JP7332731B1 - External recognition device - Google Patents

Abstract

An object of the present invention is to accurately recognize an external situation around a vehicle while reducing processing load. An external world recognition device (50) includes a rider (5) that irradiates electromagnetic waves around the own vehicle to detect external conditions around the own vehicle, and a road recognition unit (111) that recognizes the road structure in the traveling direction of the own vehicle. , based on the road structure recognized by the road recognition unit 111, a detection area is demarcated at predetermined distance intervals along the traveling direction on a plane substantially perpendicular to the irradiation direction of the electromagnetic wave emitted from the lidar 5. A defining unit 112 and a setting unit 113 that sets an irradiation position of the rider 5 within the detection area defined by the defining unit 112 based on a predetermined size of a detection target. The defining 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 defines the detection area according to the determined size. [Selection drawing] Fig. 2

Description

The present invention relates to an external world recognition device for recognizing the external world situation of a vehicle.

As this type of device, conventionally, in order to reduce the processing load during autonomous driving, the area to be observed is determined according to the distance from the own vehicle to the detected object and the position of the object, and the area to be watched is determined. A device has been proposed in which information from only one of a plurality of on-board cameras corresponding to the area is used for autonomous driving (see Patent Document 1, for example).

Japanese Patent Application Laid-Open No. 2020-125102

By the way, in order to perform good autonomous driving, it is necessary to fully recognize the external conditions around the vehicle. However, with the device described in Patent Document 1, since the area to be observed is limited to a part of the area, necessary information on the external environment cannot be obtained, and there is a possibility that the autonomous driving cannot be carried out satisfactorily.

An external world recognition device, which is one aspect of the present invention, includes an in-vehicle detector that emits electromagnetic waves around the own vehicle to detect the external world situation around the own vehicle, and a road recognition device that recognizes the road structure in the traveling direction of the own vehicle. and the road structure recognized by the road recognition unit, on a plane substantially perpendicular to the irradiation direction of the electromagnetic wave emitted from the vehicle-mounted detector, along the direction of travel, a detection area is set at every predetermined distance. and a setting unit configured to set an irradiation position of the vehicle-mounted detector based on a predetermined size of a detection target within the detection area defined by the defining unit. The defining 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 defines the detection area according to the determined size. Angular resolution corresponding to the detection area is calculated based on the predetermined size of the detection target and the distance of the detection area from the own vehicle, and each rectangle obtained by dividing the detection area horizontally based on the angular resolution. The area is associated with the irradiation position of the vehicle-mounted detector .

Advantageous Effects of Invention According to the present invention, it is possible to accurately recognize the external situation around the vehicle while reducing the processing load.

The figure which shows a mode that a vehicle drive|works a road. The figure which shows an example of the point cloud data of the point of FIG. 1A. 1 is a block diagram schematically showing the main configuration of a vehicle control device according to an embodiment of the invention; FIG. A diagram for explaining a detection area. A diagram for explaining a detection area. A diagram for explaining a detection area. FIG. 4 is a diagram for explaining irradiation points of each detection area; FIG. 3 is a flowchart showing an example of processing executed by a CPU of the controller in FIG. 2; FIG. FIG. 4 is a diagram for explaining alignment of detection areas;

Embodiments of the present invention will now be described with reference to FIGS. 1A to 6. FIG. The external world recognition device according to the embodiment of the present invention can be applied to a vehicle having an automatic driving function, that is, an automatic driving vehicle. A vehicle to which the external world recognition device according to the present embodiment is applied may be called an own vehicle to distinguish it from other vehicles. The host vehicle may be any of an engine vehicle having an internal combustion engine (engine) as a drive source, an electric vehicle having a drive motor as a drive source, and a hybrid vehicle having both an engine and a drive motor as drive sources. The self-vehicle can run not only in an automatic driving mode that does not require driving operations by the driver, but also in a manual driving mode that requires driving operations by the driver.

When driving in autonomous driving mode (hereinafter referred to as automatic driving or autonomous driving), an autonomous vehicle detects the surroundings of the vehicle based on detection data from on-board detectors such as cameras and lidar (LiDAR: Light Detection and Ranging). to recognize the external world situation. Based on the recognition result, the autonomous vehicle generates a travel trajectory (target trajectory) for a predetermined time from the current time, and controls the travel actuator so that the vehicle travels along the target trajectory.

FIG. 1A is a diagram showing how a self-vehicle 101, which is an automatically driven vehicle, travels on a road RD. FIG. 1B is a diagram showing an example of detection data (feature points) obtained by a rider mounted on the own vehicle 101. As shown in FIG. A feature point is a characteristic point of an object, such as an edge intersection (a corner of a building or a corner of a road sign). Data composed of a plurality of feature points as shown in FIG. 1B is called point cloud data. FIG. 1B shows point cloud data corresponding to the points in FIG. 1A. Based on the point cloud data shown in FIG. 1B, the host vehicle 101 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.

By the way, as a method of sufficiently recognizing the external environment around the vehicle, it is conceivable to increase the number of irradiation points of electromagnetic waves emitted from an on-vehicle detector such as a lidar. On the other hand, increasing the number of irradiation points may increase the processing load for controlling the vehicle-mounted detector and the amount of detection data (point cloud data) obtained by the vehicle-mounted detector. In particular, as shown in FIG. 1B, in situations where there are many objects (people, buildings, etc. in addition to trees) on the side of the road, the volume of point cloud data further increases. Moreover, when trying to deal with such problems, there is a risk of increasing the scale of the apparatus. In consideration of this point, in the present embodiment, the vehicle control device is configured as follows.

FIG. 2 is a block diagram showing the essential configuration of the vehicle control device 100 according to the embodiment of the invention. This vehicle control device 100 has a controller 10, a communication unit 1, a positioning unit 2, an internal sensor group 3, a camera 4, a rider 5, and an actuator AC for traveling. The vehicle control device 100 also has an external world recognition device 50 that constitutes a part of the vehicle control device 100 . The external world recognition device 50 recognizes the situation of the external world of the own vehicle 101, more specifically, the road structure and objects around the own vehicle 101, based on the detection data of the vehicle-mounted detectors such as the camera 4 and the rider 5. It is.

The communication unit 1 communicates with various servers (not shown) via networks including wireless communication networks such as the Internet and mobile phone networks, and periodically or arbitrarily sends map information, travel history information, traffic information, and the like. obtained from the server at the timing of The network includes not only a public wireless communication network but also a closed communication network provided for each predetermined management area, such as wireless LAN, Wi-Fi (registered trademark), Bluetooth (registered trademark), and the like. 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 positioning signals transmitted from positioning satellites. Positioning satellites are artificial satellites such as GPS satellites and quasi-zenith satellites. 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 .

The internal sensor group 3 is a general term for a plurality of sensors (internal sensors) that detect the running state of the vehicle 101 . For example, the internal sensor group 3 includes a vehicle speed sensor for detecting the vehicle speed of the vehicle 101, an acceleration sensor for detecting the acceleration in the longitudinal direction and the acceleration in the lateral direction (lateral acceleration) of the vehicle 101, and the rotation speed of the driving source. A rotational speed sensor for detection, a yaw rate sensor for detecting the rotational angular velocity of the center of gravity of the vehicle 101 around the vertical axis, and the like are included. The internal sensor group 3 also includes sensors that detect driver's driving operations in the manual driving mode, such as accelerator pedal operation, brake pedal operation, steering wheel operation, and the like.

The camera 4 has an imaging element such as a CCD or CMOS, and images the surroundings (front, rear, and sides) of the own vehicle 101 . The rider 5 measures the scattered light of the omnidirectional irradiation light (a type of electromagnetic wave) of the own vehicle 101 to measure the distance from the own vehicle 101 to surrounding objects, the positions and shapes of the objects, and the like.

Actuator AC is a travel actuator for controlling travel of host vehicle 101 . When the travel drive source is the engine, the actuator AC includes a throttle actuator that adjusts the opening of the throttle valve of the engine (throttle opening). If the travel drive source is a travel motor, the travel motor is included in actuator AC. Actuator AC also includes a brake actuator that operates the braking device of host vehicle 101 and a steering actuator that drives a steering device.

The controller 10 is configured by an electronic control unit (ECU). More specifically, the controller 10 includes a computer having an arithmetic unit 11 such as a CPU (microprocessor), a storage unit 12 such as ROM and RAM, and other peripheral circuits (not shown) such as an I/O interface. consists of Although a plurality of ECUs having different functions, such as an engine control ECU, a traction motor control ECU, and a braking system ECU, can be provided separately, FIG. 2 shows the controller 10 as a set of these ECUs for convenience. .

The storage unit 12 stores high-precision detailed map information (referred to as high-precision map information). High-definition map information includes road location information, road shape (curvature, etc.) information, road gradient information, intersection and branch point location information, number of lanes, lane width and location information for each lane ( Lane center position and lane boundary line information), position information of landmarks (traffic lights, signs, buildings, etc.) as landmarks on the map, and road surface profile information such as unevenness of the road surface. The storage unit 12 also stores information about various control programs and information such as thresholds used in the programs.

The calculation unit 11 has a road recognition unit 111, a demarcation unit 112, a setting unit 113, and a travel control unit 114 as functional configurations. Note that the road recognition unit 111, the demarcation unit 112, and the setting unit 113 are included in the external world recognition device 50, as shown in FIG.

The road recognition unit 111 recognizes the road structure in the traveling direction of the own vehicle 101 . Specifically, the road recognition unit 111 uses detection data (feature points) detected by the rider 5 to generate three-dimensional point cloud data (three-dimensional map data). Note that edges indicating the outline of an object are extracted based on information on the brightness and color of each pixel from captured image data in the traveling direction (hereinafter simply referred to as captured image) acquired by the camera 4, and the Point cloud data may be generated by extracting feature points using edge information.

The road recognition unit 111 recognizes the road structure based on the generated point cloud data. More specifically, the road recognition unit 111 uses machine learning to recognize boundary lines (curbs and division lines) RL and RB of the road RD ahead in the direction of travel, which are included in the point cloud data. Note that the method of recognizing the boundary line is not limited to this, and the boundary line may be recognized by other methods. The road recognition unit 111 recognizes an area sandwiched between the boundary lines RL and RB as an area corresponding to the road (hereinafter referred to as a road segment). The road recognition unit 111 acquires the high-precision map information stored in the storage unit 12, and based on the acquired high-precision map information and the own vehicle position recognized by the sensor value of the positioning unit 2, road segment may be recognized. Also, the road segment recognition method is not limited to this, and road segments may be recognized by other methods.

In some cases, the boundary lines RL and RB are hidden behind the vehicle in front, and a part of the road segment cannot be recognized, that is, occlusion may occur. Therefore, the road recognition unit 111 determines whether or not occlusion occurs, and complements the road segment when occlusion occurs. Specifically, the road recognition unit 111 uses point cloud data near the current vehicle position among the point cloud data generated in the past to recognize a road segment in an area where occlusion occurs, and recognizes the road segment. Complement road segments with results. It is assumed that point cloud data generated in the past by the road recognition unit 111 is stored in the storage unit 12 . Note that the road recognition unit 111 may complement road segments using the high-precision map information stored in the storage unit 12 .

The defining unit 112 is a plane (hereinafter referred to as a virtual plane) that is substantially perpendicular to the irradiation direction of the electromagnetic wave emitted from the rider 5 based on the road segment recognized by the road recognition unit 111, Detection regions are defined on virtual planes provided at predetermined distances along the traveling direction. The defining unit 112 defines each detection area so that the size of the detection area decreases as the distance from the host vehicle 101 increases. However, in situations where the road width increases as the distance increases, the detection area may increase as the distance increases. The demarcation unit 112 calculates the maximum detection distance indicating the range in the traveling direction in which the rider 5 should detect the external situation based on the vehicle speed of the own vehicle 101 detected by the vehicle speed sensor of the internal sensor group 3 . At this time, the demarcation unit 112 may calculate a braking distance at which the vehicle 101 can be stopped at a predetermined deceleration or less based on the current vehicle speed of the vehicle 101, and set the braking distance as the maximum detection distance. A distance obtained by multiplying the braking distance by a predetermined coefficient may be set as the maximum detectable distance. The defining unit 112 sets virtual planes at predetermined distances toward the vehicle 101 from a point that is the maximum detection distance away from the vehicle 101, and defines a detection area on each virtual plane.

3A, 3B, and 3C are diagrams for explaining detection areas. A region RS shown in FIG. 3A is a road segment recognized by the road recognition unit 111 while the host vehicle 101 is traveling on the road RD in FIG. 1A. A rectangular box BX in FIG. 3A is a detection area defined on a virtual plane set at a point away from the host vehicle 101 by the maximum detection distance. The length of arrow line F in FIG. 3A represents the maximum detection distance. As indicated by the arrow line F, the maximum detection distance is, in detail, the distance from the installation position of the rider 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 an area to be watched while traveling in the automatic driving mode. Specifically, the detection area BX is defined so that the center position in the road width direction overlaps 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 length as the road width at that position or longer than the road width by a predetermined length. The height of the detection area BX is set to be the same length as the height of the vehicle 101 or longer than the height of the vehicle by a predetermined length.

FIG. 3B schematically shows the detection areas BX defined on the virtual plane set at every predetermined distance D. As shown in FIG. FIG. 3C shows a diagram in which each detection region BX in FIG. 3B is schematically superimposed on an image in front of the host vehicle 101 with the rider 5 as a viewpoint. As shown in FIG. 3C, when viewed from the viewpoint of the rider 5, the farther the detection area BX from the host vehicle 101 (the more inward the detection area BX in FIG. 3C), the smaller the size. However, in situations where the road width increases as the distance increases, the detection area BX may increase as the distance increases.

The setting unit 113 sets a position (hereinafter referred to as an irradiation point or called the irradiation point.) is calculated. More specifically, the setting unit 113 irradiates each detection area BX according to the angular resolution calculated based on the minimum size of the detection target and the distance (distance in the traveling direction) from the own vehicle 101 of each detection area BX. Calculate points. The setting unit 113 generates information indicating the position of the calculated irradiation point (hereinafter referred to as irradiation point information), and stores it in the storage unit 12 in association with the position information indicating the current traveling position of the own vehicle 101 . .

The setting unit 113 reads the irradiation point information corresponding to the current running position of the vehicle 101 from the storage unit 12 when the own vehicle 101 is traveling in the automatic driving mode, and irradiates the rider 5 according to the irradiation point information. set points. Thereby, the irradiation light from the rider 5 is irradiated toward the set irradiation point.

In the automatic driving mode, the travel control unit 114 generates a target trajectory based on the external conditions around the vehicle recognized based on the data detected by the rider 5, and operates the actuator so that the vehicle 101 travels along the target trajectory. Control AC. Note that in the manual operation mode, the travel control unit 114 controls the actuator AC according to a travel command (steering operation, etc.) from the driver acquired by the internal sensor group 3 .

FIG. 4 is a diagram for explaining irradiation points of each detection area BX calculated by the setting unit 113. As shown in FIG. The vertical and horizontal intervals of the grids in each detection area BX in FIG. 4 represent the angular resolution corresponding to each detection area BX. The intersection points of the grid represent the irradiation points of the lidar 5, and the irradiation light of the lidar 5 is irradiated toward the intersection points of the grid. The irradiation light of the lidar 5 may be irradiated by a raster scanning method, or may be intermittently irradiated so that the electromagnetic wave is irradiated only to the irradiation point set by the setting unit 113, It may be irradiated in other manners.

As shown in FIG. 4, the angular resolution of the detection area BX corresponding to the maximum detection distance away from the vehicle 101 is the smallest, and the angular resolution of the detection area BX closest to the vehicle 101 is the largest. Thus, the angular resolution of each detection area BX is determined so as to decrease as the distance between the detection area BX and the own vehicle 101 increases (as the size of the detection area BX decreases). As a result, the number of irradiation points of the lidar 5 can be reduced without lowering the recognition accuracy of the position and size of the distant object and the recognition accuracy of the distance to the distant object. In FIG. 4, when the detection area BX includes grid intersections of other detection areas BX, the grid intersections of the detection area BX with smaller angular resolution are preferentially set as irradiation points.

FIG. 5 is a flow chart showing an example of processing executed by the controller 10 of FIG. 2 according to a predetermined program. The process shown in the flowchart of FIG. 5 is repeated, for example, at predetermined intervals while the host vehicle 101 is running in the automatic driving mode.

First, in step S11, three-dimensional point cloud data is generated using detection data detected by the lidar 5. FIG. At step S12, road segmentation is performed. Specifically, the boundary line of the road in front of the vehicle is recognized from the point cloud data generated in step S11, and the road segment is recognized based on the boundary line. In step S13, it is determined whether or not occlusion has occurred. If the result in step S13 is NO, the process proceeds to step S15. If the result in step S13 is affirmative, then in step S14 the road segment data is complemented.

In step S15, a detection area BX is set at a point ahead of the maximum detection distance on the road segment recognized in step S14. Specifically, a virtual plane is set at a point ahead of the maximum detection distance, and a detection area BX is defined on the virtual plane. Next, in step S16, detection areas BX are set at predetermined distance intervals along the traveling direction. Specifically, virtual planes are set at predetermined distances along the direction of travel, and the detection area BX is defined on each virtual plane. At this time, the size of the detection area BX is determined based on the distance from the own vehicle 101 to the detection area BX and the road segments recognized in steps S12 and S13, and the detection area BX is demarcated according to the determined size. . In a situation where the road width hardly changes, each detection area BX is set to become smaller as the distance between the detection area BX and the host vehicle 101 increases (FIG. 3C). However, in situations where the road width increases as the distance increases, the detection area BX may increase as the distance increases.

In step S17, the angular resolution corresponding to each detection area BX is calculated. In step S18, the irradiation point is calculated for each detection area BX according to the angular resolution calculated in step S17, and the irradiation point information indicating the calculated irradiation point is associated with the position information indicating the current traveling position of the vehicle 101. Stored in the storage unit 12 .

The operation of the external world recognition device 50 according to this embodiment is summarized as follows. When the own vehicle 101 travels on the road RD for the first time, the irradiation point information corresponding to the traveling position is not stored in the storage unit 12, so the irradiation point is not set based on the irradiation point information. Therefore, the irradiation light from the rider 5 irradiates the entire area in front of the own vehicle 101, so detection data (point cloud data) as shown in FIG. 1B is acquired (S11). Next, detection areas BX are defined at predetermined distance intervals according to road segments recognized based on the point cloud data (S12 to S16), and irradiation points are calculated for each detection area. Then, irradiation point information indicating the calculated irradiation point is stored in the storage unit 12 (S17, S18). On the other hand, when the host vehicle 101 travels again on the road RD in the automatic driving mode, the storage unit 12 stores irradiation point information corresponding to the traveling position. Therefore, since the irradiation light from the rider 5 is irradiated to the irradiation point specified by the irradiation point information, only the detection data (point cloud data) corresponding to the area to be observed during automatic driving is acquired (S11). . If the position and shape of the road segment recognized based on the point cloud data acquired at this time (S12) does not differ from the road segment recognized during the previous run by a predetermined amount or more, the subsequent processing, that is, The processing of S13 to S18 may be skipped.

According to this embodiment, the following effects can be obtained.
(1) The external world recognition device 50 includes the lidar 5 that irradiates electromagnetic waves around the vehicle 101 to detect external conditions around the vehicle 101, and a road recognition unit that recognizes the road structure in the traveling direction of the vehicle 101. 111, and based on the road structure recognized by the road recognition unit 111, on a plane substantially perpendicular to the irradiation direction of the electromagnetic wave (irradiation light) emitted from the lidar 5, along the direction of travel, at predetermined distance intervals. and a setting for setting an irradiation position (irradiation point) of the rider 5 based on a predetermined size of the detection target within the detection region BX defined by the demarcation unit 112. and a section 113 . The demarcation unit 112 determines the size of the detection area BX based on the distance from the 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. do. The predetermined detection target is an object of minimum size among the objects to be detected by the rider 5 . As a result, the number of irradiation points of the rider 5 can be reduced without lowering the recognition accuracy of the external situation. As a result, the external conditions around the vehicle can be accurately recognized while reducing the processing load.

(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 of the detection area BX from the host vehicle 101, and calculates the angular resolution corresponding to the detection area BX based on the calculated angular resolution. is divided in the left-right direction (the left-right direction in FIG. 4), and each rectangular area obtained is associated with the irradiation position of the rider 5 . Further, the setting unit 113 associates the irradiation position of the rider 5 with each rectangular area obtained by further dividing the detection area BX in the vertical direction (vertical direction in FIG. 4) based on the calculated angular resolution. As a result, the number of irradiation points of the rider 5 can be reduced without lowering the object detection accuracy of the rider 5 .

(3) The demarcation unit 112 calculates the maximum distance (maximum detection distance) indicating the range of the traveling direction in which the rider 5 should detect the external situation based on the vehicle speed of the vehicle 101, and calculates the maximum detection distance from the vehicle 101. A detection area BX is demarcated at predetermined distances from a distant point toward the own vehicle 101 . As a result, regardless of the vehicle speed of the own vehicle 101, the external conditions around the vehicle can be accurately recognized.

(4) The road recognition unit 111 recognizes the boundary line of the road in the traveling direction of the vehicle 101 based on the detection data of the rider 5, and recognizes the road structure indicated by the boundary line. Thereby, the road structure can be recognized without using map information. When map information (high-precision map information) is stored in the storage unit 12, the road recognition unit 111, instead of the detection data of the rider 5, or based on the map information together with the detection data of the rider 5, The road structure in the traveling direction of the own vehicle 101 is recognized. As a result, the road structure can be recognized with high accuracy.

The above embodiment can be modified in various forms. Some modifications will be described below. In the above embodiment, the setting unit 113 generates the irradiation point information indicating the position of the irradiation light of the rider 5, and sets the irradiation point of the rider 5 based on the irradiation point information. is not limited to this. For example, if the vehicle control device has a radar as an in-vehicle detector that detects other vehicles and obstacles around the own vehicle by emitting electromagnetic waves and detecting reflected waves, the setting unit It is also possible to generate irradiation point information indicating a position to be irradiated with radar electromagnetic waves, and set a radar irradiation point based on the irradiation point information. Then, the external world recognition device may recognize the situation of the external world of the own vehicle 101 based on the detection data of the radar.

In the above embodiment, the demarcation unit 112 defines 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 vehicle 101 travels, if the detection area BX is set in this way, there is a possibility that an overlooked area will occur. FIG. 6(a) is a diagram for explaining the overlooked area. Note that FIG. 6(a) shows only four detection areas BX (BX1 to BX4) for simplification of explanation. As shown in (a) of FIG. 6, when the road RD is extremely curving to the right, the right end of the detection area BX1 is far left of the right end of the detection area BX2 behind the detection area BX1. placed in As a result, an area that is not included in either of the detection areas BX1 and BX2, that is, an area that is not irradiated with the irradiation light of the rider 5 (missing area), although it is an area that should be watched during traveling in the automatic driving mode. occurs. Such overlooked areas similarly occur between the detection areas BX2 and BX3 and between the detection areas BX3 and BX4. A shaded area MA in the figure represents an overlooked area.

Therefore, when the overlooked area MA occurs, the demarcation unit 112 detects the positions of the right ends of the detection areas BX1, BX2, and BX3 respectively one rearward, as shown in FIG. 6(b). It may be shifted in the direction of the arrow in the drawing so as to match the positions of the right ends of the regions BX2, BX3, and BX4. As a result, even when the road is extremely curved, the external environment around the vehicle can be accurately recognized.

Further, in the above-described embodiment, the process shown in FIG. 5 shows an example in which the process shown in FIG. 5 is repeatedly executed while the vehicle 101 is running in the automatic driving mode. It may be repeatedly executed during running. Specifically, the irradiation point information is generated while traveling in the manual operation mode and stored in the storage unit 12, and when the road traveled in the manual operation mode is traveled again in the automatic operation mode, the information stored in the storage unit 12. The irradiation point of the rider 5 may be set according to the irradiation point information.

Furthermore, in the above embodiment, the external world recognition device 50 is applied to an automatically driving vehicle, but the external world recognition device 50 can also be applied to vehicles other than an automatically driving vehicle. For example, the external recognition device 50 can be applied to a manually operated vehicle equipped with ADAS (Advanced driver-assistance systems).

The above description is merely an example, and the present invention is not limited by the above-described embodiments and modifications as long as the features of the present invention are not impaired. It is also possible to arbitrarily combine one or more of the above embodiments and modifications, and it is also possible to combine modifications with each other.

1 communication unit, 2 positioning unit, 3 internal sensor group, 4 camera, 5 lidar, 10 controller, 12 storage unit, 111 road recognition unit, 112 demarcation unit, 113 setting unit, 114 traveling control unit, AC actuator

Claims (7)

an in-vehicle detector that emits electromagnetic waves around the own vehicle to detect external conditions around the own vehicle;
a road recognition unit that recognizes the road structure in the traveling direction of the own vehicle;
Based on the road structure recognized by the road recognition unit, a detection area is demarcated at predetermined distance intervals along the traveling direction on a plane substantially perpendicular to the irradiation direction of the electromagnetic wave emitted from the vehicle-mounted detector. a defining part to
a setting unit that sets an irradiation position of the vehicle-mounted detector based on a predetermined size of a detection target within the detection area defined by the defining unit;
The defining 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 determines the detection area according to the determined size. demarcate ,
The setting unit calculates angular resolution corresponding to the detection area based on the predetermined size of the detection target and the distance of the detection area from the vehicle, and determines the detection area based on the angular resolution. An external world recognition device , wherein each rectangular area obtained by dividing in the horizontal direction is associated with an irradiation position of the vehicle-mounted detector . In the external world recognition device according to claim 1,
The external world recognition apparatus, wherein the predetermined detection target is an object of minimum size among objects to be detected by the vehicle-mounted detector. In the external world recognition device according to claim 1 or 2,
The external world recognition device, wherein the setting unit associates the irradiation position of the vehicle-mounted detector with each rectangular area obtained by further dividing the detection area in the vertical direction based on the angular resolution. In the external world recognition device according to any one of claims 1 to 3,
Based on the vehicle speed of the own vehicle, the defining unit calculates a maximum distance indicating a range of a traveling direction in which the on-vehicle detector should detect the external situation, An apparatus for recognizing external worlds, wherein the detection area is demarcated for each of the predetermined distances. In the external world recognition device according to any one of claims 1 to 4,
The external world recognition device, wherein the road recognition unit recognizes a boundary line of a road in a traveling direction of the vehicle based on detection data of the vehicle-mounted detector, and recognizes a road structure indicated by the boundary line. In the external world recognition device according to any one of claims 1 to 5,
further comprising a storage unit for storing map information,
The external world recognition device, wherein the road recognition unit recognizes the road structure in the traveling direction of the vehicle based on the map information stored in the storage unit. In the external world recognition device according to any one of claims 1 to 6,
The external world recognition device, wherein the vehicle-mounted detector is a lidar.

Images