External identification device

Abstract

The external environment recognition device (50) includes: a laser radar (5) that irradiates electromagnetic waves around the vehicle to detect the external environment around the vehicle; a road recognition unit (111) that recognizes the road structure in the direction of travel of the vehicle; a demarcation unit (112) that demarcates a detection area at predetermined intervals along the direction of travel on a plane approximately perpendicular to the irradiation direction of the electromagnetic waves irradiated from the laser radar (5) based on the road structure recognized by the road recognition unit (111); and a setting unit (113) that sets the irradiation position of the laser radar (5) according to the size of the detection object determined in advance within the detection area determined by the demarcation unit (112). The demarcation unit (112) determines the size of the detection area based on the distance from the vehicle to the detection area and the road structure recognized by the road recognition unit (111), and demarcates the detection area according to the determined size.

Description

Technical Field

[0001] The present invention relates to an external environment recognition device for recognizing the external environment of a vehicle. Background Art

[0002] As such a device, the following device has been mentioned in the past: an area to be watched is determined based on the distance from the vehicle to a detected object and the position of the object, and only information from a plurality of vehicle-mounted cameras mounted on the vehicle that corresponds to the area is used for autonomous driving, thereby reducing the processing load during autonomous driving (for example, see Patent Document 1).

[0003] However, in order to perform good autonomous driving, it is necessary to fully recognize the external conditions around the vehicle. However, the device described in Patent Document 1 limits the area to be observed to a certain area, and cannot obtain the necessary information about the external conditions, which may prevent good autonomous driving.

[0004] Prior art literature

[0005] Patent Literature

[0006] Patent Document 1: Japanese Patent Application Laid-Open No. 2020-125102. Summary of the Invention

[0007] An external environment recognition device according to one embodiment of the present invention includes: an on-vehicle detector that radiates electromagnetic waves around a vehicle to detect external conditions surrounding the vehicle; a road recognition unit that recognizes the road structure in the vehicle's travel direction; a demarcation unit that, based on the road structure recognized by the road recognition unit, defines a detection area at predetermined intervals along the travel direction on a plane approximately perpendicular to the direction of the electromagnetic waves radiated from the on-vehicle detector; and a setting unit that sets the irradiation position of the on-vehicle detector within the detection area defined by the demarcation unit based on the size of a predetermined detection target. The demarcation unit determines the size of the detection area based on the distance from the vehicle to the detection area and the road structure recognized by the road recognition unit, and demarcates the detection area according to the determined size. 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 1A It is a diagram showing a situation where a vehicle travels on a road.

[0010] Figure 1B It shows Figure 1A An example of point cloud data of a location.

[0011] Figure 2This is a block diagram schematically showing the main configuration of a vehicle control device according to an embodiment of the present invention.

[0012] Figure 3A It is a diagram for explaining the detection area.

[0013] Figure 3B It is a diagram for explaining the detection area.

[0014] Figure 3C It is a diagram for explaining the detection area.

[0015] Figure 4 It is a diagram for explaining the irradiation target point of each detection area.

[0016] Figure 5 It is shown by Figure 2 A flowchart of an example of processing executed by the CPU of the controller.

[0017] Figure 6 It is a diagram for explaining the positioning of the detection area. DETAILED DESCRIPTION

[0018] The following reference Figures 1A to 6 The embodiments of the present invention are described. The external recognition device of the embodiments of the present invention can be applied to vehicles with automatic driving functions, that is, automatic driving vehicles. It should be noted that sometimes the vehicle to which the external recognition device of the present embodiment is applied is distinguished from other vehicles and referred to as the present vehicle. The present vehicle can be any one of an engine vehicle having an internal combustion engine (engine) as a driving source, an electric vehicle having a driving motor as a driving source, and a hybrid vehicle having an engine and a driving motor as driving sources. The present vehicle can not only travel in an automatic driving mode that does not require the driver's driving operation, but can also travel in a manual driving mode based on the driver's driving operation.

[0019] When an autonomous vehicle is operating in autonomous driving mode (hereinafter referred to as autonomous driving or autonomous driving), it uses data from onboard sensors such as cameras and LiDAR (Light Detection and Ranging) to identify the surrounding environment. Based on this identification, the autonomous vehicle generates a driving trajectory (target trajectory) extending from the current point in time to a predetermined time, and controls the driving actuators to ensure the vehicle follows the target trajectory.

[0020] Figure 1A 1 is a diagram showing a situation in which a host vehicle 101 as an automatically driven vehicle is traveling on a road RD. Figure 1B1 is a diagram showing an example of detection data (feature points) obtained by the laser radar installed in the vehicle 101. Feature points are characteristic points of an object, such as the intersection of edges (corners of buildings, corners of road signs), etc. Figure 1B The data composed of the multiple feature points shown is called point cloud data. Figure 1B Shown in Figure 1A The point cloud data corresponding to the location of the vehicle 101. Figure 1B The point cloud data shown recognizes the external conditions around the vehicle, more specifically, the road structure and objects around the vehicle, and generates a target trajectory based on the recognition results.

[0021] However, as a method for fully recognizing the external conditions around the vehicle, it is possible to increase the number of irradiation points of electromagnetic waves emitted from vehicle-mounted detectors such as lidar. On the other hand, when the number of irradiation points is increased, the processing load for controlling the vehicle-mounted detectors and the capacity of the detection data (point cloud data) obtained by the vehicle-mounted detectors may increase. In particular, if Figure 1B As shown, if there are many objects (people, buildings, etc. in addition to trees) along the road, the point cloud data capacity increases further. Furthermore, addressing such issues may increase the size of the device. With this in mind, the present embodiment constructs the vehicle control device as follows.

[0022] Figure 2 This is a block diagram illustrating the main components of a vehicle control device 100 according to an embodiment of the present invention. The vehicle control device 100 includes a controller 10, a communication unit 1, a positioning unit 2, an internal sensor group 3, a camera 4, a laser radar 5, and actuators AC for driving. Furthermore, the vehicle control device 100 includes an external environment recognition device 50, which constitutes a portion of the vehicle control device 100. The external environment recognition device 50 identifies the external conditions of the vehicle 101, more specifically, the road structure and objects surrounding the vehicle 101, based on detection data from onboard sensors such as the camera 4 and the laser radar 5.

[0023] The communication unit 1 communicates with various servers not shown in the figure via a network including a wireless communication network represented by the Internet, a mobile phone network, etc., and obtains map information, driving record information, traffic information, etc. from the server regularly or at any time. The network includes not only a public wireless communication network, but also a closed communication network set up for each specified management area, such as a wireless LAN, Wi-Fi (registered trademark), Bluetooth (registered trademark), etc. The acquired map information is output to the storage unit 12, and the map information is updated. The positioning unit (GNSS unit) 2 has a positioning sensor that receives a positioning signal sent from a positioning satellite. The positioning satellite is an artificial satellite such as a GPS satellite and a quasi-zenith satellite. The positioning unit 2 uses the positioning information received by the positioning sensor to measure the current position (latitude, longitude, altitude) of the vehicle 101.

[0024] The internal sensor group 3 is a collective term for multiple sensors (internal sensors) that detect the driving state of the vehicle 101. For example, the internal sensor group 3 includes a speed sensor that detects the speed of the vehicle 101, acceleration sensors that detect the front-to-rear acceleration and the left-to-right acceleration (lateral acceleration) of the vehicle 101, a rotational speed sensor that detects the rotational speed of the driving source, and a yaw rate sensor that detects the angular velocity of the center of gravity of the vehicle 101 about the vertical axis. 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 3.

[0025] The camera 4 includes an imaging element such as a CCD (charge-coupled device) or a CMOS (complementary metal oxide semiconductor) and captures images of the surroundings (front, rear, and sides) of the vehicle 101. The lidar 5 measures scattered light (a type of electromagnetic wave) from the omnidirectional illumination of the vehicle 101, thereby determining the distance from the vehicle 101 to surrounding objects, as well as the position and shape of the objects.

[0026] Actuators AC are driving actuators used to control the driving of vehicle 101. If the driving source is an engine, actuators AC include 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 actuators AC. Actuators AC also include a brake actuator that activates the braking system of vehicle 101 and a steering actuator that drives the steering system.

[0027] 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, such as an I / O 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 system ECU, can be provided separately. Figure 2 , for convenience, the controller 10 is shown as a collection of these ECUs.

[0028] The storage unit 12 stores high-precision, detailed map information (referred to as high-precision map information). This high-precision map information includes road location information, road shape information (such as curvature), road slope information, intersection and fork location information, lane number information, lane width, and lane location information (including lane center positions and lane boundary lines), location information of landmarks (such as traffic lights, signs, and buildings) that serve as map markers, and road surface contour information such as road surface irregularities. The storage unit 12 also stores information regarding various control programs and the thresholds used by these programs.

[0029] The computing unit 11 includes a road recognition unit 111, a demarcation unit 112, a setting unit 113, and a driving control unit 114 as functional structures. Figure 2 As shown, the road recognition unit 111 , the demarcation unit 112 , and the setting unit 113 are included in the outside world recognition device 50 .

[0030] The road recognition unit 111 identifies the road structure in the direction of travel of the host vehicle 101. Specifically, the road recognition unit 111 generates three-dimensional point cloud data (three-dimensional map data) using the detection data (feature points) detected by the laser radar 5. It should be noted that the point cloud data can also be generated by extracting edges representing the outlines of objects from the captured image data (hereinafter referred to as the captured image) captured by the camera 4 in the direction of travel based on the brightness and color information of each pixel, and using this edge information to extract feature points.

[0031] The road recognition unit 111 identifies the road structure based on the generated point cloud data. More specifically, the road recognition unit 111 uses machine learning to identify the boundary lines (curbstones, road markings) RL and RB of the road RD ahead in the direction of travel, as contained in the point cloud data. It should be noted that the method for identifying the boundary lines is not limited to this, and other methods can also be used to identify the boundary lines. The road recognition unit 111 identifies the area between the boundary lines RL and RB as the area corresponding to the road (hereinafter referred to as the road segment). It should be noted that the road recognition unit 111 can also obtain high-precision map information stored in the storage unit 12 and identify the road segment based on the obtained high-precision map information and the vehicle position identified by the sensor values ​​of the positioning unit 2. In addition, the method for identifying the road segment is not limited to this, and other methods can also be used to identify the road segment. The road recognition unit 111 stores the recognition result of the road segment (hereinafter referred to as road structure information) in the storage unit 12 in correspondence with the current position of the vehicle 101 measured by the positioning unit 2.

[0032] It should be noted that sometimes the dividing lines RL and RB may be hidden behind the vehicle ahead, etc., making it impossible to identify a portion of the road segment, i.e., occlusion. Therefore, the road recognition unit 111 determines whether occlusion has occurred, and if so, supplements the road segment. Specifically, the road recognition unit 111 uses point cloud data generated in the past near the current vehicle position to identify the road segment in the occluded area, and uses this recognition result to supplement the road segment. The point cloud data generated in the past by the road recognition unit 111 is stored in the storage unit 12. It should be noted that the road recognition unit 111 can also use high-precision map information stored in the storage unit 12 to supplement the road segment.

[0033] Based on the road segments identified by the road recognition unit 111, the demarcation unit 112 demarcates detection areas on planes (hereinafter referred to as virtual planes) approximately perpendicular to the direction of electromagnetic waves emitted by the laser radar 5, i.e., virtual planes set at predetermined intervals along the direction of travel. The demarcation unit 112 demarcates each detection area so that the size of the detection area decreases as the distance from the vehicle 101 increases. However, in situations where the road width increases with distance, the detection area may increase with distance. Based on the speed of the vehicle 101 detected by the vehicle speed sensor of the internal sensor group 3, the demarcation unit 112 calculates the maximum detection distance in the direction of travel, representing the range within which the laser radar 5 should detect external conditions. In this case, the demarcation unit 112 may calculate the braking distance that can stop the vehicle 101 at a deceleration less than a predetermined deceleration based on the current speed of the vehicle 101 and use this braking distance as the maximum detection distance, or it may use the distance obtained by multiplying this braking distance by a predetermined coefficient as the maximum detection distance. The demarcation unit 112 sets virtual planes at predetermined intervals from a point at the maximum detection distance from the host vehicle 101 toward the host vehicle 101 , and demarcates a detection area on each virtual plane.

[0034] Figure 3A 、 Figure 3B as well as Figure 3C It is a diagram for explaining the detection area. Figure 3A The area RS shown is where the vehicle 101 is located. Figure 1A The road segments identified by the road recognition unit 111 during the vehicle traveling on the road RD. Figure 3A The rectangular frame BX is a detection area defined on a virtual plane set at a point at the maximum detection distance from the host vehicle 101 . Figure 3A The length of the arrow line F indicates the maximum detection distance. As shown by the arrow line F, the maximum detection distance is specifically the distance from the installation position of the laser radar 5 to the lower left corner or lower right corner of the detection area BX. The width and height of the detection area BX are set so as to include the area to be monitored when driving in the autonomous driving mode. Specifically, the detection area BX is defined so that the center position in the road width direction overlaps with the center position in the road width direction of the road segment. The width of the detection area BX is set to be the same as the road width at that position or longer than the road width by a specified length. The height of the detection area BX is set to be the same as the vehicle height of the host vehicle 101 or longer than the vehicle height by a specified length.

[0035] Figure 3B Schematically shows a detection area BX defined on a virtual plane set with a predetermined distance D as a unit. Figure 3C shown in the Figure 3BThe detection areas BX are schematically overlapped with the image in front of the vehicle 101 with the laser radar 5 as the viewpoint. Figure 3C As shown, when viewed from the viewpoint of the laser radar 5, the detection area BX (

[0036] Figure 3C The further inward the detection area BX is, the smaller its size is. However, if the road width increases with distance, the detection area BX may become larger with distance.

[0037] The setting unit 113 calculates the position (hereinafter referred to as the irradiation point or irradiation target point) of the electromagnetic wave (irradiation light) irradiating the laser radar 5 within each detection area BX defined by the defining unit 112, based on the pre-set minimum size of the detection object. More specifically, the setting unit 113 calculates the irradiation target point for each detection area BX according to the angular resolution calculated based on the minimum size of the detection object and the distance (in the direction of travel) between each detection area BX and the host vehicle 101. The setting unit 113 generates information indicating the calculated position of the irradiation target point (hereinafter referred to as irradiation target point information) and stores it in the storage unit 12 in association with the position information indicating the current driving position of the host vehicle 101.

[0038] When the vehicle 101 is traveling in the automatic driving mode, the setting unit 113 reads the irradiation target point information corresponding to the current driving position of the vehicle 101 from the storage unit 12 and sets the irradiation target point of the laser radar 5 according to the irradiation target point information. As a result, the irradiation light from the laser radar 5 is directed toward the set irradiation target point.

[0039] In the automatic driving mode, the driving control unit 114 generates a target trajectory based on the external conditions surrounding the vehicle as detected by the laser radar 5, and controls the actuators AC to drive the vehicle 101 along the target trajectory. It should be noted that in the manual driving mode, the driving control unit 114 controls the actuators AC based on driving instructions (such as steering operations) from the driver obtained by the internal sensor group 3.

[0040] Figure 4 This is a diagram for explaining the irradiation target point of each detection area BX calculated by the setting unit 113 . Figure 4The vertical and horizontal spacing of the squares within each detection area BX represents the angular resolution corresponding to each detection area BX. The intersections of the squares represent the target points of illumination by the laser radar 5, and the illumination light of the laser radar 5 is directed toward the intersections of the squares. It should be noted that the illumination light of the laser radar 5 can be emitted in a raster scanning manner, intermittently irradiating electromagnetic waves only toward the illumination target points set by the setting unit 113, or in other ways.

[0041] like Figure 4 As shown, the angular resolution of the detection area BX corresponding to the location with the maximum detection distance from the vehicle 101 is the smallest, and the angular resolution of the detection area BX closest to the vehicle 101 is the largest. In this way, the angular resolution of each detection area BX is determined to be smaller the longer the distance between the detection area BX and the vehicle 101 (the smaller the size of the detection area BX). Thus, the number of target points irradiated by the laser radar 5 can be reduced without reducing the recognition accuracy of the position and size of distant objects and the recognition accuracy of the distance to distant objects. It should be noted that in Figure 4 In the case where the detection area BX includes intersection points of squares of other detection areas BX, the intersection points of squares of the detection area BX having a smaller angular resolution are preferentially set as irradiation target points.

[0042] Figure 5 It is done according to a pre-set program. Figure 2 Flowchart of an example of processing executed by the controller 10. Figure 5 The processing shown in the flowchart is repeatedly executed at predetermined intervals while the vehicle 101 is traveling in the automatic driving mode, for example.

[0043] First, in step S11, three-dimensional point cloud data is generated using the detection data from the laser radar 5. In step S12, road segmentation is performed. Specifically, the boundary of the road ahead of the vehicle is identified based on the point cloud data generated in step S11, and road segments are identified based on these boundary lines. In step S13, a determination is made as to whether occlusion has occurred. If the result of step S13 is negative (S13: No), the process proceeds to step S15. If the result of step S13 is positive (S13: Yes), the process supplements the road segment data in step S14.

[0044] In step S15, a detection area BX is set at a location in front of the maximum detection distance on the road segment identified in step S14. Specifically, a virtual plane is set at a location in front of the maximum detection distance, and the detection area BX is delineated on the virtual plane. Next, in step S16, detection areas BX are set at predetermined distances along the direction of travel. Specifically, virtual planes are set at predetermined distances along the direction of travel, and detection areas BX are delineated on each virtual plane. At this time, the size of the detection area BX is determined based on the distance from the vehicle 101 to the detection area BX and the road segment identified in steps S12 and S13, and the detection area BX is delineated according to the determined size. Under the condition that the road width hardly changes, each detection area BX is set in such a way that it becomes smaller as the distance between the detection area BX and the vehicle 101 increases ( Figure 3C However, in a situation where the road width increases as the distance increases, the detection area BX may become larger as the distance increases.

[0045] In step S17, the angular resolution corresponding to each detection area BX is calculated. In step S18, an irradiation target point is calculated for each detection area BX according to the angular resolution calculated in step S17, and irradiation target point information indicating the calculated irradiation target point is stored in the storage unit 12 in a corresponding relationship with position information indicating the current driving position of the vehicle 101.

[0046] The operation of the outside world recognition device 50 of this embodiment is summarized as follows. When the vehicle 101 first travels on the road RD, since the irradiation target point information corresponding to the travel position is not stored in the storage unit 12, the irradiation target point is not set based on the irradiation target point information. Therefore, the irradiation light from the laser radar 5 irradiates the entire area in front of the vehicle 101, and the following is obtained: Figure 1BThe detection data (point cloud data) shown is obtained (S11). Next, detection areas BX are demarcated at predetermined intervals based on the road segments identified based on the point cloud data (S12-S16), and an illumination target point is calculated for each detection area. Illumination target point information representing the calculated illumination target point is then stored in the storage unit 12 (S17, S18). Meanwhile, when the vehicle 101 travels on the road RD again in autonomous driving mode, the illumination target point information corresponding to the driving position is stored in the storage unit 12. Therefore, the illumination light from the laser radar 5 illuminates the illumination target point specified by the illumination target point information, and only detection data (point cloud data) corresponding to the area to be monitored during autonomous driving is obtained (S11). It should be noted that if the road structure (position and shape of the road segment) identified based on the point cloud data obtained at this time (S12) differs from the road structure identified during the previous driving by a predetermined degree or more, the subsequent processing, namely, the processing from S13 to S18, may be executed. On the other hand, if there is no difference by a predetermined degree or more, the subsequent processing may be skipped.

[0047] According to this embodiment, the following effects can be achieved.

[0048] (1) The external environment recognition device 50 includes: a laser radar 5 that irradiates electromagnetic waves around the host vehicle 101 to detect the external environment around the host vehicle 101; a road recognition unit 111 that recognizes the road structure in the direction of travel of the host vehicle 101; a demarcation unit 112 that demarcates a detection area BX at predetermined intervals along the direction of travel on a plane approximately perpendicular to the irradiation direction of the electromagnetic waves (irradiation light) irradiated from the laser radar 5 based on the road structure recognized by the road recognition unit 111; and a setting unit 113 that sets the irradiation position (irradiation target point) of the laser radar 5 within the detection area BX defined by the demarcation unit 112 based on the size of a predetermined detection object. The demarcation unit 112 determines the size of the detection area BX based on the distance from the host vehicle 101 to the detection area BX and the road structure recognized by the road recognition unit 111, and demarcates the detection area BX according to the determined size. The predetermined detection object is the smallest object among the objects to be detected by the laser radar 5. This allows the number of target points illuminated by the laser radar 5 to be reduced without reducing the accuracy of identifying the external environment. As a result, the external environment around the vehicle can be accurately identified while reducing the processing load.

[0049] (2) The setting unit 113 calculates the angular resolution corresponding to the detection area BX based on the value of the minimum size and the distance between the detection area BX and the vehicle 101, and sets the irradiation position of the laser radar 5 to the detection area BX in the left and right directions ( Figure 4In addition, the setting unit 113 sets the irradiation position of the laser radar 5 and the detection area BX in the vertical direction ( Figure 4 Thus, the number of target points illuminated by the laser radar 5 can be reduced without reducing the accuracy of the laser radar 5 in detecting objects.

[0050] (3) The demarcation unit 112 calculates the maximum distance (maximum detection distance) representing the range in the travel direction within which the laser radar 5 should detect external conditions based on the speed of the host vehicle 101, and demarcates the detection area BX at predetermined intervals from the point at the maximum detection distance from the host vehicle 101 toward the host vehicle 101. This allows accurate recognition of the external conditions surrounding the vehicle regardless of the speed of the host vehicle 101.

[0051] (4) The road recognition unit 111 identifies the boundary line of the road in the direction of travel of the host vehicle 101 based on the detection data of the laser radar 5, and identifies the road structure indicated by the boundary line. In this way, the road structure can be identified without using map information. It should be noted that when the road recognition unit 111 stores map information (high-precision map information) in the storage unit 12, it identifies the road structure in the direction of travel of the host vehicle 101 based on the map information instead of or together with the detection data of the laser radar 5. In this way, the road structure can be accurately identified.

[0052] The above-mentioned embodiment can be modified in various ways. Several modified examples are described below. In the above-mentioned embodiment, the setting unit 113 generates irradiation target point information showing the position of the irradiation light of the laser radar 5, and sets the irradiation target point of the laser radar 5 based on the irradiation target point information, but the configuration of the setting unit is not limited to this. For example, in the case where the vehicle control device has a radar as an on-board detector that detects other vehicles, obstacles, etc. around the vehicle by irradiating electromagnetic waves and detecting reflected waves, the setting unit can also generate irradiation target point information showing the position of the electromagnetic waves irradiating the radar, and set the irradiation target point of the radar based on the irradiation target point information. In addition, the external recognition device can also identify the external conditions of the vehicle 101 based on the detection data of the radar.

[0053] In the above embodiment, the delimiting unit 112 delimits the detection area BX so that the center position of the detection area BX in the road width direction overlaps the center position of the road segment in the road width direction. However, depending on the shape of the road on which the host vehicle 101 is traveling, there is a possibility that areas may be missed when the detection area BX is set in this manner. Figure 6 (a) is a diagram for explaining the omitted area. Figure 6 Only four detection areas BX (BX1 to BX4) are shown in (a). Figure 6 As shown in (a), when the road RD curves extremely rightward (with a curvature greater than a specified value), the right end of detection area BX1 is positioned significantly to the left compared to the right end of detection area BX2, which is located behind detection area BX1. As a result, even though the vehicle should be watching for the area during autonomous driving, areas not included in detection areas BX1 or BX2—that is, areas not illuminated by the laser radar 5 (missing areas)—occur. Such missed areas also occur between detection areas BX2 and BX3, and between detection areas BX3 and BX4. The hatched area MA in the figure represents the missed area.

[0054] Therefore, in the case where a missing area MA occurs, Figure 6 As shown in (b), the demarcation unit 112 can also shift the positions of the right ends of the detection areas BX1, BX2, and BX3 in the directions of the arrows in the figure, so that they coincide with the positions of the right ends of the detection areas BX2, BX3, and BX4 behind them. Figure 6 Figures (a) and (b) illustrate an example where the road RD curves sharply to the right. However, if the road curves sharply to the left, the left end of the detection area can be offset so that it coincides with the left end of a detection area behind. This allows accurate recognition of the external conditions surrounding the vehicle even when the road curves sharply.

[0055] In addition, in the above embodiment, Figure 5 The processing shown is an example of repeatedly executing while the vehicle 101 is traveling in the automatic driving mode. Figure 5 The illustrated process can also be repeatedly executed while the vehicle 101 is traveling in the manual driving mode. Specifically, while traveling in the manual driving mode, illumination target point information is generated and stored in the storage unit 12. When the vehicle 101 is again traveling in the automatic driving mode on the road that was previously traveled in the manual driving mode, the illumination target point of the laser radar 5 can be set according to the illumination target point information stored in the storage unit 12.

[0056] Furthermore, in the above embodiment, the outside world recognition device 50 is applied to an autonomous vehicle. However, the outside world recognition device 50 can also be applied to vehicles other than autonomous vehicles. For example, the outside world recognition device 50 can also be applied to manually driven vehicles equipped with ADAS (Advanced Driver-Assistance Systems).

[0057] The above description is merely an example, and the above embodiment and modifications do not limit the present invention unless the characteristics of the present invention are impaired. One or more of the above embodiment and modifications can be arbitrarily combined, and modifications can also be combined with each other.

[0058] By adopting the present invention, it is possible to accurately identify the external conditions around the vehicle while reducing the processing load.

[0059] 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. An external recognition device, characterized in that: have: A vehicle-mounted detector (5) that irradiates electromagnetic waves around the vehicle (101) to detect external conditions around the vehicle; A road recognition unit (111) that recognizes the road structure in the direction of travel of the vehicle; a demarcation unit (112) for demarcating detection areas at predetermined intervals along the traveling direction on a plane approximately perpendicular to the irradiation direction of electromagnetic waves irradiated from the vehicle-mounted detector (5) based on the road structure identified by the road identification unit (111); and A setting unit (113) sets the irradiation position of the vehicle-mounted detector (5) according to the size of the predetermined detection object within the detection area defined by the defining unit (112), The demarcation unit (112) determines the size of the detection area based on the distance from the vehicle (101) to the detection area and the road structure identified by the road identification unit (111), and demarcates the detection area according to the determined size. The setting unit (113) calculates the angular resolution corresponding to the detection area based on the size of the predetermined detection object and the distance of the detection area from the vehicle (101), and establishes a correspondence between the irradiation position of the vehicle-mounted detector (5) and each rectangular area obtained by dividing the detection area in the left and right directions according to the angular resolution.

2. The outside world recognition device according to claim 1, characterized in that: The predetermined detection object is an object of the smallest size among objects that the vehicle-mounted detector (5) should detect.

3. The outside world recognition device according to claim 1, characterized in that: The setting unit (113) establishes a correspondence between the irradiation position of the vehicle-mounted detector (5) and each rectangular area obtained by further dividing the detection area in the upper and lower directions according to the angular resolution.

4. The outside world recognition device according to claim 1, characterized in that: The demarcation unit (113) calculates the maximum distance of the range of the direction of travel of the vehicle-mounted detector (5) that should detect the external condition based on the speed of the vehicle (101), and demarcates the detection area in units of the specified distance from the location at the maximum distance from the vehicle (101) toward the vehicle (101).

5. The outside world recognition device according to claim 1, characterized in that: The road recognition unit (111) recognizes a boundary line of a road in a traveling direction of the vehicle (101) based on detection data from the vehicle-mounted detector (5), and recognizes a road structure indicated by the boundary line.

6. The outside world recognition device according to claim 1, characterized in that: It also includes a storage unit (12) for storing map information, The road recognition unit (111) recognizes the road structure in the traveling direction of the host vehicle (101) based on the map information stored in the storage unit (12).

7. The outside world recognition device according to claim 1, characterized in that: It also includes a storage unit (12), When the road recognition unit (111) recognizes the road structure in front of the vehicle (101) while the vehicle (101) is traveling on the road, the road recognition unit (111) stores the road structure information indicating the recognized road structure in the storage unit (12) in correspondence with the traveling position of the vehicle (101). The demarcation unit (112) demarcates the detection area based on the road structure identified by the road recognition unit (111) when the road structure corresponding to the driving position of the vehicle (101) identified by the road recognition unit (111) differs from the road structure indicated by the road structure information stored in the storage unit (12) by a predetermined degree or more when the vehicle (101) is driving on the road again. When the detection area is determined by the delimiting unit (112), the setting unit (113) sets the irradiation position of the vehicle-mounted detector (5) within the detection area.

8. The outside world recognition device according to any one of claims 1 to 7, characterized in that: The vehicle-mounted detector (5) is a laser radar.

Images