JP2020073893A - Local product data structure, storage medium, information processing apparatus, and detection apparatus - Google Patents

Abstract

To provide a map data structure, a storage medium, an information processing apparatus, and a detection apparatus capable of detecting a local product by a sensor in an appropriate manner.SOLUTION: In an advanced map DB43 stored by a server device 4, local product information IF is registered for each local product to be detected as an object by an external field sensor 30 of an on-vehicle device 1. A data structure of the local product information IF is provided with a field of sensor attributes that include setting information or environmental information about the detection of the local product. The server device 4 updates the field of the sensor attributes based on the statistical analysis of conditional information IC that indicates condition at a detection time of the local product received from the plurality of on-vehicle devices 1.SELECTED DRAWING: Figure 3

Description

  The present invention relates to a technique for updating map data.

  2. Description of the Related Art Conventionally, a technique for detecting a feature existing around a vehicle is known. For example, in Patent Document 1, a laser is intermittently emitted while scanning in the horizontal direction, and a reflected light is received to detect a point group on the surface of an object, or a surrounding image is captured. An in-vehicle system equipped with the camera is disclosed.

JP, 2014-89691, A

  The accuracy of feature detection differs depending on the type and method of sensors that detect features existing around the vehicle.Even with the same sensor, the types of features that are easy to detect depend on the surrounding environment. It may change. Therefore, in order to improve the detection accuracy of the feature, it is necessary to appropriately select the type and setting of the sensor to be used. On the other hand, registering information such as the optimum sensor type and setting for each feature in the map data requires enormous cost and time. Patent Document 1 does not disclose or suggest these problems.

  The present invention has been made, for example, in order to solve the above-mentioned problems, and its main object is to suitably perform detection of a feature by a sensor.

  In the invention according to the claim, the feature data structure for each feature used when detecting a feature by the external sensor included in the detection device relates to the type of the external sensor used for detecting the feature. It is characterized by including information and environmental information regarding the environment at the time of detecting the feature for each kind of the external sensor.

  Further, in the invention described in the claims, the information processing device has a feature data structure for each feature, which is used when detecting a feature by an external sensor included in the detection device, and detects the feature. A storage unit for storing a record of a feature data structure including information about the type of an external sensor used for the environment, and environmental information about an environment for detecting the feature for each type of the external sensor; and the detection device. And a transmission unit that transmits the record to the detection device in response to the request.

  Further, in the invention described in the claims, the detection device is used for detecting the object existing around the moving body, position information regarding the position of the feature around the moving body, and detecting the feature. A feature data structure including information about the type of the external sensor, environmental information about the environment when detecting the feature for each type of the external sensor, and setting information of the external sensor according to the environmental information. An acquisition unit that acquires a record that has, a control unit that controls the detection of the object by the external sensor based on the setting information, and an object that is detected by the external sensor based on the position information of the feature. And a specifying unit for specifying as an object.

1 is a schematic configuration of an advanced map system. (A) shows a functional configuration of the vehicle-mounted device. (B) shows the functional configuration of the server device. It is a functional block diagram which shows the functional relationship of an in-vehicle device and a server apparatus. It is an example of the data structure of the feature information. (A) shows an example of the data structure of the field of "sensor attribute" for the rider. (B) shows an example of the data structure of the field of "sensor attribute" targeted at the camera. It is an example of a data structure of condition information. It is an example of a flowchart showing a processing procedure executed by the vehicle-mounted device. It is an example of a flowchart showing a processing procedure executed by the server device.

  According to a preferred embodiment of the present invention, there is a feature data structure indicating a feature, which can be updated based on a detection result by a detection device capable of detecting the feature, or setting information regarding the detection of the feature or A detection related information field including environment information is provided. Here, the “feature” refers to all natural or artificial objects, trees, rivers, houses, roads, railways, etc. existing on the ground. According to this aspect, the feature data structure indicating the feature includes the detection related information field including the setting information or the environment information regarding the detection of the feature. The detection related information field can be updated based on the detection result by the detection device that can detect the feature. In this aspect, the feature data structure can hold updatable setting information and environment information useful when detecting a feature, and the feature data structure can be stored in a device that refers to the data of the feature data structure. Can be suitably executed.

  In one aspect of the above-mentioned feature data structure, the detection related information field is updated by a server device that analyzes a detection result of the detection device mounted on a plurality of moving bodies by a statistical method. According to this aspect, the detection related information field is preferably updated based on the analysis of the detection result of the detection device based on the statistical method by the server device.

  In another aspect of the above-mentioned feature data structure, a plurality of the detection related information fields are provided for each type of the detection device. According to this aspect, it is possible to cause the detection device to refer to the setting information and the environment information suitable for the type of the detection device and execute the feature detection process. In a preferable example of the feature data structure, the detection related information field includes a subfield indicating setting information or environment information regarding the detection of the feature corresponding to each type of the detection device.

  In another aspect of the above-mentioned feature data structure, the subfield is a time zone or a weather when a detection rate of the feature by each of the detection devices is a predetermined value or more or less than a predetermined value for each type of the detection device. At least one of the above is included. According to this aspect, the detection device refers to the record of the feature data structure to determine whether the current detection environment corresponds to a time zone or weather suitable (or unsuitable) for detection of the target feature. It can be grasped appropriately.

  In another aspect of the above-mentioned feature data structure, the subfield is a feature in which a detection rate of the feature by each of the detection devices is a predetermined value or more or less than a predetermined value for each type of the detection device. Contains relevant spatial extent information. According to this aspect, the detection device refers to the record of the feature data structure to specify a portion of the outer shape of the target feature that is easy or difficult to detect and efficiently perform the feature detection process. can do.

  In another aspect of the feature data structure, the feature data structure includes a position information field indicating information about a position of the feature and an attribute information field indicating information about an attribute of the feature. Detects the feature based on the information on the position of the feature and the information on the attribute of the feature. According to this aspect, the detection device can detect the feature with high accuracy by identifying the position and the attribute of the feature by referring to the record of the feature data structure.

  Preferably, the storage medium stores a record of the feature data structure described in any one of the above.

  According to another preferred embodiment of the present invention, the information processing device has a feature data structure indicating a feature and is based on a detection result by a detection device which is mounted on a moving body and can detect the feature. A storage unit that stores a record of a feature data structure that is updatable and that has a detection-related information field that includes setting information or environment information related to the detection of the feature, and the detection device has succeeded in detecting the feature or An acquisition unit that acquires state information including at least one of a state of the moving body, a state around the moving body, and a state of the detection device at the time of failure, and the state information obtained by the obtaining unit. And an updating unit that updates the detection related information field based on the above. The information processing device includes a storage unit that stores a record of a feature data structure, an acquisition unit that acquires state information, and an update unit that updates the detection related information field. According to this aspect, the information processing apparatus can suitably update the content of the detection related information field of the record of the feature data structure.

  In one aspect of the information processing device, the acquisition unit acquires the state information regarding a plurality of features transmitted from a plurality of moving bodies, and the update unit statistically acquires a plurality of the state information regarding the feature. The update content of the detection related information field corresponding to the feature is determined by performing an analysis by a statistical method. According to this aspect, the information processing apparatus can suitably update the content of the detection related information field of the record of the feature data structure by analyzing the state information transmitted from the plurality of mobile bodies by the statistical method. ..

  According to another preferred embodiment of the present invention, the detection device includes a detection unit that detects an object existing around a moving body, a position information field that indicates information about the position of the feature, and the detection device that detects the feature. An acquisition unit that acquires a record having a data structure including a detection related information field indicating related information from an external device, and an object detected by the detection unit based on the information about the position of the feature. And a state of the moving body at the time when the specifying unit that specifies the object as a matter of success or failure to specify the feature is included, a state around the moving body, or a state of the detection device. A transmitting unit that transmits the state information to the external device, and the detecting unit changes a setting related to detection of the object based on information related to detection of the feature. In this aspect, the detection device includes a detection unit, an acquisition unit, a specification unit, and a transmission unit. Then, the detection device transmits the state information when the object detected by the detection unit is specified as a feature (including the case where the specification fails) to the external device. Further, the detection device changes the setting related to the detection of the object based on the information related to the detection of the feature indicated by the detection related information field. According to this aspect, the detection device preferably supplies the external device with the state information necessary for updating the record having the data structure including the detection related information field, and the setting related to the detection of the feature based on the record acquired from the external device. Can be determined.

  In one aspect of the detection device, the detection-related information field includes a subfield indicating a detection condition in which the detection success rate of the feature is equal to or more than a predetermined value, and the detection unit determines that the detection success rate of the feature is The range of the detection area of the detection unit is changed based on the detection condition that is equal to or greater than the predetermined value. According to this aspect, the detection device can appropriately determine the range of the detection region based on the detection condition that the detection success rate of the feature is high.

  In another aspect of the detection apparatus, the detection-related information field includes a subfield indicating a detection condition that a detection success rate of the feature is less than a predetermined value, and the detection unit is a detection success of the feature. When the state of the moving body, the state around the moving body, or the state of the detection device corresponds to the detection condition that the rate is less than a predetermined value, the feature is excluded from the detection target. According to this aspect, the detection device can preferably suppress the feature detection process under a situation in which the probability of detection failure is high.

  According to another preferred embodiment of the present invention, a feature data structure indicating a feature, which is updatable based on a detection result of a detection device mounted on a mobile body and capable of detecting the feature, A control method executed by an information processing apparatus that refers to a storage unit that stores a record of a feature data structure including a detection-related information field that includes setting information or environment information regarding the detection of a feature, wherein the detection apparatus is An acquisition step of acquiring state information including at least one of a state of the moving body, a state around the moving body, and a state of the detecting device when the detection of the feature succeeds or fails; An updating step of updating the detection related information field based on the state information acquired by the step. By executing this control method, the information processing apparatus can suitably update the contents of the detection related information field of the record of the feature data structure.

  According to another preferred embodiment of the present invention, a feature data structure indicating a feature, which is updatable based on a detection result of a detection device mounted on a mobile body and capable of detecting the feature, A program executed by a computer that refers to a storage unit that stores a record of a feature data structure including a detection related information field that includes setting information or environment information related to feature detection, wherein the detection device is the feature. An acquisition unit that acquires state information including at least one of the state of the moving body, the state of the periphery of the moving body, and the state of the detection device when the detection is successful or unsuccessful; The computer is caused to function as an updating unit that updates the detection related information field based on the status information that has been obtained. By executing this program, the computer can suitably update the contents of the detection related information field of the record of the feature data structure.

  According to another preferred embodiment of the present invention, there is provided a control method executed by the detection device, comprising a detection step of detecting an object existing around a moving body, and a position information field indicating information on the position of the feature. An acquisition step of acquiring a record having a data structure including a detection related information field indicating information related to the detection of the feature from an external device, and the detection step based on the information on the position of the feature. A specifying step of specifying the detected object as the feature, the state of the moving body when the specifying step succeeds or fails in specifying the feature, a state around the moving body, or the detection device. A step of transmitting state information including at least one of the states to the external device, wherein the detecting step includes detecting the object based on information related to the detection of the feature. To the setting of the change. By executing this control method, the detection device preferably supplies the external device with the state information necessary for updating the record having the data structure including the detection related information field, and also performs the local information based on the record acquired from the external device. Settings for detecting objects can be defined.

  According to another preferred embodiment of the present invention, a program executed by a computer, the detecting unit detecting an object existing around a moving body, a position information field indicating information on the position of a feature, and An acquisition unit that acquires a record having a data structure including a detection related information field indicating information related to the detection of a feature from an external device, and the detection unit detects the record based on information about the position of the feature. A specific unit that identifies the object as the feature, and the state of the moving body when the specific unit succeeds or fails to identify the feature, a state around the moving body, or a state of the detection device. And a transmission unit that transmits status information including at least one of the external devices to the external device, wherein the detection unit relates to detection of the object based on information related to detection of the feature. Changing a constant. By executing this program, the computer suitably supplies the external device with the state information necessary for updating the record having the data structure including the detection related information field, and at the same time, based on the record acquired from the external device, Settings for detection can be defined.

  Hereinafter, preferred embodiments of the present invention will be described with reference to the drawings.

[System configuration]
FIG. 1 is a schematic configuration of an advanced map system according to this embodiment. The advanced map system includes the vehicle-mounted device 1 that includes the external sensor 31, and the server device 4 that stores the advanced map DB 43. Then, the advanced map system automatically generates setting information and the like necessary for accurately detecting a feature (signboard 5 in the example of FIG. 1) existing around the road by various external sensors.

  The vehicle-mounted device 1 includes one or a plurality of external environment sensors 31 such as a lidar (Light Detection and Ranging or Laser Illuminated Detection And Range) and a camera, and based on the output of the external world sensor 31, the vehicle position is highly accurate. Such as estimation.

  In the present embodiment, the in-vehicle device 1 exists near the own vehicle position from the server device 4 by transmitting a predetermined request signal including the own vehicle position information based on the output of a GPS receiver described later to the server device 4. Information regarding a feature to be performed (also referred to as “feature information IF”) is received. As will be described later, the feature information IF includes information on the attributes (also referred to as “sensor attributes”) of the external sensor 31 suitable or unsuitable for detecting the corresponding features by the external sensor 31. There is. Then, when detecting the feature to be detected by the external field sensor 31, the vehicle-mounted device 1 controls the external field sensor 31 based on the received feature information IF so that the external field sensor 31 detects the feature. After that, the vehicle-mounted device 1 transmits information (also referred to as “condition information IC”) regarding the detection condition of the feature by the external sensor 31 to the server device 4. As will be described later, the condition information IC includes information regarding whether or not the detection of the target feature has succeeded, information regarding the detection environment of the target feature, and setting information of the external sensor 31 (that is, parameter information). included. Although only one vehicle-mounted device 1 is shown in FIG. 1 for the sake of convenience, a plurality of vehicle-mounted devices 1 mounted on each vehicle on the road are actually the server device 4, the feature information IF, and the condition information IC. Give and receive. The vehicle-mounted device 1 is an example of the “detection device” in the present invention.

  The server device 4 stores the advanced map DB 43 including the feature information IF corresponding to each feature existing around the road, and when the request signal for the feature information IF is received from the vehicle-mounted device 1, the request signal is added to the request signal. The feature information IF corresponding to the features around the vehicle-mounted device 1 is extracted from the advanced map DB 43 based on the included position information of the vehicle-mounted device 1 and transmitted to the vehicle-mounted device 1. The features registered in the advanced map DB 43 as the feature information IF are, for example, kiloposts, 100m posts, delineators, transportation infrastructure equipment (eg, signs, direction signs, signals), telephone poles, which are periodically arranged alongside the road. In addition to artificial features such as streetlights, natural features such as trees may be used. Further, the server device 4 accumulates the condition information IC received from the plurality of vehicle-mounted devices 1 and statistically analyzes the accumulated condition information IC, so that the server device 4 includes the feature information IF registered in the advanced map DB 43. Performs sensor attribute update processing. The server device 4 is an example of the “information processing device” in the present invention.

[Configuration of in-vehicle device and server device]
FIG. 2A is a block diagram showing a functional configuration of the vehicle-mounted device 1. The vehicle-mounted device 1 mainly includes a communication unit 11, a storage unit 12, a sensor unit 13, an input unit 14, a control unit 15, and an output unit 16. Each of these elements is connected to each other via a bus line.

  The communication unit 11 performs data communication with the server device 4 under the control of the control unit 15. The storage unit 12 stores a program executed by the control unit 15 and information necessary for the control unit 15 to execute a predetermined process. For example, the storage unit 12 may store the feature information IF received from the server device 4 or map data including the feature information IF.

  The sensor unit 13 includes one or a plurality of external sensors 31 for recognizing the surrounding environment of the vehicle, a GPS receiver 32, a gyro sensor 33, an acceleration sensor 34, a speed sensor 35, and the like. In the present embodiment, the external sensor 31 is configured so that the output-related settings can be adjusted based on the control signal from the controller 15. For example, when the outside world sensor 31 is a lidar, the outside world sensor 31 is based on a control signal supplied from the vehicle-mounted device 1, and the peak power of the pulsed laser to be emitted and the pulse period (so-called laser pulse density) for repeatedly emitting the pulsed laser. And a laser irradiation angle range indicating an angle range irradiated by the laser are configured to be adjustable. In another example, when the external world sensor 31 is a camera, the external world sensor 31 is configured to be able to adjust the frame rate, the resolution, the angle of view, the sensitivity, the exposure, etc. based on the control signal supplied from the vehicle-mounted device 1.

  The input unit 14 is a button operated by a user, a touch panel, a remote controller, a voice input device, and the like, and the output unit 16 is, for example, a display, a speaker, and the like that output based on the control of the control unit 15.

  The control unit 15 includes a CPU that executes programs and controls the entire vehicle-mounted device 1. The control unit 15 predicts the vehicle position based on the outputs of the GPS receiver 32, the gyro sensor 33, the acceleration sensor 34, and the like. Further, the control unit 15 calculates the position information of the feature by the external sensor 31 for the feature around the position of the own vehicle, and compares it with the position information indicated by the feature information IF of the detection target feature. , Correct the predicted vehicle position. As a result, the control unit 15 acquires a highly accurate vehicle position for automatic driving or the like. Further, in the present embodiment, the control unit 15 executes a process for detecting a feature with high accuracy, and functionally, the feature information acquisition unit 21, the feature detection unit 22, and the condition information transmission. And a part 23. Each of these elements will be described later with reference to FIG.

  FIG. 2B is a block diagram showing the functional configuration of the server device 4. The server device 4 mainly includes a communication unit 41, a storage unit 42, and a control unit 45. Each of these elements is connected to each other via a bus line.

  The communication unit 41 performs data communication with the vehicle-mounted device 1 under the control of the control unit 45. The storage unit 42 stores a program executed by the control unit 45 and information necessary for the control unit 45 to execute a predetermined process. In this embodiment, the storage unit 42 stores the advanced map DB 43. The advanced map DB 43 includes feature information IF corresponding to each feature to be detected by the external sensor 31 of the vehicle-mounted device 1. In the field of the sensor attribute of the feature information IF of each feature registered in the advanced map DB 43, for example, empty data is registered in the initial state, and is appropriately updated based on the statistical analysis of the condition information IC by the control unit 45. It The data structure of the feature information IF will be described in detail in the [Data structure] section. The storage unit 42 is an example of the “storage medium” in the present invention.

  The control unit 45 includes a CPU that executes programs and controls the entire server device 4. In the present embodiment, the control unit 45 functionally includes a feature information transmission unit 46, a condition information acquisition unit 47, and a sensor attribute update unit 48.

  FIG. 3 is a functional block diagram showing a functional relationship between the vehicle-mounted device 1 and the server device 4.

  The feature information acquisition unit 21 predicts the own vehicle position based on the outputs of the GPS receiver 32, the gyro sensor 33, the acceleration sensor 34, and the like, and sends a request signal of the feature information IF including information on the predicted own vehicle position, It is transmitted to the server device 4 by the communication unit 11. In this case, for example, when the feature information acquisition unit 21 determines that the feature information IF around the vehicle position has not been acquired from the server device 4, the communication unit 11 transmits the above-described request signal to the server device 4. Send. When the feature information acquisition unit 21 receives the feature information IF from the server device 4, the feature information acquisition unit 21 supplies the received feature information IF to the feature detection unit 22. The feature information acquisition unit 21 is an example of the “acquisition unit” in the present invention, and the feature information IF is an example of the “record” in the present invention.

  The feature detection unit 22 performs the feature detection processing based on the feature information IF corresponding to at least one feature among the received feature information IF. In this case, the feature detection unit 22 extracts the sensor attribute corresponding to the external sensor 31 used for feature detection from the target feature information IF, for example. Here, in the feature information IF, as will be described later, setting information of the external sensor 31 when the detection rate is statistically high (for example, in the case of a lidar, information on parameters such as laser power and laser pulse density). It is included. Therefore, for example, the feature detection unit 22 transmits a control signal for applying a setting, which is included in the referenced sensor attribute and has a high statistical detection rate, to the external sensor 31 used for feature detection, and the target feature is detected. Make settings suitable for object detection. Then, the feature detection unit 22 acquires or calculates three-dimensional position information (including point cloud information) of the feature based on the output signal received from the external sensor 31 after the setting based on the feature information IF. Then, the feature detection unit 22 compares the position information of the feature included in the target feature information IF to determine whether or not the detection of the feature has succeeded. Then, the feature detection unit 22 determines whether or not the feature detection is successful, the setting information of the external sensor 31 used to detect the feature, environmental information such as time and weather at the time of feature detection, and the like. And are supplied to the condition information transmission unit 23.

  Note that the feature detection unit 22 detects a feature regardless of the sensor attribute when each subfield of the referenced sensor attribute is empty data in the initial state. In this case, the feature detection unit 22 may, for example, set each parameter of the external sensor 31 used for feature detection to a standard setting value set in advance, and set each parameter of the external sensor 31 used for feature detection. The set value may be randomly determined. The feature detection unit 22 is an example of the “detection unit” or the “specification unit” in the present invention.

  The condition information transmission unit 23 generates the condition information IC based on the information received from the feature detection unit 22 and transmits it to the server device 4 by the communication unit 11. The transmission may be sequentially performed each time a feature is detected, or may be collectively transmitted when the condition information IC is accumulated to some extent. As will be described later, the condition information IC includes information such as the position, attitude, and speed of the vehicle, information about whether or not the detection of the feature has succeeded, and setting information of the external sensor 31 used for detecting the feature. Is included at least. The data structure and the generation method of the condition information IC will be described later with reference to FIG. The condition information transmitter 23 is an example of the “transmitter” in the present invention, and the condition information IC is an example of the “state information” in the present invention.

  When the communication unit 41 receives the request signal for the feature information IF from the vehicle-mounted device 1, the feature-information transmission unit 46 registers the position information of the vehicle-mounted device 1 included in the request signal and the advanced map DB 43, for example. The feature information IF around the vehicle-mounted device 1 is extracted by comparing the position information of the feature included in the generated feature information IF. Then, the feature information transmission unit 46 transmits the extracted feature information IF to the vehicle-mounted device 1 by the communication unit 41.

  The condition information acquisition unit 47 receives the condition information IC transmitted from each vehicle-mounted device 1 mounted on the vehicle traveling on the road by the communication unit 41 and stores the condition information IC in the storage unit 42. The condition information acquisition unit 47 is an example of the “acquisition unit” in the present invention.

  The sensor attribute update unit 48 updates the sensor attribute of the local feature information IF registered in the advanced map DB 43 by statistically analyzing the condition information IC received from the plurality of vehicle-mounted devices 1.

[data structure]
Next, the data structures of the feature information IF and the condition information IC will be specifically described.

(1) Feature Information FIG. 4 is an example of a data structure (feature data structure) of the feature information IF. The feature information IF shown in FIG. 4 includes header information and body information. The header information includes fields of "header ID", "version information", and "body length". Identification information indicating that the corresponding body information is related to a feature is registered in the "header ID". In “Version information”, a version of the data structure of body information is registered. The data size of body information is registered in “body length”.

  The body information includes fields of “feature ID”, “coordinates”, “type”, “attribute information”, and a plurality (here, N) of “sensor attributes”. In the “feature ID”, the identification information of the feature uniquely assigned in the advanced map DB 43 is registered. In the "coordinates", coordinates representing the position of the feature are registered, and for example, respective coordinates of latitude, longitude, and ground height (elevation) are registered. The type to which the feature belongs is registered in "type". For example, "types" include road signs (including signs, pillars, direction signs, etc.), traffic lights (including vehicle signals, pedestrian signals, railroad crossing gates, etc.), equipment (electric poles, street lights, guardrails, tunnels, etc.). , (Including bridges), facilities (including buildings, signboards, etc.), natural objects (including standing trees, rocks, etc.) are registered. General attributes of the feature are registered in the "attribute information". The information registered in the “attribute information” changes according to the type of the target feature. For example, when the feature is a road sign, information such as the type of road sign (for example, traffic regulation, speed regulation, etc.), the direction of the marking surface of the road sign, and the size of the road sign is registered in the “attribute information”. .. The “coordinate” field is an example of the “positional information field” in the present invention, and the “attribute information” field is an example of the “attribute information field” in the present invention.

  In the "sensor attribute", setting information (that is, parameter information) of the external sensor 31 suitable or unsuitable for detecting the target feature and environment information regarding the detection environment are registered. The “sensor attribute” is provided for each type of the external sensor 31, and is registered and updated by the statistical analysis processing of the condition information IC by the server device 4. Each "sensor attribute" field is an example of the "detection related information field" in the present invention.

  FIG. 5A shows an example of the data structure of the “sensor attribute” field for the lidar, and FIG. 5B shows an example of the data structure of the “sensor attribute” field for the camera. Show. As shown in FIGS. 5A and 5B, in this case, the setting information of the target external sensor such as “sensor type”, “maker information”, and “hardware ID” is set in the “sensor attribute” field. And a plurality of subfields in which environmental information regarding the detection environment is registered. These subfields are initially set to Null (empty data) or a general-purpose standard value, and are appropriately registered and updated by the statistical analysis processing of the condition information IC by the server device 4.

  First, the contents of each subfield of the “sensor attribute” field for the lidar shown in FIG. 5A and the use when the vehicle-mounted device 1 refers will be described.

  Information indicating the type (here, a rider) of the target external sensor 31 is registered in the "sensor type". Information on the manufacturer of the target external sensor 31 is registered in the "maker information". In the “hardware ID”, information that identifies the model of the target external sensor 31 is registered. By referring to these subfields, the vehicle-mounted device 1 can use the external sensor 31 used for feature detection from a plurality (N in the example of FIG. 4) of “sensor attribute” fields registered in the feature information IF. Extract the field of "sensor attribute" that conforms to.

  In the “time zone with the highest detection rate” or the “time zone with the lowest detection rate”, the time zone with the highest probability of successful detection of the target feature (detection success rate) (for example, 0 to 24) Any one of the hourly hours up to the hour) is registered.

  Generally, in the case of feature detection by a rider, for example, in a time zone when traffic jam occurs, another vehicle is present within the laser irradiation range of the rider and becomes an obstacle, and the feature detection tends to fail. Similarly, it is conceivable that the detection success rate of the feature will be low in a time zone when the target feature is backlit due to the sunset or the like.

  Therefore, in the first example, the in-vehicle device 1 refers to the sensor attributes shown in FIG. 5A, and only when the current time belongs to the time zone indicated by “the time zone having the highest detection rate”. The detection processing of the target feature by is executed. In this case, the vehicle-mounted device 1 can perform feature detection only when highly accurate feature detection can be expected. In the second example, the vehicle-mounted device 1 executes the detection process of the target feature by the rider when the current time is other than the time zone indicated by the “time zone having the lowest detection rate”. As a result, the vehicle-mounted device 1 can preferably prevent unnecessary feature detection that is likely to fail.

  "Average laser power in the above time zone" and "laser pulse density in the above time zone" are provided for "the time zone with the highest detection rate" and "the time zone with the lowest detection rate", respectively. The average laser power and the average value of the laser pulse density of the lidar set at the time of detecting the feature in each applicable time zone are registered. For example, when the current time belongs to the time zone indicated by “the time zone having the highest detection rate”, the vehicle-mounted device 1 indicates the laser power indicated by the corresponding “average laser power in the time zone” and the corresponding “time zone”. The feature is detected by setting the lidar to the laser pulse density indicated by "Laser pulse density in." This prevents the vehicle-mounted device 1 from unnecessarily setting the laser power and the laser pulse density of the lidar at the time of detecting a feature, thereby reducing power consumption. Further, in another example, when the current time belongs to the time zone indicated by “the time zone with the lowest detection rate”, the vehicle-mounted device 1 needs to increase the accuracy of the rider in order for the feature detection by the rider to succeed. It is judged that the laser power and laser pulse density are higher than the laser power indicated by the corresponding "average laser power in the above time zone" and the laser pulse density indicated by the corresponding "laser pulse density in the above time zone". Set and perform feature detection.

  The "relative distance (range) of the vehicle having a high detection rate" is registered with the relative distance of the vehicle to the feature when the detection rate of the feature is equal to or higher than a predetermined rate. In this case, for example, the "vehicle relative distance (range) with a high detection rate" is a combination of the lane number in which the vehicle was present when the feature was detected and the range of the distance between the vehicle and the feature in the direction perpendicular to the lane. Is registered. Similarly, in the “vehicle relative distance (range) with low detection rate”, the relative distance of the vehicle with respect to the feature when the detection rate of the feature is less than the predetermined rate is registered. When the vehicle-mounted device 1 refers to the sensor attribute shown in FIG. 5 (A), for example, the vehicle-mounted device 1 has a relative distance that the relative distance to the target feature is represented by “vehicle relative distance (range) with high detection rate”. The target feature detection process is executed only when the value is within the range. In another example, when the relative distance to the target feature is outside the range of the relative distance indicated by the “vehicle relative distance (range) with a low detection rate”, the vehicle-mounted device 1 performs the target feature detection process. To execute.

  Further, in the "region of the feature itself having a high detection rate", information on a region in which the detection rate is detected at a predetermined rate or more in the entire surface area of the target feature is registered. For example, in the “area of the feature itself with a high detection rate”, the ground clearance of the area detected with a probability of a predetermined rate or more and information on the direction in which the area is facing are registered. Similarly, in the "region of the feature itself having a low detection rate", information on a region detected with a probability less than a predetermined rate in the entire surface region of the target feature is registered. For example, the vehicle-mounted device 1 defines only the area indicated by the “area of the feature itself having a high detection rate” as the detection target area of the feature by the rider. As a result, the vehicle-mounted device 1 can efficiently perform feature detection. Similarly, the vehicle-mounted device 1 may exclude the area indicated by the “area of the feature itself having a low detection rate” from the detection target area of the feature by the rider. The region indicated by the “region of the feature itself having a high detection rate” is an example of the “spatial range” in the present invention.

  In “weather with high detection rate”, information on weather with a detection rate equal to or higher than a predetermined rate is registered. In the "weather with low detection rate", information on weather where the detection rate is less than a predetermined rate is registered. For example, the vehicle-mounted device 1 executes the feature detection processing by the rider only when the current weather matches the weather indicated by “weather with high detection rate”. In this case, the vehicle-mounted device 1 can perform feature detection by the rider only when highly accurate detection of features can be expected. In another example, the vehicle-mounted device 1 executes the detection processing of the target feature by the rider when the current weather is other than “weather with a low detection rate”. As a result, the in-vehicle device 1 can preferably prevent unnecessary execution of the feature detection by the rider in an environment where there is a high possibility of failure.

  In addition, "a time zone having the highest detection rate", "a vehicle relative distance (range) having a high detection rate", "a region of a feature itself having a high detection rate", and "weather having a high detection rate" are " 3 is an example of a "subfield indicating a detection condition that a detection success rate of a feature is equal to or higher than a predetermined value". Further, "a time zone having the lowest detection rate", "a vehicle relative distance (range) having a low detection rate", "a region of the feature itself having a low detection rate" and "weather having a low detection rate" are " 3 is an example of a "subfield indicating a detection condition that a detection success rate of a feature is less than a predetermined value".

  Next, the “sensor attribute” field for the camera shown in FIG. 5B will be described.

  The “sensor attribute” field for the camera shown in FIG. 5B includes “sensor type”, “maker information”, “hardware ID”, “highest detection rate time zone”, and “time zone above”. Frame rate "," resolution in the above time zone "," time zone with the lowest detection rate "," frame rate in the above time zone "," resolution in the above time zone "," vehicle with a high detection rate " "Relative distance (range)", "vehicle relative distance (range) with low detection rate", "area of feature itself with high detection rate", "area of feature itself with low detection rate", "weather with high detection rate" , And “weather with low detection rate”.

  The "sensor attribute" field for the camera includes the "average laser power in the above time zone" and the "laser pulse density in the above time zone" provided in the "sensor attribute" field for the lidar. In place of each subfield of, the subfields of "frame rate in the above time period" and "resolution in the above time period", which are items specific to the camera, are provided. Here, the “frame rate in the above time period” and the “resolution in the above time period” include the time period indicated by the corresponding “highest detection rate time period” or “lowest detection rate time period”. The average value of the frame rate of the camera and the average value of the resolution set at the time of feature detection are registered. The other subfields overlap each subfield described in the example of FIG. 5A, and the same content as the content described in the example of FIG. 5A is registered.

  As described above, in the body information of the feature information IF, the setting information and the environment-related information corresponding to each type of the external sensor supposed to be used for feature detection are registered. Therefore, the vehicle-mounted device 1 can refer to the sensor attribute corresponding to the external sensor 31 used to detect the feature and accurately execute the detection process of the target feature.

(2) Condition Information FIG. 6 is an example of the data structure of the condition information IC. The condition information IC shown in FIG. 6 includes header information and body information. The header information includes fields of "header ID", "version information", and "body length". In the "header ID", information for identifying whether the corresponding body information is the information when the detection of the feature succeeds or the information when the detection fails is registered. Therefore, when the vehicle-mounted device 1 transmits the condition information IC to the server device 4 when the feature is successfully detected, the “header ID” identifies that the corresponding body information has successfully detected the feature. Register the information. On the other hand, when the vehicle-mounted device 1 transmits the condition information IC to the server device 4 when the feature detection fails, the “header ID” identifies the corresponding body information indicating that the feature detection failed. Register the information. In “Version information”, a version of the data structure of body information is registered. The data size of body information is registered in “body length”.

  The body information is information indicating the state of the vehicle on which the vehicle-mounted device 1 that performs feature detection is mounted, the state around the vehicle, or the state of the external sensor 31, and in the example of FIG. 6, “feature ID”, "Sensor type", "Manufacturer information", "Hardware ID", "Vehicle attitude", "Vehicle speed", "Vehicle position", "Time", "Weather", and multiple "used parameters" Including each field of.

  In the "feature ID", the identification information of the feature that is detected by the vehicle-mounted device 1 that generates the condition information IC is registered. This identification information is identification information of the feature that is uniquely assigned in the advanced map DB 43. Information indicating the type of the external sensor 31 used by the vehicle-mounted device 1 that generates the condition information IC to detect a feature is registered in the "sensor type". In the "maker information", the information on the maker of the external sensor 31 used by the vehicle-mounted device 1 that generates the condition information IC to detect a feature is registered. In the “hardware ID”, information that specifies the model of the external sensor 31 used by the vehicle-mounted device 1 that generates the condition information IC for feature detection is registered. In the "vehicle attitude", the attitude information of the vehicle on which the vehicle-mounted device 1 that generates the condition information IC is detected when the feature is detected is registered. For example, the vehicle-mounted device 1 calculates the roll angle, the pitch angle, and the yaw angle of the vehicle at the time of detecting a feature based on the detection signals from the internal sensors such as the gyro sensor 33 and the acceleration sensor 34, and these angles are calculated. Information is registered in the "vehicle attitude" field. In the "vehicle speed", information on the vehicle speed based on the output of the speed sensor 35 and the like at the time of detecting a feature of the vehicle on which the vehicle-mounted device 1 that generates the condition information IC is detected is registered. In the “vehicle position”, information on the vehicle position based on the output of the GPS receiver 32 at the time of detecting a feature of the vehicle on which the vehicle-mounted device 1 that generates the condition information IC is detected is registered.

  In addition, corresponding information is registered in the “vehicle attitude”, the “vehicle speed”, and the “vehicle position” regardless of whether or not the feature detection is successful. That is, when the feature detection is successful, the posture, speed, and position of the vehicle when the feature detection is successful are registered in the “vehicle posture”, “vehicle speed”, and “vehicle position”. In case of failure, the posture, speed and position of the vehicle at the time of failure are registered. The same applies to the following fields of "time", "weather", and a plurality of "used parameters".

  In "time", the time when the feature is detected is registered. The time when the feature is detected is registered in “weather”. The vehicle-mounted device 1 may determine the weather to be registered in the “weather” based on the output of an illuminance sensor, a raindrop sensor, or the like (not shown), and the weather information to be registered in the “weather” from the server device that manages the weather information. May be obtained.

  The setting information of the external sensor 31 used for feature detection at the time of feature detection is registered in a plurality of “used parameters” (“used parameter 1”, “used parameter 2” in FIG. 6). It For example, when the external sensor 31 used for feature detection is a lidar, the setting information indicating the laser power, the laser pulse density, the angle range irradiated by the laser, etc. at the time of feature detection is the “used parameter”. Registered in each. In another example, when the external sensor 31 used for feature detection is a camera, setting information indicating the frame rate, resolution, angle of view, etc. is registered in each of the "used parameters".

[Processing flow]
(1) In-vehicle device processing FIG. 7 is an example of a flowchart showing a processing procedure executed by the in-vehicle device 1. The vehicle-mounted device 1 repeatedly executes the process of the flowchart shown in FIG. 7.

  First, the vehicle-mounted device 1 detects the current position, posture, speed, etc. of the vehicle based on the outputs of the GPS receiver 32, the gyro sensor 33, the acceleration sensor 34, the speed sensor 35, etc. (step S101).

  Next, the feature information acquisition unit 21 of the vehicle-mounted device 1 determines whether the feature information IF around the vehicle position has not been acquired from the server device 4 (step S102). In this case, the feature information acquisition unit 21 has not acquired the feature information IF around the position of the own vehicle from the server device 4, for example, when the feature information IF has been separated from the position where the feature information IF was previously received from the server device 4 by a predetermined distance or more. It is determined that In another example, the feature information acquisition unit 21 still outputs the feature information IF around the vehicle position from the server device 4 when entering an area that has not been entered within a predetermined period among the areas divided in advance. It is determined that it has not been acquired, and the feature information IF corresponding to the area is acquired in step S103 described below.

  When the feature information acquisition unit 21 has not yet acquired the feature information IF around the vehicle position from the server device 4 (step S102; Yes), the feature information IF around the vehicle position is acquired from the server device 4. Is acquired (step S103). In this case, the feature information acquisition unit 21 transmits the request signal of the feature information IF including the own vehicle position detected in step S101 to the server device 4 to obtain the feature information IF around the own vehicle position. Receive from 4. In this case, the feature information acquisition unit 21 may receive the map data around the vehicle position including the feature information IF. On the other hand, when the feature information acquisition unit 21 has already acquired the feature information IF around the vehicle position from the server device 4 (step S102; No), the process proceeds to step S104.

  Next, the feature detection unit 22 of the vehicle-mounted device 1 determines whether or not a feature exists within the detection range of the external world sensor 31 (step S104). For example, the feature detection unit 22 determines whether the position indicated by the “coordinate” field of the feature information IF received from the server device 4 is included in the detection range of the external sensor 31. The feature detection unit 22 may specify the detection range of the external sensor 31 by referring to the information of the detection range of the external sensor 31 stored in the storage unit 12 in advance, and it is set in the external sensor 31. You may calculate based on a parameter.

  Then, when a feature is present within the detection range of the external sensor 31 (step S104; Yes), the feature detection unit 22 performs a feature detection process based on the output of the external sensor 31 for the feature. (Step S105). In this case, the feature detection unit 22 refers to the field of the sensor attribute of the feature information IF of the feature to be detected, and obtains information about parameters to be set in the external sensor 31 when detecting the feature. recognize. Then, the feature detection unit 22 compares, for example, the output of the external sensor 31 with the contents of the “coordinate” and “attribute information” fields of the feature information IF shown in FIG. 4 to detect a known feature. Based on the technology, it is determined whether the target feature has been detected. Note that the feature detection unit 22 refers to the field of the sensor attribute of the feature information IF of the feature to be detected, and if it is determined that the feature is difficult to detect, the processing in subsequent steps S106 to S108. The process of the flowchart may be ended without executing the process.

  Then, when the feature detection unit 22 has succeeded in detecting the target feature (step S106; Yes), the condition information transmission unit 23 of the vehicle-mounted device 1 provides the server device 4 with the condition information IC indicating a condition at the time of success. (Step S107). In this case, the condition information transmission unit 23 registers a specific identification number or the like indicating that the corresponding body information is information at the time of successful detection, in the “header ID” of the header information of the condition information IC to be transmitted. On the other hand, when the feature detection unit 22 fails to detect the target feature (step S106; No), the condition information transmission unit 23 transmits the condition information IC indicating the condition at the time of failure to the server device 4 ( Step S108). In this case, the condition information transmitting unit 23 registers a specific identification number or the like indicating that the corresponding body information is information at the time of detection failure, in the “header ID” of the header information of the condition information IC to be transmitted.

(2) Processing of Server Device FIG. 8 is an example of a flowchart showing a processing procedure executed by the server device 4. The server device 4 repeatedly executes the process of the flowchart of FIG.

  First, the condition information acquisition unit 47 of the server device 4 determines whether the condition information IC has been received from the vehicle-mounted device 1 (step S201). Then, when the condition information acquisition unit 47 receives the condition information IC from the vehicle-mounted device 1 (step S201; Yes), the condition information acquisition unit 47 accumulates the received condition information IC (step S202). At this time, for example, the condition information acquisition unit 47 stores the condition information IC for each feature ID. On the other hand, if the condition information acquisition unit 47 has not received the condition information IC from the vehicle-mounted device 1 (step S201; No), the process proceeds to step S203.

  Next, the sensor attribute update unit 48 of the server device 4 determines whether or not it is the timing of the statistical analysis processing (step S203). For example, the sensor attribute update unit 48 executes the statistical analysis process for the condition information IC corresponding to the feature ID when there is a feature ID for which the accumulated number of condition information IC is equal to or more than a predetermined number. It is determined that it is time to do. In this case, the above-mentioned predetermined number is preset to the minimum number required for the statistical analysis process to be executed.

  Then, when it is determined that it is the timing of the statistical analysis process (step S203; Yes), the sensor attribute update unit 48 updates the sensor attribute field of the feature information IF in the advanced map DB 43 by the statistical analysis process. (Step S204). In this case, for example, the sensor attribute update unit 48 targets each of the feature information IF of the feature ID in which the minimum number of condition information IC required for the statistical analysis process is accumulated, and each subfield belonging to the field of the sensor attribute. Update the value of. Further, when updating the sensor attribute field, the sensor attribute updating unit 48 also updates the version registered in the version information of the corresponding header information. On the other hand, when the sensor attribute update unit 48 determines that it is not the timing of the statistical analysis process (step S203; No), the process proceeds to step S205.

  Next, the feature information transmission unit 46 of the server device 4 determines whether or not a request to transmit the feature information IF is received from the vehicle-mounted device 1 (step S205). When the feature information transmitting unit 46 determines that the request for transmitting the feature information IF is received from the vehicle-mounted device 1 (step S205; Yes), the feature-information IF corresponding to the request-source vehicle-mounted device 1 is transmitted. Is transmitted (step S206). In this case, the feature information transmission unit 46 refers to the position information included in the transmission request of the feature information IF and the “coordinates” of the body information of the feature information IF, respectively, and determines the position included in the feature information IF. The feature information IF of a feature existing within a predetermined distance from the position indicated by the information is extracted from the advanced map DB 43 and transmitted to the vehicle-mounted device 1. On the other hand, when there is no request to transmit the feature information IF (step S205; No), the feature information transmission unit 46 ends the process of the flowchart.

  As described above, in the present embodiment, the feature information IF is registered in the advanced map DB 43 stored in the server device 4 for each target feature detected by the external sensor 31 of the vehicle-mounted device 1. ing. The data structure of the feature information IF includes a sensor attribute field including setting information or environment information related to feature detection. The server device 4 updates the sensor attribute field by statistically analyzing the condition information IC received from the plurality of vehicle-mounted devices 1 and indicating the condition at the time of feature detection. As a result, the server device 4 can hold the setting information and environment information of the external sensor 31 useful for detecting a feature as the feature information IF so that the feature information IF can be stored in the vehicle-mounted device 1. The distribution enables the in-vehicle device 1 to appropriately perform feature detection.

[Modification]
Next, a modified example suitable for the embodiment will be described. The following modifications may be applied to the above-described embodiment in any combination.

(Modification 1)
The vehicle-mounted device 1 may receive the feature information IF including only the sensor attribute related to the external sensor 31 included in the vehicle-mounted device 1 from the server device 4.

  In this case, the in-vehicle device 1 includes the type information of the external world sensor 31 included in the transmission request of the feature information IF and transmits the feature information IF to the server device 4. Then, when the server device 4 receives the transmission request of the feature information IF, the server device 4 extracts the feature information IF excluding the sensor attribute not related to the external sensor 31 indicated by the type information included in the transmission request from the vehicle-mounted device. Send to 1. Alternatively, the server device 4 stores the external field sensor 31 mounted on each vehicle for each vehicle, and the vehicle-mounted device 1 transmits the vehicle information for identifying the vehicle to the server device 4, and the server device 4 4 may transmit the feature information IF corresponding to the received vehicle information, excluding sensor attributes unrelated to the external sensor 31 mounted on the vehicle. In this example, the vehicle-mounted device 1 does not need to receive the sensor attribute regarding the external sensor of the type that is not mounted.

(Modification 2)
The in-vehicle device 1 may receive only the sensor attribute from the server device 4 instead of receiving the feature information IF.

  In this case, for example, the vehicle-mounted device 1 stores in advance the map data including the feature information IF in which the information other than the sensor attribute is registered in the storage unit 12. Then, in step S102 of FIG. 7, the vehicle-mounted device 1 determines whether or not the sensor attribute around the vehicle position has not been acquired, and receives the sensor information around the vehicle position from the server device 4 in step S103. According to this aspect, it is possible to preferably reduce the amount of communication between the vehicle-mounted device 1 and the server device 4. In this case, the vehicle-mounted device 1 may receive only the sensor attribute related to the external sensor 31 included in the vehicle-mounted device 1 by combining with the above-described (Modification 1).

(Modification 3)
The vehicle-mounted device 1 may transmit information about the date or season at the time of detecting a feature to the server device 4 in addition to or in place of the information such as time and weather at the time of detecting a feature included in the condition information IC. Good. For example, when the feature is a tree or the like, the amount and color of the leaves are different depending on the season, and thus the setting of the external sensor 31 suitable for detection may be different. The server device 4 receives such condition information ICs from a plurality of vehicle-mounted devices 1, accumulates them, and statistically analyzes them, so that the advanced map DB 43 also applies to a feature whose mode changes depending on the season. It is possible to preferably update the sensor attribute of the feature information IF registered in.

  The present invention is not limited to the above-described embodiments, but can be appropriately modified within a range not departing from the gist or idea of the invention that can be read from the claims and the entire specification, and feature data accompanied by such modifications. A structure, a storage medium, an information processing device, and a detection device are also included in the technical scope of the present invention.

1 In-vehicle device 4 Server device 11, 41 Communication unit 12, 42 Storage unit 13 Sensor unit 14 Input unit 15, 45 Control unit 16 Output unit 31 External sensor 43 Advanced map DB

Claims (15)

A feature data structure for each feature, which is used when detecting a feature by the external sensor of the detection device,
Information about the type of the external sensor used to detect the feature,
For each type of the external sensor, environmental information about the environment when detecting the feature,
Feature data structure containing.   The feature data structure according to claim 1, wherein the environment information includes information regarding a detection rate of the feature by the external sensor.   The environmental information includes at least one of a time zone, a weather, and a spatial range in which a detection rate of the feature by the external sensor is a predetermined value or more or less than a predetermined value. Feature data structure. The feature data structure according to any one of claims 1 to 3,
The feature data structure, further comprising setting information of the external sensor according to the environmental information for each type of the external sensor.   The feature data structure according to claim 4, wherein the setting information is information of a parameter set in the external sensor.   The feature data structure according to any one of claims 1 to 5, wherein the feature data structure can be updated based on statistical analysis of detection results by a plurality of the detection devices.   A storage medium storing a record of the feature data structure according to claim 1. A feature data structure for each feature, which is used when detecting a feature by the external sensor of the detection device,
A storage unit that stores a record of a feature data structure including information about the type of the external sensor used for detecting the feature and environment information regarding the environment when the feature is detected for each type of the external sensor. When,
A transmission unit that transmits the record to the detection device in response to a request from the detection device,
An information processing apparatus including. From the detection device, an acquisition unit that acquires condition information including information about the environment when the detection of the feature succeeds or fails,
An update unit that updates the record based on the condition information acquired by the acquisition unit;
The information processing apparatus according to claim 8, further comprising: The detection device is mounted on a moving body,
The condition information includes at least one of a state of the moving body, a state around the moving body, and a state of the acquisition unit when the detection of the feature succeeds or fails. The information processing device according to claim 8 or 9. The acquisition unit acquires the condition information regarding the feature from a plurality of moving bodies,
The information processing apparatus according to claim 10, wherein the update unit determines update content of the record corresponding to the feature by analyzing a plurality of the condition information by a statistical method. An external sensor that detects an object existing around a moving body,
Position information about the position of a feature around the moving body, information about the type of the external sensor used to detect the feature, and environmental information about the environment when detecting the feature for each type of the external sensor. And an acquisition unit that acquires a record having a feature data structure including the setting information of the external sensor according to the environment information,
A control unit that controls the detection of the object by the external sensor based on the setting information;
Based on the position information of the feature, a specifying unit that specifies the object detected by the external sensor as the feature,
A detection device comprising.   Condition information including at least one of the state of the moving body, the state of the periphery of the moving body, and the state of the detection device when the specifying unit succeeds or fails in specifying the feature, The detection device according to claim 12, further comprising a transmission unit that transmits a record having a feature data structure to an external device. The feature data structure includes a detection condition such that the detection success rate of the feature is equal to or more than a predetermined value,
14. The detection device according to claim 12, wherein the external world sensor detects the feature based on a detection condition that a detection success rate of the feature is equal to or higher than a predetermined value. The feature data structure includes a detection condition that a detection success rate of the feature is less than a predetermined value,
In the case where one of the state of the moving body, the state around the moving body, or the state of the detection device corresponds to the detection condition that the detection success rate of the feature is less than a predetermined value, the external sensor The detection device according to claim 12, wherein the feature is excluded from the detection target.

Images