on the position information obtained by the camera and the position information obtained by the detector; a step of controlling a driving actuator mounted on the vehicle based on the estimated position of the object; and a step of detecting whether the slope of the road surface in front of the vehicle is an upward slope of a prescribed degree or more based on the road surface at the current position of the vehicle, i.e., a prescribed slope state, the estimating step including reducing the reliability of the position information of the object captured on the road surface in the prescribed slope state, which is the position information along the traveling direction of the vehicle, obtained by the camera, when the prescribed slope state is detected, and estimating the position of the object.

[0064] One or more of the above-described embodiments and modifications may be arbitrarily combined, and modifications may be combined with each other.

[0065] According to the present invention, even when the road surface ahead of the host vehicle is inclined at an uphill gradient compared to the road surface on which the host vehicle is located, it is possible to accurately recognize a target object.

[0066] The present invention has been described above with reference to preferred embodiments. However, it will be understood by those skilled in the art that various modifications and changes can be made without departing from the scope of the claims set forth below.

Claims

1. A vehicle control device, characterized in that: have: A camera (1a) for capturing images of the surroundings of the vehicle (101) and obtaining location information of an object; A detector (1b) that obtains position information of an object based on a reflected wave from a detection object within a shooting area of ​​the camera (1a); a position estimating unit (14b) for estimating the position of the target object based on the position information obtained by the camera (1a) and the position information obtained by the detector (1b); an actuator control unit (16) for controlling a traveling actuator (AC) mounted on the vehicle (101) based on the position of the target object estimated by the position estimating unit (14b); and A slope detection unit (14a) detects whether the slope of the road ahead of the vehicle (101) is an upward slope of a predetermined degree or more based on the road surface at the current position of the vehicle (101), i.e., a predetermined slope state. When the slope detection unit (14a) detects the predetermined slope state, the position estimation unit (14b) reduces the reliability of the position information of the object captured on the road surface in the predetermined slope state, which is obtained by the camera (1a) along the traveling direction of the vehicle (101), and estimates the position of the object. The detector (1b) is configured to obtain position information of an object at every predetermined time. The position estimation unit (14b) estimates the position of an object along the traveling direction of the vehicle (101) based on the position information of an object captured by the camera (1a) and obtained by the detector (1b) in the past, when the camera (1a) obtains the position information of an object on the road surface with the specified slope state at the current time point, while the detector (1b) does not obtain the position information of an object on the road surface with the specified slope state at the current time point.

2. The vehicle control device according to claim 1, wherein: The position estimation unit (14b) obtains the difference between the position information of the object captured on the road surface with the specified slope state, the position information along the traveling direction of the vehicle (101) obtained by the camera (1a) and the position information along the traveling direction of the vehicle (101) obtained by the detector (1b), and when the difference is greater than a specified value, the position of the object is estimated based on the position information along the traveling direction of the vehicle (101) obtained by the detector (1b) instead of using the position information along the traveling direction of the vehicle (101) obtained by the camera (1a).

3. The vehicle control device according to claim 1, wherein: The position estimation unit (14b) estimates the position of the object based on the position information along the traveling direction of the vehicle (101) obtained by the camera (1a) on the basis of establishing an unstable flag when the slope detection unit (14a) detects the predetermined slope state and the detector (1b) does not obtain the object mark of the detection object that is the same as the object mark obtained by the camera (1a). The actuator control unit (16) controls the actuator (AC) so that the acceleration and deceleration of the vehicle (101) when the unstable flag is established by the position estimation unit (14b) is different from the acceleration and deceleration of the vehicle (101) when the unstable flag is not established.

4. The vehicle control device according to claim 3, wherein: The actuator control unit (16) controls the actuator when the unstable flag is established by the position estimation unit (14b), so that the timing of acceleration and deceleration when performing inter-vehicle distance control to control the inter-vehicle distance from the vehicle (101) to the preceding vehicle (102) traveling in front of the vehicle (101) at a specified value is delayed compared to when the unstable flag is not established.

5. The vehicle control device according to claim 3 or 4, characterized in that: The driving actuator (AC) includes a braking actuator for braking the vehicle (101). When the unstable flag is generated by the position estimating unit (14b), the actuator control unit (16) controls the brake actuator so that the automatic braking action is performed earlier than when the unstable flag is not generated.

6. The vehicle control device according to claim 1, wherein: When in the specified condition, the position estimation unit (14b) estimates the position of the object along the traveling direction of the vehicle (101) based on the position information of the object corresponding to the object captured by the camera (1a) and acquired by the detector (1b) before the specified time.

7. The vehicle control device according to claim 1, wherein: The position estimation unit (14b) takes as a condition that the difference between the position information of the object mark on the road surface with the specified slope state obtained by the camera (1a) at the current time point and the position information of the object mark on the road surface with the specified slope state obtained by the camera (1a) before the specified time is greater than a specified value. When in the specified condition, the position of the object mark along the traveling direction of the vehicle (101) is estimated based on the position information of the object mark obtained in the past by the detector (1b) corresponding to the object mark captured by the camera (1a).

8. The vehicle control device according to claim 1 or 2, characterized in that: The slope detection unit (14a) detects the specified slope state when the camera (1a) captures a front vehicle (102) traveling in front of the host vehicle (101) and the length (Δh) from the lower end to the upper end of the image showing the front vehicle (102) in the height direction on the camera image is greater than a specified value, or when the ratio (α) between the length (h2) from the lower end of the camera image to the upper end of the image showing the front vehicle (102) and the length (h1) from the lower end of the camera image to the lower end of the image showing the front vehicle (102) is greater than a specified value.

9. A vehicle control method, characterized in that: include: The step of photographing the surroundings of the vehicle (101) by a camera (1a) to obtain position information of an object; A step of obtaining, by the detector (1b), position information of an object based on a reflected wave from a detection object within a shooting area of ​​the camera (1a); A step of estimating the position of an object based on the position information obtained by the camera (1a) and the position information obtained by the detector (1b); A step of controlling a driving actuator (AC) mounted on the vehicle (101) based on the estimated position of the target object; and The step of detecting whether the slope of the road ahead of the vehicle (101) is an upward slope of a predetermined degree or more based on the road surface at the current position of the vehicle (101), i.e., a predetermined slope state, The estimating step includes, when the predetermined slope state is detected, reducing the reliability of the position information of the object captured on the road surface in the predetermined slope state, which is the position information along the traveling direction of the vehicle (101) obtained by the camera (1a), and estimating the position of the object. The detector (1b) is configured to obtain position information of an object at every predetermined time. The estimating step includes estimating the position of the object along the traveling direction of the vehicle (101) based on the position information of the object captured by the camera (1a) and obtained by the detector (1b) in the past, when the camera (1a) obtains the position information of the object on the road surface with the specified slope state at the current time point, and the detector (1b) does not obtain the position information of the object on the road surface with the specified slope state at the current time point.

Images